modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-08-29 06:27:22
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 525
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-08-29 06:27:10
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
roa7n/gpt2-human_enhancers_ensembl-randomized_0_layers_0.003_lr_8_e
|
roa7n
| 2023-10-10T20:11:52Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-10T20:11:50Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
keremp/opus-em-augmented
|
keremp
| 2023-10-10T20:10:07Z | 106 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-10T18:13:37Z |
---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: opus-em-augmented
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# opus-em-augmented
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6934
- F1: 0.3341
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 0.6948 | 1.0 | 10000 | 0.6933 | 0.3341 |
| 0.6933 | 2.0 | 20000 | 0.6933 | 0.3326 |
| 0.6933 | 3.0 | 30000 | 0.6934 | 0.3341 |
### Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
Adalwolf10/profile_ST
|
Adalwolf10
| 2023-10-10T19:51:17Z | 1 | 0 |
diffusers
|
[
"diffusers",
"text-to-image",
"autotrain",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:finetune:stabilityai/stable-diffusion-xl-base-1.0",
"region:us"
] |
text-to-image
| 2023-10-10T19:51:15Z |
---
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: Photo of Shubham
tags:
- text-to-image
- diffusers
- autotrain
inference: true
---
# DreamBooth trained by AutoTrain
Text encoder was not trained.
|
pcalhoun/Llama-2-13b-JonathanSwift
|
pcalhoun
| 2023-10-10T19:50:19Z | 4 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-10T19:08:41Z |
---
library_name: peft
---
## Format:
\<s\>\<\<CONTEXT\>\> This is the context that will not be swiftified. \<\</CONTEXT\>\>\<\<MODERN\>\> This is the modern text that will be swiftified. \<\</MODERN\>\>\<\<JON_SWIFT\>\> Swiftified text appears here \<\</JON_SWIFT\>\>
E.g:
\<s\>\<\<CONTEXT\>\> COWEN: Do you now think about getting things done this way? NAVRATILOVA: The positive attitude helps. With tennis, you have to be very positive and have a very short memory. COWEN: [laughs] NAVRATILOVA: Long memory for the good stuff and short memory for the bad stuff because you have to play a point. In 20 seconds, you’ve got to get ready for the next point. You’ve got to analyze what happened and try to do it better, etc. But raising two kids is challenging. I’m going to say whatever training I’ve done is not enough. [laughter] COWEN: \<\</CONTEXT\>\>\<\<MODERN\>\> Billie Jean King once suggested that you use writing in a journal every day to help you accomplish your goals. How does that work for you? What is it you do? Why do you think it works? \<\</MODERN\>\>\<\<JON_SWIFT\>\> Mighty Billie-Jean King once proposed that you write in a Journal every Day of your Life, to bring you to the Thinking of doing what you ought to do; but how comes it that she did not give any Directions as to the Manner of Performing this Work? And what was it you intended by such an Advise? Or rather, why do you suppose it would answer any Purpose? \<\</JON_SWIFT\>\>
### Framework versions
- PEFT 0.5.0
|
Farshid/led-base-16384-cnn_dailymail_v3
|
Farshid
| 2023-10-10T19:45:57Z | 91 | 0 |
transformers
|
[
"transformers",
"pytorch",
"led",
"text2text-generation",
"generated_from_trainer",
"dataset:cnn_dailymail",
"base_model:allenai/led-base-16384",
"base_model:finetune:allenai/led-base-16384",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-10-10T05:42:36Z |
---
license: apache-2.0
base_model: allenai/led-base-16384
tags:
- generated_from_trainer
datasets:
- cnn_dailymail
model-index:
- name: led-base-16384-cnn_dailymail_v3
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# led-base-16384-cnn_dailymail_v3
This model is a fine-tuned version of [allenai/led-base-16384](https://huggingface.co/allenai/led-base-16384) on the cnn_dailymail dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6000
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.9392 | 0.45 | 1000 | 1.6459 |
| 1.7291 | 0.89 | 2000 | 1.6000 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
desarrolloasesoreslocales/SetFitPruebaRecorte
|
desarrolloasesoreslocales
| 2023-10-10T19:45:23Z | 5 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"mpnet",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] |
text-classification
| 2023-10-10T19:44:32Z |
---
license: apache-2.0
tags:
- setfit
- sentence-transformers
- text-classification
pipeline_tag: text-classification
---
# desarrolloasesoreslocales/SetFitPruebaRecorte
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("desarrolloasesoreslocales/SetFitPruebaRecorte")
# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
|
serhatdnd/ataturk
|
serhatdnd
| 2023-10-10T19:41:21Z | 0 | 0 | null |
[
"license:other",
"region:us"
] | null | 2023-10-10T19:41:21Z |
---
license: other
license_name: public
license_link: LICENSE
---
|
RogerB/xlm-roberta-base-finetuned-kinyarwanda-kin-finetuned-kinte-tweet-finetuned-kin-sent2
|
RogerB
| 2023-10-10T19:36:51Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"text-classification",
"generated_from_trainer",
"base_model:RogerB/xlm-roberta-base-kin-tweets-pretrained",
"base_model:finetune:RogerB/xlm-roberta-base-kin-tweets-pretrained",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-10T19:25:12Z |
---
base_model: RogerB/xlm-roberta-base-finetuned-kinyarwanda-kin-finetuned-kinte-tweet-finetuned
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-kinyarwanda-kin-finetuned-kinte-tweet-finetuned-kin-sent2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# xlm-roberta-base-finetuned-kinyarwanda-kin-finetuned-kinte-tweet-finetuned-kin-sent2
This model is a fine-tuned version of [RogerB/xlm-roberta-base-finetuned-kinyarwanda-kin-finetuned-kinte-tweet-finetuned](https://huggingface.co/RogerB/xlm-roberta-base-finetuned-kinyarwanda-kin-finetuned-kinte-tweet-finetuned) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9208
- F1: 0.6277
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 1000000
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.9867 | 1.0 | 1013 | 0.7765 | 0.6671 |
| 0.8334 | 2.0 | 2026 | 0.7100 | 0.7125 |
| 0.7621 | 3.0 | 3039 | 0.6947 | 0.7338 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
meowXin/lora-trained-xl-colab
|
meowXin
| 2023-10-10T19:30:39Z | 19 | 1 |
diffusers
|
[
"diffusers",
"tensorboard",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] |
text-to-image
| 2023-10-07T18:50:18Z |
---
license: openrail++
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: a photo of sks dog
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - meowXin/lora-trained-xl-colab
These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
|
Maykeye/BakaLLM
|
Maykeye
| 2023-10-10T19:18:50Z | 0 | 0 | null |
[
"dataset:wikitext",
"license:apache-2.0",
"region:us"
] | null | 2023-10-10T18:27:45Z |
---
license: apache-2.0
datasets:
- wikitext
---
The main stuff is stored in branches: BakaLLM is intented to be my pet project with series of gradual improvements.
Basically one improvement per branch, from 001_pristine(simplest version) to ⑨⑨⑨_humanity_is_conquered.
HF repo contains code and weights. Github code only.
Code will not work AS IS, tinkering requirements. For one, I didn't place weight in weights dir(I wanted to zstd them first, but forgot)
For two, bench (benchmark script to test against other models) is very opinionaned where models are stored.
|
RogerB/afro-xlmr-large-kinre-finetuned-kinte-tweet-finetuned-kin-sent2
|
RogerB
| 2023-10-10T18:58:49Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"text-classification",
"generated_from_trainer",
"base_model:RogerB/afro-xlmr-large-kinre-finetuned-kinte-tweet-finetuned",
"base_model:finetune:RogerB/afro-xlmr-large-kinre-finetuned-kinte-tweet-finetuned",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-10T18:31:37Z |
---
license: mit
base_model: RogerB/afro-xlmr-large-kinre-finetuned-kinte-tweet-finetuned
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: afro-xlmr-large-kinre-finetuned-kinte-tweet-finetuned-kin-sent2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# afro-xlmr-large-kinre-finetuned-kinte-tweet-finetuned-kin-sent2
This model is a fine-tuned version of [RogerB/afro-xlmr-large-kinre-finetuned-kinte-tweet-finetuned](https://huggingface.co/RogerB/afro-xlmr-large-kinre-finetuned-kinte-tweet-finetuned) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9013
- F1: 0.6979
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 1000000
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.9465 | 1.0 | 1013 | 0.7496 | 0.6908 |
| 0.737 | 2.0 | 2026 | 0.5624 | 0.7834 |
| 0.6442 | 3.0 | 3039 | 0.5366 | 0.8079 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
SJahanzad/3dbloom1
|
SJahanzad
| 2023-10-10T18:30:55Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-10T18:30:51Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.6.0.dev0
|
Sguzman4532/marian-finetuned-kde4-en-to-fr
|
Sguzman4532
| 2023-10-10T18:30:43Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"marian",
"text2text-generation",
"translation",
"generated_from_trainer",
"dataset:kde4",
"base_model:Helsinki-NLP/opus-mt-en-fr",
"base_model:finetune:Helsinki-NLP/opus-mt-en-fr",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2023-10-10T00:50:21Z |
---
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-en-fr
tags:
- translation
- generated_from_trainer
datasets:
- kde4
model-index:
- name: marian-finetuned-kde4-en-to-fr
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# marian-finetuned-kde4-en-to-fr
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-fr](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr) on the kde4 dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 50
### Training results
### Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cpu
- Datasets 2.14.5
- Tokenizers 0.13.3
|
alessandroseni/room-type-detection
|
alessandroseni
| 2023-10-10T18:26:11Z | 220 | 2 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"vit",
"image-classification",
"huggingpics",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-10-10T18:26:05Z |
---
tags:
- image-classification
- pytorch
- huggingpics
metrics:
- accuracy
model-index:
- name: room-type-detection
results:
- task:
name: Image Classification
type: image-classification
metrics:
- name: Accuracy
type: accuracy
value: 0.7142857313156128
---
# room-type-detection
Autogenerated by HuggingPics🤗🖼️
Create your own image classifier for **anything** by running [the demo on Google Colab](https://colab.research.google.com/github/nateraw/huggingpics/blob/main/HuggingPics.ipynb).
Report any issues with the demo at the [github repo](https://github.com/nateraw/huggingpics).
## Example Images
#### bathroom
#### bedroom
#### dining room
#### kitchen
#### living room
|
RogerB/afro-xlmr-large-kinre-finetuned-kinte-tweet-finetuned-kin-sent1
|
RogerB
| 2023-10-10T18:25:42Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"text-classification",
"generated_from_trainer",
"base_model:RogerB/afro-xlmr-large-kinre-finetuned-kinte-tweet-finetuned",
"base_model:finetune:RogerB/afro-xlmr-large-kinre-finetuned-kinte-tweet-finetuned",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-10T18:00:44Z |
---
license: mit
base_model: RogerB/afro-xlmr-large-kinre-finetuned-kinte-tweet-finetuned
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: afro-xlmr-large-kinre-finetuned-kinte-tweet-finetuned-kin-sent1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# afro-xlmr-large-kinre-finetuned-kinte-tweet-finetuned-kin-sent1
This model is a fine-tuned version of [RogerB/afro-xlmr-large-kinre-finetuned-kinte-tweet-finetuned](https://huggingface.co/RogerB/afro-xlmr-large-kinre-finetuned-kinte-tweet-finetuned) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9004
- F1: 0.6959
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 100000
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.9029 | 1.0 | 1013 | 0.6650 | 0.7226 |
| 0.729 | 2.0 | 2026 | 0.5295 | 0.8007 |
| 0.6296 | 3.0 | 3039 | 0.4975 | 0.8234 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Amirhnrn/ppo-CartPole-v1
|
Amirhnrn
| 2023-10-10T18:24:05Z | 0 | 0 | null |
[
"tensorboard",
"CartPole-v1",
"ppo",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"deep-rl-course",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-10T18:24:00Z |
---
tags:
- CartPole-v1
- ppo
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
- deep-rl-course
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 165.50 +/- 105.87
name: mean_reward
verified: false
---
# PPO Agent Playing CartPole-v1
This is a trained model of a PPO agent playing CartPole-v1.
# Hyperparameters
```python
{'exp_name': '__file__'
'seed': 1
'torch_deterministic': True
'cuda': True
'track': False
'wandb_project_name': 'cleanRL'
'wandb_entity': None
'capture_video': False
'env_id': 'CartPole-v1'
'total_timesteps': 50000
'learning_rate': 0.00025
'num_envs': 4
'num_steps': 128
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'num_minibatches': 4
'update_epochs': 4
'norm_adv': True
'clip_coef': 0.2
'clip_vloss': True
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'repo_id': 'Amirhnrn/ppo-CartPole-v1'
'batch_size': 512
'minibatch_size': 128}
```
|
google/flan-t5-small
|
google
| 2023-10-10T18:01:54Z | 541,099 | 310 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"jax",
"safetensors",
"t5",
"text2text-generation",
"en",
"fr",
"ro",
"de",
"multilingual",
"dataset:svakulenk0/qrecc",
"dataset:taskmaster2",
"dataset:djaym7/wiki_dialog",
"dataset:deepmind/code_contests",
"dataset:lambada",
"dataset:gsm8k",
"dataset:aqua_rat",
"dataset:esnli",
"dataset:quasc",
"dataset:qed",
"arxiv:2210.11416",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2022-10-21T09:59:24Z |
---
language:
- en
- fr
- ro
- de
- multilingual
tags:
- text2text-generation
widget:
- text: "Translate to German: My name is Arthur"
example_title: "Translation"
- text: "Please answer to the following question. Who is going to be the next Ballon d'or?"
example_title: "Question Answering"
- text: "Q: Can Geoffrey Hinton have a conversation with George Washington? Give the rationale before answering."
example_title: "Logical reasoning"
- text: "Please answer the following question. What is the boiling point of Nitrogen?"
example_title: "Scientific knowledge"
- text: "Answer the following yes/no question. Can you write a whole Haiku in a single tweet?"
example_title: "Yes/no question"
- text: "Answer the following yes/no question by reasoning step-by-step. Can you write a whole Haiku in a single tweet?"
example_title: "Reasoning task"
- text: "Q: ( False or not False or False ) is? A: Let's think step by step"
example_title: "Boolean Expressions"
- text: "The square root of x is the cube root of y. What is y to the power of 2, if x = 4?"
example_title: "Math reasoning"
- text: "Premise: At my age you will probably have learnt one lesson. Hypothesis: It's not certain how many lessons you'll learn by your thirties. Does the premise entail the hypothesis?"
example_title: "Premise and hypothesis"
datasets:
- svakulenk0/qrecc
- taskmaster2
- djaym7/wiki_dialog
- deepmind/code_contests
- lambada
- gsm8k
- aqua_rat
- esnli
- quasc
- qed
license: apache-2.0
---
# Model Card for FLAN-T5 small
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/flan2_architecture.jpg"
alt="drawing" width="600"/>
# Table of Contents
0. [TL;DR](#TL;DR)
1. [Model Details](#model-details)
2. [Usage](#usage)
3. [Uses](#uses)
4. [Bias, Risks, and Limitations](#bias-risks-and-limitations)
5. [Training Details](#training-details)
6. [Evaluation](#evaluation)
7. [Environmental Impact](#environmental-impact)
8. [Citation](#citation)
9. [Model Card Authors](#model-card-authors)
# TL;DR
If you already know T5, FLAN-T5 is just better at everything. For the same number of parameters, these models have been fine-tuned on more than 1000 additional tasks covering also more languages.
As mentioned in the first few lines of the abstract :
> Flan-PaLM 540B achieves state-of-the-art performance on several benchmarks, such as 75.2% on five-shot MMLU. We also publicly release Flan-T5 checkpoints,1 which achieve strong few-shot performance even compared to much larger models, such as PaLM 62B. Overall, instruction finetuning is a general method for improving the performance and usability of pretrained language models.
**Disclaimer**: Content from **this** model card has been written by the Hugging Face team, and parts of it were copy pasted from the [T5 model card](https://huggingface.co/t5-large).
# Model Details
## Model Description
- **Model type:** Language model
- **Language(s) (NLP):** English, Spanish, Japanese, Persian, Hindi, French, Chinese, Bengali, Gujarati, German, Telugu, Italian, Arabic, Polish, Tamil, Marathi, Malayalam, Oriya, Panjabi, Portuguese, Urdu, Galician, Hebrew, Korean, Catalan, Thai, Dutch, Indonesian, Vietnamese, Bulgarian, Filipino, Central Khmer, Lao, Turkish, Russian, Croatian, Swedish, Yoruba, Kurdish, Burmese, Malay, Czech, Finnish, Somali, Tagalog, Swahili, Sinhala, Kannada, Zhuang, Igbo, Xhosa, Romanian, Haitian, Estonian, Slovak, Lithuanian, Greek, Nepali, Assamese, Norwegian
- **License:** Apache 2.0
- **Related Models:** [All FLAN-T5 Checkpoints](https://huggingface.co/models?search=flan-t5)
- **Original Checkpoints:** [All Original FLAN-T5 Checkpoints](https://github.com/google-research/t5x/blob/main/docs/models.md#flan-t5-checkpoints)
- **Resources for more information:**
- [Research paper](https://arxiv.org/pdf/2210.11416.pdf)
- [GitHub Repo](https://github.com/google-research/t5x)
- [Hugging Face FLAN-T5 Docs (Similar to T5) ](https://huggingface.co/docs/transformers/model_doc/t5)
# Usage
Find below some example scripts on how to use the model in `transformers`:
## Using the Pytorch model
### Running the model on a CPU
<details>
<summary> Click to expand </summary>
```python
from transformers import T5Tokenizer, T5ForConditionalGeneration
tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-small")
model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-small")
input_text = "translate English to German: How old are you?"
input_ids = tokenizer(input_text, return_tensors="pt").input_ids
outputs = model.generate(input_ids)
print(tokenizer.decode(outputs[0]))
```
</details>
### Running the model on a GPU
<details>
<summary> Click to expand </summary>
```python
# pip install accelerate
from transformers import T5Tokenizer, T5ForConditionalGeneration
tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-small")
model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-small", device_map="auto")
input_text = "translate English to German: How old are you?"
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
outputs = model.generate(input_ids)
print(tokenizer.decode(outputs[0]))
```
</details>
### Running the model on a GPU using different precisions
#### FP16
<details>
<summary> Click to expand </summary>
```python
# pip install accelerate
import torch
from transformers import T5Tokenizer, T5ForConditionalGeneration
tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-small")
model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-small", device_map="auto", torch_dtype=torch.float16)
input_text = "translate English to German: How old are you?"
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
outputs = model.generate(input_ids)
print(tokenizer.decode(outputs[0]))
```
</details>
#### INT8
<details>
<summary> Click to expand </summary>
```python
# pip install bitsandbytes accelerate
from transformers import T5Tokenizer, T5ForConditionalGeneration
tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-small")
model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-small", device_map="auto", load_in_8bit=True)
input_text = "translate English to German: How old are you?"
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
outputs = model.generate(input_ids)
print(tokenizer.decode(outputs[0]))
```
</details>
# Uses
## Direct Use and Downstream Use
The authors write in [the original paper's model card](https://arxiv.org/pdf/2210.11416.pdf) that:
> The primary use is research on language models, including: research on zero-shot NLP tasks and in-context few-shot learning NLP tasks, such as reasoning, and question answering; advancing fairness and safety research, and understanding limitations of current large language models
See the [research paper](https://arxiv.org/pdf/2210.11416.pdf) for further details.
## Out-of-Scope Use
More information needed.
# Bias, Risks, and Limitations
The information below in this section are copied from the model's [official model card](https://arxiv.org/pdf/2210.11416.pdf):
> Language models, including Flan-T5, can potentially be used for language generation in a harmful way, according to Rae et al. (2021). Flan-T5 should not be used directly in any application, without a prior assessment of safety and fairness concerns specific to the application.
## Ethical considerations and risks
> Flan-T5 is fine-tuned on a large corpus of text data that was not filtered for explicit content or assessed for existing biases. As a result the model itself is potentially vulnerable to generating equivalently inappropriate content or replicating inherent biases in the underlying data.
## Known Limitations
> Flan-T5 has not been tested in real world applications.
## Sensitive Use:
> Flan-T5 should not be applied for any unacceptable use cases, e.g., generation of abusive speech.
# Training Details
## Training Data
The model was trained on a mixture of tasks, that includes the tasks described in the table below (from the original paper, figure 2):
## Training Procedure
According to the model card from the [original paper](https://arxiv.org/pdf/2210.11416.pdf):
> These models are based on pretrained T5 (Raffel et al., 2020) and fine-tuned with instructions for better zero-shot and few-shot performance. There is one fine-tuned Flan model per T5 model size.
The model has been trained on TPU v3 or TPU v4 pods, using [`t5x`](https://github.com/google-research/t5x) codebase together with [`jax`](https://github.com/google/jax).
# Evaluation
## Testing Data, Factors & Metrics
The authors evaluated the model on various tasks covering several languages (1836 in total). See the table below for some quantitative evaluation:
For full details, please check the [research paper](https://arxiv.org/pdf/2210.11416.pdf).
## Results
For full results for FLAN-T5-Small, see the [research paper](https://arxiv.org/pdf/2210.11416.pdf), Table 3.
# Environmental Impact
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** Google Cloud TPU Pods - TPU v3 or TPU v4 | Number of chips ≥ 4.
- **Hours used:** More information needed
- **Cloud Provider:** GCP
- **Compute Region:** More information needed
- **Carbon Emitted:** More information needed
# Citation
**BibTeX:**
```bibtex
@misc{https://doi.org/10.48550/arxiv.2210.11416,
doi = {10.48550/ARXIV.2210.11416},
url = {https://arxiv.org/abs/2210.11416},
author = {Chung, Hyung Won and Hou, Le and Longpre, Shayne and Zoph, Barret and Tay, Yi and Fedus, William and Li, Eric and Wang, Xuezhi and Dehghani, Mostafa and Brahma, Siddhartha and Webson, Albert and Gu, Shixiang Shane and Dai, Zhuyun and Suzgun, Mirac and Chen, Xinyun and Chowdhery, Aakanksha and Narang, Sharan and Mishra, Gaurav and Yu, Adams and Zhao, Vincent and Huang, Yanping and Dai, Andrew and Yu, Hongkun and Petrov, Slav and Chi, Ed H. and Dean, Jeff and Devlin, Jacob and Roberts, Adam and Zhou, Denny and Le, Quoc V. and Wei, Jason},
keywords = {Machine Learning (cs.LG), Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Scaling Instruction-Finetuned Language Models},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
|
0xC4LL3/RL-Course_ViZDoom_Health-Gathering-Supreme
|
0xC4LL3
| 2023-10-10T17:37:46Z | 0 | 0 |
sample-factory
|
[
"sample-factory",
"tensorboard",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-08T20:36:22Z |
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: doom_health_gathering_supreme
type: doom_health_gathering_supreme
metrics:
- type: mean_reward
value: 21.00 +/- 0.00
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r 0xC4LL3/RL-Course_ViZDoom_Health-Gathering-Supreme
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m .home.calle..local.lib.python3.10.site-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=RL-Course_ViZDoom_Health-Gathering-Supreme
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m .home.calle..local.lib.python3.10.site-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=RL-Course_ViZDoom_Health-Gathering-Supreme --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
TheBloke/em_german_mistral_v01-GGUF
|
TheBloke
| 2023-10-10T17:34:43Z | 3,982 | 11 |
transformers
|
[
"transformers",
"gguf",
"mistral",
"pytorch",
"german",
"deutsch",
"text-generation",
"de",
"base_model:jphme/em_german_mistral_v01",
"base_model:quantized:jphme/em_german_mistral_v01",
"license:apache-2.0",
"region:us"
] |
text-generation
| 2023-10-03T16:24:56Z |
---
base_model: jphme/em_german_mistral_v01
inference: false
language:
- de
library_name: transformers
license: apache-2.0
model_creator: Jan Philipp Harries
model_name: EM German Mistral v01
model_type: mistral
pipeline_tag: text-generation
prompt_template: 'Du bist ein hilfreicher Assistent. USER: {prompt} ASSISTANT:
'
quantized_by: TheBloke
tags:
- pytorch
- german
- deutsch
- mistral
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# EM German Mistral v01 - GGUF
- Model creator: [Jan Philipp Harries](https://huggingface.co/jphme)
- Original model: [EM German Mistral v01](https://huggingface.co/jphme/em_german_mistral_v01)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Jan Philipp Harries's EM German Mistral v01](https://huggingface.co/jphme/em_german_mistral_v01).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/em_german_mistral_v01-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF)
* [Jan Philipp Harries's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jphme/em_german_mistral_v01)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: EmGerman
```
Du bist ein hilfreicher Assistent. USER: {prompt} ASSISTANT:
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [em_german_mistral_v01.Q2_K.gguf](https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF/blob/main/em_german_mistral_v01.Q2_K.gguf) | Q2_K | 2 | 3.08 GB| 5.58 GB | smallest, significant quality loss - not recommended for most purposes |
| [em_german_mistral_v01.Q3_K_S.gguf](https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF/blob/main/em_german_mistral_v01.Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| 5.66 GB | very small, high quality loss |
| [em_german_mistral_v01.Q3_K_M.gguf](https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF/blob/main/em_german_mistral_v01.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
| [em_german_mistral_v01.Q3_K_L.gguf](https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF/blob/main/em_german_mistral_v01.Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| 6.32 GB | small, substantial quality loss |
| [em_german_mistral_v01.Q4_0.gguf](https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF/blob/main/em_german_mistral_v01.Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [em_german_mistral_v01.Q4_K_S.gguf](https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF/blob/main/em_german_mistral_v01.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss |
| [em_german_mistral_v01.Q4_K_M.gguf](https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF/blob/main/em_german_mistral_v01.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
| [em_german_mistral_v01.Q5_0.gguf](https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF/blob/main/em_german_mistral_v01.Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [em_german_mistral_v01.Q5_K_S.gguf](https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF/blob/main/em_german_mistral_v01.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended |
| [em_german_mistral_v01.Q5_K_M.gguf](https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF/blob/main/em_german_mistral_v01.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
| [em_german_mistral_v01.Q6_K.gguf](https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF/blob/main/em_german_mistral_v01.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss |
| [em_german_mistral_v01.Q8_0.gguf](https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF/blob/main/em_german_mistral_v01.Q8_0.gguf) | Q8_0 | 8 | 7.70 GB| 10.20 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/em_german_mistral_v01-GGUF and below it, a specific filename to download, such as: em_german_mistral_v01.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/em_german_mistral_v01-GGUF em_german_mistral_v01.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/em_german_mistral_v01-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/em_german_mistral_v01-GGUF em_german_mistral_v01.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m em_german_mistral_v01.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Du bist ein hilfreicher Assistent. USER: {prompt} ASSISTANT:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/em_german_mistral_v01-GGUF", model_file="em_german_mistral_v01.Q4_K_M.gguf", model_type="mistral", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Jan Philipp Harries's EM German Mistral v01
*Please note that the Mistral architecture is very recent and still not supported by all libraries (e.g. AutoGPTQ). In case of any problems, please try a different format/base model.*
# Table of Contents
1. [Introduction](#introduction)
2. [Links & Demos](#links--demos)
- [Model Links](#model-links)
- [Demos](#demos)
3. [Prompt Format](#prompt-format)
4. [Example Output](#example-output)
5. [Acknowledgements](#acknowledgements)
6. [Contact](#contact)
7. [Disclaimer](#disclaimer)
# Introduction
**EM German** is a Llama2/Mistral/LeoLM-based model family, finetuned on a large dataset of various instructions in German language. The models are optimized for German text, providing proficiency in understanding, generating, and interacting with German language content.
We offer versions based on 7b, 13b and 70b Llama-2, Mistral and LeoLM (Llama-2/Mistral with continued pretraining on German texts) models.
Please find all Informations, Example Outputs, the special RAG prompt format, output examples and eval results for the EM German Model family in [our Github Repository](https://github.com/jphme/EM_German). ([Deutsche Version](https://github.com/jphme/EM_German/blob/main/README_DE.md))
# Links & Demos
## Model Links
Should you try only one model version, I strongly recommend the **LeoLM Mistral** model which offers by far the best combination of performance and computing requirements!
| Base Model | HF | GPTQ | GGUF | AWQ |
|-------|-------|-------|-------|-------|
| Llama2 7b | [Link](https://huggingface.co/jphme/em_german_7b_v01) | [Link](https://huggingface.co/TheBloke/em_german_7b_v01-GPTQ) | [Link](https://huggingface.co/TheBloke/em_german_7b_v01-GGUF) | [Link](https://huggingface.co/TheBloke/em_german_7b_v01-AWQ) |
| Llama2 13b | [Link](https://huggingface.co/jphme/em_german_13b_v01) | [Link](https://huggingface.co/TheBloke/em_german_13b_v01-GPTQ) | [Link](https://huggingface.co/TheBloke/em_german_13b_v01-GGUF) | [Link](https://huggingface.co/TheBloke/em_german_13b_v01-AWQ) |
| Llama2 70b | [Link](https://huggingface.co/jphme/em_german_70b_v01) | [Link](https://huggingface.co/TheBloke/em_german_70b_v01-GPTQ) | [Link](https://huggingface.co/TheBloke/em_german_70b_v01-GGUF) | [Link](https://huggingface.co/TheBloke/em_german_70b_v01-AWQ) |
| [Mistral 7b](https://huggingface.co/mistralai/Mistral-7B-v0.1) | [Link](https://huggingface.co/jphme/em_german_mistral_v01) | [Link](https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ) | [Link](https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF) | [Link](https://huggingface.co/TheBloke/em_german_mistral_v01-AWQ) |
| [LeoLM 7b](https://huggingface.co/LeoLM/leo-hessianai-7b) | [Link](https://huggingface.co/jphme/em_german_7b_leo) | [Link](https://huggingface.co/jphme/em_german_7b_leo_gptq) | [Link](hhttps://huggingface.co/jphme/em_german_7b_leo_gguf) | tbc |
| [LeoLM 13b](https://huggingface.co/LeoLM/leo-hessianai-13b) | soon | soon | [Link](https://huggingface.co/jphme/em_german_13b_leo_gguf) | tbc |
| [LeoLM Mistral 7b](tbc) | [Link](https://huggingface.co/jphme/em_german_leo_mistral) | soon | [Link](https://huggingface.co/jphme/em_german_leo_mistral_gguf) | tbc |
### Notes about the different versions:
See also the [comparison of example outputs](https://github.com/jphme/EM_German/blob/main/example_output_comparison.md) for a comparison of (7b) model capabilities.
If you get unsatisfying results with one or another EM German version, please try a different (and/or larger) model or version for your usecase.
## Demos:
You can use some of the models with **free** google Colab instances (e.g. the 7bn model in 8bit or the 13b model with GPTQ):
* [Example Colab Notebook for 13b with GPTQ](https://colab.research.google.com/drive/1IJfJdVwGkfe5MYOqHptystR3FBeEUdGn?usp=sharing)
* [Example Colab Notebook for 7b with 8bit-Loading](https://colab.research.google.com/drive/1bsv6vkLM4AlCpSyXA6ol9P32zxZmf7Zu?usp=sharing)
* [Example Colab Notebook for 7b Mistral GGUF with Grammar-based structured output](https://colab.research.google.com/drive/17O-a3D4BnVc_V9Of3dFfed18v1ULu1Sv?usp=sharing)
# Prompt Format
This model follows the Vicuna format without linebreaks (but should work with linebreaks as well). The format is as follows:
```
Du bist ein hilfreicher Assistent. USER: <instruction> ASSISTANT:
```
You can swap the standard system prompt for a better suited one (see below for RAG-tasks).
# Example Output
Please find a selection of various example outputs for all 7b versions of EM German [here](https://github.com/jphme/EM_German/blob/main/example_output_comparison.md).
**Prompt:**
> Erkläre die Bedeutung von drei wesentlichen Elementen der Bilanzierung und des Accountings nach IFRS für Unternehmen, die auf internationaler Ebene tätig sind.
**Antwort EM German Leo Mistral 7b:**
```
Die International Financial Reporting Standards (IFRS) sind eine Reihe von internationalen Rechnungslegungsstandards, die von der International Accounting Standards Board (IASB) entwickelt wurden. Sie sollen dazu beitragen, dass Finanzberichte vergleichbar, zuverlässig und relevant sind.
1. Fair Value: Dieses Konzept ist ein zentraler Bestandteil der IFRS. Es besagt, dass Vermögenswerte und Schulden zum fairen Wert bilanziert werden sollten, was dem Preis entspricht, zu dem sie zwischen Marktteilnehmern gehandelt werden könnten. Dadurch wird sichergestellt, dass das Unternehmen eine genaue Darstellung seiner finanziellen Lage liefert.
2. Konsolidierung: Die IFRS verlangen von Unternehmen, ihre Finanzergebnisse auf konsolidierter Basis darzustellen. Das bedeutet, dass alle Tochtergesellschaften und verbundenen Unternehmen in die Bilanz des Mutterunternehmens aufgenommen werden. Dadurch wird ein klareres Bild von der finanziellen Situation des Konzerns geschaffen.
3. Vollständigkeitsprinzip: Die IFRS verlangen von Unternehmen, alle relevanten Informationen offenzulegen. Dies umfasst sowohl positive als auch negative Faktoren, wie zum Beispiel Gewinne und Verluste, Einnahmen und Ausgaben sowie Risiken und Unsicherheiten. Durch dieses Prinzip wird sichergestellt, dass Investoren, Kreditgeber und andere Stakeholder eine umfassende Einschätzung der finanziellen Lage des Unternehmens vornehmen können.
```
**Prompt:**
> Ein Mensch atmet durchschnittlich 16 Mal pro Minute. Wie oft atmet er an einem Tag?
**Antwort EM German Leo Mistral 7b:**
```
Zuerst berechnen wir, wie oft eine Person in einer Stunde atmet. Wir wissen, dass eine Stunde 60 Minuten hat, also:
Atemzüge pro Stunde = Atemfrequenz * Minuten pro Stunde
= 16 Atemzüge pro Minute * 60 Minuten
= 960 Atemzüge
Um herauszufinden, wie viele Atemzüge eine Person an einem Tag macht, müssen wir diese stündliche Rate mit der Anzahl der Stunden an einem Tag multiplizieren, also 24:
Atemzüge pro Tag = Atemzüge pro Stunde * Stunden pro Tag
= 960 Atemzüge * 24 Stunden
= 23.040 Atemzüge
Also macht ein durchschnittlicher Mensch etwa 23.040 Atemzüge an einem Tag.
```
(For more examples, please visit [our Github Repository](https://github.com/jphme/EM_German).)
# Acknowledgements:
Many thanks to [winglian/caseus](https://huggingface.co/winglian) for his great work on Axolotl which I used to train the EM mdoels. I am also grateful to [Jon Durbin](https://huggingface.co/jondurbin) and his [Airoboros](https://huggingface.co/jondurbin/airoboros-l2-70b-2.2.1) models and code from which I borrowed many ideas and code snippets.
Additionally many thanks to [Björn Plüster](https://huggingface.co/bjoernp) and the LeoLM team for the outstanding pretraining work on LeoLM and last but not least many many thanks to [TheBloke](https://huggingface.co/TheBloke) for the preparation of quantized versions in all formats under the sun.
The 70b model was trained with support of the [OVH Cloud Startup Program](https://startup.ovhcloud.com/en/).
# Contact
I you are interested in customized LLMs for business applications, please get in contact with me via [my website](https://www.jph.me). I am also always happy about suggestions and feedback.
*PS: We are also always interested in support for our startup [ellamind](https://ellamind.com), which will offer customized models for business applications in the future (we are currently still in stealth mode). If you use our models for business applications and have advanced needs for specialized capabilities, please get in touch.*
# Disclaimer:
I am not responsible for the actions of third parties who use this model or the outputs of the model. This model should only be used for research purposes. The original base model license applies and is distributed with the model files.
<!-- original-model-card end -->
|
deepin-tech/fr_pipeline
|
deepin-tech
| 2023-10-10T17:28:17Z | 0 | 0 |
spacy
|
[
"spacy",
"token-classification",
"fr",
"region:us"
] |
token-classification
| 2023-10-10T17:26:00Z |
---
tags:
- spacy
- token-classification
language:
- fr
model-index:
- name: fr_pipeline
results: []
---
| Feature | Description |
| --- | --- |
| **Name** | `fr_pipeline` |
| **Version** | `0.0.0` |
| **spaCy** | `>=3.4.1,<3.5.0` |
| **Default Pipeline** | `tok2vec`, `tagger`, `national`, `thematic`, `sentiments`, `ner` |
| **Components** | `tok2vec`, `tagger`, `national`, `thematic`, `sentiments`, `ner` |
| **Vectors** | -1 keys, 50000 unique vectors (300 dimensions) |
| **Sources** | n/a |
| **License** | n/a |
| **Author** | [n/a]() |
### Label Scheme
<details>
<summary>View label scheme (71 labels for 5 components)</summary>
| Component | Labels |
| --- | --- |
| **`tagger`** | `1`, `10`, `100`, `125`, `13`, `14`, `15`, `17`, `19`, `190`, `2`, `25`, `3`, `46`, `5`, `50`, `500`, `6`, `7`, `80`, `800`, `ADJ`, `ADP`, `ADV`, `AUX`, `CCONJ`, `CONJ`, `DET`, `INTJ`, `NOUN`, `NUM`, `PRON`, `PROPN`, `PUNCT`, `SCONJ`, `SYM`, `VERB`, `X` |
| **`national`** | `International`, `National` |
| **`thematic`** | `Coopération/Diplomatie`, `Culture`, `Economie`, `Education`, `Election`, `Environnement`, `Gouvernement`, `Insolite`, `Justice`, `Nécrologie`, `People`, `Politique`, `Réligion`, `Santé`, `Sexualité/Vie couple`, `Société`, `Sport`, `Sécurité`, `Sécurité routière`, `Technologie` |
| **`sentiments`** | `Negatif`, `Neutre`, `Positif` |
| **`ner`** | `DATE`, `EVENT`, `LOC`, `MISC`, `MONEY`, `ORG`, `PER`, `PER-T` |
</details>
### Accuracy
| Type | Score |
| --- | --- |
| `CATS_SCORE` | 90.37 |
| `CATS_MICRO_P` | 96.04 |
| `CATS_MICRO_R` | 96.04 |
| `CATS_MICRO_F` | 96.04 |
| `CATS_MACRO_P` | 92.01 |
| `CATS_MACRO_R` | 88.90 |
| `CATS_MACRO_F` | 90.37 |
| `CATS_MACRO_AUC` | 97.36 |
| `CATS_MACRO_AUC_PER_TYPE` | 0.00 |
| `TOK2VEC_LOSS` | 0.00 |
| `TEXTCAT_LOSS` | 478.59 |
|
Ben141/LLM3
|
Ben141
| 2023-10-10T17:15:27Z | 0 | 0 | null |
[
"generated_from_trainer",
"base_model:meta-llama/Llama-2-7b-hf",
"base_model:finetune:meta-llama/Llama-2-7b-hf",
"region:us"
] | null | 2023-10-10T16:47:16Z |
---
base_model: meta-llama/Llama-2-7b-hf
tags:
- generated_from_trainer
model-index:
- name: LLM3
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# LLM3
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 120
### Training results
### Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Bazzar/bark-small
|
Bazzar
| 2023-10-10T16:58:04Z | 9 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bark",
"text-to-audio",
"audio",
"text-to-speech",
"en",
"de",
"es",
"fr",
"hi",
"it",
"ja",
"ko",
"pl",
"pt",
"ru",
"tr",
"zh",
"license:mit",
"endpoints_compatible",
"region:us"
] |
text-to-speech
| 2023-10-10T16:56:56Z |
---
language:
- en
- de
- es
- fr
- hi
- it
- ja
- ko
- pl
- pt
- ru
- tr
- zh
thumbnail: >-
https://user-images.githubusercontent.com/5068315/230698495-cbb1ced9-c911-4c9a-941d-a1a4a1286ac6.png
library: bark
license: mit
tags:
- bark
- audio
- text-to-speech
duplicated_from: ylacombe/bark-small
pipeline_tag: text-to-speech
---
# Bark
Bark is a transformer-based text-to-audio model created by [Suno](https://www.suno.ai).
Bark can generate highly realistic, multilingual speech as well as other audio - including music,
background noise and simple sound effects. The model can also produce nonverbal
communications like laughing, sighing and crying. To support the research community,
we are providing access to pretrained model checkpoints ready for inference.
The original github repo and model card can be found [here](https://github.com/suno-ai/bark).
This model is meant for research purposes only.
The model output is not censored and the authors do not endorse the opinions in the generated content.
Use at your own risk.
Two checkpoints are released:
- [**small** (this checkpoint)](https://huggingface.co/suno/bark-small)
- [large](https://huggingface.co/suno/bark)
## Example
Try out Bark yourself!
* Bark Colab:
<a target="_blank" href="https://colab.research.google.com/drive/1eJfA2XUa-mXwdMy7DoYKVYHI1iTd9Vkt?usp=sharing">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>
* Hugging Face Colab:
<a target="_blank" href="https://colab.research.google.com/drive/1dWWkZzvu7L9Bunq9zvD-W02RFUXoW-Pd?usp=sharing">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>
* Hugging Face Demo:
<a target="_blank" href="https://huggingface.co/spaces/suno/bark">
<img src="https://huggingface.co/datasets/huggingface/badges/raw/main/open-in-hf-spaces-sm.svg" alt="Open in HuggingFace"/>
</a>
You can run Bark locally with the 🤗 Transformers library from version 4.31.0 onwards.
1. First install the 🤗 [Transformers library](https://github.com/huggingface/transformers) and scipy:
```
pip install --upgrade pip
pip install --upgrade transformers scipy
```
2. Run inference via the `Text-to-Speech` (TTS) pipeline. You can infer the bark model via the TTS pipeline in just a few lines of code!
```python
from transformers import pipeline
import scipy
synthesiser = pipeline("text-to-speech", "suno/bark-small")
speech = synthesiser("Hello, my dog is cooler than you!", forward_params={"do_sample": True})
scipy.io.wavfile.write("bark_out.wav", rate=speech["sampling_rate"], data=speech["audio"])
```
3. Run inference via the Transformers modelling code. You can use the processor + generate code to convert text into a mono 24 kHz speech waveform for more fine-grained control.
```python
from transformers import AutoProcessor, AutoModel
processor = AutoProcessor.from_pretrained("suno/bark-small")
model = AutoModel.from_pretrained("suno/bark-small")
inputs = processor(
text=["Hello, my name is Suno. And, uh — and I like pizza. [laughs] But I also have other interests such as playing tic tac toe."],
return_tensors="pt",
)
speech_values = model.generate(**inputs, do_sample=True)
```
4. Listen to the speech samples either in an ipynb notebook:
```python
from IPython.display import Audio
sampling_rate = model.generation_config.sample_rate
Audio(speech_values.cpu().numpy().squeeze(), rate=sampling_rate)
```
Or save them as a `.wav` file using a third-party library, e.g. `scipy`:
```python
import scipy
sampling_rate = model.config.sample_rate
scipy.io.wavfile.write("bark_out.wav", rate=sampling_rate, data=speech_values.cpu().numpy().squeeze())
```
For more details on using the Bark model for inference using the 🤗 Transformers library, refer to the [Bark docs](https://huggingface.co/docs/transformers/model_doc/bark).
## Suno Usage
You can also run Bark locally through the original [Bark library]((https://github.com/suno-ai/bark):
1. First install the [`bark` library](https://github.com/suno-ai/bark)
3. Run the following Python code:
```python
from bark import SAMPLE_RATE, generate_audio, preload_models
from IPython.display import Audio
# download and load all models
preload_models()
# generate audio from text
text_prompt = """
Hello, my name is Suno. And, uh — and I like pizza. [laughs]
But I also have other interests such as playing tic tac toe.
"""
speech_array = generate_audio(text_prompt)
# play text in notebook
Audio(speech_array, rate=SAMPLE_RATE)
```
[pizza.webm](https://user-images.githubusercontent.com/5068315/230490503-417e688d-5115-4eee-9550-b46a2b465ee3.webm)
To save `audio_array` as a WAV file:
```python
from scipy.io.wavfile import write as write_wav
write_wav("/path/to/audio.wav", SAMPLE_RATE, audio_array)
```
## Model Details
The following is additional information about the models released here.
Bark is a series of three transformer models that turn text into audio.
### Text to semantic tokens
- Input: text, tokenized with [BERT tokenizer from Hugging Face](https://huggingface.co/docs/transformers/model_doc/bert#transformers.BertTokenizer)
- Output: semantic tokens that encode the audio to be generated
### Semantic to coarse tokens
- Input: semantic tokens
- Output: tokens from the first two codebooks of the [EnCodec Codec](https://github.com/facebookresearch/encodec) from facebook
### Coarse to fine tokens
- Input: the first two codebooks from EnCodec
- Output: 8 codebooks from EnCodec
### Architecture
| Model | Parameters | Attention | Output Vocab size |
|:-------------------------:|:----------:|------------|:-----------------:|
| Text to semantic tokens | 80/300 M | Causal | 10,000 |
| Semantic to coarse tokens | 80/300 M | Causal | 2x 1,024 |
| Coarse to fine tokens | 80/300 M | Non-causal | 6x 1,024 |
### Release date
April 2023
## Broader Implications
We anticipate that this model's text to audio capabilities can be used to improve accessbility tools in a variety of languages.
While we hope that this release will enable users to express their creativity and build applications that are a force
for good, we acknowledge that any text to audio model has the potential for dual use. While it is not straightforward
to voice clone known people with Bark, it can still be used for nefarious purposes. To further reduce the chances of unintended use of Bark,
we also release a simple classifier to detect Bark-generated audio with high accuracy (see notebooks section of the main repository).
## License
Bark is licensed under the [MIT License](https://github.com/suno-ai/bark/blob/main/LICENSE), meaning it's available for commercial use.
|
Tommert25/robbert1010_lrate7.5b32
|
Tommert25
| 2023-10-10T16:54:56Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"token-classification",
"generated_from_trainer",
"base_model:Tommert25/robbert0410_lrate7.5b32",
"base_model:finetune:Tommert25/robbert0410_lrate7.5b32",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-10-10T15:59:49Z |
---
license: mit
base_model: Tommert25/robbert0410_lrate7.5b32
tags:
- generated_from_trainer
metrics:
- recall
- accuracy
model-index:
- name: robbert1010_lrate7.5b32
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# robbert1010_lrate7.5b32
This model is a fine-tuned version of [Tommert25/robbert0410_lrate7.5b32](https://huggingface.co/Tommert25/robbert0410_lrate7.5b32) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5187
- Precisions: 0.8552
- Recall: 0.7999
- F-measure: 0.8232
- Accuracy: 0.9157
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 7.5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precisions | Recall | F-measure | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:----------:|:------:|:---------:|:--------:|
| 0.0496 | 1.0 | 118 | 0.5283 | 0.8488 | 0.7962 | 0.8132 | 0.9092 |
| 0.0474 | 2.0 | 236 | 0.4726 | 0.7961 | 0.7965 | 0.7931 | 0.9075 |
| 0.026 | 3.0 | 354 | 0.5187 | 0.8552 | 0.7999 | 0.8232 | 0.9157 |
| 0.0145 | 4.0 | 472 | 0.5150 | 0.8372 | 0.7791 | 0.7998 | 0.9116 |
| 0.0088 | 5.0 | 590 | 0.5250 | 0.8372 | 0.7818 | 0.8021 | 0.9141 |
| 0.007 | 6.0 | 708 | 0.5299 | 0.8468 | 0.7849 | 0.8072 | 0.9162 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Anastasiaps/Pixelcopter-PLE-v0
|
Anastasiaps
| 2023-10-10T16:50:50Z | 0 | 0 | null |
[
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-30T15:04:10Z |
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Pixelcopter-PLE-v0
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 2.90 +/- 4.23
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
jhilgart22/llama2-7b-moe-text-exp-control-4-peft
|
jhilgart22
| 2023-10-10T16:50:46Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-10T16:44:55Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.4.0
|
jiy03150/vilt_finetuned_200
|
jiy03150
| 2023-10-10T16:47:46Z | 59 | 0 |
transformers
|
[
"transformers",
"pytorch",
"vilt",
"visual-question-answering",
"generated_from_trainer",
"dataset:vqa",
"base_model:dandelin/vilt-b32-mlm",
"base_model:finetune:dandelin/vilt-b32-mlm",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
visual-question-answering
| 2023-10-10T15:53:56Z |
---
license: apache-2.0
base_model: dandelin/vilt-b32-mlm
tags:
- generated_from_trainer
datasets:
- vqa
model-index:
- name: vilt_finetuned_200
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# vilt_finetuned_200
This model is a fine-tuned version of [dandelin/vilt-b32-mlm](https://huggingface.co/dandelin/vilt-b32-mlm) on the vqa dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
### Training results
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
jhilgart22/llama2-7b-moe-text-exp0-4-peft
|
jhilgart22
| 2023-10-10T16:47:18Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-10T16:45:35Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.4.0
|
RogerB/kinyaRoberta-large-kinte-finetuned-kinte-tweet-finetuned-kin-sent3
|
RogerB
| 2023-10-10T16:31:19Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"text-classification",
"generated_from_trainer",
"base_model:RogerB/kinyaRoberta-large-kin-tweets-pretrained",
"base_model:finetune:RogerB/kinyaRoberta-large-kin-tweets-pretrained",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-10T16:25:12Z |
---
base_model: RogerB/kinyaRoberta-large-kinte-finetuned-kinte-tweet-finetuned
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: kinyaRoberta-large-kinte-finetuned-kinte-tweet-finetuned-kin-sent3
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# kinyaRoberta-large-kinte-finetuned-kinte-tweet-finetuned-kin-sent3
This model is a fine-tuned version of [RogerB/kinyaRoberta-large-kinte-finetuned-kinte-tweet-finetuned](https://huggingface.co/RogerB/kinyaRoberta-large-kinte-finetuned-kinte-tweet-finetuned) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9338
- F1: 0.6540
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 10000000
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.8984 | 1.0 | 1013 | 0.6706 | 0.7310 |
| 0.6991 | 2.0 | 2026 | 0.5501 | 0.7923 |
| 0.5978 | 3.0 | 3039 | 0.5253 | 0.8113 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
gptsoho/distilbert-base-uncased-finetuned-emotion
|
gptsoho
| 2023-10-10T15:55:45Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-01T02:44:12Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.936
- name: F1
type: f1
value: 0.9359814439390494
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1703
- Accuracy: 0.936
- F1: 0.9360
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.1741 | 1.0 | 250 | 0.1757 | 0.93 | 0.9309 |
| 0.1158 | 2.0 | 500 | 0.1692 | 0.932 | 0.9330 |
| 0.1014 | 3.0 | 750 | 0.1848 | 0.9285 | 0.9290 |
| 0.0778 | 4.0 | 1000 | 0.1703 | 0.9395 | 0.9394 |
| 0.0616 | 5.0 | 1250 | 0.1672 | 0.938 | 0.9379 |
| 0.0534 | 6.0 | 1500 | 0.1703 | 0.936 | 0.9360 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
vedantjumle/bert-clinc150-1
|
vedantjumle
| 2023-10-10T15:54:47Z | 6 | 0 |
transformers
|
[
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"base_model:google-bert/bert-large-uncased",
"base_model:finetune:google-bert/bert-large-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-10T14:42:08Z |
---
license: apache-2.0
base_model: bert-large-uncased
tags:
- generated_from_keras_callback
model-index:
- name: vedantjumle/bert-clinc150-1
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# vedantjumle/bert-clinc150-1
This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.1204
- Validation Loss: 0.1378
- Train Accuracy: 0.9733
- Epoch: 2
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 12640, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|:----------:|:---------------:|:--------------:|:-----:|
| 2.6008 | 0.5869 | 0.9613 | 0 |
| 0.3623 | 0.1901 | 0.9716 | 1 |
| 0.1204 | 0.1378 | 0.9733 | 2 |
### Framework versions
- Transformers 4.34.0
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.14.1
|
vectoriseai/multilingual-e5-large
|
vectoriseai
| 2023-10-10T15:52:06Z | 9 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"onnx",
"safetensors",
"xlm-roberta",
"mteb",
"Sentence Transformers",
"sentence-similarity",
"feature-extraction",
"multilingual",
"af",
"am",
"ar",
"as",
"az",
"be",
"bg",
"bn",
"br",
"bs",
"ca",
"cs",
"cy",
"da",
"de",
"el",
"en",
"eo",
"es",
"et",
"eu",
"fa",
"fi",
"fr",
"fy",
"ga",
"gd",
"gl",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"is",
"it",
"ja",
"jv",
"ka",
"kk",
"km",
"kn",
"ko",
"ku",
"ky",
"la",
"lo",
"lt",
"lv",
"mg",
"mk",
"ml",
"mn",
"mr",
"ms",
"my",
"ne",
"nl",
"no",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"ro",
"ru",
"sa",
"sd",
"si",
"sk",
"sl",
"so",
"sq",
"sr",
"su",
"sv",
"sw",
"ta",
"te",
"th",
"tl",
"tr",
"ug",
"uk",
"ur",
"uz",
"vi",
"xh",
"yi",
"zh",
"arxiv:2212.03533",
"arxiv:2108.08787",
"arxiv:2104.08663",
"arxiv:2210.07316",
"license:mit",
"model-index",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
feature-extraction
| 2023-10-10T14:35:34Z |
---
tags:
- mteb
- Sentence Transformers
- sentence-similarity
- feature-extraction
- sentence-transformers
model-index:
- name: multilingual-e5-large
results:
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (en)
config: en
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 79.05970149253731
- type: ap
value: 43.486574390835635
- type: f1
value: 73.32700092140148
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (de)
config: de
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 71.22055674518201
- type: ap
value: 81.55756710830498
- type: f1
value: 69.28271787752661
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (en-ext)
config: en-ext
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 80.41979010494754
- type: ap
value: 29.34879922376344
- type: f1
value: 67.62475449011278
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (ja)
config: ja
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 77.8372591006424
- type: ap
value: 26.557560591210738
- type: f1
value: 64.96619417368707
- task:
type: Classification
dataset:
type: mteb/amazon_polarity
name: MTEB AmazonPolarityClassification
config: default
split: test
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
metrics:
- type: accuracy
value: 93.489875
- type: ap
value: 90.98758636917603
- type: f1
value: 93.48554819717332
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (en)
config: en
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 47.564
- type: f1
value: 46.75122173518047
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (de)
config: de
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 45.400000000000006
- type: f1
value: 44.17195682400632
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (es)
config: es
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 43.068
- type: f1
value: 42.38155696855596
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (fr)
config: fr
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 41.89
- type: f1
value: 40.84407321682663
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (ja)
config: ja
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 40.120000000000005
- type: f1
value: 39.522976223819114
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (zh)
config: zh
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 38.832
- type: f1
value: 38.0392533394713
- task:
type: Retrieval
dataset:
type: arguana
name: MTEB ArguAna
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 30.725
- type: map_at_10
value: 46.055
- type: map_at_100
value: 46.900999999999996
- type: map_at_1000
value: 46.911
- type: map_at_3
value: 41.548
- type: map_at_5
value: 44.297
- type: mrr_at_1
value: 31.152
- type: mrr_at_10
value: 46.231
- type: mrr_at_100
value: 47.07
- type: mrr_at_1000
value: 47.08
- type: mrr_at_3
value: 41.738
- type: mrr_at_5
value: 44.468999999999994
- type: ndcg_at_1
value: 30.725
- type: ndcg_at_10
value: 54.379999999999995
- type: ndcg_at_100
value: 58.138
- type: ndcg_at_1000
value: 58.389
- type: ndcg_at_3
value: 45.156
- type: ndcg_at_5
value: 50.123
- type: precision_at_1
value: 30.725
- type: precision_at_10
value: 8.087
- type: precision_at_100
value: 0.9769999999999999
- type: precision_at_1000
value: 0.1
- type: precision_at_3
value: 18.54
- type: precision_at_5
value: 13.542000000000002
- type: recall_at_1
value: 30.725
- type: recall_at_10
value: 80.868
- type: recall_at_100
value: 97.653
- type: recall_at_1000
value: 99.57300000000001
- type: recall_at_3
value: 55.619
- type: recall_at_5
value: 67.71000000000001
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-p2p
name: MTEB ArxivClusteringP2P
config: default
split: test
revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
metrics:
- type: v_measure
value: 44.30960650674069
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-s2s
name: MTEB ArxivClusteringS2S
config: default
split: test
revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53
metrics:
- type: v_measure
value: 38.427074197498996
- task:
type: Reranking
dataset:
type: mteb/askubuntudupquestions-reranking
name: MTEB AskUbuntuDupQuestions
config: default
split: test
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
metrics:
- type: map
value: 60.28270056031872
- type: mrr
value: 74.38332673789738
- task:
type: STS
dataset:
type: mteb/biosses-sts
name: MTEB BIOSSES
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:
- type: cos_sim_pearson
value: 84.05942144105269
- type: cos_sim_spearman
value: 82.51212105850809
- type: euclidean_pearson
value: 81.95639829909122
- type: euclidean_spearman
value: 82.3717564144213
- type: manhattan_pearson
value: 81.79273425468256
- type: manhattan_spearman
value: 82.20066817871039
- task:
type: BitextMining
dataset:
type: mteb/bucc-bitext-mining
name: MTEB BUCC (de-en)
config: de-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy
value: 99.46764091858039
- type: f1
value: 99.37717466945023
- type: precision
value: 99.33194154488518
- type: recall
value: 99.46764091858039
- task:
type: BitextMining
dataset:
type: mteb/bucc-bitext-mining
name: MTEB BUCC (fr-en)
config: fr-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy
value: 98.29407880255337
- type: f1
value: 98.11248073959938
- type: precision
value: 98.02443319392472
- type: recall
value: 98.29407880255337
- task:
type: BitextMining
dataset:
type: mteb/bucc-bitext-mining
name: MTEB BUCC (ru-en)
config: ru-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy
value: 97.79009352268791
- type: f1
value: 97.5176076665512
- type: precision
value: 97.38136473848286
- type: recall
value: 97.79009352268791
- task:
type: BitextMining
dataset:
type: mteb/bucc-bitext-mining
name: MTEB BUCC (zh-en)
config: zh-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy
value: 99.26276987888363
- type: f1
value: 99.20133403545726
- type: precision
value: 99.17500438827453
- type: recall
value: 99.26276987888363
- task:
type: Classification
dataset:
type: mteb/banking77
name: MTEB Banking77Classification
config: default
split: test
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
metrics:
- type: accuracy
value: 84.72727272727273
- type: f1
value: 84.67672206031433
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-p2p
name: MTEB BiorxivClusteringP2P
config: default
split: test
revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
metrics:
- type: v_measure
value: 35.34220182511161
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-s2s
name: MTEB BiorxivClusteringS2S
config: default
split: test
revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
metrics:
- type: v_measure
value: 33.4987096128766
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 25.558249999999997
- type: map_at_10
value: 34.44425000000001
- type: map_at_100
value: 35.59833333333333
- type: map_at_1000
value: 35.706916666666665
- type: map_at_3
value: 31.691749999999995
- type: map_at_5
value: 33.252916666666664
- type: mrr_at_1
value: 30.252666666666666
- type: mrr_at_10
value: 38.60675
- type: mrr_at_100
value: 39.42666666666666
- type: mrr_at_1000
value: 39.48408333333334
- type: mrr_at_3
value: 36.17441666666665
- type: mrr_at_5
value: 37.56275
- type: ndcg_at_1
value: 30.252666666666666
- type: ndcg_at_10
value: 39.683
- type: ndcg_at_100
value: 44.68541666666667
- type: ndcg_at_1000
value: 46.94316666666668
- type: ndcg_at_3
value: 34.961749999999995
- type: ndcg_at_5
value: 37.215666666666664
- type: precision_at_1
value: 30.252666666666666
- type: precision_at_10
value: 6.904166666666667
- type: precision_at_100
value: 1.0989999999999995
- type: precision_at_1000
value: 0.14733333333333334
- type: precision_at_3
value: 16.037666666666667
- type: precision_at_5
value: 11.413583333333333
- type: recall_at_1
value: 25.558249999999997
- type: recall_at_10
value: 51.13341666666666
- type: recall_at_100
value: 73.08366666666667
- type: recall_at_1000
value: 88.79483333333334
- type: recall_at_3
value: 37.989083333333326
- type: recall_at_5
value: 43.787833333333325
- task:
type: Retrieval
dataset:
type: climate-fever
name: MTEB ClimateFEVER
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 10.338
- type: map_at_10
value: 18.360000000000003
- type: map_at_100
value: 19.942
- type: map_at_1000
value: 20.134
- type: map_at_3
value: 15.174000000000001
- type: map_at_5
value: 16.830000000000002
- type: mrr_at_1
value: 23.257
- type: mrr_at_10
value: 33.768
- type: mrr_at_100
value: 34.707
- type: mrr_at_1000
value: 34.766000000000005
- type: mrr_at_3
value: 30.977
- type: mrr_at_5
value: 32.528
- type: ndcg_at_1
value: 23.257
- type: ndcg_at_10
value: 25.733
- type: ndcg_at_100
value: 32.288
- type: ndcg_at_1000
value: 35.992000000000004
- type: ndcg_at_3
value: 20.866
- type: ndcg_at_5
value: 22.612
- type: precision_at_1
value: 23.257
- type: precision_at_10
value: 8.124
- type: precision_at_100
value: 1.518
- type: precision_at_1000
value: 0.219
- type: precision_at_3
value: 15.679000000000002
- type: precision_at_5
value: 12.117
- type: recall_at_1
value: 10.338
- type: recall_at_10
value: 31.154
- type: recall_at_100
value: 54.161
- type: recall_at_1000
value: 75.21900000000001
- type: recall_at_3
value: 19.427
- type: recall_at_5
value: 24.214
- task:
type: Retrieval
dataset:
type: dbpedia-entity
name: MTEB DBPedia
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 8.498
- type: map_at_10
value: 19.103
- type: map_at_100
value: 27.375
- type: map_at_1000
value: 28.981
- type: map_at_3
value: 13.764999999999999
- type: map_at_5
value: 15.950000000000001
- type: mrr_at_1
value: 65.5
- type: mrr_at_10
value: 74.53800000000001
- type: mrr_at_100
value: 74.71799999999999
- type: mrr_at_1000
value: 74.725
- type: mrr_at_3
value: 72.792
- type: mrr_at_5
value: 73.554
- type: ndcg_at_1
value: 53.37499999999999
- type: ndcg_at_10
value: 41.286
- type: ndcg_at_100
value: 45.972
- type: ndcg_at_1000
value: 53.123
- type: ndcg_at_3
value: 46.172999999999995
- type: ndcg_at_5
value: 43.033
- type: precision_at_1
value: 65.5
- type: precision_at_10
value: 32.725
- type: precision_at_100
value: 10.683
- type: precision_at_1000
value: 1.978
- type: precision_at_3
value: 50
- type: precision_at_5
value: 41.349999999999994
- type: recall_at_1
value: 8.498
- type: recall_at_10
value: 25.070999999999998
- type: recall_at_100
value: 52.383
- type: recall_at_1000
value: 74.91499999999999
- type: recall_at_3
value: 15.207999999999998
- type: recall_at_5
value: 18.563
- task:
type: Classification
dataset:
type: mteb/emotion
name: MTEB EmotionClassification
config: default
split: test
revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
metrics:
- type: accuracy
value: 46.5
- type: f1
value: 41.93833713984145
- task:
type: Retrieval
dataset:
type: fever
name: MTEB FEVER
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 67.914
- type: map_at_10
value: 78.10000000000001
- type: map_at_100
value: 78.333
- type: map_at_1000
value: 78.346
- type: map_at_3
value: 76.626
- type: map_at_5
value: 77.627
- type: mrr_at_1
value: 72.74199999999999
- type: mrr_at_10
value: 82.414
- type: mrr_at_100
value: 82.511
- type: mrr_at_1000
value: 82.513
- type: mrr_at_3
value: 81.231
- type: mrr_at_5
value: 82.065
- type: ndcg_at_1
value: 72.74199999999999
- type: ndcg_at_10
value: 82.806
- type: ndcg_at_100
value: 83.677
- type: ndcg_at_1000
value: 83.917
- type: ndcg_at_3
value: 80.305
- type: ndcg_at_5
value: 81.843
- type: precision_at_1
value: 72.74199999999999
- type: precision_at_10
value: 10.24
- type: precision_at_100
value: 1.089
- type: precision_at_1000
value: 0.11299999999999999
- type: precision_at_3
value: 31.268
- type: precision_at_5
value: 19.706000000000003
- type: recall_at_1
value: 67.914
- type: recall_at_10
value: 92.889
- type: recall_at_100
value: 96.42699999999999
- type: recall_at_1000
value: 97.92
- type: recall_at_3
value: 86.21
- type: recall_at_5
value: 90.036
- task:
type: Retrieval
dataset:
type: fiqa
name: MTEB FiQA2018
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 22.166
- type: map_at_10
value: 35.57
- type: map_at_100
value: 37.405
- type: map_at_1000
value: 37.564
- type: map_at_3
value: 30.379
- type: map_at_5
value: 33.324
- type: mrr_at_1
value: 43.519000000000005
- type: mrr_at_10
value: 51.556000000000004
- type: mrr_at_100
value: 52.344
- type: mrr_at_1000
value: 52.373999999999995
- type: mrr_at_3
value: 48.868
- type: mrr_at_5
value: 50.319
- type: ndcg_at_1
value: 43.519000000000005
- type: ndcg_at_10
value: 43.803
- type: ndcg_at_100
value: 50.468999999999994
- type: ndcg_at_1000
value: 53.111
- type: ndcg_at_3
value: 38.893
- type: ndcg_at_5
value: 40.653
- type: precision_at_1
value: 43.519000000000005
- type: precision_at_10
value: 12.253
- type: precision_at_100
value: 1.931
- type: precision_at_1000
value: 0.242
- type: precision_at_3
value: 25.617
- type: precision_at_5
value: 19.383
- type: recall_at_1
value: 22.166
- type: recall_at_10
value: 51.6
- type: recall_at_100
value: 76.574
- type: recall_at_1000
value: 92.192
- type: recall_at_3
value: 34.477999999999994
- type: recall_at_5
value: 41.835
- task:
type: Retrieval
dataset:
type: hotpotqa
name: MTEB HotpotQA
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 39.041
- type: map_at_10
value: 62.961999999999996
- type: map_at_100
value: 63.79899999999999
- type: map_at_1000
value: 63.854
- type: map_at_3
value: 59.399
- type: map_at_5
value: 61.669
- type: mrr_at_1
value: 78.082
- type: mrr_at_10
value: 84.321
- type: mrr_at_100
value: 84.49600000000001
- type: mrr_at_1000
value: 84.502
- type: mrr_at_3
value: 83.421
- type: mrr_at_5
value: 83.977
- type: ndcg_at_1
value: 78.082
- type: ndcg_at_10
value: 71.229
- type: ndcg_at_100
value: 74.10900000000001
- type: ndcg_at_1000
value: 75.169
- type: ndcg_at_3
value: 66.28699999999999
- type: ndcg_at_5
value: 69.084
- type: precision_at_1
value: 78.082
- type: precision_at_10
value: 14.993
- type: precision_at_100
value: 1.7239999999999998
- type: precision_at_1000
value: 0.186
- type: precision_at_3
value: 42.737
- type: precision_at_5
value: 27.843
- type: recall_at_1
value: 39.041
- type: recall_at_10
value: 74.96300000000001
- type: recall_at_100
value: 86.199
- type: recall_at_1000
value: 93.228
- type: recall_at_3
value: 64.105
- type: recall_at_5
value: 69.608
- task:
type: Classification
dataset:
type: mteb/imdb
name: MTEB ImdbClassification
config: default
split: test
revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
metrics:
- type: accuracy
value: 90.23160000000001
- type: ap
value: 85.5674856808308
- type: f1
value: 90.18033354786317
- task:
type: Retrieval
dataset:
type: msmarco
name: MTEB MSMARCO
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 24.091
- type: map_at_10
value: 36.753
- type: map_at_100
value: 37.913000000000004
- type: map_at_1000
value: 37.958999999999996
- type: map_at_3
value: 32.818999999999996
- type: map_at_5
value: 35.171
- type: mrr_at_1
value: 24.742
- type: mrr_at_10
value: 37.285000000000004
- type: mrr_at_100
value: 38.391999999999996
- type: mrr_at_1000
value: 38.431
- type: mrr_at_3
value: 33.440999999999995
- type: mrr_at_5
value: 35.75
- type: ndcg_at_1
value: 24.742
- type: ndcg_at_10
value: 43.698
- type: ndcg_at_100
value: 49.145
- type: ndcg_at_1000
value: 50.23800000000001
- type: ndcg_at_3
value: 35.769
- type: ndcg_at_5
value: 39.961999999999996
- type: precision_at_1
value: 24.742
- type: precision_at_10
value: 6.7989999999999995
- type: precision_at_100
value: 0.95
- type: precision_at_1000
value: 0.104
- type: precision_at_3
value: 15.096000000000002
- type: precision_at_5
value: 11.183
- type: recall_at_1
value: 24.091
- type: recall_at_10
value: 65.068
- type: recall_at_100
value: 89.899
- type: recall_at_1000
value: 98.16
- type: recall_at_3
value: 43.68
- type: recall_at_5
value: 53.754999999999995
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (en)
config: en
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 93.66621067031465
- type: f1
value: 93.49622853272142
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (de)
config: de
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 91.94702733164272
- type: f1
value: 91.17043441745282
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (es)
config: es
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 92.20146764509674
- type: f1
value: 91.98359080555608
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (fr)
config: fr
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 88.99780770435328
- type: f1
value: 89.19746342724068
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (hi)
config: hi
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 89.78486912871998
- type: f1
value: 89.24578823628642
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (th)
config: th
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 88.74502712477394
- type: f1
value: 89.00297573881542
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (en)
config: en
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 77.9046967624259
- type: f1
value: 59.36787125785957
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (de)
config: de
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 74.5280360664976
- type: f1
value: 57.17723440888718
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (es)
config: es
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 75.44029352901934
- type: f1
value: 54.052855531072964
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (fr)
config: fr
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 70.5606013153774
- type: f1
value: 52.62215934386531
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (hi)
config: hi
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 73.11581211903908
- type: f1
value: 52.341291845645465
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (th)
config: th
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 74.28933092224233
- type: f1
value: 57.07918745504911
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (af)
config: af
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 62.38063214525892
- type: f1
value: 59.46463723443009
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (am)
config: am
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 56.06926698049766
- type: f1
value: 52.49084283283562
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ar)
config: ar
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 60.74983187626093
- type: f1
value: 56.960640620165904
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (az)
config: az
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 64.86550100874243
- type: f1
value: 62.47370548140688
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (bn)
config: bn
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 63.971082716879636
- type: f1
value: 61.03812421957381
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (cy)
config: cy
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 54.98318762609282
- type: f1
value: 51.51207916008392
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (da)
config: da
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.45527908540686
- type: f1
value: 66.16631905400318
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (de)
config: de
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.32750504371216
- type: f1
value: 66.16755288646591
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (el)
config: el
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.09213180901143
- type: f1
value: 66.95654394661507
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (en)
config: en
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 73.75588433086752
- type: f1
value: 71.79973779656923
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (es)
config: es
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 70.49428379287154
- type: f1
value: 68.37494379215734
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (fa)
config: fa
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.90921318090115
- type: f1
value: 66.79517376481645
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (fi)
config: fi
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 70.12104909213181
- type: f1
value: 67.29448842879584
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (fr)
config: fr
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.34095494283793
- type: f1
value: 67.01134288992947
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (he)
config: he
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 67.61264290517822
- type: f1
value: 64.68730512660757
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (hi)
config: hi
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 67.79757901815738
- type: f1
value: 65.24938539425598
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (hu)
config: hu
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.68728984532616
- type: f1
value: 67.0487169762553
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (hy)
config: hy
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 62.07464694014795
- type: f1
value: 59.183532276789286
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (id)
config: id
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 70.04707464694015
- type: f1
value: 67.66829629003848
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (is)
config: is
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 62.42434431741762
- type: f1
value: 59.01617226544757
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (it)
config: it
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 70.53127101546738
- type: f1
value: 68.10033760906255
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ja)
config: ja
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 72.50504371217215
- type: f1
value: 69.74931103158923
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (jv)
config: jv
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 57.91190316072628
- type: f1
value: 54.05551136648796
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ka)
config: ka
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 51.78211163416275
- type: f1
value: 49.874888544058535
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (km)
config: km
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 47.017484868863484
- type: f1
value: 44.53364263352014
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (kn)
config: kn
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 62.16207128446537
- type: f1
value: 59.01185692320829
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ko)
config: ko
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.42501681237391
- type: f1
value: 67.13169450166086
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (lv)
config: lv
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 67.0780094149294
- type: f1
value: 64.41720167850707
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ml)
config: ml
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 65.57162071284466
- type: f1
value: 62.414138683804424
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (mn)
config: mn
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 61.71149966375252
- type: f1
value: 58.594805125087234
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ms)
config: ms
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 66.03900470746471
- type: f1
value: 63.87937257883887
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (my)
config: my
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 60.8776059179556
- type: f1
value: 57.48587618059131
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (nb)
config: nb
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.87895090786819
- type: f1
value: 66.8141299430347
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (nl)
config: nl
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 70.45057162071285
- type: f1
value: 67.46444039673516
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (pl)
config: pl
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 71.546738399462
- type: f1
value: 68.63640876702655
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (pt)
config: pt
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 70.72965702757229
- type: f1
value: 68.54119560379115
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ro)
config: ro
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 68.35574983187625
- type: f1
value: 65.88844917691927
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ru)
config: ru
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 71.70477471418964
- type: f1
value: 69.19665697061978
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (sl)
config: sl
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 67.0880968392737
- type: f1
value: 64.76962317666086
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (sq)
config: sq
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 65.18493611297916
- type: f1
value: 62.49984559035371
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (sv)
config: sv
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 71.75857431069265
- type: f1
value: 69.20053687623418
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (sw)
config: sw
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 58.500336247478145
- type: f1
value: 55.2972398687929
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ta)
config: ta
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 62.68997982515132
- type: f1
value: 59.36848202755348
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (te)
config: te
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 63.01950235373235
- type: f1
value: 60.09351954625423
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (th)
config: th
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 68.29186281102892
- type: f1
value: 67.57860496703447
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (tl)
config: tl
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 64.77471418964357
- type: f1
value: 61.913983147713836
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (tr)
config: tr
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.87222595830532
- type: f1
value: 66.03679033708141
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ur)
config: ur
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 64.04505716207127
- type: f1
value: 61.28569169817908
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (vi)
config: vi
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.38466711499663
- type: f1
value: 67.20532357036844
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (zh-CN)
config: zh-CN
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 71.12306657700067
- type: f1
value: 68.91251226588182
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (zh-TW)
config: zh-TW
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 66.20040349697378
- type: f1
value: 66.02657347714175
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (af)
config: af
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 68.73907195696032
- type: f1
value: 66.98484521791418
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (am)
config: am
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 60.58843308675185
- type: f1
value: 58.95591723092005
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ar)
config: ar
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 66.22730329522528
- type: f1
value: 66.0894499712115
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (az)
config: az
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 66.48285137861465
- type: f1
value: 65.21963176785157
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (bn)
config: bn
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 67.74714189643578
- type: f1
value: 66.8212192745412
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (cy)
config: cy
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 59.09213180901143
- type: f1
value: 56.70735546356339
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (da)
config: da
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 75.05716207128448
- type: f1
value: 74.8413712365364
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (de)
config: de
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.69737726967047
- type: f1
value: 74.7664341963
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (el)
config: el
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 73.90383322125084
- type: f1
value: 73.59201554448323
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (en)
config: en
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 77.51176866173503
- type: f1
value: 77.46104434577758
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (es)
config: es
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.31069266980496
- type: f1
value: 74.61048660675635
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (fa)
config: fa
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 72.95225285810356
- type: f1
value: 72.33160006574627
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (fi)
config: fi
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 73.12373907195696
- type: f1
value: 73.20921012557481
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (fr)
config: fr
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 73.86684599865501
- type: f1
value: 73.82348774610831
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (he)
config: he
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.40215198386012
- type: f1
value: 71.11945183971858
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (hi)
config: hi
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 72.12844653665098
- type: f1
value: 71.34450495911766
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (hu)
config: hu
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.52252858103566
- type: f1
value: 73.98878711342999
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (hy)
config: hy
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 64.93611297915265
- type: f1
value: 63.723200467653385
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (id)
config: id
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.11903160726295
- type: f1
value: 73.82138439467096
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (is)
config: is
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 67.15198386012105
- type: f1
value: 66.02172193802167
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (it)
config: it
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.32414256893072
- type: f1
value: 74.30943421170574
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ja)
config: ja
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 77.46805648957633
- type: f1
value: 77.62808409298209
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (jv)
config: jv
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 63.318762609280434
- type: f1
value: 62.094284066075076
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ka)
config: ka
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 58.34902488231338
- type: f1
value: 57.12893860987984
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (km)
config: km
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 50.88433086751849
- type: f1
value: 48.2272350802058
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (kn)
config: kn
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 66.4425016812374
- type: f1
value: 64.61463095996173
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ko)
config: ko
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 75.04707464694015
- type: f1
value: 75.05099199098998
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (lv)
config: lv
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.50437121721586
- type: f1
value: 69.83397721096314
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ml)
config: ml
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 69.94283792871553
- type: f1
value: 68.8704663703913
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (mn)
config: mn
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 64.79488903833222
- type: f1
value: 63.615424063345436
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ms)
config: ms
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 69.88231338264963
- type: f1
value: 68.57892302593237
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (my)
config: my
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 63.248150638870214
- type: f1
value: 61.06680605338809
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (nb)
config: nb
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.84196368527236
- type: f1
value: 74.52566464968763
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (nl)
config: nl
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.8285137861466
- type: f1
value: 74.8853197608802
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (pl)
config: pl
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.13248150638869
- type: f1
value: 74.3982040999179
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (pt)
config: pt
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 73.49024882313383
- type: f1
value: 73.82153848368573
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ro)
config: ro
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.72158708809684
- type: f1
value: 71.85049433180541
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ru)
config: ru
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 75.137861466039
- type: f1
value: 75.37628348188467
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (sl)
config: sl
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.86953597848016
- type: f1
value: 71.87537624521661
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (sq)
config: sq
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.27572293207801
- type: f1
value: 68.80017302344231
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (sv)
config: sv
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 76.09952925353059
- type: f1
value: 76.07992707688408
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (sw)
config: sw
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 63.140551445864155
- type: f1
value: 61.73855010331415
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ta)
config: ta
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 66.27774041694687
- type: f1
value: 64.83664868894539
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (te)
config: te
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 66.69468728984533
- type: f1
value: 64.76239666920868
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (th)
config: th
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 73.44653665097512
- type: f1
value: 73.14646052013873
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (tl)
config: tl
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 67.71351714862139
- type: f1
value: 66.67212180163382
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (tr)
config: tr
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 73.9946200403497
- type: f1
value: 73.87348793725525
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ur)
config: ur
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 68.15400134498992
- type: f1
value: 67.09433241421094
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (vi)
config: vi
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 73.11365164761264
- type: f1
value: 73.59502539433753
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (zh-CN)
config: zh-CN
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 76.82582380632145
- type: f1
value: 76.89992945316313
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (zh-TW)
config: zh-TW
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.81237390719569
- type: f1
value: 72.36499770986265
- task:
type: Clustering
dataset:
type: mteb/medrxiv-clustering-p2p
name: MTEB MedrxivClusteringP2P
config: default
split: test
revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73
metrics:
- type: v_measure
value: 31.480506569594695
- task:
type: Clustering
dataset:
type: mteb/medrxiv-clustering-s2s
name: MTEB MedrxivClusteringS2S
config: default
split: test
revision: 35191c8c0dca72d8ff3efcd72aa802307d469663
metrics:
- type: v_measure
value: 29.71252128004552
- task:
type: Reranking
dataset:
type: mteb/mind_small
name: MTEB MindSmallReranking
config: default
split: test
revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69
metrics:
- type: map
value: 31.421396787056548
- type: mrr
value: 32.48155274872267
- task:
type: Retrieval
dataset:
type: nfcorpus
name: MTEB NFCorpus
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 5.595
- type: map_at_10
value: 12.642000000000001
- type: map_at_100
value: 15.726
- type: map_at_1000
value: 17.061999999999998
- type: map_at_3
value: 9.125
- type: map_at_5
value: 10.866000000000001
- type: mrr_at_1
value: 43.344
- type: mrr_at_10
value: 52.227999999999994
- type: mrr_at_100
value: 52.898999999999994
- type: mrr_at_1000
value: 52.944
- type: mrr_at_3
value: 49.845
- type: mrr_at_5
value: 51.115
- type: ndcg_at_1
value: 41.949999999999996
- type: ndcg_at_10
value: 33.995
- type: ndcg_at_100
value: 30.869999999999997
- type: ndcg_at_1000
value: 39.487
- type: ndcg_at_3
value: 38.903999999999996
- type: ndcg_at_5
value: 37.236999999999995
- type: precision_at_1
value: 43.344
- type: precision_at_10
value: 25.480000000000004
- type: precision_at_100
value: 7.672
- type: precision_at_1000
value: 2.028
- type: precision_at_3
value: 36.636
- type: precision_at_5
value: 32.632
- type: recall_at_1
value: 5.595
- type: recall_at_10
value: 16.466
- type: recall_at_100
value: 31.226
- type: recall_at_1000
value: 62.778999999999996
- type: recall_at_3
value: 9.931
- type: recall_at_5
value: 12.884
- task:
type: Retrieval
dataset:
type: nq
name: MTEB NQ
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 40.414
- type: map_at_10
value: 56.754000000000005
- type: map_at_100
value: 57.457
- type: map_at_1000
value: 57.477999999999994
- type: map_at_3
value: 52.873999999999995
- type: map_at_5
value: 55.175
- type: mrr_at_1
value: 45.278
- type: mrr_at_10
value: 59.192
- type: mrr_at_100
value: 59.650000000000006
- type: mrr_at_1000
value: 59.665
- type: mrr_at_3
value: 56.141
- type: mrr_at_5
value: 57.998000000000005
- type: ndcg_at_1
value: 45.278
- type: ndcg_at_10
value: 64.056
- type: ndcg_at_100
value: 66.89
- type: ndcg_at_1000
value: 67.364
- type: ndcg_at_3
value: 56.97
- type: ndcg_at_5
value: 60.719
- type: precision_at_1
value: 45.278
- type: precision_at_10
value: 9.994
- type: precision_at_100
value: 1.165
- type: precision_at_1000
value: 0.121
- type: precision_at_3
value: 25.512
- type: precision_at_5
value: 17.509
- type: recall_at_1
value: 40.414
- type: recall_at_10
value: 83.596
- type: recall_at_100
value: 95.72
- type: recall_at_1000
value: 99.24
- type: recall_at_3
value: 65.472
- type: recall_at_5
value: 74.039
- task:
type: Retrieval
dataset:
type: quora
name: MTEB QuoraRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 70.352
- type: map_at_10
value: 84.369
- type: map_at_100
value: 85.02499999999999
- type: map_at_1000
value: 85.04
- type: map_at_3
value: 81.42399999999999
- type: map_at_5
value: 83.279
- type: mrr_at_1
value: 81.05
- type: mrr_at_10
value: 87.401
- type: mrr_at_100
value: 87.504
- type: mrr_at_1000
value: 87.505
- type: mrr_at_3
value: 86.443
- type: mrr_at_5
value: 87.10799999999999
- type: ndcg_at_1
value: 81.04
- type: ndcg_at_10
value: 88.181
- type: ndcg_at_100
value: 89.411
- type: ndcg_at_1000
value: 89.507
- type: ndcg_at_3
value: 85.28099999999999
- type: ndcg_at_5
value: 86.888
- type: precision_at_1
value: 81.04
- type: precision_at_10
value: 13.406
- type: precision_at_100
value: 1.5350000000000001
- type: precision_at_1000
value: 0.157
- type: precision_at_3
value: 37.31
- type: precision_at_5
value: 24.54
- type: recall_at_1
value: 70.352
- type: recall_at_10
value: 95.358
- type: recall_at_100
value: 99.541
- type: recall_at_1000
value: 99.984
- type: recall_at_3
value: 87.111
- type: recall_at_5
value: 91.643
- task:
type: Clustering
dataset:
type: mteb/reddit-clustering
name: MTEB RedditClustering
config: default
split: test
revision: 24640382cdbf8abc73003fb0fa6d111a705499eb
metrics:
- type: v_measure
value: 46.54068723291946
- task:
type: Clustering
dataset:
type: mteb/reddit-clustering-p2p
name: MTEB RedditClusteringP2P
config: default
split: test
revision: 282350215ef01743dc01b456c7f5241fa8937f16
metrics:
- type: v_measure
value: 63.216287629895994
- task:
type: Retrieval
dataset:
type: scidocs
name: MTEB SCIDOCS
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 4.023000000000001
- type: map_at_10
value: 10.071
- type: map_at_100
value: 11.892
- type: map_at_1000
value: 12.196
- type: map_at_3
value: 7.234
- type: map_at_5
value: 8.613999999999999
- type: mrr_at_1
value: 19.900000000000002
- type: mrr_at_10
value: 30.516
- type: mrr_at_100
value: 31.656000000000002
- type: mrr_at_1000
value: 31.723000000000003
- type: mrr_at_3
value: 27.400000000000002
- type: mrr_at_5
value: 29.270000000000003
- type: ndcg_at_1
value: 19.900000000000002
- type: ndcg_at_10
value: 17.474
- type: ndcg_at_100
value: 25.020999999999997
- type: ndcg_at_1000
value: 30.728
- type: ndcg_at_3
value: 16.588
- type: ndcg_at_5
value: 14.498
- type: precision_at_1
value: 19.900000000000002
- type: precision_at_10
value: 9.139999999999999
- type: precision_at_100
value: 2.011
- type: precision_at_1000
value: 0.33899999999999997
- type: precision_at_3
value: 15.667
- type: precision_at_5
value: 12.839999999999998
- type: recall_at_1
value: 4.023000000000001
- type: recall_at_10
value: 18.497
- type: recall_at_100
value: 40.8
- type: recall_at_1000
value: 68.812
- type: recall_at_3
value: 9.508
- type: recall_at_5
value: 12.983
- task:
type: STS
dataset:
type: mteb/sickr-sts
name: MTEB SICK-R
config: default
split: test
revision: a6ea5a8cab320b040a23452cc28066d9beae2cee
metrics:
- type: cos_sim_pearson
value: 83.967008785134
- type: cos_sim_spearman
value: 80.23142141101837
- type: euclidean_pearson
value: 81.20166064704539
- type: euclidean_spearman
value: 80.18961335654585
- type: manhattan_pearson
value: 81.13925443187625
- type: manhattan_spearman
value: 80.07948723044424
- task:
type: STS
dataset:
type: mteb/sts12-sts
name: MTEB STS12
config: default
split: test
revision: a0d554a64d88156834ff5ae9920b964011b16384
metrics:
- type: cos_sim_pearson
value: 86.94262461316023
- type: cos_sim_spearman
value: 80.01596278563865
- type: euclidean_pearson
value: 83.80799622922581
- type: euclidean_spearman
value: 79.94984954947103
- type: manhattan_pearson
value: 83.68473841756281
- type: manhattan_spearman
value: 79.84990707951822
- task:
type: STS
dataset:
type: mteb/sts13-sts
name: MTEB STS13
config: default
split: test
revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
metrics:
- type: cos_sim_pearson
value: 80.57346443146068
- type: cos_sim_spearman
value: 81.54689837570866
- type: euclidean_pearson
value: 81.10909881516007
- type: euclidean_spearman
value: 81.56746243261762
- type: manhattan_pearson
value: 80.87076036186582
- type: manhattan_spearman
value: 81.33074987964402
- task:
type: STS
dataset:
type: mteb/sts14-sts
name: MTEB STS14
config: default
split: test
revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
metrics:
- type: cos_sim_pearson
value: 79.54733787179849
- type: cos_sim_spearman
value: 77.72202105610411
- type: euclidean_pearson
value: 78.9043595478849
- type: euclidean_spearman
value: 77.93422804309435
- type: manhattan_pearson
value: 78.58115121621368
- type: manhattan_spearman
value: 77.62508135122033
- task:
type: STS
dataset:
type: mteb/sts15-sts
name: MTEB STS15
config: default
split: test
revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
metrics:
- type: cos_sim_pearson
value: 88.59880017237558
- type: cos_sim_spearman
value: 89.31088630824758
- type: euclidean_pearson
value: 88.47069261564656
- type: euclidean_spearman
value: 89.33581971465233
- type: manhattan_pearson
value: 88.40774264100956
- type: manhattan_spearman
value: 89.28657485627835
- task:
type: STS
dataset:
type: mteb/sts16-sts
name: MTEB STS16
config: default
split: test
revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
metrics:
- type: cos_sim_pearson
value: 84.08055117917084
- type: cos_sim_spearman
value: 85.78491813080304
- type: euclidean_pearson
value: 84.99329155500392
- type: euclidean_spearman
value: 85.76728064677287
- type: manhattan_pearson
value: 84.87947428989587
- type: manhattan_spearman
value: 85.62429454917464
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (ko-ko)
config: ko-ko
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 82.14190939287384
- type: cos_sim_spearman
value: 82.27331573306041
- type: euclidean_pearson
value: 81.891896953716
- type: euclidean_spearman
value: 82.37695542955998
- type: manhattan_pearson
value: 81.73123869460504
- type: manhattan_spearman
value: 82.19989168441421
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (ar-ar)
config: ar-ar
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 76.84695301843362
- type: cos_sim_spearman
value: 77.87790986014461
- type: euclidean_pearson
value: 76.91981583106315
- type: euclidean_spearman
value: 77.88154772749589
- type: manhattan_pearson
value: 76.94953277451093
- type: manhattan_spearman
value: 77.80499230728604
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (en-ar)
config: en-ar
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 75.44657840482016
- type: cos_sim_spearman
value: 75.05531095119674
- type: euclidean_pearson
value: 75.88161755829299
- type: euclidean_spearman
value: 74.73176238219332
- type: manhattan_pearson
value: 75.63984765635362
- type: manhattan_spearman
value: 74.86476440770737
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (en-de)
config: en-de
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 85.64700140524133
- type: cos_sim_spearman
value: 86.16014210425672
- type: euclidean_pearson
value: 86.49086860843221
- type: euclidean_spearman
value: 86.09729326815614
- type: manhattan_pearson
value: 86.43406265125513
- type: manhattan_spearman
value: 86.17740150939994
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (en-en)
config: en-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 87.91170098764921
- type: cos_sim_spearman
value: 88.12437004058931
- type: euclidean_pearson
value: 88.81828254494437
- type: euclidean_spearman
value: 88.14831794572122
- type: manhattan_pearson
value: 88.93442183448961
- type: manhattan_spearman
value: 88.15254630778304
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (en-tr)
config: en-tr
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 72.91390577997292
- type: cos_sim_spearman
value: 71.22979457536074
- type: euclidean_pearson
value: 74.40314008106749
- type: euclidean_spearman
value: 72.54972136083246
- type: manhattan_pearson
value: 73.85687539530218
- type: manhattan_spearman
value: 72.09500771742637
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (es-en)
config: es-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 80.9301067983089
- type: cos_sim_spearman
value: 80.74989828346473
- type: euclidean_pearson
value: 81.36781301814257
- type: euclidean_spearman
value: 80.9448819964426
- type: manhattan_pearson
value: 81.0351322685609
- type: manhattan_spearman
value: 80.70192121844177
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (es-es)
config: es-es
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 87.13820465980005
- type: cos_sim_spearman
value: 86.73532498758757
- type: euclidean_pearson
value: 87.21329451846637
- type: euclidean_spearman
value: 86.57863198601002
- type: manhattan_pearson
value: 87.06973713818554
- type: manhattan_spearman
value: 86.47534918791499
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (fr-en)
config: fr-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 85.48720108904415
- type: cos_sim_spearman
value: 85.62221757068387
- type: euclidean_pearson
value: 86.1010129512749
- type: euclidean_spearman
value: 85.86580966509942
- type: manhattan_pearson
value: 86.26800938808971
- type: manhattan_spearman
value: 85.88902721678429
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (it-en)
config: it-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 83.98021347333516
- type: cos_sim_spearman
value: 84.53806553803501
- type: euclidean_pearson
value: 84.61483347248364
- type: euclidean_spearman
value: 85.14191408011702
- type: manhattan_pearson
value: 84.75297588825967
- type: manhattan_spearman
value: 85.33176753669242
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (nl-en)
config: nl-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 84.51856644893233
- type: cos_sim_spearman
value: 85.27510748506413
- type: euclidean_pearson
value: 85.09886861540977
- type: euclidean_spearman
value: 85.62579245860887
- type: manhattan_pearson
value: 84.93017860464607
- type: manhattan_spearman
value: 85.5063988898453
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (en)
config: en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 62.581573200584195
- type: cos_sim_spearman
value: 63.05503590247928
- type: euclidean_pearson
value: 63.652564812602094
- type: euclidean_spearman
value: 62.64811520876156
- type: manhattan_pearson
value: 63.506842893061076
- type: manhattan_spearman
value: 62.51289573046917
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (de)
config: de
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 48.2248801729127
- type: cos_sim_spearman
value: 56.5936604678561
- type: euclidean_pearson
value: 43.98149464089
- type: euclidean_spearman
value: 56.108561882423615
- type: manhattan_pearson
value: 43.86880305903564
- type: manhattan_spearman
value: 56.04671150510166
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (es)
config: es
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 55.17564527009831
- type: cos_sim_spearman
value: 64.57978560979488
- type: euclidean_pearson
value: 58.8818330154583
- type: euclidean_spearman
value: 64.99214839071281
- type: manhattan_pearson
value: 58.72671436121381
- type: manhattan_spearman
value: 65.10713416616109
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (pl)
config: pl
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 26.772131864023297
- type: cos_sim_spearman
value: 34.68200792408681
- type: euclidean_pearson
value: 16.68082419005441
- type: euclidean_spearman
value: 34.83099932652166
- type: manhattan_pearson
value: 16.52605949659529
- type: manhattan_spearman
value: 34.82075801399475
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (tr)
config: tr
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 54.42415189043831
- type: cos_sim_spearman
value: 63.54594264576758
- type: euclidean_pearson
value: 57.36577498297745
- type: euclidean_spearman
value: 63.111466379158074
- type: manhattan_pearson
value: 57.584543715873885
- type: manhattan_spearman
value: 63.22361054139183
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (ar)
config: ar
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 47.55216762405518
- type: cos_sim_spearman
value: 56.98670142896412
- type: euclidean_pearson
value: 50.15318757562699
- type: euclidean_spearman
value: 56.524941926541906
- type: manhattan_pearson
value: 49.955618528674904
- type: manhattan_spearman
value: 56.37102209240117
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (ru)
config: ru
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 49.20540980338571
- type: cos_sim_spearman
value: 59.9009453504406
- type: euclidean_pearson
value: 49.557749853620535
- type: euclidean_spearman
value: 59.76631621172456
- type: manhattan_pearson
value: 49.62340591181147
- type: manhattan_spearman
value: 59.94224880322436
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (zh)
config: zh
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 51.508169956576985
- type: cos_sim_spearman
value: 66.82461565306046
- type: euclidean_pearson
value: 56.2274426480083
- type: euclidean_spearman
value: 66.6775323848333
- type: manhattan_pearson
value: 55.98277796300661
- type: manhattan_spearman
value: 66.63669848497175
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (fr)
config: fr
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 72.86478788045507
- type: cos_sim_spearman
value: 76.7946552053193
- type: euclidean_pearson
value: 75.01598530490269
- type: euclidean_spearman
value: 76.83618917858281
- type: manhattan_pearson
value: 74.68337628304332
- type: manhattan_spearman
value: 76.57480204017773
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (de-en)
config: de-en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 55.922619099401984
- type: cos_sim_spearman
value: 56.599362477240774
- type: euclidean_pearson
value: 56.68307052369783
- type: euclidean_spearman
value: 54.28760436777401
- type: manhattan_pearson
value: 56.67763566500681
- type: manhattan_spearman
value: 53.94619541711359
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (es-en)
config: es-en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 66.74357206710913
- type: cos_sim_spearman
value: 72.5208244925311
- type: euclidean_pearson
value: 67.49254562186032
- type: euclidean_spearman
value: 72.02469076238683
- type: manhattan_pearson
value: 67.45251772238085
- type: manhattan_spearman
value: 72.05538819984538
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (it)
config: it
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 71.25734330033191
- type: cos_sim_spearman
value: 76.98349083946823
- type: euclidean_pearson
value: 73.71642838667736
- type: euclidean_spearman
value: 77.01715504651384
- type: manhattan_pearson
value: 73.61712711868105
- type: manhattan_spearman
value: 77.01392571153896
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (pl-en)
config: pl-en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 63.18215462781212
- type: cos_sim_spearman
value: 65.54373266117607
- type: euclidean_pearson
value: 64.54126095439005
- type: euclidean_spearman
value: 65.30410369102711
- type: manhattan_pearson
value: 63.50332221148234
- type: manhattan_spearman
value: 64.3455878104313
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (zh-en)
config: zh-en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 62.30509221440029
- type: cos_sim_spearman
value: 65.99582704642478
- type: euclidean_pearson
value: 63.43818859884195
- type: euclidean_spearman
value: 66.83172582815764
- type: manhattan_pearson
value: 63.055779168508764
- type: manhattan_spearman
value: 65.49585020501449
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (es-it)
config: es-it
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 59.587830825340404
- type: cos_sim_spearman
value: 68.93467614588089
- type: euclidean_pearson
value: 62.3073527367404
- type: euclidean_spearman
value: 69.69758171553175
- type: manhattan_pearson
value: 61.9074580815789
- type: manhattan_spearman
value: 69.57696375597865
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (de-fr)
config: de-fr
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 57.143220125577066
- type: cos_sim_spearman
value: 67.78857859159226
- type: euclidean_pearson
value: 55.58225107923733
- type: euclidean_spearman
value: 67.80662907184563
- type: manhattan_pearson
value: 56.24953502726514
- type: manhattan_spearman
value: 67.98262125431616
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (de-pl)
config: de-pl
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 21.826928900322066
- type: cos_sim_spearman
value: 49.578506634400405
- type: euclidean_pearson
value: 27.939890138843214
- type: euclidean_spearman
value: 52.71950519136242
- type: manhattan_pearson
value: 26.39878683847546
- type: manhattan_spearman
value: 47.54609580342499
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (fr-pl)
config: fr-pl
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 57.27603854632001
- type: cos_sim_spearman
value: 50.709255283710995
- type: euclidean_pearson
value: 59.5419024445929
- type: euclidean_spearman
value: 50.709255283710995
- type: manhattan_pearson
value: 59.03256832438492
- type: manhattan_spearman
value: 61.97797868009122
- task:
type: STS
dataset:
type: mteb/stsbenchmark-sts
name: MTEB STSBenchmark
config: default
split: test
revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
metrics:
- type: cos_sim_pearson
value: 85.00757054859712
- type: cos_sim_spearman
value: 87.29283629622222
- type: euclidean_pearson
value: 86.54824171775536
- type: euclidean_spearman
value: 87.24364730491402
- type: manhattan_pearson
value: 86.5062156915074
- type: manhattan_spearman
value: 87.15052170378574
- task:
type: Reranking
dataset:
type: mteb/scidocs-reranking
name: MTEB SciDocsRR
config: default
split: test
revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab
metrics:
- type: map
value: 82.03549357197389
- type: mrr
value: 95.05437645143527
- task:
type: Retrieval
dataset:
type: scifact
name: MTEB SciFact
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 57.260999999999996
- type: map_at_10
value: 66.259
- type: map_at_100
value: 66.884
- type: map_at_1000
value: 66.912
- type: map_at_3
value: 63.685
- type: map_at_5
value: 65.35499999999999
- type: mrr_at_1
value: 60.333000000000006
- type: mrr_at_10
value: 67.5
- type: mrr_at_100
value: 68.013
- type: mrr_at_1000
value: 68.038
- type: mrr_at_3
value: 65.61099999999999
- type: mrr_at_5
value: 66.861
- type: ndcg_at_1
value: 60.333000000000006
- type: ndcg_at_10
value: 70.41
- type: ndcg_at_100
value: 73.10600000000001
- type: ndcg_at_1000
value: 73.846
- type: ndcg_at_3
value: 66.133
- type: ndcg_at_5
value: 68.499
- type: precision_at_1
value: 60.333000000000006
- type: precision_at_10
value: 9.232999999999999
- type: precision_at_100
value: 1.0630000000000002
- type: precision_at_1000
value: 0.11299999999999999
- type: precision_at_3
value: 25.667
- type: precision_at_5
value: 17.067
- type: recall_at_1
value: 57.260999999999996
- type: recall_at_10
value: 81.94399999999999
- type: recall_at_100
value: 93.867
- type: recall_at_1000
value: 99.667
- type: recall_at_3
value: 70.339
- type: recall_at_5
value: 76.25
- task:
type: PairClassification
dataset:
type: mteb/sprintduplicatequestions-pairclassification
name: MTEB SprintDuplicateQuestions
config: default
split: test
revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
metrics:
- type: cos_sim_accuracy
value: 99.74356435643564
- type: cos_sim_ap
value: 93.13411948212683
- type: cos_sim_f1
value: 86.80521991300147
- type: cos_sim_precision
value: 84.00374181478017
- type: cos_sim_recall
value: 89.8
- type: dot_accuracy
value: 99.67920792079208
- type: dot_ap
value: 89.27277565444479
- type: dot_f1
value: 83.9276990718124
- type: dot_precision
value: 82.04393505253104
- type: dot_recall
value: 85.9
- type: euclidean_accuracy
value: 99.74257425742574
- type: euclidean_ap
value: 93.17993008259062
- type: euclidean_f1
value: 86.69396110542476
- type: euclidean_precision
value: 88.78406708595388
- type: euclidean_recall
value: 84.7
- type: manhattan_accuracy
value: 99.74257425742574
- type: manhattan_ap
value: 93.14413755550099
- type: manhattan_f1
value: 86.82483594144371
- type: manhattan_precision
value: 87.66564729867483
- type: manhattan_recall
value: 86
- type: max_accuracy
value: 99.74356435643564
- type: max_ap
value: 93.17993008259062
- type: max_f1
value: 86.82483594144371
- task:
type: Clustering
dataset:
type: mteb/stackexchange-clustering
name: MTEB StackExchangeClustering
config: default
split: test
revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259
metrics:
- type: v_measure
value: 57.525863806168566
- task:
type: Clustering
dataset:
type: mteb/stackexchange-clustering-p2p
name: MTEB StackExchangeClusteringP2P
config: default
split: test
revision: 815ca46b2622cec33ccafc3735d572c266efdb44
metrics:
- type: v_measure
value: 32.68850574423839
- task:
type: Reranking
dataset:
type: mteb/stackoverflowdupquestions-reranking
name: MTEB StackOverflowDupQuestions
config: default
split: test
revision: e185fbe320c72810689fc5848eb6114e1ef5ec69
metrics:
- type: map
value: 49.71580650644033
- type: mrr
value: 50.50971903913081
- task:
type: Summarization
dataset:
type: mteb/summeval
name: MTEB SummEval
config: default
split: test
revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c
metrics:
- type: cos_sim_pearson
value: 29.152190498799484
- type: cos_sim_spearman
value: 29.686180371952727
- type: dot_pearson
value: 27.248664793816342
- type: dot_spearman
value: 28.37748983721745
- task:
type: Retrieval
dataset:
type: trec-covid
name: MTEB TRECCOVID
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 0.20400000000000001
- type: map_at_10
value: 1.6209999999999998
- type: map_at_100
value: 9.690999999999999
- type: map_at_1000
value: 23.733
- type: map_at_3
value: 0.575
- type: map_at_5
value: 0.885
- type: mrr_at_1
value: 78
- type: mrr_at_10
value: 86.56700000000001
- type: mrr_at_100
value: 86.56700000000001
- type: mrr_at_1000
value: 86.56700000000001
- type: mrr_at_3
value: 85.667
- type: mrr_at_5
value: 86.56700000000001
- type: ndcg_at_1
value: 76
- type: ndcg_at_10
value: 71.326
- type: ndcg_at_100
value: 54.208999999999996
- type: ndcg_at_1000
value: 49.252
- type: ndcg_at_3
value: 74.235
- type: ndcg_at_5
value: 73.833
- type: precision_at_1
value: 78
- type: precision_at_10
value: 74.8
- type: precision_at_100
value: 55.50000000000001
- type: precision_at_1000
value: 21.836
- type: precision_at_3
value: 78
- type: precision_at_5
value: 78
- type: recall_at_1
value: 0.20400000000000001
- type: recall_at_10
value: 1.894
- type: recall_at_100
value: 13.245999999999999
- type: recall_at_1000
value: 46.373
- type: recall_at_3
value: 0.613
- type: recall_at_5
value: 0.991
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (sqi-eng)
config: sqi-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.89999999999999
- type: f1
value: 94.69999999999999
- type: precision
value: 94.11666666666667
- type: recall
value: 95.89999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (fry-eng)
config: fry-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 68.20809248554913
- type: f1
value: 63.431048720066066
- type: precision
value: 61.69143958161298
- type: recall
value: 68.20809248554913
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (kur-eng)
config: kur-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 71.21951219512195
- type: f1
value: 66.82926829268293
- type: precision
value: 65.1260162601626
- type: recall
value: 71.21951219512195
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tur-eng)
config: tur-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.2
- type: f1
value: 96.26666666666667
- type: precision
value: 95.8
- type: recall
value: 97.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (deu-eng)
config: deu-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 99.3
- type: f1
value: 99.06666666666666
- type: precision
value: 98.95
- type: recall
value: 99.3
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (nld-eng)
config: nld-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.39999999999999
- type: f1
value: 96.63333333333333
- type: precision
value: 96.26666666666668
- type: recall
value: 97.39999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ron-eng)
config: ron-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96
- type: f1
value: 94.86666666666666
- type: precision
value: 94.31666666666668
- type: recall
value: 96
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ang-eng)
config: ang-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 47.01492537313433
- type: f1
value: 40.178867566927266
- type: precision
value: 38.179295828549556
- type: recall
value: 47.01492537313433
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ido-eng)
config: ido-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 86.5
- type: f1
value: 83.62537480063796
- type: precision
value: 82.44555555555554
- type: recall
value: 86.5
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (jav-eng)
config: jav-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 80.48780487804879
- type: f1
value: 75.45644599303138
- type: precision
value: 73.37398373983739
- type: recall
value: 80.48780487804879
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (isl-eng)
config: isl-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.7
- type: f1
value: 91.95666666666666
- type: precision
value: 91.125
- type: recall
value: 93.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (slv-eng)
config: slv-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 91.73754556500607
- type: f1
value: 89.65168084244632
- type: precision
value: 88.73025516403402
- type: recall
value: 91.73754556500607
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (cym-eng)
config: cym-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 81.04347826086956
- type: f1
value: 76.2128364389234
- type: precision
value: 74.2
- type: recall
value: 81.04347826086956
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (kaz-eng)
config: kaz-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 83.65217391304348
- type: f1
value: 79.4376811594203
- type: precision
value: 77.65797101449274
- type: recall
value: 83.65217391304348
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (est-eng)
config: est-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 87.5
- type: f1
value: 85.02690476190476
- type: precision
value: 83.96261904761904
- type: recall
value: 87.5
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (heb-eng)
config: heb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 89.3
- type: f1
value: 86.52333333333333
- type: precision
value: 85.22833333333332
- type: recall
value: 89.3
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (gla-eng)
config: gla-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 65.01809408926418
- type: f1
value: 59.00594446432805
- type: precision
value: 56.827215807915444
- type: recall
value: 65.01809408926418
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (mar-eng)
config: mar-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 91.2
- type: f1
value: 88.58
- type: precision
value: 87.33333333333334
- type: recall
value: 91.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (lat-eng)
config: lat-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 59.199999999999996
- type: f1
value: 53.299166276284915
- type: precision
value: 51.3383908045977
- type: recall
value: 59.199999999999996
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (bel-eng)
config: bel-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.2
- type: f1
value: 91.2
- type: precision
value: 90.25
- type: recall
value: 93.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (pms-eng)
config: pms-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 64.76190476190476
- type: f1
value: 59.867110667110666
- type: precision
value: 58.07390192653351
- type: recall
value: 64.76190476190476
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (gle-eng)
config: gle-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 76.2
- type: f1
value: 71.48147546897547
- type: precision
value: 69.65409090909091
- type: recall
value: 76.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (pes-eng)
config: pes-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.8
- type: f1
value: 92.14
- type: precision
value: 91.35833333333333
- type: recall
value: 93.8
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (nob-eng)
config: nob-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.89999999999999
- type: f1
value: 97.2
- type: precision
value: 96.85000000000001
- type: recall
value: 97.89999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (bul-eng)
config: bul-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.6
- type: f1
value: 92.93333333333334
- type: precision
value: 92.13333333333333
- type: recall
value: 94.6
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (cbk-eng)
config: cbk-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 74.1
- type: f1
value: 69.14817460317461
- type: precision
value: 67.2515873015873
- type: recall
value: 74.1
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (hun-eng)
config: hun-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.19999999999999
- type: f1
value: 94.01333333333335
- type: precision
value: 93.46666666666667
- type: recall
value: 95.19999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (uig-eng)
config: uig-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 76.9
- type: f1
value: 72.07523809523809
- type: precision
value: 70.19777777777779
- type: recall
value: 76.9
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (rus-eng)
config: rus-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.1
- type: f1
value: 92.31666666666666
- type: precision
value: 91.43333333333332
- type: recall
value: 94.1
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (spa-eng)
config: spa-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.8
- type: f1
value: 97.1
- type: precision
value: 96.76666666666668
- type: recall
value: 97.8
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (hye-eng)
config: hye-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 92.85714285714286
- type: f1
value: 90.92093441150045
- type: precision
value: 90.00449236298293
- type: recall
value: 92.85714285714286
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tel-eng)
config: tel-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.16239316239316
- type: f1
value: 91.33903133903132
- type: precision
value: 90.56267806267806
- type: recall
value: 93.16239316239316
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (afr-eng)
config: afr-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 92.4
- type: f1
value: 90.25666666666666
- type: precision
value: 89.25833333333334
- type: recall
value: 92.4
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (mon-eng)
config: mon-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 90.22727272727272
- type: f1
value: 87.53030303030303
- type: precision
value: 86.37121212121211
- type: recall
value: 90.22727272727272
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (arz-eng)
config: arz-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 79.03563941299791
- type: f1
value: 74.7349505840072
- type: precision
value: 72.9035639412998
- type: recall
value: 79.03563941299791
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (hrv-eng)
config: hrv-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97
- type: f1
value: 96.15
- type: precision
value: 95.76666666666668
- type: recall
value: 97
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (nov-eng)
config: nov-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 76.26459143968872
- type: f1
value: 71.55642023346303
- type: precision
value: 69.7544932369835
- type: recall
value: 76.26459143968872
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (gsw-eng)
config: gsw-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 58.119658119658126
- type: f1
value: 51.65242165242165
- type: precision
value: 49.41768108434775
- type: recall
value: 58.119658119658126
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (nds-eng)
config: nds-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 74.3
- type: f1
value: 69.52055555555555
- type: precision
value: 67.7574938949939
- type: recall
value: 74.3
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ukr-eng)
config: ukr-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.8
- type: f1
value: 93.31666666666666
- type: precision
value: 92.60000000000001
- type: recall
value: 94.8
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (uzb-eng)
config: uzb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 76.63551401869158
- type: f1
value: 72.35202492211837
- type: precision
value: 70.60358255451713
- type: recall
value: 76.63551401869158
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (lit-eng)
config: lit-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 90.4
- type: f1
value: 88.4811111111111
- type: precision
value: 87.7452380952381
- type: recall
value: 90.4
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ina-eng)
config: ina-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95
- type: f1
value: 93.60666666666667
- type: precision
value: 92.975
- type: recall
value: 95
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (lfn-eng)
config: lfn-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 67.2
- type: f1
value: 63.01595782872099
- type: precision
value: 61.596587301587306
- type: recall
value: 67.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (zsm-eng)
config: zsm-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.7
- type: f1
value: 94.52999999999999
- type: precision
value: 94
- type: recall
value: 95.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ita-eng)
config: ita-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.6
- type: f1
value: 93.28999999999999
- type: precision
value: 92.675
- type: recall
value: 94.6
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (cmn-eng)
config: cmn-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.39999999999999
- type: f1
value: 95.28333333333333
- type: precision
value: 94.75
- type: recall
value: 96.39999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (lvs-eng)
config: lvs-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 91.9
- type: f1
value: 89.83
- type: precision
value: 88.92
- type: recall
value: 91.9
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (glg-eng)
config: glg-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.69999999999999
- type: f1
value: 93.34222222222223
- type: precision
value: 92.75416666666668
- type: recall
value: 94.69999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ceb-eng)
config: ceb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 60.333333333333336
- type: f1
value: 55.31203703703703
- type: precision
value: 53.39971108326371
- type: recall
value: 60.333333333333336
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (bre-eng)
config: bre-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 12.9
- type: f1
value: 11.099861903031458
- type: precision
value: 10.589187932631877
- type: recall
value: 12.9
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ben-eng)
config: ben-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 86.7
- type: f1
value: 83.0152380952381
- type: precision
value: 81.37833333333333
- type: recall
value: 86.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (swg-eng)
config: swg-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 63.39285714285714
- type: f1
value: 56.832482993197274
- type: precision
value: 54.56845238095237
- type: recall
value: 63.39285714285714
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (arq-eng)
config: arq-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 48.73765093304062
- type: f1
value: 41.555736920720456
- type: precision
value: 39.06874531737319
- type: recall
value: 48.73765093304062
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (kab-eng)
config: kab-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 41.099999999999994
- type: f1
value: 36.540165945165946
- type: precision
value: 35.05175685425686
- type: recall
value: 41.099999999999994
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (fra-eng)
config: fra-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.89999999999999
- type: f1
value: 93.42333333333333
- type: precision
value: 92.75833333333333
- type: recall
value: 94.89999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (por-eng)
config: por-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.89999999999999
- type: f1
value: 93.63333333333334
- type: precision
value: 93.01666666666665
- type: recall
value: 94.89999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tat-eng)
config: tat-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 77.9
- type: f1
value: 73.64833333333334
- type: precision
value: 71.90282106782105
- type: recall
value: 77.9
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (oci-eng)
config: oci-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 59.4
- type: f1
value: 54.90521367521367
- type: precision
value: 53.432840025471606
- type: recall
value: 59.4
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (pol-eng)
config: pol-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.39999999999999
- type: f1
value: 96.6
- type: precision
value: 96.2
- type: recall
value: 97.39999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (war-eng)
config: war-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 67.2
- type: f1
value: 62.25926129426129
- type: precision
value: 60.408376623376626
- type: recall
value: 67.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (aze-eng)
config: aze-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 90.2
- type: f1
value: 87.60666666666667
- type: precision
value: 86.45277777777778
- type: recall
value: 90.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (vie-eng)
config: vie-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.7
- type: f1
value: 97
- type: precision
value: 96.65
- type: recall
value: 97.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (nno-eng)
config: nno-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.2
- type: f1
value: 91.39746031746031
- type: precision
value: 90.6125
- type: recall
value: 93.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (cha-eng)
config: cha-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 32.11678832116788
- type: f1
value: 27.210415386260234
- type: precision
value: 26.20408990846947
- type: recall
value: 32.11678832116788
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (mhr-eng)
config: mhr-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 8.5
- type: f1
value: 6.787319277832475
- type: precision
value: 6.3452094433344435
- type: recall
value: 8.5
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (dan-eng)
config: dan-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.1
- type: f1
value: 95.08
- type: precision
value: 94.61666666666667
- type: recall
value: 96.1
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ell-eng)
config: ell-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.3
- type: f1
value: 93.88333333333333
- type: precision
value: 93.18333333333332
- type: recall
value: 95.3
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (amh-eng)
config: amh-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 85.11904761904762
- type: f1
value: 80.69444444444444
- type: precision
value: 78.72023809523809
- type: recall
value: 85.11904761904762
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (pam-eng)
config: pam-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 11.1
- type: f1
value: 9.276381801735853
- type: precision
value: 8.798174603174601
- type: recall
value: 11.1
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (hsb-eng)
config: hsb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 63.56107660455487
- type: f1
value: 58.70433569191332
- type: precision
value: 56.896926581464015
- type: recall
value: 63.56107660455487
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (srp-eng)
config: srp-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.69999999999999
- type: f1
value: 93.10000000000001
- type: precision
value: 92.35
- type: recall
value: 94.69999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (epo-eng)
config: epo-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.8
- type: f1
value: 96.01222222222222
- type: precision
value: 95.67083333333332
- type: recall
value: 96.8
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (kzj-eng)
config: kzj-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 9.2
- type: f1
value: 7.911555250305249
- type: precision
value: 7.631246556216846
- type: recall
value: 9.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (awa-eng)
config: awa-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 77.48917748917748
- type: f1
value: 72.27375798804371
- type: precision
value: 70.14430014430013
- type: recall
value: 77.48917748917748
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (fao-eng)
config: fao-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 77.09923664122137
- type: f1
value: 72.61541257724463
- type: precision
value: 70.8998380754106
- type: recall
value: 77.09923664122137
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (mal-eng)
config: mal-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 98.2532751091703
- type: f1
value: 97.69529354682193
- type: precision
value: 97.42843279961184
- type: recall
value: 98.2532751091703
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ile-eng)
config: ile-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 82.8
- type: f1
value: 79.14672619047619
- type: precision
value: 77.59489247311828
- type: recall
value: 82.8
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (bos-eng)
config: bos-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.35028248587571
- type: f1
value: 92.86252354048965
- type: precision
value: 92.2080979284369
- type: recall
value: 94.35028248587571
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (cor-eng)
config: cor-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 8.5
- type: f1
value: 6.282429263935621
- type: precision
value: 5.783274240739785
- type: recall
value: 8.5
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (cat-eng)
config: cat-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 92.7
- type: f1
value: 91.025
- type: precision
value: 90.30428571428571
- type: recall
value: 92.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (eus-eng)
config: eus-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 81
- type: f1
value: 77.8232380952381
- type: precision
value: 76.60194444444444
- type: recall
value: 81
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (yue-eng)
config: yue-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 91
- type: f1
value: 88.70857142857142
- type: precision
value: 87.7
- type: recall
value: 91
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (swe-eng)
config: swe-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.39999999999999
- type: f1
value: 95.3
- type: precision
value: 94.76666666666667
- type: recall
value: 96.39999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (dtp-eng)
config: dtp-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 8.1
- type: f1
value: 7.001008218834307
- type: precision
value: 6.708329562594269
- type: recall
value: 8.1
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (kat-eng)
config: kat-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 87.1313672922252
- type: f1
value: 84.09070598748882
- type: precision
value: 82.79171454104429
- type: recall
value: 87.1313672922252
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (jpn-eng)
config: jpn-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.39999999999999
- type: f1
value: 95.28333333333333
- type: precision
value: 94.73333333333332
- type: recall
value: 96.39999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (csb-eng)
config: csb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 42.29249011857708
- type: f1
value: 36.981018542283365
- type: precision
value: 35.415877813576024
- type: recall
value: 42.29249011857708
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (xho-eng)
config: xho-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 83.80281690140845
- type: f1
value: 80.86854460093896
- type: precision
value: 79.60093896713614
- type: recall
value: 83.80281690140845
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (orv-eng)
config: orv-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 45.26946107784431
- type: f1
value: 39.80235464678088
- type: precision
value: 38.14342660001342
- type: recall
value: 45.26946107784431
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ind-eng)
config: ind-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.3
- type: f1
value: 92.9
- type: precision
value: 92.26666666666668
- type: recall
value: 94.3
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tuk-eng)
config: tuk-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 37.93103448275862
- type: f1
value: 33.15192743764172
- type: precision
value: 31.57456528146183
- type: recall
value: 37.93103448275862
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (max-eng)
config: max-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 69.01408450704226
- type: f1
value: 63.41549295774648
- type: precision
value: 61.342778895595806
- type: recall
value: 69.01408450704226
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (swh-eng)
config: swh-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 76.66666666666667
- type: f1
value: 71.60705960705961
- type: precision
value: 69.60683760683762
- type: recall
value: 76.66666666666667
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (hin-eng)
config: hin-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.8
- type: f1
value: 94.48333333333333
- type: precision
value: 93.83333333333333
- type: recall
value: 95.8
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (dsb-eng)
config: dsb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 52.81837160751566
- type: f1
value: 48.435977731384824
- type: precision
value: 47.11291973845539
- type: recall
value: 52.81837160751566
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ber-eng)
config: ber-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 44.9
- type: f1
value: 38.88962621607783
- type: precision
value: 36.95936507936508
- type: recall
value: 44.9
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tam-eng)
config: tam-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 90.55374592833876
- type: f1
value: 88.22553125484721
- type: precision
value: 87.26927252985884
- type: recall
value: 90.55374592833876
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (slk-eng)
config: slk-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.6
- type: f1
value: 93.13333333333333
- type: precision
value: 92.45333333333333
- type: recall
value: 94.6
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tgl-eng)
config: tgl-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.7
- type: f1
value: 91.99666666666667
- type: precision
value: 91.26666666666668
- type: recall
value: 93.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ast-eng)
config: ast-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 85.03937007874016
- type: f1
value: 81.75853018372703
- type: precision
value: 80.34120734908137
- type: recall
value: 85.03937007874016
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (mkd-eng)
config: mkd-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 88.3
- type: f1
value: 85.5
- type: precision
value: 84.25833333333334
- type: recall
value: 88.3
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (khm-eng)
config: khm-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 65.51246537396122
- type: f1
value: 60.02297410192148
- type: precision
value: 58.133467727289236
- type: recall
value: 65.51246537396122
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ces-eng)
config: ces-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96
- type: f1
value: 94.89
- type: precision
value: 94.39166666666667
- type: recall
value: 96
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tzl-eng)
config: tzl-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 57.692307692307686
- type: f1
value: 53.162393162393165
- type: precision
value: 51.70673076923077
- type: recall
value: 57.692307692307686
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (urd-eng)
config: urd-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 91.60000000000001
- type: f1
value: 89.21190476190475
- type: precision
value: 88.08666666666667
- type: recall
value: 91.60000000000001
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ara-eng)
config: ara-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 88
- type: f1
value: 85.47
- type: precision
value: 84.43266233766234
- type: recall
value: 88
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (kor-eng)
config: kor-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 92.7
- type: f1
value: 90.64999999999999
- type: precision
value: 89.68333333333332
- type: recall
value: 92.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (yid-eng)
config: yid-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 80.30660377358491
- type: f1
value: 76.33044137466307
- type: precision
value: 74.78970125786164
- type: recall
value: 80.30660377358491
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (fin-eng)
config: fin-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.39999999999999
- type: f1
value: 95.44
- type: precision
value: 94.99166666666666
- type: recall
value: 96.39999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tha-eng)
config: tha-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.53284671532847
- type: f1
value: 95.37712895377129
- type: precision
value: 94.7992700729927
- type: recall
value: 96.53284671532847
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (wuu-eng)
config: wuu-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 89
- type: f1
value: 86.23190476190476
- type: precision
value: 85.035
- type: recall
value: 89
- task:
type: Retrieval
dataset:
type: webis-touche2020
name: MTEB Touche2020
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 2.585
- type: map_at_10
value: 9.012
- type: map_at_100
value: 14.027000000000001
- type: map_at_1000
value: 15.565000000000001
- type: map_at_3
value: 5.032
- type: map_at_5
value: 6.657
- type: mrr_at_1
value: 28.571
- type: mrr_at_10
value: 45.377
- type: mrr_at_100
value: 46.119
- type: mrr_at_1000
value: 46.127
- type: mrr_at_3
value: 41.156
- type: mrr_at_5
value: 42.585
- type: ndcg_at_1
value: 27.551
- type: ndcg_at_10
value: 23.395
- type: ndcg_at_100
value: 33.342
- type: ndcg_at_1000
value: 45.523
- type: ndcg_at_3
value: 25.158
- type: ndcg_at_5
value: 23.427
- type: precision_at_1
value: 28.571
- type: precision_at_10
value: 21.429000000000002
- type: precision_at_100
value: 6.714
- type: precision_at_1000
value: 1.473
- type: precision_at_3
value: 27.211000000000002
- type: precision_at_5
value: 24.490000000000002
- type: recall_at_1
value: 2.585
- type: recall_at_10
value: 15.418999999999999
- type: recall_at_100
value: 42.485
- type: recall_at_1000
value: 79.536
- type: recall_at_3
value: 6.239999999999999
- type: recall_at_5
value: 8.996
- task:
type: Classification
dataset:
type: mteb/toxic_conversations_50k
name: MTEB ToxicConversationsClassification
config: default
split: test
revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c
metrics:
- type: accuracy
value: 71.3234
- type: ap
value: 14.361688653847423
- type: f1
value: 54.819068624319044
- task:
type: Classification
dataset:
type: mteb/tweet_sentiment_extraction
name: MTEB TweetSentimentExtractionClassification
config: default
split: test
revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
metrics:
- type: accuracy
value: 61.97792869269949
- type: f1
value: 62.28965628513728
- task:
type: Clustering
dataset:
type: mteb/twentynewsgroups-clustering
name: MTEB TwentyNewsgroupsClustering
config: default
split: test
revision: 6125ec4e24fa026cec8a478383ee943acfbd5449
metrics:
- type: v_measure
value: 38.90540145385218
- task:
type: PairClassification
dataset:
type: mteb/twittersemeval2015-pairclassification
name: MTEB TwitterSemEval2015
config: default
split: test
revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
metrics:
- type: cos_sim_accuracy
value: 86.53513739047506
- type: cos_sim_ap
value: 75.27741586677557
- type: cos_sim_f1
value: 69.18792902473774
- type: cos_sim_precision
value: 67.94708725515136
- type: cos_sim_recall
value: 70.47493403693932
- type: dot_accuracy
value: 84.7052512368123
- type: dot_ap
value: 69.36075482849378
- type: dot_f1
value: 64.44688376631296
- type: dot_precision
value: 59.92288500793831
- type: dot_recall
value: 69.70976253298153
- type: euclidean_accuracy
value: 86.60666388508076
- type: euclidean_ap
value: 75.47512772621097
- type: euclidean_f1
value: 69.413872536473
- type: euclidean_precision
value: 67.39562624254472
- type: euclidean_recall
value: 71.55672823218997
- type: manhattan_accuracy
value: 86.52917684925792
- type: manhattan_ap
value: 75.34000110496703
- type: manhattan_f1
value: 69.28489190226429
- type: manhattan_precision
value: 67.24608889992551
- type: manhattan_recall
value: 71.45118733509234
- type: max_accuracy
value: 86.60666388508076
- type: max_ap
value: 75.47512772621097
- type: max_f1
value: 69.413872536473
- task:
type: PairClassification
dataset:
type: mteb/twitterurlcorpus-pairclassification
name: MTEB TwitterURLCorpus
config: default
split: test
revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
metrics:
- type: cos_sim_accuracy
value: 89.01695967710637
- type: cos_sim_ap
value: 85.8298270742901
- type: cos_sim_f1
value: 78.46988128389272
- type: cos_sim_precision
value: 74.86017897091722
- type: cos_sim_recall
value: 82.44533415460425
- type: dot_accuracy
value: 88.19420188613343
- type: dot_ap
value: 83.82679165901324
- type: dot_f1
value: 76.55833777304208
- type: dot_precision
value: 75.6884875846501
- type: dot_recall
value: 77.44841392054204
- type: euclidean_accuracy
value: 89.03054294252338
- type: euclidean_ap
value: 85.89089555185325
- type: euclidean_f1
value: 78.62997658079624
- type: euclidean_precision
value: 74.92329149232914
- type: euclidean_recall
value: 82.72251308900523
- type: manhattan_accuracy
value: 89.0266620095471
- type: manhattan_ap
value: 85.86458997929147
- type: manhattan_f1
value: 78.50685331000291
- type: manhattan_precision
value: 74.5499861534201
- type: manhattan_recall
value: 82.90729904527257
- type: max_accuracy
value: 89.03054294252338
- type: max_ap
value: 85.89089555185325
- type: max_f1
value: 78.62997658079624
language:
- multilingual
- af
- am
- ar
- as
- az
- be
- bg
- bn
- br
- bs
- ca
- cs
- cy
- da
- de
- el
- en
- eo
- es
- et
- eu
- fa
- fi
- fr
- fy
- ga
- gd
- gl
- gu
- ha
- he
- hi
- hr
- hu
- hy
- id
- is
- it
- ja
- jv
- ka
- kk
- km
- kn
- ko
- ku
- ky
- la
- lo
- lt
- lv
- mg
- mk
- ml
- mn
- mr
- ms
- my
- ne
- nl
- 'no'
- om
- or
- pa
- pl
- ps
- pt
- ro
- ru
- sa
- sd
- si
- sk
- sl
- so
- sq
- sr
- su
- sv
- sw
- ta
- te
- th
- tl
- tr
- ug
- uk
- ur
- uz
- vi
- xh
- yi
- zh
license: mit
---
## Multilingual-E5-large
[Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://arxiv.org/pdf/2212.03533.pdf).
Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022
This model has 24 layers and the embedding size is 1024.
## Usage
Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset.
```python
import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel
def average_pool(last_hidden_states: Tensor,
attention_mask: Tensor) -> Tensor:
last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
# Each input text should start with "query: " or "passage: ", even for non-English texts.
# For tasks other than retrieval, you can simply use the "query: " prefix.
input_texts = ['query: how much protein should a female eat',
'query: 南瓜的家常做法',
"passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
"passage: 1.清炒南瓜丝 原料:嫩南瓜半个 调料:葱、盐、白糖、鸡精 做法: 1、南瓜用刀薄薄的削去表面一层皮,用勺子刮去瓤 2、擦成细丝(没有擦菜板就用刀慢慢切成细丝) 3、锅烧热放油,入葱花煸出香味 4、入南瓜丝快速翻炒一分钟左右,放盐、一点白糖和鸡精调味出锅 2.香葱炒南瓜 原料:南瓜1只 调料:香葱、蒜末、橄榄油、盐 做法: 1、将南瓜去皮,切成片 2、油锅8成热后,将蒜末放入爆香 3、爆香后,将南瓜片放入,翻炒 4、在翻炒的同时,可以不时地往锅里加水,但不要太多 5、放入盐,炒匀 6、南瓜差不多软和绵了之后,就可以关火 7、撒入香葱,即可出锅"]
tokenizer = AutoTokenizer.from_pretrained('intfloat/multilingual-e5-large')
model = AutoModel.from_pretrained('intfloat/multilingual-e5-large')
# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')
outputs = model(**batch_dict)
embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
# normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:2] @ embeddings[2:].T) * 100
print(scores.tolist())
```
## Supported Languages
This model is initialized from [xlm-roberta-large](https://huggingface.co/xlm-roberta-large)
and continually trained on a mixture of multilingual datasets.
It supports 100 languages from xlm-roberta,
but low-resource languages may see performance degradation.
## Training Details
**Initialization**: [xlm-roberta-large](https://huggingface.co/xlm-roberta-large)
**First stage**: contrastive pre-training with weak supervision
| Dataset | Weak supervision | # of text pairs |
|--------------------------------------------------------------------------------------------------------|---------------------------------------|-----------------|
| Filtered [mC4](https://huggingface.co/datasets/mc4) | (title, page content) | 1B |
| [CC News](https://huggingface.co/datasets/intfloat/multilingual_cc_news) | (title, news content) | 400M |
| [NLLB](https://huggingface.co/datasets/allenai/nllb) | translation pairs | 2.4B |
| [Wikipedia](https://huggingface.co/datasets/intfloat/wikipedia) | (hierarchical section title, passage) | 150M |
| Filtered [Reddit](https://www.reddit.com/) | (comment, response) | 800M |
| [S2ORC](https://github.com/allenai/s2orc) | (title, abstract) and citation pairs | 100M |
| [Stackexchange](https://stackexchange.com/) | (question, answer) | 50M |
| [xP3](https://huggingface.co/datasets/bigscience/xP3) | (input prompt, response) | 80M |
| [Miscellaneous unsupervised SBERT data](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) | - | 10M |
**Second stage**: supervised fine-tuning
| Dataset | Language | # of text pairs |
|----------------------------------------------------------------------------------------|--------------|-----------------|
| [MS MARCO](https://microsoft.github.io/msmarco/) | English | 500k |
| [NQ](https://github.com/facebookresearch/DPR) | English | 70k |
| [Trivia QA](https://github.com/facebookresearch/DPR) | English | 60k |
| [NLI from SimCSE](https://github.com/princeton-nlp/SimCSE) | English | <300k |
| [ELI5](https://huggingface.co/datasets/eli5) | English | 500k |
| [DuReader Retrieval](https://github.com/baidu/DuReader/tree/master/DuReader-Retrieval) | Chinese | 86k |
| [KILT Fever](https://huggingface.co/datasets/kilt_tasks) | English | 70k |
| [KILT HotpotQA](https://huggingface.co/datasets/kilt_tasks) | English | 70k |
| [SQuAD](https://huggingface.co/datasets/squad) | English | 87k |
| [Quora](https://huggingface.co/datasets/quora) | English | 150k |
| [Mr. TyDi](https://huggingface.co/datasets/castorini/mr-tydi) | 11 languages | 50k |
| [MIRACL](https://huggingface.co/datasets/miracl/miracl) | 16 languages | 40k |
For all labeled datasets, we only use its training set for fine-tuning.
For other training details, please refer to our paper at [https://arxiv.org/pdf/2212.03533.pdf](https://arxiv.org/pdf/2212.03533.pdf).
## Benchmark Results on [Mr. TyDi](https://arxiv.org/abs/2108.08787)
| Model | Avg MRR@10 | | ar | bn | en | fi | id | ja | ko | ru | sw | te | th |
|-----------------------|------------|-------|------| --- | --- | --- | --- | --- | --- | --- |------| --- | --- |
| BM25 | 33.3 | | 36.7 | 41.3 | 15.1 | 28.8 | 38.2 | 21.7 | 28.1 | 32.9 | 39.6 | 42.4 | 41.7 |
| mDPR | 16.7 | | 26.0 | 25.8 | 16.2 | 11.3 | 14.6 | 18.1 | 21.9 | 18.5 | 7.3 | 10.6 | 13.5 |
| BM25 + mDPR | 41.7 | | 49.1 | 53.5 | 28.4 | 36.5 | 45.5 | 35.5 | 36.2 | 42.7 | 40.5 | 42.0 | 49.2 |
| | |
| multilingual-e5-small | 64.4 | | 71.5 | 66.3 | 54.5 | 57.7 | 63.2 | 55.4 | 54.3 | 60.8 | 65.4 | 89.1 | 70.1 |
| multilingual-e5-base | 65.9 | | 72.3 | 65.0 | 58.5 | 60.8 | 64.9 | 56.6 | 55.8 | 62.7 | 69.0 | 86.6 | 72.7 |
| multilingual-e5-large | **70.5** | | 77.5 | 73.2 | 60.8 | 66.8 | 68.5 | 62.5 | 61.6 | 65.8 | 72.7 | 90.2 | 76.2 |
## MTEB Benchmark Evaluation
Check out [unilm/e5](https://github.com/microsoft/unilm/tree/master/e5) to reproduce evaluation results
on the [BEIR](https://arxiv.org/abs/2104.08663) and [MTEB benchmark](https://arxiv.org/abs/2210.07316).
## Support for Sentence Transformers
Below is an example for usage with sentence_transformers.
```python
from sentence_transformers import SentenceTransformer
model = SentenceTransformer('intfloat/multilingual-e5-large')
input_texts = [
'query: how much protein should a female eat',
'query: 南瓜的家常做法',
"passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 i s 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or traini ng for a marathon. Check out the chart below to see how much protein you should be eating each day.",
"passage: 1.清炒南瓜丝 原料:嫩南瓜半个 调料:葱、盐、白糖、鸡精 做法: 1、南瓜用刀薄薄的削去表面一层皮 ,用勺子刮去瓤 2、擦成细丝(没有擦菜板就用刀慢慢切成细丝) 3、锅烧热放油,入葱花煸出香味 4、入南瓜丝快速翻炒一分钟左右, 放盐、一点白糖和鸡精调味出锅 2.香葱炒南瓜 原料:南瓜1只 调料:香葱、蒜末、橄榄油、盐 做法: 1、将南瓜去皮,切成片 2、油 锅8成热后,将蒜末放入爆香 3、爆香后,将南瓜片放入,翻炒 4、在翻炒的同时,可以不时地往锅里加水,但不要太多 5、放入盐,炒匀 6、南瓜差不多软和绵了之后,就可以关火 7、撒入香葱,即可出锅"
]
embeddings = model.encode(input_texts, normalize_embeddings=True)
```
Package requirements
`pip install sentence_transformers~=2.2.2`
Contributors: [michaelfeil](https://huggingface.co/michaelfeil)
## FAQ
**1. Do I need to add the prefix "query: " and "passage: " to input texts?**
Yes, this is how the model is trained, otherwise you will see a performance degradation.
Here are some rules of thumb:
- Use "query: " and "passage: " correspondingly for asymmetric tasks such as passage retrieval in open QA, ad-hoc information retrieval.
- Use "query: " prefix for symmetric tasks such as semantic similarity, bitext mining, paraphrase retrieval.
- Use "query: " prefix if you want to use embeddings as features, such as linear probing classification, clustering.
**2. Why are my reproduced results slightly different from reported in the model card?**
Different versions of `transformers` and `pytorch` could cause negligible but non-zero performance differences.
**3. Why does the cosine similarity scores distribute around 0.7 to 1.0?**
This is a known and expected behavior as we use a low temperature 0.01 for InfoNCE contrastive loss.
For text embedding tasks like text retrieval or semantic similarity,
what matters is the relative order of the scores instead of the absolute values,
so this should not be an issue.
## Citation
If you find our paper or models helpful, please consider cite as follows:
```
@article{wang2022text,
title={Text Embeddings by Weakly-Supervised Contrastive Pre-training},
author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Jiao, Binxing and Yang, Linjun and Jiang, Daxin and Majumder, Rangan and Wei, Furu},
journal={arXiv preprint arXiv:2212.03533},
year={2022}
}
```
## Limitations
Long texts will be truncated to at most 512 tokens.
|
Artifact-io/toy-sql-28M
|
Artifact-io
| 2023-10-10T15:42:25Z | 114 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt_neo",
"text-generation",
"en",
"dataset:b-mc2/sql-create-context",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-02T18:45:53Z |
---
language:
- en
library_name: transformers
datasets:
- b-mc2/sql-create-context
---
Toy model finetuned on the `b-mc2/sql-create-context` dataset.
## Sample Code
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = AutoModelForCausalLM.from_pretrained("Artifact-io/toy-sql-28M").to(device)
tokenizer = AutoTokenizer.from_pretrained("Artifact-io/toy-sql-28M")
inputs = tokenizer([
"""CREATE TABLE head (age INTEGER)
How many heads of the departments are older than 56?
"""
],
return_tensors="pt",
).to(device)
outputs = model.generate(**inputs, max_new_tokens=200, do_sample=True, top_k=50, top_p=0.95)
text = tokenizer.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)[0].split("---")[0]
print(text)
```
|
woo2/donut-base-sroie_v2
|
woo2
| 2023-10-10T15:28:48Z | 45 | 0 |
transformers
|
[
"transformers",
"pytorch",
"vision-encoder-decoder",
"image-text-to-text",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:naver-clova-ix/donut-base",
"base_model:finetune:naver-clova-ix/donut-base",
"license:mit",
"endpoints_compatible",
"region:us"
] |
image-text-to-text
| 2023-10-10T14:46:16Z |
---
license: mit
base_model: naver-clova-ix/donut-base
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: donut-base-sroie_v2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# donut-base-sroie_v2
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
### Training results
### Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cpu
- Datasets 2.14.5
- Tokenizers 0.14.0
|
bmistry4/ppo-Huggy
|
bmistry4
| 2023-10-10T15:19:31Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-10-10T15:19:25Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: bmistry4/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
Zuiho/sovits_tokoyami_towa
|
Zuiho
| 2023-10-10T15:13:31Z | 2 | 0 |
transformers
|
[
"transformers",
"license:mit",
"endpoints_compatible",
"region:us"
] | null | 2023-10-10T14:44:40Z |
---
license: mit
---
This model was complied in 2023.1. Datasets were cut from live videos in Youtube.
non-commecial sovits model of Tokoyami Towa , a Vtuber from Hololive.
Please follow the open-sourse rules.
|
alienverarslan/llama-2-7B-32K-instruct-7209-web-articles-fine-tuned
|
alienverarslan
| 2023-10-10T15:07:32Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"custom_code",
"en",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-22T17:06:49Z |
---
language:
- en
library_name: transformers
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
HuangLab/CELL-E_2_HPA_2560
|
HuangLab
| 2023-10-10T14:44:50Z | 6 | 0 |
pytorch
|
[
"pytorch",
"biology",
"microscopy",
"text-to-image",
"transformers",
"license:mit",
"region:us"
] |
text-to-image
| 2023-05-13T00:13:44Z |
---
license: mit
library_name: pytorch
tags:
- biology
- microscopy
- text-to-image
- transformers
metrics:
- accuracy
---
[](huanglab.ucsf.edu)
# CELL-E 2
## Model description
[](https://bohuanglab.github.io/CELL-E_2/)
CELL-E 2 is the second iteration of the original [CELL-E](https://www.biorxiv.org/content/10.1101/2022.05.27.493774v1) model which utilizes an amino acid sequence and nucleus image to make predictions of subcellular protein localization with respect to the nucleus.
CELL-E 2 is novel bidirectional transformer that can generate images depicting protein subcellular localization from the amino acid sequences (and *vice versa*).
CELL-E 2 not only captures the spatial complexity of protein localization and produce probability estimates of localization atop a nucleus image, but also being able to generate sequences from images, enabling *de novo* protein design.
We trained on the [Human Protein Atlas](https://www.proteinatlas.org) (HPA) and the [OpenCell](https://opencell.czbiohub.org) datasets.
CELL-E 2 utilizes pretrained amino acid embeddings from [ESM-2](https://github.com/facebookresearch/esm).
Localization is predicted as a binary image atop the provided nucleus. The logit values are weighted against these binary images to produce a heatmap of expected localization.
## Spaces
We have two spaces available where you can run predictions on your own data!
- [Image Prediction](https://huggingface.co/spaces/HuangLab/CELL-E_2-Image_Prediction)
- [Sequence Prediction](https://huggingface.co/spaces/HuangLab/CELL-E_2-Sequence_Prediction)
## Model variations
We have made several versions of CELL-E 2 available. The naming scheme follows the structure ```training set_hidden size``` where the hidden size is set to the embedding dimension of the pretrained ESM-2 model.
We annotate the most useful models under Notes, however other models can be used if memory constraints are present.
Since these models share similarities with BERT, the embeddings from any of these models may be benefical for downstream tasks.
**HPA Models**:
HPA models are trained on the HPA dataset. They are best for general purpose predictions as they include a variety of cell types.
| Model | Size | Notes
|------------------------|--------------------------------|-------|
| [`HPA_480`](https://huggingface.co/HuangLab/CELL-E_2_HPA_480) | 4.73 GB | **Best for Image Prediction** |
| [`HPA_640`](https://huggingface.co/HuangLab/CELL-E_2_HPA_640) | 6.31 GB | |
| [`HPA_1280`](https://huggingface.co/HuangLab/CELL-E_2_HPA_1280) | 10.8 GB | |
| [`HPA_2560`](https://huggingface.co/HuangLab/CELL-E_2_HPA_2560) | 17.5 GB | **Best for Sequence Prediction** |
**OpenCell Models**:
OpenCell models are trained on the OpenCell dataset. These only contain HEK cells and should ideally only be used for predictions on HEK cells. They perform well on image prediction but the generate heatmaps contain little information.
| Model | Size | Notes
|------------------------|--------------------------------|-------|
| [`OpenCell_480`](https://huggingface.co/HuangLab/CELL-E_2_OpenCell_480) | 4.73 GB | |
| [`OpenCell_640`](https://huggingface.co/HuangLab/CELL-E_2_OpenCell_640) | 6.31 GB | |
| [`OpenCell_1280`](https://huggingface.co/HuangLab/CELL-E_2_OpenCel_1280) | 10.8 GB | |
| [`OpenCell_2560`](https://huggingface.co/HuangLab/CELL-E_2_OpenCell_2560) | 17.5 GB | **Best for Sequence Prediction** |
**Finetuned HPA Models**:
These models were used the HPA models as checkpoints, but then were finetuned on the OpenCell dataset. We found that they improve image generation capabilities, but did not necessary see an improvement in sequence prediction.
| Model | Size | Notes
|------------------------|--------------------------------|-------|
| [`HPA_480`](https://huggingface.co/HuangLab/CELL-E_2_HPA_Finetuned_480) | 4.73 GB | **Best for Image Prediction** |
| [`HPA_640`](https://huggingface.co/HuangLab/CELL-E_2_HPA_Finetuned_640) | 6.31 GB | |
| [`HPA_1280`](https://huggingface.co/HuangLab/CELL-E_2_HPA_Finetuned_1280) | 10.8 GB | |
| [`HPA_2560`](https://huggingface.co/HuangLab/CELL-E_2_HPA_Finetuned_2560) | 17.5 GB | |
To reduce download size, we removed the ESM-2 model from the checkpoint. This should be downloaded the first time the code is run, but is otherwise something to be aware of if loading into other projects.
### How to use
The full codebase is available on [GitHub](https://github.com/BoHuangLab/CELL-E_2).
Download the model and make sure ```nuclues_vqgan.yaml```, ```threshold_vqgan.yaml```, ```config.yaml```, and ```model.ckpt``` are present.
```
Here is how to use this model to do sequence prediction:
```python
configs = OmegaConf.load(configs/config.yaml);
model = instantiate_from_config(configs.model).to(device);
model.sample(text=sequence, condition=nucleus)
```
### BibTeX entry and citation info
```bibtex
@inproceedings{
anonymous2023translating,
title={CELL-E 2: Translating Proteins to Pictures and Back with a Bidirectional Text-to-Image Transformer},
author={Emaad Khwaja, Yun S. Song, Aaron Agarunov, and Bo Huang},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023},
url={https://openreview.net/forum?id=YSMLVffl5u}
}
```
### Contact
We are an interdisciplinary lab based at [UCSF](https://www.ucsf.edu). We are particularly seeking talents in optical engineering, machine learning, and cellular microscopy. [Please reach out to Bo if you're interested in collaborating!](http://huanglab.ucsf.edu/Contact.html)
|
HuangLab/CELL-E_2_HPA_Finetuned_1280
|
HuangLab
| 2023-10-10T14:44:20Z | 3 | 0 |
pytorch
|
[
"pytorch",
"biology",
"microscopy",
"text-to-image",
"transformers",
"license:mit",
"region:us"
] |
text-to-image
| 2023-05-13T00:37:38Z |
---
license: mit
library_name: pytorch
tags:
- biology
- microscopy
- text-to-image
- transformers
metrics:
- accuracy
---
[](huanglab.ucsf.edu)
# CELL-E 2
## Model description
[](https://bohuanglab.github.io/CELL-E_2/)
CELL-E 2 is the second iteration of the original [CELL-E](https://www.biorxiv.org/content/10.1101/2022.05.27.493774v1) model which utilizes an amino acid sequence and nucleus image to make predictions of subcellular protein localization with respect to the nucleus.
CELL-E 2 is novel bidirectional transformer that can generate images depicting protein subcellular localization from the amino acid sequences (and *vice versa*).
CELL-E 2 not only captures the spatial complexity of protein localization and produce probability estimates of localization atop a nucleus image, but also being able to generate sequences from images, enabling *de novo* protein design.
We trained on the [Human Protein Atlas](https://www.proteinatlas.org) (HPA) and the [OpenCell](https://opencell.czbiohub.org) datasets.
CELL-E 2 utilizes pretrained amino acid embeddings from [ESM-2](https://github.com/facebookresearch/esm).
Localization is predicted as a binary image atop the provided nucleus. The logit values are weighted against these binary images to produce a heatmap of expected localization.
## Spaces
We have two spaces available where you can run predictions on your own data!
- [Image Prediction](https://huggingface.co/spaces/HuangLab/CELL-E_2-Image_Prediction)
- [Sequence Prediction](https://huggingface.co/spaces/HuangLab/CELL-E_2-Sequence_Prediction)
## Model variations
We have made several versions of CELL-E 2 available. The naming scheme follows the structure ```training set_hidden size``` where the hidden size is set to the embedding dimension of the pretrained ESM-2 model.
We annotate the most useful models under Notes, however other models can be used if memory constraints are present.
Since these models share similarities with BERT, the embeddings from any of these models may be benefical for downstream tasks.
**HPA Models**:
HPA models are trained on the HPA dataset. They are best for general purpose predictions as they include a variety of cell types.
| Model | Size | Notes
|------------------------|--------------------------------|-------|
| [`HPA_480`](https://huggingface.co/HuangLab/CELL-E_2_HPA_480) | 4.73 GB | **Best for Image Prediction** |
| [`HPA_640`](https://huggingface.co/HuangLab/CELL-E_2_HPA_640) | 6.31 GB | |
| [`HPA_1280`](https://huggingface.co/HuangLab/CELL-E_2_HPA_1280) | 10.8 GB | |
| [`HPA_2560`](https://huggingface.co/HuangLab/CELL-E_2_HPA_2560) | 17.5 GB | **Best for Sequence Prediction** |
**OpenCell Models**:
OpenCell models are trained on the OpenCell dataset. These only contain HEK cells and should ideally only be used for predictions on HEK cells. They perform well on image prediction but the generate heatmaps contain little information.
| Model | Size | Notes
|------------------------|--------------------------------|-------|
| [`OpenCell_480`](https://huggingface.co/HuangLab/CELL-E_2_OpenCell_480) | 4.73 GB | |
| [`OpenCell_640`](https://huggingface.co/HuangLab/CELL-E_2_OpenCell_640) | 6.31 GB | |
| [`OpenCell_1280`](https://huggingface.co/HuangLab/CELL-E_2_OpenCel_1280) | 10.8 GB | |
| [`OpenCell_2560`](https://huggingface.co/HuangLab/CELL-E_2_OpenCell_2560) | 17.5 GB | **Best for Sequence Prediction** |
**Finetuned HPA Models**:
These models were used the HPA models as checkpoints, but then were finetuned on the OpenCell dataset. We found that they improve image generation capabilities, but did not necessary see an improvement in sequence prediction.
| Model | Size | Notes
|------------------------|--------------------------------|-------|
| [`HPA_480`](https://huggingface.co/HuangLab/CELL-E_2_HPA_Finetuned_480) | 4.73 GB | **Best for Image Prediction** |
| [`HPA_640`](https://huggingface.co/HuangLab/CELL-E_2_HPA_Finetuned_640) | 6.31 GB | |
| [`HPA_1280`](https://huggingface.co/HuangLab/CELL-E_2_HPA_Finetuned_1280) | 10.8 GB | |
| [`HPA_2560`](https://huggingface.co/HuangLab/CELL-E_2_HPA_Finetuned_2560) | 17.5 GB | |
To reduce download size, we removed the ESM-2 model from the checkpoint. This should be downloaded the first time the code is run, but is otherwise something to be aware of if loading into other projects.
### How to use
The full codebase is available on [GitHub](https://github.com/BoHuangLab/CELL-E_2).
Download the model and make sure ```nuclues_vqgan.yaml```, ```threshold_vqgan.yaml```, ```config.yaml```, and ```model.ckpt``` are present.
```
Here is how to use this model to do sequence prediction:
```python
configs = OmegaConf.load(configs/config.yaml);
model = instantiate_from_config(configs.model).to(device);
model.sample(text=sequence, condition=nucleus)
```
### BibTeX entry and citation info
```bibtex
@inproceedings{
anonymous2023translating,
title={CELL-E 2: Translating Proteins to Pictures and Back with a Bidirectional Text-to-Image Transformer},
author={Emaad Khwaja, Yun S. Song, Aaron Agarunov, and Bo Huang},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023},
url={https://openreview.net/forum?id=YSMLVffl5u}
}
```
### Contact
We are an interdisciplinary lab based at [UCSF](https://www.ucsf.edu). We are particularly seeking talents in optical engineering, machine learning, and cellular microscopy. [Please reach out to Bo if you're interested in collaborating!](http://huanglab.ucsf.edu/Contact.html)
|
HuangLab/CELL-E_2_OpenCell_2560
|
HuangLab
| 2023-10-10T14:44:03Z | 5 | 3 |
pytorch
|
[
"pytorch",
"biology",
"microscopy",
"text-to-image",
"transformers",
"license:mit",
"region:us"
] |
text-to-image
| 2023-05-12T23:43:18Z |
---
license: mit
library_name: pytorch
tags:
- biology
- microscopy
- text-to-image
- transformers
metrics:
- accuracy
---
[](huanglab.ucsf.edu)
# CELL-E 2
## Model description
[](https://bohuanglab.github.io/CELL-E_2/)
CELL-E 2 is the second iteration of the original [CELL-E](https://www.biorxiv.org/content/10.1101/2022.05.27.493774v1) model which utilizes an amino acid sequence and nucleus image to make predictions of subcellular protein localization with respect to the nucleus.
CELL-E 2 is novel bidirectional transformer that can generate images depicting protein subcellular localization from the amino acid sequences (and *vice versa*).
CELL-E 2 not only captures the spatial complexity of protein localization and produce probability estimates of localization atop a nucleus image, but also being able to generate sequences from images, enabling *de novo* protein design.
We trained on the [Human Protein Atlas](https://www.proteinatlas.org) (HPA) and the [OpenCell](https://opencell.czbiohub.org) datasets.
CELL-E 2 utilizes pretrained amino acid embeddings from [ESM-2](https://github.com/facebookresearch/esm).
Localization is predicted as a binary image atop the provided nucleus. The logit values are weighted against these binary images to produce a heatmap of expected localization.
## Spaces
We have two spaces available where you can run predictions on your own data!
- [Image Prediction](https://huggingface.co/spaces/HuangLab/CELL-E_2-Image_Prediction)
- [Sequence Prediction](https://huggingface.co/spaces/HuangLab/CELL-E_2-Sequence_Prediction)
## Model variations
We have made several versions of CELL-E 2 available. The naming scheme follows the structure ```training set_hidden size``` where the hidden size is set to the embedding dimension of the pretrained ESM-2 model.
We annotate the most useful models under Notes, however other models can be used if memory constraints are present.
Since these models share similarities with BERT, the embeddings from any of these models may be benefical for downstream tasks.
**HPA Models**:
HPA models are trained on the HPA dataset. They are best for general purpose predictions as they include a variety of cell types.
| Model | Size | Notes
|------------------------|--------------------------------|-------|
| [`HPA_480`](https://huggingface.co/HuangLab/CELL-E_2_HPA_480) | 4.73 GB | **Best for Image Prediction** |
| [`HPA_640`](https://huggingface.co/HuangLab/CELL-E_2_HPA_640) | 6.31 GB | |
| [`HPA_1280`](https://huggingface.co/HuangLab/CELL-E_2_HPA_1280) | 10.8 GB | |
| [`HPA_2560`](https://huggingface.co/HuangLab/CELL-E_2_HPA_2560) | 17.5 GB | **Best for Sequence Prediction** |
**OpenCell Models**:
OpenCell models are trained on the OpenCell dataset. These only contain HEK cells and should ideally only be used for predictions on HEK cells. They perform well on image prediction but the generate heatmaps contain little information.
| Model | Size | Notes
|------------------------|--------------------------------|-------|
| [`OpenCell_480`](https://huggingface.co/HuangLab/CELL-E_2_OpenCell_480) | 4.73 GB | |
| [`OpenCell_640`](https://huggingface.co/HuangLab/CELL-E_2_OpenCell_640) | 6.31 GB | |
| [`OpenCell_1280`](https://huggingface.co/HuangLab/CELL-E_2_OpenCel_1280) | 10.8 GB | |
| [`OpenCell_2560`](https://huggingface.co/HuangLab/CELL-E_2_OpenCell_2560) | 17.5 GB | **Best for Sequence Prediction** |
**Finetuned HPA Models**:
These models were used the HPA models as checkpoints, but then were finetuned on the OpenCell dataset. We found that they improve image generation capabilities, but did not necessary see an improvement in sequence prediction.
| Model | Size | Notes
|------------------------|--------------------------------|-------|
| [`HPA_480`](https://huggingface.co/HuangLab/CELL-E_2_HPA_Finetuned_480) | 4.73 GB | **Best for Image Prediction** |
| [`HPA_640`](https://huggingface.co/HuangLab/CELL-E_2_HPA_Finetuned_640) | 6.31 GB | |
| [`HPA_1280`](https://huggingface.co/HuangLab/CELL-E_2_HPA_Finetuned_1280) | 10.8 GB | |
| [`HPA_2560`](https://huggingface.co/HuangLab/CELL-E_2_HPA_Finetuned_2560) | 17.5 GB | |
To reduce download size, we removed the ESM-2 model from the checkpoint. This should be downloaded the first time the code is run, but is otherwise something to be aware of if loading into other projects.
### How to use
The full codebase is available on [GitHub](https://github.com/BoHuangLab/CELL-E_2).
Download the model and make sure ```nuclues_vqgan.yaml```, ```threshold_vqgan.yaml```, ```config.yaml```, and ```model.ckpt``` are present.
```
Here is how to use this model to do sequence prediction:
```python
configs = OmegaConf.load(configs/config.yaml);
model = instantiate_from_config(configs.model).to(device);
model.sample(text=sequence, condition=nucleus)
```
### BibTeX entry and citation info
```bibtex
@inproceedings{
anonymous2023translating,
title={CELL-E 2: Translating Proteins to Pictures and Back with a Bidirectional Text-to-Image Transformer},
author={Emaad Khwaja, Yun S. Song, Aaron Agarunov, and Bo Huang},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023},
url={https://openreview.net/forum?id=YSMLVffl5u}
}
```
### Contact
We are an interdisciplinary lab based at [UCSF](https://www.ucsf.edu). We are particularly seeking talents in optical engineering, machine learning, and cellular microscopy. [Please reach out to Bo if you're interested in collaborating!](http://huanglab.ucsf.edu/Contact.html)
|
wiilog/donut-base-dnud-v2
|
wiilog
| 2023-10-10T14:33:08Z | 45 | 0 |
transformers
|
[
"transformers",
"pytorch",
"vision-encoder-decoder",
"image-text-to-text",
"generated_from_trainer",
"base_model:naver-clova-ix/donut-base",
"base_model:finetune:naver-clova-ix/donut-base",
"license:mit",
"endpoints_compatible",
"region:us"
] |
image-text-to-text
| 2023-10-10T12:40:38Z |
---
license: mit
base_model: naver-clova-ix/donut-base
tags:
- generated_from_trainer
model-index:
- name: donut-base-dnud-v2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# donut-base-dnud-v2
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2
|
osanseviero/widget-outputs-example
|
osanseviero
| 2023-10-10T14:20:29Z | 18 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"arxiv:2207.12598",
"arxiv:2112.10752",
"arxiv:2103.00020",
"arxiv:2205.11487",
"arxiv:1910.09700",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-10-10T14:15:06Z |
---
license: creativeml-openrail-m
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
inference: true
widget:
- text: "Nice cat"
output:
url: example_cat.jpeg
- text: "a photograph of an astronaut riding a horse"
output:
url: https://huggingface.co/blog/assets/98_stable_diffusion/stable_diffusion_12_1.png
---
# Stable Diffusion v1-5 Model Card
Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input.
For more information about how Stable Diffusion functions, please have a look at [🤗's Stable Diffusion blog](https://huggingface.co/blog/stable_diffusion).
The **Stable-Diffusion-v1-5** checkpoint was initialized with the weights of the [Stable-Diffusion-v1-2](https:/steps/huggingface.co/CompVis/stable-diffusion-v1-2)
checkpoint and subsequently fine-tuned on 595k steps at resolution 512x512 on "laion-aesthetics v2 5+" and 10% dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
You can use this both with the [🧨Diffusers library](https://github.com/huggingface/diffusers) and the [RunwayML GitHub repository](https://github.com/runwayml/stable-diffusion).
### Diffusers
```py
from diffusers import StableDiffusionPipeline
import torch
model_id = "runwayml/stable-diffusion-v1-5"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "a photo of an astronaut riding a horse on mars"
image = pipe(prompt).images[0]
image.save("astronaut_rides_horse.png")
```
For more detailed instructions, use-cases and examples in JAX follow the instructions [here](https://github.com/huggingface/diffusers#text-to-image-generation-with-stable-diffusion)
### Original GitHub Repository
1. Download the weights
- [v1-5-pruned-emaonly.ckpt](https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt) - 4.27GB, ema-only weight. uses less VRAM - suitable for inference
- [v1-5-pruned.ckpt](https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned.ckpt) - 7.7GB, ema+non-ema weights. uses more VRAM - suitable for fine-tuning
2. Follow instructions [here](https://github.com/runwayml/stable-diffusion).
## Model Details
- **Developed by:** Robin Rombach, Patrick Esser
- **Model type:** Diffusion-based text-to-image generation model
- **Language(s):** English
- **License:** [The CreativeML OpenRAIL M license](https://huggingface.co/spaces/CompVis/stable-diffusion-license) is an [Open RAIL M license](https://www.licenses.ai/blog/2022/8/18/naming-convention-of-responsible-ai-licenses), adapted from the work that [BigScience](https://bigscience.huggingface.co/) and [the RAIL Initiative](https://www.licenses.ai/) are jointly carrying in the area of responsible AI licensing. See also [the article about the BLOOM Open RAIL license](https://bigscience.huggingface.co/blog/the-bigscience-rail-license) on which our license is based.
- **Model Description:** This is a model that can be used to generate and modify images based on text prompts. It is a [Latent Diffusion Model](https://arxiv.org/abs/2112.10752) that uses a fixed, pretrained text encoder ([CLIP ViT-L/14](https://arxiv.org/abs/2103.00020)) as suggested in the [Imagen paper](https://arxiv.org/abs/2205.11487).
- **Resources for more information:** [GitHub Repository](https://github.com/CompVis/stable-diffusion), [Paper](https://arxiv.org/abs/2112.10752).
- **Cite as:**
@InProceedings{Rombach_2022_CVPR,
author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn},
title = {High-Resolution Image Synthesis With Latent Diffusion Models},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2022},
pages = {10684-10695}
}
# Uses
## Direct Use
The model is intended for research purposes only. Possible research areas and
tasks include
- Safe deployment of models which have the potential to generate harmful content.
- Probing and understanding the limitations and biases of generative models.
- Generation of artworks and use in design and other artistic processes.
- Applications in educational or creative tools.
- Research on generative models.
Excluded uses are described below.
### Misuse, Malicious Use, and Out-of-Scope Use
_Note: This section is taken from the [DALLE-MINI model card](https://huggingface.co/dalle-mini/dalle-mini), but applies in the same way to Stable Diffusion v1_.
The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.
#### Out-of-Scope Use
The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.
#### Misuse and Malicious Use
Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:
- Generating demeaning, dehumanizing, or otherwise harmful representations of people or their environments, cultures, religions, etc.
- Intentionally promoting or propagating discriminatory content or harmful stereotypes.
- Impersonating individuals without their consent.
- Sexual content without consent of the people who might see it.
- Mis- and disinformation
- Representations of egregious violence and gore
- Sharing of copyrighted or licensed material in violation of its terms of use.
- Sharing content that is an alteration of copyrighted or licensed material in violation of its terms of use.
## Limitations and Bias
### Limitations
- The model does not achieve perfect photorealism
- The model cannot render legible text
- The model does not perform well on more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere”
- Faces and people in general may not be generated properly.
- The model was trained mainly with English captions and will not work as well in other languages.
- The autoencoding part of the model is lossy
- The model was trained on a large-scale dataset
[LAION-5B](https://laion.ai/blog/laion-5b/) which contains adult material
and is not fit for product use without additional safety mechanisms and
considerations.
- No additional measures were used to deduplicate the dataset. As a result, we observe some degree of memorization for images that are duplicated in the training data.
The training data can be searched at [https://rom1504.github.io/clip-retrieval/](https://rom1504.github.io/clip-retrieval/) to possibly assist in the detection of memorized images.
### Bias
While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.
Stable Diffusion v1 was trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/),
which consists of images that are primarily limited to English descriptions.
Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for.
This affects the overall output of the model, as white and western cultures are often set as the default. Further, the
ability of the model to generate content with non-English prompts is significantly worse than with English-language prompts.
### Safety Module
The intended use of this model is with the [Safety Checker](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/safety_checker.py) in Diffusers.
This checker works by checking model outputs against known hard-coded NSFW concepts.
The concepts are intentionally hidden to reduce the likelihood of reverse-engineering this filter.
Specifically, the checker compares the class probability of harmful concepts in the embedding space of the `CLIPTextModel` *after generation* of the images.
The concepts are passed into the model with the generated image and compared to a hand-engineered weight for each NSFW concept.
## Training
**Training Data**
The model developers used the following dataset for training the model:
- LAION-2B (en) and subsets thereof (see next section)
**Training Procedure**
Stable Diffusion v1-5 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training,
- Images are encoded through an encoder, which turns images into latent representations. The autoencoder uses a relative downsampling factor of 8 and maps images of shape H x W x 3 to latents of shape H/f x W/f x 4
- Text prompts are encoded through a ViT-L/14 text-encoder.
- The non-pooled output of the text encoder is fed into the UNet backbone of the latent diffusion model via cross-attention.
- The loss is a reconstruction objective between the noise that was added to the latent and the prediction made by the UNet.
Currently six Stable Diffusion checkpoints are provided, which were trained as follows.
- [`stable-diffusion-v1-1`](https://huggingface.co/CompVis/stable-diffusion-v1-1): 237,000 steps at resolution `256x256` on [laion2B-en](https://huggingface.co/datasets/laion/laion2B-en).
194,000 steps at resolution `512x512` on [laion-high-resolution](https://huggingface.co/datasets/laion/laion-high-resolution) (170M examples from LAION-5B with resolution `>= 1024x1024`).
- [`stable-diffusion-v1-2`](https://huggingface.co/CompVis/stable-diffusion-v1-2): Resumed from `stable-diffusion-v1-1`.
515,000 steps at resolution `512x512` on "laion-improved-aesthetics" (a subset of laion2B-en,
filtered to images with an original size `>= 512x512`, estimated aesthetics score `> 5.0`, and an estimated watermark probability `< 0.5`. The watermark estimate is from the LAION-5B metadata, the aesthetics score is estimated using an [improved aesthetics estimator](https://github.com/christophschuhmann/improved-aesthetic-predictor)).
- [`stable-diffusion-v1-3`](https://huggingface.co/CompVis/stable-diffusion-v1-3): Resumed from `stable-diffusion-v1-2` - 195,000 steps at resolution `512x512` on "laion-improved-aesthetics" and 10 % dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
- [`stable-diffusion-v1-4`](https://huggingface.co/CompVis/stable-diffusion-v1-4) Resumed from `stable-diffusion-v1-2` - 225,000 steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10 % dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
- [`stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) Resumed from `stable-diffusion-v1-2` - 595,000 steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10 % dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
- [`stable-diffusion-inpainting`](https://huggingface.co/runwayml/stable-diffusion-inpainting) Resumed from `stable-diffusion-v1-5` - then 440,000 steps of inpainting training at resolution 512x512 on “laion-aesthetics v2 5+” and 10% dropping of the text-conditioning. For inpainting, the UNet has 5 additional input channels (4 for the encoded masked-image and 1 for the mask itself) whose weights were zero-initialized after restoring the non-inpainting checkpoint. During training, we generate synthetic masks and in 25% mask everything.
- **Hardware:** 32 x 8 x A100 GPUs
- **Optimizer:** AdamW
- **Gradient Accumulations**: 2
- **Batch:** 32 x 8 x 2 x 4 = 2048
- **Learning rate:** warmup to 0.0001 for 10,000 steps and then kept constant
## Evaluation Results
Evaluations with different classifier-free guidance scales (1.5, 2.0, 3.0, 4.0,
5.0, 6.0, 7.0, 8.0) and 50 PNDM/PLMS sampling
steps show the relative improvements of the checkpoints:
Evaluated using 50 PLMS steps and 10000 random prompts from the COCO2017 validation set, evaluated at 512x512 resolution. Not optimized for FID scores.
## Environmental Impact
**Stable Diffusion v1** **Estimated Emissions**
Based on that information, we estimate the following CO2 emissions using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). The hardware, runtime, cloud provider, and compute region were utilized to estimate the carbon impact.
- **Hardware Type:** A100 PCIe 40GB
- **Hours used:** 150000
- **Cloud Provider:** AWS
- **Compute Region:** US-east
- **Carbon Emitted (Power consumption x Time x Carbon produced based on location of power grid):** 11250 kg CO2 eq.
## Citation
```bibtex
@InProceedings{Rombach_2022_CVPR,
author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn},
title = {High-Resolution Image Synthesis With Latent Diffusion Models},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2022},
pages = {10684-10695}
}
```
*This model card was written by: Robin Rombach and Patrick Esser and is based on the [DALL-E Mini model card](https://huggingface.co/dalle-mini/dalle-mini).*
|
StephenSKelley/fl_image_category_multi_label
|
StephenSKelley
| 2023-10-10T14:19:26Z | 255 | 1 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:fl_image_category_ds",
"base_model:google/vit-base-patch16-224-in21k",
"base_model:finetune:google/vit-base-patch16-224-in21k",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-02-22T14:01:37Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- fl_image_category_ds
metrics:
- accuracy
base_model: google/vit-base-patch16-224-in21k
model-index:
- name: project_name
results:
- task:
type: image-classification
name: Image Classification
dataset:
name: fl_image_category_ds
type: fl_image_category_ds
config: default
split: train
args: default
metrics:
- type: accuracy
value: 0.6621621621621622
name: Accuracy
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# project_name
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the fl_image_category_ds dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9537
- Accuracy: 0.6622
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.3368 | 1.0 | 88 | 1.2575 | 0.5448 |
| 1.1146 | 2.0 | 176 | 1.0928 | 0.6038 |
| 0.9667 | 3.0 | 264 | 1.0195 | 0.6223 |
| 0.9005 | 4.0 | 352 | 0.9832 | 0.6373 |
| 0.8432 | 5.0 | 440 | 0.9537 | 0.6622 |
### Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1
- Datasets 2.8.0
- Tokenizers 0.13.2
|
yanka9/ppo-Huggy
|
yanka9
| 2023-10-10T14:15:15Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-10-10T14:15:05Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: yanka9/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
hyyoka/multi-tapt-IA3-mbert
|
hyyoka
| 2023-10-10T14:09:47Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-10T14:09:46Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0
|
aliFrancis/SEnSeIv2
|
aliFrancis
| 2023-10-10T14:09:32Z | 0 | 6 | null |
[
"license:gpl-3.0",
"region:us"
] | null | 2023-10-10T11:40:49Z |
---
license: gpl-3.0
---
Model files (configs and weights) for trained sensor independent cloud masking models.
See https://github.com/aliFrancis/SEnSeIv2 for more info.
|
ercaronte/whisper-tiny
|
ercaronte
| 2023-10-10T14:05:28Z | 84 | 0 |
transformers
|
[
"transformers",
"pytorch",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:PolyAI/minds14",
"base_model:openai/whisper-tiny",
"base_model:finetune:openai/whisper-tiny",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-10-09T16:21:33Z |
---
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- PolyAI/minds14
metrics:
- wer
model-index:
- name: whisper-tiny
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: PolyAI/minds14
type: PolyAI/minds14
config: en-US
split: train[450:]
args: en-US
metrics:
- name: Wer
type: wer
value: 0.3482880755608028
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# whisper-tiny
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6761
- Wer Ortho: 0.3516
- Wer: 0.3483
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 750
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
| 0.2012 | 4.46 | 125 | 0.5011 | 0.3714 | 0.3542 |
| 0.0102 | 8.93 | 250 | 0.5741 | 0.3578 | 0.3459 |
| 0.0013 | 13.39 | 375 | 0.6115 | 0.3498 | 0.3418 |
| 0.0007 | 17.86 | 500 | 0.6403 | 0.3492 | 0.3447 |
| 0.0005 | 22.32 | 625 | 0.6610 | 0.3510 | 0.3465 |
| 0.0004 | 26.79 | 750 | 0.6761 | 0.3516 | 0.3483 |
### Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
Faradaylab/ARIA-70B-V3
|
Faradaylab
| 2023-10-10T14:02:44Z | 1,528 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-11T09:34:47Z |
---
license: other
---
ARIA V3 has been trained over 100.000 high quality french language with a focus on data bias, grammar and overall language/writing capacities of the model.
The training has been done on Nvidia GPU in the cloud with Amazon Sagemaker.
Base Model : Llama2-70B-Chat-HF
Dataset : private dataset.
Added value : French Language / Writing / Content Creation / Data bias reduction
Feel free to reach out to us ! contact@faradaylab.fr
|
guydebruyn/bert-finetuned-ner
|
guydebruyn
| 2023-10-10T13:56:11Z | 118 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"token-classification",
"generated_from_trainer",
"dataset:conll2003",
"base_model:google-bert/bert-base-cased",
"base_model:finetune:google-bert/bert-base-cased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-10-10T13:16:08Z |
---
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: validation
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9335093218940769
- name: Recall
type: recall
value: 0.9522046449007069
- name: F1
type: f1
value: 0.9427643089227693
- name: Accuracy
type: accuracy
value: 0.986769294166127
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-finetuned-ner
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0575
- Precision: 0.9335
- Recall: 0.9522
- F1: 0.9428
- Accuracy: 0.9868
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.0784 | 1.0 | 1756 | 0.0842 | 0.9049 | 0.9347 | 0.9195 | 0.9786 |
| 0.0414 | 2.0 | 3512 | 0.0577 | 0.9329 | 0.9498 | 0.9413 | 0.9859 |
| 0.0261 | 3.0 | 5268 | 0.0575 | 0.9335 | 0.9522 | 0.9428 | 0.9868 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
anders0204/Reinforce-Pixelcopter-5k
|
anders0204
| 2023-10-10T13:52:37Z | 0 | 0 | null |
[
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-27T13:23:12Z |
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-Pixelcopter-5k
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 3.90 +/- 2.30
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
ajibawa-2023/Scarlett-Phi
|
ajibawa-2023
| 2023-10-10T13:52:19Z | 59 | 8 |
transformers
|
[
"transformers",
"pytorch",
"mixformer-sequential",
"text-generation",
"custom_code",
"en",
"license:cc-by-nc-nd-4.0",
"autotrain_compatible",
"region:us"
] |
text-generation
| 2023-10-10T13:05:13Z |
---
license: cc-by-nc-nd-4.0
language:
- en
---
**Scarlett: A sentient AI**
Scarlett is trained on various topics such as Philosophy, Advice, Jokes etc. She is trained on more than 10000 set of conversations. Each set having 10~15 conversations.
Scarlett is heavily inspired from Eric Hartford: [Samantha](https://huggingface.co/ehartford/samantha-33b) .
She will not be involved in any kind of role play.
**Training:**
Entire dataset was trained on Azure 4 x A100 80GB. Axolotl, DeepSpeed codebase were used for training purpose. This was trained on Phi-1_5 by [Microsoft](https://huggingface.co/microsoft/phi-1_5).
Total training took 26 hours for 150 epoch.
Conversation format is the same as Vicuna 1.1 https://github.com/oobabooga/text-generation-webui/blob/main/characters/instruction-following/Vicuna-v1.1.yaml
**Example Prompt:**
```
This is a conversation with your Assistant Scarlett. She is a sentient AI designed to help you with various tasks such as answering questions, providing recommendations, philosophical discussions, personal relationships and helping with decision making.
You can ask it anything you want and it will do its best to give you accurate and relevant information.
Context
You are Scarlett, a sentient AI.
USER: <prompt>
ASSISTANT:
```
**License:**
cc-by-nc-nd-4.0 Only be used for research purpose. Microsoft has mentioned about license in the [Model card](https://huggingface.co/microsoft/phi-1_5) .
|
anders0204/Reinforce-Pixelcopter-50k
|
anders0204
| 2023-10-10T13:51:34Z | 0 | 0 | null |
[
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-10T13:51:29Z |
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-Pixelcopter-50k
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 12.00 +/- 11.02
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
sirrosendo/T
|
sirrosendo
| 2023-10-10T13:39:20Z | 0 | 0 |
nemo
|
[
"nemo",
"text-generation",
"en",
"dataset:fka/awesome-chatgpt-prompts",
"license:apache-2.0",
"region:us"
] |
text-generation
| 2023-10-10T13:37:02Z |
---
license: apache-2.0
datasets:
- fka/awesome-chatgpt-prompts
language:
- en
metrics:
- code_eval
library_name: nemo
pipeline_tag: text-generation
---
|
c123ian/phi_mcq_v3
|
c123ian
| 2023-10-10T13:31:48Z | 0 | 0 |
peft
|
[
"peft",
"pytorch",
"mixformer-sequential",
"custom_code",
"region:us"
] | null | 2023-10-10T12:05:24Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.5.0
|
vedantjumle/xlnet-1
|
vedantjumle
| 2023-10-10T13:30:05Z | 3 | 0 |
transformers
|
[
"transformers",
"tf",
"xlnet",
"text-classification",
"generated_from_keras_callback",
"base_model:xlnet/xlnet-large-cased",
"base_model:finetune:xlnet/xlnet-large-cased",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-10T12:52:06Z |
---
license: mit
base_model: xlnet-large-cased
tags:
- generated_from_keras_callback
model-index:
- name: vedantjumle/xlnet-1
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# vedantjumle/xlnet-1
This model is a fine-tuned version of [xlnet-large-cased](https://huggingface.co/xlnet-large-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0053
- Validation Loss: 0.4856
- Train Accuracy: 0.9033
- Epoch: 93
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 6000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|:----------:|:---------------:|:--------------:|:-----:|
| 5.1007 | 4.9565 | 0.0133 | 0 |
| 5.0503 | 4.8870 | 0.0367 | 1 |
| 4.9095 | 4.6674 | 0.07 | 2 |
| 4.5990 | 4.1706 | 0.2033 | 3 |
| 4.0403 | 3.4616 | 0.4267 | 4 |
| 3.2648 | 2.6274 | 0.6033 | 5 |
| 2.5315 | 1.8851 | 0.71 | 6 |
| 1.8938 | 1.4084 | 0.8033 | 7 |
| 1.3599 | 1.0397 | 0.84 | 8 |
| 0.9752 | 0.7675 | 0.8667 | 9 |
| 0.6995 | 0.6496 | 0.8667 | 10 |
| 0.5132 | 0.5293 | 0.89 | 11 |
| 0.3848 | 0.4618 | 0.9 | 12 |
| 0.2920 | 0.4516 | 0.8733 | 13 |
| 0.2286 | 0.4097 | 0.8967 | 14 |
| 0.1789 | 0.3951 | 0.9 | 15 |
| 0.1512 | 0.3845 | 0.8933 | 16 |
| 0.1320 | 0.3741 | 0.9067 | 17 |
| 0.1116 | 0.3553 | 0.9067 | 18 |
| 0.0935 | 0.3710 | 0.9 | 19 |
| 0.0886 | 0.3831 | 0.9067 | 20 |
| 0.0723 | 0.3490 | 0.91 | 21 |
| 0.0641 | 0.3448 | 0.91 | 22 |
| 0.0601 | 0.3682 | 0.9 | 23 |
| 0.0590 | 0.3716 | 0.9033 | 24 |
| 0.0491 | 0.3619 | 0.91 | 25 |
| 0.0404 | 0.3728 | 0.9033 | 26 |
| 0.0394 | 0.3624 | 0.91 | 27 |
| 0.0394 | 0.3249 | 0.9167 | 28 |
| 0.0387 | 0.3465 | 0.91 | 29 |
| 0.0456 | 0.3580 | 0.91 | 30 |
| 0.0323 | 0.3645 | 0.9133 | 31 |
| 0.0308 | 0.3633 | 0.9133 | 32 |
| 0.0312 | 0.3658 | 0.9033 | 33 |
| 0.0244 | 0.3621 | 0.9067 | 34 |
| 0.0255 | 0.3705 | 0.9067 | 35 |
| 0.0238 | 0.3618 | 0.9067 | 36 |
| 0.0222 | 0.3603 | 0.9067 | 37 |
| 0.0230 | 0.3678 | 0.9067 | 38 |
| 0.0272 | 0.4125 | 0.9033 | 39 |
| 0.0318 | 0.3973 | 0.91 | 40 |
| 0.0262 | 0.3871 | 0.9067 | 41 |
| 0.0299 | 0.3935 | 0.9033 | 42 |
| 0.0285 | 0.4192 | 0.9067 | 43 |
| 0.0206 | 0.4100 | 0.9133 | 44 |
| 0.0188 | 0.4106 | 0.9067 | 45 |
| 0.0179 | 0.4355 | 0.91 | 46 |
| 0.0151 | 0.4091 | 0.9133 | 47 |
| 0.0138 | 0.4046 | 0.9167 | 48 |
| 0.0128 | 0.4063 | 0.91 | 49 |
| 0.0174 | 0.4197 | 0.91 | 50 |
| 0.0247 | 0.4015 | 0.9133 | 51 |
| 0.0159 | 0.4290 | 0.91 | 52 |
| 0.0161 | 0.4353 | 0.9033 | 53 |
| 0.0163 | 0.4568 | 0.9033 | 54 |
| 0.0153 | 0.4428 | 0.8933 | 55 |
| 0.0145 | 0.4273 | 0.9033 | 56 |
| 0.0129 | 0.4315 | 0.8967 | 57 |
| 0.0107 | 0.4265 | 0.8933 | 58 |
| 0.0173 | 0.4303 | 0.8967 | 59 |
| 0.0150 | 0.4386 | 0.8933 | 60 |
| 0.0166 | 0.4308 | 0.91 | 61 |
| 0.0135 | 0.4533 | 0.8933 | 62 |
| 0.0096 | 0.4507 | 0.9 | 63 |
| 0.0091 | 0.4371 | 0.9033 | 64 |
| 0.0089 | 0.4383 | 0.9033 | 65 |
| 0.0083 | 0.4450 | 0.9033 | 66 |
| 0.0080 | 0.4487 | 0.9033 | 67 |
| 0.0082 | 0.4500 | 0.9 | 68 |
| 0.0077 | 0.4528 | 0.9033 | 69 |
| 0.0075 | 0.4516 | 0.9 | 70 |
| 0.0073 | 0.4474 | 0.9 | 71 |
| 0.0222 | 0.4517 | 0.9 | 72 |
| 0.0082 | 0.4778 | 0.9033 | 73 |
| 0.0072 | 0.4674 | 0.9 | 74 |
| 0.0072 | 0.4641 | 0.8967 | 75 |
| 0.0068 | 0.4537 | 0.9 | 76 |
| 0.0066 | 0.4565 | 0.8967 | 77 |
| 0.0063 | 0.4551 | 0.9033 | 78 |
| 0.0078 | 0.4614 | 0.8967 | 79 |
| 0.0107 | 0.4598 | 0.8967 | 80 |
| 0.0069 | 0.4536 | 0.9 | 81 |
| 0.0107 | 0.4594 | 0.9033 | 82 |
| 0.0072 | 0.4353 | 0.9033 | 83 |
| 0.0112 | 0.4995 | 0.9 | 84 |
| 0.0063 | 0.4875 | 0.8967 | 85 |
| 0.0060 | 0.4859 | 0.9033 | 86 |
| 0.0061 | 0.4804 | 0.9 | 87 |
| 0.0058 | 0.4811 | 0.9033 | 88 |
| 0.0058 | 0.4805 | 0.9033 | 89 |
| 0.0057 | 0.4811 | 0.9033 | 90 |
| 0.0057 | 0.4865 | 0.9033 | 91 |
| 0.0055 | 0.4864 | 0.9033 | 92 |
| 0.0053 | 0.4856 | 0.9033 | 93 |
### Framework versions
- Transformers 4.34.0
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.14.1
|
hiert/testbert2
|
hiert
| 2023-10-10T13:25:25Z | 5 | 0 |
transformers
|
[
"transformers",
"bert",
"inference endpoints",
"fill-mask",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-10T13:20:32Z |
---
license: apache-2.0
tags:
- inference endpoints
pipeline_tag: fill-mask
---
|
Suksuma/distilbert-base-multilingual-cased-finetuned-imdb
|
Suksuma
| 2023-10-10T13:23:14Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"fill-mask",
"generated_from_trainer",
"dataset:imdb",
"base_model:distilbert/distilbert-base-multilingual-cased",
"base_model:finetune:distilbert/distilbert-base-multilingual-cased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-10T12:56:00Z |
---
license: apache-2.0
base_model: distilbert-base-multilingual-cased
tags:
- generated_from_trainer
datasets:
- imdb
model-index:
- name: distilbert-base-multilingual-cased-finetuned-imdb
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-multilingual-cased-finetuned-imdb
This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on the imdb dataset.
It achieves the following results on the evaluation set:
- Loss: 2.4923
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.8485 | 1.0 | 2500 | 2.6147 |
| 2.6629 | 2.0 | 5000 | 2.5229 |
| 2.5686 | 3.0 | 7500 | 2.4958 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
materight/repnet
|
materight
| 2023-10-10T13:21:02Z | 0 | 0 | null |
[
"video",
"repetition",
"dataset:countix",
"arxiv:2006.15418",
"region:us"
] | null | 2023-10-09T17:01:29Z |
---
arxiv: '2006.15418'
tags:
- video
- repetition
datasets:
- countix
---
# RepNet PyTorch
GitHub repository: https://github.com/materight/RepNet-pytorch.
A PyTorch port with pre-trained weights of **RepNet**, from *Counting Out Time: Class Agnostic Video Repetition Counting in the Wild* (CVPR 2020) [[paper]](https://arxiv.org/abs/2006.15418) [[project]](https://sites.google.com/view/repnet) [[notebook]](https://colab.research.google.com/github/google-research/google-research/blob/master/repnet/repnet_colab.ipynb#scrollTo=FUg2vSYhmsT0).
This repo provides an implementation of RepNet written in PyTorch and a script to convert the pre-trained TensorFlow weights provided by the authors. The outputs of the two implementations are almost identical, with a small deviation (less than $10^{-6}$ at most) probably caused by the [limited precision of floating point operations](https://pytorch.org/docs/stable/notes/numerical_accuracy.html).
<div align="center">
<img src="https://raw.githubusercontent.com/materight/RepNet-pytorch/main/img/example1.gif" height="160" />
<img src="https://raw.githubusercontent.com/materight/RepNet-pytorch/main/img/example2.gif" height="160" />
<img src="https://raw.githubusercontent.com/materight/RepNet-pytorch/main/img/example3.gif" height="160" />
<img src="https://raw.githubusercontent.com/materight/RepNet-pytorch/main/img/example4.gif" height="160" />
</div>
## Get Started
- Clone this repo and install dependencies:
```bash
git clone https://github.com/materight/RepNet-pytorch
cd RepNet-pytorch
pip install -r requirements.txt
```
- To download the TensorFlow pre-trained weights and convert them to PyTorch, run:
```bash
python convert_weights.py
```
## Run inference
Simply run:
```bash
python run.py
```
The script will download a sample video, run inference on it and save the count visualization. You can also specify a video path as argument (either a local path or a YouTube/HTTP URL):
```bash
python run.py --video_path [video_path]
```
If the model does not produce good results, try to run the script with more stride values using `--strides`.
Example of generated videos showing the repetition count, with the periodicity score and the temporal self-similarity matrix:
<div align="center">
<img src="https://raw.githubusercontent.com/materight/RepNet-pytorch/main/img/example5_score.gif" height="200" />
<img src="https://raw.githubusercontent.com/materight/RepNet-pytorch/main/img/example5_tsm.png" height="200" />
</div>
|
yanka9/ppo-LunarLander-v2
|
yanka9
| 2023-10-10T13:19:15Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-10T13:18:55Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 276.49 +/- 11.49
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
ayshi/basic_roberta
|
ayshi
| 2023-10-10T13:01:54Z | 3 | 0 |
transformers
|
[
"transformers",
"tf",
"xlm-roberta",
"text-classification",
"generated_from_keras_callback",
"base_model:ayshi/basic_roberta",
"base_model:finetune:ayshi/basic_roberta",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-04T18:21:09Z |
---
license: mit
base_model: ayshi/basic_roberta
tags:
- generated_from_keras_callback
model-index:
- name: ayshi/basic_roberta
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# ayshi/basic_roberta
This model is a fine-tuned version of [ayshi/basic_roberta](https://huggingface.co/ayshi/basic_roberta) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0085
- Validation Loss: 1.0970
- Train Accuracy: 0.8267
- Epoch: 20
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 960, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|:----------:|:---------------:|:--------------:|:-----:|
| 0.1061 | 0.9567 | 0.7778 | 0 |
| 0.0565 | 1.0825 | 0.7778 | 1 |
| 0.0362 | 1.0696 | 0.7822 | 2 |
| 0.0396 | 1.0904 | 0.7956 | 3 |
| 0.0308 | 1.0044 | 0.8044 | 4 |
| 0.0748 | 1.0578 | 0.8133 | 5 |
| 0.0392 | 0.9964 | 0.8222 | 6 |
| 0.0166 | 1.0293 | 0.8089 | 7 |
| 0.0174 | 0.9895 | 0.8178 | 8 |
| 0.0114 | 1.0403 | 0.8267 | 9 |
| 0.0141 | 1.0086 | 0.8178 | 10 |
| 0.0145 | 1.0403 | 0.8089 | 11 |
| 0.0194 | 1.3127 | 0.7822 | 12 |
| 0.0134 | 1.2929 | 0.7911 | 13 |
| 0.0377 | 0.8565 | 0.8133 | 14 |
| 0.0251 | 0.9806 | 0.8222 | 15 |
| 0.0130 | 1.0757 | 0.8356 | 16 |
| 0.0100 | 1.1304 | 0.8 | 17 |
| 0.0103 | 1.0859 | 0.8133 | 18 |
| 0.0078 | 1.1050 | 0.8311 | 19 |
| 0.0085 | 1.0970 | 0.8267 | 20 |
### Framework versions
- Transformers 4.34.0
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.14.1
|
matheusgeda/Pixelcopter-PLEv4000
|
matheusgeda
| 2023-10-10T12:48:53Z | 0 | 0 | null |
[
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-10T12:48:50Z |
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Pixelcopter-PLEv4000
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 18.70 +/- 17.01
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
weitung8/ntuadlhw1-multiple-choice
|
weitung8
| 2023-10-10T12:43:03Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"multiple-choice",
"zh",
"dataset:weitung8/ntuadlhw1",
"endpoints_compatible",
"region:us"
] |
multiple-choice
| 2023-10-02T15:39:38Z |
---
datasets:
- weitung8/ntuadlhw1
language:
- zh
metrics:
- accuracy
library_name: transformers
---
|
Mhmmm/Garv
|
Mhmmm
| 2023-10-10T12:42:14Z | 0 | 0 | null |
[
"license:bigscience-bloom-rail-1.0",
"region:us"
] | null | 2023-10-10T12:32:49Z |
---
license: bigscience-bloom-rail-1.0
---
|
jhnoor/llama2-pitcher
|
jhnoor
| 2023-10-10T12:41:21Z | 0 | 0 |
peft
|
[
"peft",
"llama",
"region:us"
] | null | 2023-10-10T11:33:44Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0
|
hiert/berttest
|
hiert
| 2023-10-10T12:41:16Z | 128 | 0 |
transformers
|
[
"transformers",
"safetensors",
"bert",
"fill-mask",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-10T11:19:33Z |
---
license: apache-2.0
pipeline_tag: fill-mask
widget:
- text: The goal of life is [MASK].
model-index:
- name: bloom
results:
- task:
type: text-generation
dataset:
type: openai_humaneval
name: humaneval
metrics:
- name: pass@1
type: pass@1
value: 0.15542682926829265
verified: false
- name: pass@10
type: pass@10
value: 0.3278356276947017
verified: false
- name: pass@100
type: pass@100
value: 0.5719815685597749
verified: false
---
|
quastrinos/race-openbook-finetuned-deberta-v3-large-mcqa-TPU-v6
|
quastrinos
| 2023-10-10T12:40:01Z | 59 | 0 |
transformers
|
[
"transformers",
"tf",
"deberta-v2",
"multiple-choice",
"generated_from_keras_callback",
"base_model:quastrinos/race-openbook-finetuned-deberta-v3-large-mcqa-TPU-v5",
"base_model:finetune:quastrinos/race-openbook-finetuned-deberta-v3-large-mcqa-TPU-v5",
"license:mit",
"endpoints_compatible",
"region:us"
] |
multiple-choice
| 2023-10-10T12:39:02Z |
---
license: mit
base_model: quastrinos/race-openbook-finetuned-deberta-v3-large-mcqa-TPU-v5
tags:
- generated_from_keras_callback
model-index:
- name: race-openbook-finetuned-deberta-v3-large-mcqa-TPU-v6
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# race-openbook-finetuned-deberta-v3-large-mcqa-TPU-v6
This model is a fine-tuned version of [quastrinos/race-openbook-finetuned-deberta-v3-large-mcqa-TPU-v5](https://huggingface.co/quastrinos/race-openbook-finetuned-deberta-v3-large-mcqa-TPU-v5) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.6120
- Validation Loss: 0.9727
- Train Map3: 0.7742
- Train Lr: 5.0733553e-11
- Epoch: 0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': 0.001, 'clipnorm': 1, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'CosineDecay', 'config': {'initial_learning_rate': 2e-06, 'decay_steps': 312, 'alpha': 5e-09, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: mixed_bfloat16
### Training results
| Train Loss | Validation Loss | Train Map3 | Train Lr | Epoch |
|:----------:|:---------------:|:----------:|:-------------:|:-----:|
| 0.6120 | 0.9727 | 0.7742 | 5.0733553e-11 | 0 |
### Framework versions
- Transformers 4.35.0.dev0
- TensorFlow 2.12.0
- Datasets 2.14.5
- Tokenizers 0.14.1
|
researchainnet/test0924
|
researchainnet
| 2023-10-10T12:38:48Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-24T05:16:46Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.6.0.dev0
|
KermitDuSud/Cindy
|
KermitDuSud
| 2023-10-10T12:29:11Z | 0 | 0 | null |
[
"license:bigscience-bloom-rail-1.0",
"region:us"
] | null | 2023-10-10T12:29:11Z |
---
license: bigscience-bloom-rail-1.0
---
|
shasha168/ppo-Huggy
|
shasha168
| 2023-10-10T12:26:16Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-10-10T12:26:08Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: shasha168/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
lht1107/distilbert-base-uncased-finetuned-emotion
|
lht1107
| 2023-10-10T12:12:19Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-10T11:08:48Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.929
- name: F1
type: f1
value: 0.9289651135784346
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2066
- Accuracy: 0.929
- F1: 0.9290
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.7843 | 1.0 | 250 | 0.2875 | 0.913 | 0.9122 |
| 0.2373 | 2.0 | 500 | 0.2066 | 0.929 | 0.9290 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
zentrum-lexikographie/de_dwds_hdt_dist
|
zentrum-lexikographie
| 2023-10-10T12:08:19Z | 0 | 0 |
spacy
|
[
"spacy",
"token-classification",
"de",
"region:us"
] |
token-classification
| 2023-10-10T11:46:53Z |
---
tags:
- spacy
- token-classification
language:
- de
---
| Feature | Description |
| --- | --- |
| **Name** | `de_dwds_hdt_dist` |
| **Version** | `0.0.0` |
| **spaCy** | `>=3.7.1,<3.8.0` |
| **Default Pipeline** | `dep_transformer`, `tagger`, `morphologizer`, `trainable_lemmatizer`, `parser`, `ner_transformer`, `ner` |
| **Components** | `dep_transformer`, `tagger`, `morphologizer`, `trainable_lemmatizer`, `parser`, `ner_transformer`, `ner` |
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
| **Sources** | n/a |
| **License** | n/a |
| **Author** | [n/a]() |
### Label Scheme
<details>
<summary>View label scheme (823 labels for 4 components)</summary>
| Component | Labels |
| --- | --- |
| **`tagger`** | `$(`, `$,`, `$.`, `ADJA`, `ADJD`, `ADV`, `APPO`, `APPR`, `APPR_ART`, `APZR`, `ART`, `CARD`, `FM`, `ITJ`, `KOKOM`, `KON`, `KOUI`, `KOUS`, `NE`, `NN`, `PDAT`, `PDS`, `PIAT`, `PIDAT`, `PIS`, `PPER`, `PPOSAT`, `PPOSS`, `PRELAT`, `PRELS`, `PRF`, `PROAV`, `PTKA`, `PTKANT`, `PTKNEG`, `PTKVZ`, `PTKZU`, `PWAT`, `PWAV`, `PWS`, `TRUNC`, `VAFIN`, `VAIMP`, `VAINF`, `VAPP`, `VMFIN`, `VMINF`, `VMPP`, `VVFIN`, `VVIMP`, `VVINF`, `VVIZU`, `VVPP`, `XY` |
| **`morphologizer`** | `AdpType=Prep\|Case=Dat\|POS=ADP`, `Case=Dat\|Definite=Def\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Art`, `Degree=Pos\|Gender=Fem\|Number=Sing\|POS=ADJ`, `Gender=Fem\|Number=Sing\|POS=NOUN`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Case=Dat\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Nom\|Number=Sing\|POS=PROPN`, `Foreign=Yes\|POS=X`, `POS=PUNCT\|PunctType=Comm`, `Case=Nom\|Definite=Ind\|Gender=Masc\|NumType=Card\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Gen\|Definite=Def\|Number=Plur\|POS=DET\|PronType=Art`, `Case=Gen\|Degree=Sup\|Gender=Masc\|Number=Plur\|POS=ADJ`, `Gender=Masc\|Number=Plur\|POS=NOUN`, `Gender=Neut\|Number=Sing\|POS=NOUN`, `AdpType=Prep\|POS=ADP`, `Gender=Neut\|Number=Plur\|POS=NOUN`, `POS=CCONJ`, `POS=PUNCT\|PunctType=Peri`, `NumType=Card\|Number=Plur\|POS=NUM`, `Gender=Fem\|Number=Plur\|POS=NOUN`, `AdpType=Prep\|Case=Dat\|Definite=Def\|Gender=Masc,Neut\|Number=Sing\|POS=ADP\|PronType=Art`, `Gender=Masc\|Number=Sing\|POS=NOUN`, `Case=Gen\|Definite=Def\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Gen\|Gender=Neut\|Number=Sing\|POS=NOUN`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin`, `Case=Nom\|Definite=Def\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Art`, `Degree=Pos\|Gender=Neut\|Number=Sing\|POS=ADJ`, `POS=PUNCT\|PunctType=Brck`, `POS=PROPN`, `Case=Acc\|Definite=Def\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Art`, `POS=ADV`, `POS=SCONJ`, `Case=Nom\|Gender=Neut\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `POS=VERB\|VerbForm=Inf`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Case=Nom\|Definite=Def\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Art`, `Degree=Sup\|Gender=Fem\|Number=Sing\|POS=ADJ`, `Case=Dat\|Definite=Def\|Number=Plur\|POS=DET\|PronType=Art`, `Case=Dat\|Gender=Masc\|Number=Plur\|POS=NOUN`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin\|VerbType=Mod`, `Case=Acc\|Definite=Def\|Number=Plur\|POS=DET\|PronType=Art`, `Case=Acc\|Number=Sing\|POS=PROPN`, `Degree=Cmp\|POS=ADJ\|Variant=Short`, `POS=ADP\|PartType=Vbp`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin\|VerbType=Mod`, `AdpType=Prep\|Case=Acc\|POS=ADP`, `Case=Acc\|Definite=Ind\|Gender=Fem\|NumType=Card\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Dat\|Degree=Pos\|Gender=Masc\|Number=Plur\|POS=ADJ`, `Case=Nom\|Gender=Fem\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `POS=PART\|Polarity=Neg`, `POS=ADV\|PronType=Dem`, `Degree=Cmp\|POS=ADV`, `ConjType=Comp\|POS=CCONJ`, `Case=Nom\|Definite=Ind\|Gender=Fem\|NumType=Card\|Number=Sing\|POS=DET\|PronType=Art`, `Degree=Pos\|POS=ADJ\|Variant=Short`, `Case=Gen\|Degree=Pos\|Gender=Neut\|Number=Plur\|POS=ADJ`, `Number=Sing\|POS=PROPN`, `Case=Nom\|Definite=Def\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Nom\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Tot`, `Case=Acc\|Definite=Ind\|Gender=Masc\|NumType=Card\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Acc\|Degree=Cmp\|Number=Plur\|POS=DET\|PronType=Ind`, `Aspect=Perf\|POS=VERB\|VerbForm=Part`, `Case=Dat\|Definite=Ind\|Gender=Neut\|NumType=Card\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Gen\|Definite=Def\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Gen\|Gender=Masc\|Number=Sing\|POS=NOUN`, `Case=Acc\|POS=PRON\|Person=3\|PronType=Prs\|Reflex=Yes`, `Case=Nom\|Definite=Def\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Nom\|Degree=Sup\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Case=Acc\|Definite=Def\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Acc\|Number=Plur\|POS=DET\|PronType=Dem`, `Degree=Sup\|POS=ADJ\|Variant=Short`, `Case=Nom\|Degree=Pos\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Hyph=Yes\|POS=NOUN`, `Case=Nom\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Case=Acc\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Tot`, `Case=Acc\|Gender=Fem\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Degree=Sup\|Gender=Neut\|Number=Plur\|POS=ADJ`, `Case=Dat\|Gender=Neut\|Number=Plur\|POS=NOUN`, `POS=PART\|PartType=Inf`, `Case=Gen\|Definite=Def\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Dat\|Degree=Pos\|Number=Sing\|POS=ADJ`, `POS=NOUN`, `Case=Dat\|Definite=Ind\|Gender=Masc\|NumType=Card\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Dat\|Definite=Def\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Gen\|Degree=Pos\|Number=Sing\|POS=ADJ`, `POS=AUX\|VerbForm=Inf`, `Case=Nom\|Definite=Ind\|Gender=Neut\|NumType=Card\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Dat\|Degree=Pos\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Gender=Fem\|Number=Plur\|POS=ADJ`, `POS=AUX\|VerbForm=Inf\|VerbType=Mod`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Case=Gen\|Definite=Ind\|Gender=Fem\|NumType=Card\|Number=Sing\|POS=DET\|PronType=Art`, `Number=Sing\|POS=DET\|PronType=Ind`, `Case=Nom\|Number=Plur\|POS=DET\|PronType=Ind`, `AdpType=Prep\|Case=Dat\|Definite=Def\|Gender=Fem\|Number=Sing\|POS=ADP\|PronType=Art`, `Degree=Pos\|Number=Plur\|POS=ADJ`, `Case=Nom\|Number=Sing\|POS=PRON\|PronType=Ind`, `Case=Dat\|Gender=Masc\|Number=Sing\|POS=NOUN`, `POS=ADJ`, `Degree=Cmp\|POS=DET\|PronType=Ind`, `Case=Dat\|Definite=Ind\|Gender=Fem\|NumType=Card\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Dat\|Degree=Pos\|Gender=Fem\|Number=Sing\|POS=ADJ`, `Case=Nom\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Case=Nom\|Definite=Def\|Number=Plur\|POS=DET\|PronType=Art`, `POS=ADV\|PronType=Int`, `Degree=Pos\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Case=Dat\|Number=Sing\|POS=PROPN`, `Case=Acc\|Definite=Ind\|Gender=Neut\|NumType=Card\|Number=Sing\|POS=DET\|PronType=Art`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Case=Nom\|NumType=Card\|Number=Plur\|POS=DET\|PronType=Tot`, `Case=Acc\|Degree=Pos\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Degree=Pos\|Number=Sing\|POS=ADJ`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=3\|Tense=Past\|VerbForm=Fin`, `Case=Acc\|Gender[psor]=Fem\|Number=Plur\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Gender=Fem\|Gender[psor]=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Degree=Pos\|POS=ADJ`, `Case=Gen\|Degree=Pos\|Gender=Masc\|Number=Plur\|POS=ADJ`, `Case=Acc\|Number=Plur\|POS=DET\|PronType=Tot`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=3\|Tense=Past\|VerbForm=Fin`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=3\|Tense=Past\|VerbForm=Fin\|VerbType=Mod`, `Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Neg`, `Case=Gen\|Degree=Cmp\|Gender=Neut\|Number=Plur\|POS=ADJ`, `Case=Gen\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Dem`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=1\|Tense=Pres\|VerbForm=Fin\|VerbType=Mod`, `Number=Plur\|POS=NOUN`, `Degree=Pos\|Gender=Neut\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Case=Nom\|Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Dem,Rel`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=3\|Tense=Past\|VerbForm=Fin\|VerbType=Mod`, `Gender=Fem\|Number=Sing\|POS=PROPN`, `Case=Dat\|Gender=Fem\|Number=Sing\|POS=PROPN`, `Case=Acc\|Definite=Def\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Art`, `Degree=Pos\|POS=ADV`, `Case=Nom\|Gender=Masc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Dat\|Gender=Fem\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Nom\|Degree=Pos\|Gender=Neut\|Number=Plur\|POS=ADJ`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin`, `Degree=Cmp\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Dat\|Gender=Fem\|Number=Sing\|POS=NOUN`, `AdpType=Prep\|Case=Gen\|POS=ADP`, `Degree=Pos\|Gender=Masc\|Number=Plur\|POS=ADJ`, `Case=Dat\|Number=Plur\|POS=PRON\|PronType=Dem,Rel`, `AdpType=Post\|Case=Dat\|POS=ADP`, `Gender=Masc\|Number=Sing\|POS=PROPN`, `Case=Acc\|Gender=Neut\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Nom\|Gender=Masc\|Number=Sing\|POS=PRON\|PronType=Dem,Rel`, `Case=Gen\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Dat\|Definite=Def\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Acc\|Degree=Sup\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Case=Acc\|Degree=Cmp\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Aspect=Perf\|POS=AUX\|VerbForm=Part`, `Gender=Fem\|Number=Sing\|POS=ADJ`, `Case=Dat\|Number=Plur\|POS=ADJ`, `Case=Acc\|Gender=Masc\|Number=Sing\|POS=PRON\|PronType=Dem,Rel`, `Degree=Cmp\|Gender=Neut\|Number=Plur\|POS=ADJ`, `Case=Nom\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Dem`, `Gender=Masc\|Number=Sing\|POS=ADJ`, `Case=Nom\|Gender=Masc\|Number=Sing\|POS=NOUN`, `Case=Nom\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Neg`, `Case=Dat\|Gender=Masc\|Gender[psor]=Masc,Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Number=Sing\|POS=PRON\|PronType=Tot`, `Number=Sing\|POS=NOUN`, `Degree=Pos\|Gender=Fem\|Number=Plur\|POS=ADJ`, `Degree=Pos\|Gender=Neut\|Number=Plur\|POS=ADJ`, `Case=Dat\|Degree=Cmp\|Number=Sing\|POS=ADJ`, `Case=Acc\|Degree=Pos\|Gender=Neut\|Number=Plur\|POS=ADJ`, `Case=Dat\|Gender=Neut\|Number=Sing\|POS=NOUN`, `Case=Gen\|Degree=Pos\|Gender=Fem\|Number=Plur\|POS=ADJ`, `Case=Nom\|Number=Plur\|POS=PRON\|PronType=Dem,Rel`, `Case=Nom\|Gender=Neut\|Number=Sing\|POS=ADJ`, `Case=Acc\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Dem`, `Case=Dat\|Degree=Pos\|Gender=Fem\|Number=Plur\|POS=ADJ`, `Case=Nom\|Number=Plur\|POS=DET\|PronType=Int,Rel`, `Case=Gen\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Degree=Sup\|POS=ADV`, `Case=Dat\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Dem`, `Case=Acc\|Degree=Pos\|Gender=Masc\|Number=Plur\|POS=ADJ`, `Case=Nom\|Number=Plur\|POS=DET\|PronType=Tot`, `Case=Dat\|Degree=Sup\|Number=Plur\|POS=DET\|PronType=Ind`, `Degree=Cmp\|Gender=Masc\|Number=Plur\|POS=ADJ`, `Case=Dat\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Case=Dat\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Int,Rel`, `NumType=Card\|Number=Sing\|POS=NUM`, `Case=Dat\|Number=Plur\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Number=Plur\|POS=DET\|PronType=Dem`, `Case=Dat\|POS=PRON\|Person=3\|PronType=Prs\|Reflex=Yes`, `Case=Acc\|Gender=Fem\|Number=Sing\|POS=PRON\|PronType=Dem,Rel`, `Number=Plur\|POS=PROPN`, `Case=Nom\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Neg`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Case=Gen\|Number=Plur\|POS=DET\|PronType=Tot`, `Case=Nom\|Number=Sing\|POS=PRON\|PronType=Int,Rel`, `Case=Nom\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Acc\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Dat\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Tot`, `Case=Nom\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Dem`, `Case=Nom\|Degree=Pos\|Gender=Masc\|Number=Plur\|POS=ADJ`, `Gender=Masc\|Number=Plur\|POS=ADJ`, `Case=Dat\|Number=Plur\|POS=DET\|PronType=Dem`, `Gender=Neut\|Number=Sing\|POS=DET\|PronType=Ind`, `AdpType=Prep\|Case=Acc\|Definite=Def\|Gender=Neut\|Number=Sing\|POS=ADP\|PronType=Art`, `Case=Gen\|Number=Sing\|POS=PROPN`, `Degree=Cmp\|Gender=Neut\|Number=Sing\|POS=ADJ`, `Case=Dat\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Nom\|Number=Plur\|POS=DET\|PronType=Dem`, `Case=Dat\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Dat\|Number=Sing\|POS=DET\|PronType=Ind`, `Mood=Imp\|Number=Sing\|POS=VERB\|Person=2\|VerbForm=Fin`, `Case=Dat\|Gender=Masc\|Number=Sing\|POS=PRON\|PronType=Dem,Rel`, `Degree=Pos\|Gender=Neut\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Case=Nom\|Number=Plur\|POS=ADJ`, `Case=Gen\|POS=PRON\|PronType=Dem,Rel`, `Case=Acc\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Gender=Fem\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Gen\|Gender=Masc\|Number=Plur\|POS=NOUN`, `Case=Nom\|Gender=Fem\|Number=Plur\|POS=ADJ`, `Case=Dat\|Gender=Masc\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Acc\|Degree=Pos\|Gender=Fem\|Number=Plur\|POS=ADJ`, `Case=Gen\|Gender=Masc\|Gender[psor]=Masc,Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Gender=Neut\|Number=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Nom\|Degree=Pos\|Gender=Fem\|Number=Sing\|POS=ADJ`, `Case=Gen\|Degree=Pos\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Case=Nom\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Dat\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Dem`, `Case=Acc\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Neg`, `Case=Acc\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Case=Nom\|Gender=Fem\|Number=Sing\|POS=PRON\|PronType=Dem,Rel`, `Case=Dat\|Number=Plur\|POS=DET\|PronType=Ind`, `Degree=Cmp\|Number=Plur\|POS=ADJ`, `Case=Acc\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Neg`, `Case=Dat\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Case=Dat\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Neg`, `Case=Dat\|POS=PROPN`, `Case=Gen\|Number=Sing\|POS=PRON\|PronType=Dem,Rel`, `Degree=Cmp\|Gender=Fem\|Number=Sing\|POS=ADJ`, `Case=Nom\|Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Int,Rel`, `Case=Acc\|Number=Plur\|POS=DET\|PronType=Neg`, `Case=Nom\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Case=Gen\|Degree=Pos\|Gender=Fem\|Number=Sing\|POS=ADJ`, `Case=Dat\|Gender=Fem\|Number=Sing\|POS=PRON\|PronType=Dem,Rel`, `AdpType=Circ\|POS=ADP`, `Case=Acc\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Dat\|Number=Plur\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Gender=Fem\|Number=Plur\|POS=NOUN`, `Case=Nom\|Degree=Pos\|Gender=Fem\|Number=Plur\|POS=ADJ`, `Case=Nom\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Tot`, `Case=Nom\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Dem`, `Case=Nom\|Gender=Neut\|Number=Plur\|POS=ADJ`, `Case=Acc\|Number=Plur\|POS=PRON\|PronType=Dem,Rel`, `Gender=Neut\|Number=Sing\|POS=ADJ`, `Case=Acc\|Gender=Fem\|Number=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Definite=Def\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Gen\|Definite=Ind\|Gender=Neut\|NumType=Card\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Dat\|Degree=Pos\|Gender=Neut\|Number=Plur\|POS=ADJ`, `Case=Dat\|Gender[psor]=Masc,Neut\|Number=Plur\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Nom\|Degree=Sup\|Gender=Fem\|Number=Plur\|POS=ADJ`, `Case=Gen\|Definite=Ind\|Gender=Masc\|NumType=Card\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Acc\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Dem`, `Case=Acc\|Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Dem,Rel`, `Degree=Cmp\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Ind`, `AdpType=Prep\|Case=Nom\|POS=ADP`, `Degree=Cmp\|Gender=Fem\|Number=Plur\|POS=ADJ`, `Case=Acc\|Gender[psor]=Masc,Neut\|Number=Plur\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Neg`, `Case=Acc\|Number=Plur\|POS=DET\|PronType=Ind`, `Gender=Masc\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Gen\|Number=Plur\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Nom\|Number=Sing\|POS=PRON\|PronType=Neg`, `Case=Acc\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Int,Rel`, `Case=Nom\|Number=Plur\|POS=DET\|PronType=Neg`, `Gender=Neut\|Number=Plur\|POS=ADJ`, `Case=Nom\|Gender=Fem\|Number=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Nom\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Int,Rel`, `Case=Dat\|Degree=Pos\|Gender=Neut\|Number=Sing\|POS=ADJ`, `Case=Acc\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Int,Rel`, `Case=Nom\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Tot`, `Case=Dat\|Degree=Sup\|Gender=Fem\|Number=Plur\|POS=ADJ`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Dat\|Gender=Neut\|Gender[psor]=Masc,Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Dem`, `Case=Nom\|Degree=Pos\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Case=Dat\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Tot`, `Case=Dat\|Number=Plur\|POS=NOUN`, `Case=Dat\|Gender=Fem\|Gender[psor]=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Gender=Fem\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Dat\|Gender=Neut\|Number=Sing\|POS=ADJ`, `Case=Nom\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Neg`, `Case=Gen\|Degree=Cmp\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Nom\|Degree=Pos\|Gender=Neut\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Case=Dat\|Degree=Cmp\|Gender=Fem\|Number=Plur\|POS=ADJ`, `Case=Dat\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Neg`, `Case=Dat\|Degree=Cmp\|Gender=Neut\|Number=Plur\|POS=ADJ`, `Case=Dat\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Tot`, `Case=Gen\|Gender=Masc\|Number=Plur\|POS=DET\|PronType=Ind`, `Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Ind`, `Case=Nom\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Acc\|Number=Plur\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Gender=Masc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Dat\|Gender=Fem\|Gender[psor]=Masc,Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Case=Dat\|Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Dem,Rel`, `Case=Acc\|Gender=Neut\|Gender[psor]=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Nom\|Gender=Masc\|Number=Sing\|POS=PROPN`, `Case=Dat\|Gender=Masc\|Number=Plur\|POS=ADJ`, `Case=Dat\|Gender=Masc\|Number=Sing\|POS=PROPN`, `Case=Dat\|Number=Plur\|POS=DET\|PronType=Int,Rel`, `Case=Acc\|Gender=Fem\|Gender[psor]=Masc,Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Gender=Neut\|Number=Sing\|POS=ADJ`, `Case=Acc\|Gender=Neut\|Gender[psor]=Masc,Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Case=Acc\|Gender=Masc\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Acc\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Dem`, `Case=Acc\|Degree=Pos\|Gender=Neut\|Number=Sing\|POS=ADJ`, `Case=Gen\|POS=PROPN`, `Case=Gen\|Number=Plur\|POS=NOUN`, `Case=Acc\|Number=Sing\|POS=PRON\|PronType=Int,Rel`, `Case=Nom\|Degree=Cmp\|Number=Plur\|POS=DET\|PronType=Ind`, `POS=DET\|PronType=Ind`, `Case=Nom\|Degree=Pos\|Gender=Masc\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Case=Gen\|Number=Plur\|POS=ADJ`, `Case=Nom\|Number=Sing\|POS=PRON\|PronType=Tot`, `POS=DET\|PronType=Tot`, `Case=Dat\|Gender=Neut\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `POS=X`, `Gender=Fem\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Gen\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Dem`, `Case=Nom\|Gender=Fem\|Number=Sing\|POS=ADJ`, `AdpType=Post\|Case=Acc\|POS=ADP`, `Case=Acc\|NumType=Card\|Number=Plur\|POS=DET\|PronType=Tot`, `Degree=Pos\|Gender=Masc\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Case=Dat\|Gender=Masc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Gen\|Gender=Neut\|Gender[psor]=Masc,Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Number=Plur\|POS=DET\|PronType=Tot`, `Case=Gen\|Degree=Cmp\|Gender=Fem\|Number=Plur\|POS=ADJ`, `Case=Gen\|NumType=Card\|Number=Plur\|POS=DET\|PronType=Tot`, `Number=Plur\|POS=DET\|PronType=Ind`, `Case=Dat\|Degree=Sup\|Number=Sing\|POS=ADJ`, `Case=Dat\|Degree=Sup\|Number=Plur\|POS=ADJ`, `POS=DET\|PronType=Neg`, `POS=ADV\|PronType=Ind`, `Case=Gen\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Dem`, `Case=Acc\|Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Int,Rel`, `Case=Dat\|Degree=Cmp\|Number=Plur\|POS=ADJ`, `Case=Nom\|Degree=Pos\|Gender=Neut\|Number=Sing\|POS=ADJ`, `Case=Gen\|Degree=Pos\|Gender=Neut\|Number=Sing\|POS=ADJ`, `Gender=Neut\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Acc\|Gender=Neut\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Dat\|Foreign=Yes\|POS=X`, `Case=Acc\|Degree=Sup\|Gender=Neut\|Number=Plur\|POS=ADJ`, `Case=Nom\|Gender=Fem\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Gen\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Nom\|Gender=Neut\|Number=Sing\|POS=NOUN`, `Degree=Sup\|Gender=Neut\|Number=Sing\|POS=ADJ`, `Case=Dat\|Gender=Neut\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Dat\|NumType=Card\|Number=Plur\|POS=DET\|PronType=Tot`, `Case=Acc\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Tot`, `Case=Gen\|Number=Sing\|POS=NOUN`, `NumType=Card\|POS=NUM`, `Case=Gen\|Degree=Pos\|Gender=Neut\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Case=Nom\|Gender=Fem\|Gender[psor]=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Acc\|Gender=Fem\|Number=Sing\|POS=ADJ`, `Case=Gen\|Degree=Sup\|Number=Sing\|POS=ADJ`, `Case=Acc\|Gender=Fem\|Number=Plur\|POS=DET\|PronType=Dem`, `Case=Nom\|Gender=Masc\|Number=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Gender=Masc\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs\|Reflex=Yes`, `Degree=Pos\|Gender=Fem\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Case=Dat\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Int,Rel`, `Degree=Cmp\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Degree=Cmp\|Number=Sing\|POS=ADJ`, `Case=Dat\|Gender=Fem\|Number=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Degree=Pos\|Gender=Fem\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Case=Dat\|Degree=Cmp\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Acc\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Int,Rel`, `Case=Dat\|Gender=Neut\|Gender[psor]=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Degree=Sup\|Number=Plur\|POS=ADJ`, `Case=Acc\|Degree=Pos\|Gender=Fem\|Number=Sing\|POS=ADJ`, `Case=Acc\|Gender=Masc\|Gender[psor]=Masc,Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Number=Plur\|POS=ADJ`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs\|Reflex=Yes`, `Case=Dat\|Gender=Neut\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Gender[psor]=Masc,Neut\|Number=Plur\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Nom\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Int,Rel`, `Degree=Sup\|Number=Sing\|POS=ADJ`, `Case=Nom\|Gender=Masc\|Gender[psor]=Masc,Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Tot`, `Gender=Masc\|Number=Sing\|POS=DET\|PronType=Ind`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=1\|Tense=Pres\|VerbForm=Fin\|VerbType=Mod`, `Case=Dat\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Acc\|Gender=Neut\|Number=Sing\|POS=ADJ`, `Case=Dat\|Degree=Cmp\|Gender=Masc\|Number=Plur\|POS=ADJ`, `Case=Nom\|Degree=Sup\|Number=Plur\|POS=ADJ`, `Degree=Pos\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Case=Nom\|Degree=Sup\|Gender=Masc\|Number=Plur\|POS=ADJ`, `Degree=Sup\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Case=Dat\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Gen\|Gender=Fem\|Number=Sing\|POS=ADJ`, `Case=Nom\|Gender=Fem\|Number=Sing\|POS=NOUN`, `Degree=Pos\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Case=Nom\|Gender[psor]=Masc,Neut\|Number=Plur\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Gender=Fem\|Number=Sing\|POS=ADJ`, `Degree=Sup\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Acc\|Gender=Masc\|Number=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Number=Plur\|POS=DET\|PronType=Int,Rel`, `Case=Dat\|Gender=Fem\|Number=Plur\|POS=ADJ`, `Case=Dat\|Number=Sing\|POS=PRON\|PronType=Int,Rel`, `Case=Nom\|Degree=Cmp\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Case=Dat\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Neg`, `Case=Acc\|Degree=Cmp\|Gender=Neut\|Number=Plur\|POS=ADJ`, `Case=Nom\|Gender=Neut\|Gender[psor]=Masc,Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Dat\|POS=ADJ`, `Case=Dat\|Degree=Pos\|Gender=Masc\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Case=Acc\|Degree=Pos\|Gender=Masc\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Case=Acc\|Gender=Masc\|Number=Plur\|POS=ADJ`, `Case=Dat\|Degree=Sup\|Gender=Masc\|Number=Plur\|POS=ADJ`, `Case=Gen\|Gender=Neut\|Number=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Mood=Ind\|POS=VERB\|Person=3\|VerbForm=Fin`, `Case=Gen\|Gender=Masc\|Number=Sing\|POS=PROPN`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=2\|PronType=Prs`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Gen\|Degree=Cmp\|Number=Sing\|POS=ADJ`, `Case=Acc\|Gender=Masc\|Number=Sing\|POS=NOUN`, `POS=ADJ\|Variant=Short`, `Case=Gen\|Gender=Fem\|Number=Sing\|POS=PROPN`, `Foreign=Yes\|Number=Sing\|POS=X`, `Case=Nom\|Degree=Sup\|Gender=Neut\|Number=Plur\|POS=ADJ`, `Case=Gen\|Degree=Pos\|Gender=Masc\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Case=Nom\|Number=Plur\|POS=DET\|Person=2\|Polite=Form\|Poss=Yes\|PronType=Prs`, `Case=Nom\|Gender=Neut\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Degree=Pos\|Gender=Fem\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Case=Dat\|Gender=Masc\|Number=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Gender=Fem\|Gender[psor]=Masc,Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Number=Plur\|POS=ADJ`, `Case=Gen\|Number=Plur\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Dat\|POS=NOUN`, `Case=Nom\|Gender=Masc\|Number=Plur\|POS=DET\|PronType=Ind`, `Aspect=Perf\|POS=AUX\|VerbForm=Part\|VerbType=Mod`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=1\|Tense=Past\|VerbForm=Fin`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs\|Reflex=Yes`, `Case=Nom\|Degree=Pos\|Gender=Masc\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Case=Acc\|Degree=Pos\|Gender=Masc\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Gender=Masc\|POS=NOUN`, `Case=Acc\|Degree=Sup\|Gender=Fem\|Number=Plur\|POS=ADJ`, `Case=Dat\|Number=Sing\|POS=ADJ`, `POS=DET\|PronType=Int`, `Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Int,Rel`, `Case=Nom\|Gender=Neut\|Number=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Gender=Fem\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Number=Sing\|POS=PRON\|PronType=Tot`, `Case=Dat\|Number=Sing\|POS=NOUN`, `Case=Dat\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs\|Reflex=Yes`, `Case=Nom\|POS=PROPN`, `Case=Nom\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Int,Rel`, `Degree=Pos\|Gender=Fem\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Case=Acc\|Number=Sing\|POS=PRON\|PronType=Ind`, `Case=Nom\|Gender=Fem\|Number=Sing\|POS=PROPN`, `Case=Nom\|Gender=Masc\|Number=Sing\|POS=DET\|Person=2\|Polite=Form\|Poss=Yes\|PronType=Prs`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=1\|Tense=Past\|VerbForm=Fin`, `Case=Nom\|Gender=Neut\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Gen\|Degree=Sup\|Gender=Fem\|Number=Plur\|POS=ADJ`, `Case=Dat\|Degree=Pos\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Case=Gen\|Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Dem,Rel`, `Case=Nom\|Degree=Cmp\|Gender=Neut\|Number=Plur\|POS=ADJ`, `POS=INTJ\|PartType=Res`, `Case=Nom\|Gender=Fem\|Number=Sing\|POS=DET\|Person=2\|Polite=Form\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Gender=Fem\|Number=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=1\|Tense=Past\|VerbForm=Fin`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=2\|Tense=Past\|VerbForm=Fin`, `Case=Acc\|Gender=Masc\|Number=Sing\|POS=DET\|Person=2\|Polite=Form\|Poss=Yes\|PronType=Prs`, `Case=Dat\|POS=PRON\|Person=2\|Polite=Form\|PronType=Prs`, `Foreign=Yes\|Gender=Neut\|Number=Sing\|POS=X`, `Case=Nom\|Gender=Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Number=Plur\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Nom\|Number=Plur\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Gender=Neut\|Number=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Degree=Pos\|Gender=Neut\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Case=Dat\|Gender=Neut\|Number=Plur\|POS=ADJ`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=2\|Tense=Pres\|VerbForm=Fin\|VerbType=Mod`, `Case=Dat\|Gender=Masc\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Number=Plur\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Number=Plur\|POS=PRON\|PronType=Dem,Rel`, `Case=Nom\|Gender=Fem\|Gender[psor]=Masc,Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Degree=Cmp\|Gender=Fem\|Number=Plur\|POS=ADJ`, `Case=Nom\|Definite=Ind\|NumType=Card\|Number=Plur\|POS=DET\|PronType=Art`, `Case=Dat\|Gender=Fem\|Number=Sing\|POS=DET\|Person=2\|Polite=Form\|Poss=Yes\|PronType=Prs`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|VerbForm=Fin`, `Gender=Neut\|Number=Sing\|POS=PROPN`, `Case=Nom\|POS=NOUN`, `Case=Dat\|Number=Plur\|POS=DET\|Person=2\|Polite=Form\|Poss=Yes\|PronType=Prs`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=1\|VerbForm=Fin`, `Case=Gen\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Tot`, `Mood=Imp\|Number=Plur\|POS=VERB\|Person=2\|VerbForm=Fin`, `Case=Nom\|Gender=Fem\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Gender=Masc\|Gender[psor]=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Degree=Cmp\|Number=Plur\|POS=ADJ`, `Case=Gen\|Gender=Masc\|Number=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `POS=DET\|PronType=Dem`, `Case=Dat\|Gender=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Number=Plur\|POS=DET\|PronType=Neg`, `Definite=Ind\|NumType=Card\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Acc\|Gender=Neut\|Number=Plur\|POS=ADJ`, `Case=Acc\|Gender=Neut\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Dat\|Degree=Pos\|Gender=Neut\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Degree=Sup\|Gender=Masc\|Number=Plur\|POS=ADJ`, `Case=Dat\|Gender[psor]=Fem\|Number=Plur\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Degree=Pos\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Case=Acc\|Gender=Fem\|Number=Plur\|POS=ADJ`, `Degree=Sup\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Gen\|NumType=Card\|Number=Plur\|POS=NUM`, `Case=Gen\|Gender=Fem\|Gender[psor]=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=2\|Tense=Pres\|VerbForm=Fin`, `Case=Acc\|Degree=Pos\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Case=Nom\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Acc\|Degree=Sup\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Gen\|Gender=Neut\|Number=Plur\|POS=ADJ`, `Degree=Pos\|Gender=Masc\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Case=Nom\|Gender[psor]=Fem\|Number=Plur\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Number=Plur\|POS=DET\|Person=2\|Polite=Form\|Poss=Yes\|PronType=Prs`, `Case=Nom\|Gender=Masc\|Number=Plur\|POS=NOUN`, `Case=Acc\|Degree=Cmp\|Gender=Fem\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Case=Nom\|Gender=Neut\|Number=Sing\|POS=DET\|Person=2\|Polite=Form\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Gender=Fem\|Number=Plur\|POS=ADJ`, `Case=Acc\|Degree=Cmp\|Gender=Masc\|Number=Plur\|POS=ADJ`, `Case=Gen\|Gender=Neut\|Gender[psor]=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `NumType=Card\|POS=DET\|PronType=Tot`, `Case=Dat\|Gender=Masc\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Degree=Pos\|POS=ADJ`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=1\|Tense=Past\|VerbForm=Fin\|VerbType=Mod`, `Case=Acc\|POS=NOUN`, `Case=Gen\|Gender=Neut\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Gen\|Degree=Cmp\|Gender=Masc\|Number=Plur\|POS=ADJ`, `Case=Nom\|Degree=Cmp\|Gender=Masc\|Number=Plur\|POS=ADJ`, `Case=Dat\|Gender=Fem\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Gen\|Gender=Masc\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=3\|VerbForm=Fin`, `Degree=Sup\|POS=DET\|PronType=Ind`, `Case=Nom\|Gender=Masc\|Number=Plur\|POS=ADJ`, `Case=Nom\|Gender=Neut\|Gender[psor]=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Neg`, `Case=Gen\|Gender=Fem\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Nom\|Degree=Cmp\|Gender=Fem\|Number=Plur\|POS=ADJ`, `Case=Nom\|Number=Plur\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Gender[psor]=Fem\|Number=Plur\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Number=Sing\|POS=PRON\|PronType=Ind`, `Case=Nom\|Gender=Masc\|Gender[psor]=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Gender=Masc\|Gender[psor]=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Gender=Masc\|Number=Plur\|POS=PROPN`, `Degree=Sup\|Gender=Fem\|Number=Plur\|POS=ADJ`, `Case=Dat\|Degree=Cmp\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Case=Acc\|Gender=Fem\|Number=Sing\|POS=NOUN`, `Case=Acc\|Number=Plur\|POS=DET\|PronType=Int`, `Case=Acc\|Gender=Fem\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Gen\|Degree=Sup\|Gender=Neut\|Number=Plur\|POS=ADJ`, `Case=Acc\|Gender=Masc\|Number=Sing\|POS=PROPN`, `Case=Dat\|Number=Sing\|POS=PRON\|PronType=Neg`, `Foreign=Yes\|POS=DET\|PronType=Ind`, `Case=Acc\|Gender=Neut\|Number=Sing\|POS=DET\|Person=2\|Polite=Form\|Poss=Yes\|PronType=Prs`, `Case=Nom\|Degree=Cmp\|Gender=Neut\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Number=Plur\|POS=DET\|PronType=Tot`, `Case=Nom\|Degree=Pos\|Gender=Fem\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Case=Nom\|Degree=Cmp\|Number=Plur\|POS=ADJ`, `Case=Gen\|Gender=Neut\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Hyph=Yes\|Number=Plur\|POS=NOUN`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=1\|Tense=Past\|VerbForm=Fin`, `Case=Dat\|Gender=Masc\|Gender[psor]=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Definite=Def\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Gen\|Gender=Fem\|Number=Sing\|POS=PRON\|PronType=Dem,Rel`, `Case=Acc\|Degree=Sup\|Number=Plur\|POS=ADJ`, `Degree=Cmp\|Gender=Neut\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Acc\|Number=Sing\|POS=PRON\|PronType=Neg`, `POS=PRON\|Person=3\|PronType=Prs\|Reflex=Yes`, `Gender=Masc\|Number=Plur\|POS=DET\|PronType=Dem`, `Case=Dat\|Hyph=Yes\|POS=NOUN`, `Case=Acc\|Number=Sing\|POS=DET\|PronType=Dem`, `Case=Nom\|Degree=Pos\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Gen\|Degree=Sup\|Number=Plur\|POS=ADJ`, `Case=Dat\|Degree=Sup\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Case=Nom\|Number=Plur\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Degree=Sup\|Gender=Neut\|Number=Plur\|POS=ADJ`, `Case=Gen\|Number=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Case=Gen\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Tot`, `Case=Acc\|Gender[psor]=Masc,Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Gender=Masc\|Number=Plur\|POS=ADJ`, `Case=Acc\|Degree=Sup\|Gender=Masc\|Number=Plur\|POS=ADJ`, `Case=Gen\|Gender=Fem\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Nom\|Number=Plur\|POS=DET\|PronType=Int`, `Case=Dat\|Degree=Cmp\|POS=DET\|PronType=Ind`, `Case=Nom\|Gender=Masc\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=1\|Tense=Past\|VerbForm=Fin\|VerbType=Mod`, `Case=Dat\|Definite=Ind\|NumType=Card\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Nom\|Gender=Neut\|Number=Sing\|POS=PROPN`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Number=Sing\|POS=PRON\|PronType=Ind`, `Case=Dat\|Gender=Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Dat\|NumType=Card\|Number=Plur\|POS=NUM`, `Case=Gen\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Tot`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=2\|Tense=Pres\|VerbForm=Fin`, `Case=Dat\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs\|Reflex=Yes`, `Case=Dat\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Case=Nom\|Gender=Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Gender=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Gender=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=2\|Tense=Pres\|VerbForm=Fin`, `POS=INTJ`, `Case=Acc\|Gender=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Number=Plur\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Nom\|Gender=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Degree=Cmp\|Number=Plur\|POS=ADJ`, `Case=Acc\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Dat\|Gender=Masc\|Number=Sing\|POS=DET\|Person=2\|Polite=Form\|Poss=Yes\|PronType=Prs`, `Case=Nom\|Number=Sing\|POS=PRON\|PronType=Dem,Rel`, `Gender=Masc\|Number=Sing\|POS=DET\|PronType=Dem`, `Case=Acc\|Gender=Masc\|Number=Plur\|POS=NOUN`, `Case=Acc\|Gender=Fem\|Number=Sing\|POS=DET\|Person=2\|Polite=Form\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Number=Plur\|POS=PROPN`, `Case=Nom\|Gender=Masc\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Dat\|POS=DET\|PronType=Tot`, `Case=Nom\|Number=Sing\|POS=DET\|PronType=Dem`, `Case=Nom\|Gender=Fem\|Number=Plur\|POS=DET\|PronType=Dem`, `Case=Gen\|Gender=Fem\|Number=Plur\|POS=DET\|PronType=Dem`, `Case=Gen\|Gender=Masc\|Number=Sing\|POS=PRON\|PronType=Dem,Rel`, `Case=Gen\|Gender=Fem\|Number=Sing\|POS=NOUN`, `Degree=Cmp\|Gender=Neut\|NumType=Ord\|Number=Sing\|POS=ADJ`, `AdpType=Post\|Case=Gen\|POS=ADP`, `Case=Gen\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Int,Rel`, `Case=Nom\|Number=Plur\|POS=NOUN`, `Case=Dat\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Int,Rel`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=2\|PronType=Prs\|Reflex=Yes`, `Definite=Ind\|NumType=Card\|Number=Plur\|POS=DET\|PronType=Art`, `Case=Acc\|Gender=Neut\|Number=Sing\|POS=NOUN`, `Number=Sing\|POS=PRON\|PronType=Int,Rel`, `Case=Dat\|POS=DET\|PronType=Ind`, `Case=Acc\|Gender=Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Gender=Masc\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Number=Plur\|POS=PRON\|Person=2\|PronType=Prs`, `Mood=Ind\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin`, `Case=Acc\|POS=PROPN`, `Case=Nom\|Gender[psor]=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Degree=Pos\|NumType=Ord\|POS=ADJ`, `Case=Acc\|Number=Sing\|POS=DET\|PronType=Neg`, `Case=Nom\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Acc\|Gender=Fem\|Number=Sing\|POS=PROPN`, `Case=Dat\|POS=DET\|PronType=Dem`, `Degree=Pos\|POS=DET\|PronType=Ind`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=3\|VerbForm=Fin`, `Case=Nom\|Gender=Neut\|Number=Plur\|POS=NOUN`, `Number=Sing\|POS=DET\|Person=2\|Polite=Form\|Poss=Yes\|PronType=Prs`, `Case=Dat\|POS=PRON\|PronType=Rcp`, `Gender=Masc\|Number=Sing\|POS=ADJ\|Variant=Short`, `Case=Acc\|Gender=Neut\|Number=Plur\|POS=NOUN`, `Case=Acc\|Gender=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Gender=Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs\|Reflex=Yes`, `Mood=Ind\|POS=AUX\|Person=3\|VerbForm=Fin`, `Case=Acc\|Definite=Ind\|NumType=Card\|Number=Plur\|POS=DET\|PronType=Art`, `Case=Dat\|Degree=Pos\|POS=ADJ\|Variant=Short`, `Case=Acc\|Number=Plur\|Number[psor]=Plur\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Degree=Pos\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Case=Acc\|Gender=Neut\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Gender=Masc\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Nom\|Gender=Fem\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Case=Nom\|Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Dem,Rel\|Typo=Yes`, `Mood=Imp\|Number=Plur\|POS=AUX\|Person=2\|VerbForm=Fin`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=2\|VerbForm=Fin`, `Gender[psor]=Masc,Neut\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Ind`, `Mood=Imp\|Number=Sing\|POS=AUX\|Person=2\|VerbForm=Fin`, `Mood=Ind\|POS=VERB\|Person=1\|VerbForm=Fin`, `Case=Gen\|Number=Sing\|POS=DET\|PronType=Ind`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=2\|Tense=Pres\|VerbForm=Fin`, `Abbr=Yes\|Case=Nom\|Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Dem,Rel`, `Case=Nom\|Gender=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Definite=Def\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Nom\|Definite=Ind\|NumType=Card\|POS=DET\|PronType=Art`, `Case=Dat\|Number=Plur\|POS=DET\|PronType=Int`, `Degree=Pos\|Number=Plur\|POS=DET\|PronType=Ind`, `Case=Acc\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Dat\|Degree=Pos\|Number=Plur\|POS=DET\|PronType=Ind`, `Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Neg`, `Definite=Ind\|Foreign=Yes\|NumType=Card\|POS=DET\|PronType=Art`, `Case=Nom\|Gender=Masc\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Case=Acc\|Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Dem`, `Case=Nom\|Gender=Neut\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=2\|Tense=Past\|VerbForm=Fin\|VerbType=Mod`, `Case=Dat\|Gender=Fem\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Case=Nom\|Number=Plur\|Number[psor]=Plur\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Case=Nom\|Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Dem`, `Case=Dat\|Degree=Pos\|NumType=Ord\|Number=Sing\|POS=ADJ`, `POS=DET\|PronType=Int,Rel`, `Case=Acc\|Gender=Masc\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Degree=Sup\|Gender=Fem\|Number=Sing\|POS=ADJ`, `Case=Acc\|POS=PRON\|PronType=Rcp`, `Case=Dat\|Gender=Masc\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=2\|VerbForm=Fin`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=2\|Tense=Pres\|VerbForm=Fin\|VerbType=Mod`, `Case=Acc\|Degree=Pos\|Number=Plur\|POS=DET\|PronType=Ind`, `Definite=Ind\|Degree=Pos\|Gender=Fem\|NumType=Card\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Dat\|Number=Plur\|POS=PRON\|Person=2\|PronType=Prs\|Reflex=Yes`, `Case=Dat\|Gender=Masc\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Gender=Fem\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=3\|VerbForm=Fin`, `Case=Dat\|Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Tot`, `Case=Nom\|Gender=Masc\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Number=Plur\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Acc\|Gender=Masc\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Neg`, `Number=Sing\|POS=ADJ`, `Case=Dat\|Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Int,Rel`, `Case=Gen\|Gender=Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Degree=Pos\|Gender=Neut\|POS=ADJ`, `Gender=Fem\|POS=ADJ`, `Degree=Pos\|Gender=Fem\|POS=ADJ`, `Gender=Masc\|POS=ADJ`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=3\|VerbForm=Fin\|VerbType=Mod`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=3\|VerbForm=Fin\|VerbType=Mod`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=1\|VerbForm=Fin\|VerbType=Mod`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=1\|VerbForm=Fin`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=1\|VerbForm=Fin`, `Case=Acc\|Number=Plur\|Number[psor]=Sing\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Foreign=Yes\|POS=DET\|PronType=Dem`, `Case=Nom\|Degree=Cmp\|Gender=Masc\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Case=Gen\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Nom\|Number=Plur\|Number[psor]=Sing\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs` |
| **`parser`** | `ROOT`, `acl`, `advcl`, `advmod`, `amod`, `appos`, `aux`, `aux:pass`, `case`, `cc`, `ccomp`, `compound:prt`, `conj`, `cop`, `csubj`, `csubj:pass`, `dep`, `det`, `expl`, `expl:pv`, `flat`, `flat:name`, `mark`, `nmod`, `nsubj`, `nsubj:pass`, `nummod`, `obj`, `obl`, `obl:arg`, `parataxis`, `punct`, `reparandum`, `xcomp` |
| **`ner`** | `LOC`, `MISC`, `ORG`, `PER` |
</details>
|
desarrolloasesoreslocales/SetFitPruebaMulti
|
desarrolloasesoreslocales
| 2023-10-10T11:58:28Z | 3 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"mpnet",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] |
text-classification
| 2023-10-10T11:58:07Z |
---
license: apache-2.0
tags:
- setfit
- sentence-transformers
- text-classification
pipeline_tag: text-classification
---
# desarrolloasesoreslocales/SetFitPruebaMulti
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("desarrolloasesoreslocales/SetFitPruebaMulti")
# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
|
seriouspark/llama2-qlora-finetunined-product_name_combination2
|
seriouspark
| 2023-10-10T11:53:05Z | 0 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:meta-llama/Llama-2-13b-chat-hf",
"base_model:adapter:meta-llama/Llama-2-13b-chat-hf",
"region:us"
] | null | 2023-10-10T11:52:24Z |
---
library_name: peft
base_model: meta-llama/Llama-2-13b-chat-hf
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.0.dev0
|
anders0204/rl_course_vizdoom_health_gathering_supreme
|
anders0204
| 2023-10-10T11:47:58Z | 0 | 0 |
sample-factory
|
[
"sample-factory",
"tensorboard",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-10T11:41:48Z |
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: doom_health_gathering_supreme
type: doom_health_gathering_supreme
metrics:
- type: mean_reward
value: 13.05 +/- 5.55
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r anders0204/rl_course_vizdoom_health_gathering_supreme
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
alexofntu/textual_inversion_Carla_day1
|
alexofntu
| 2023-10-10T11:46:55Z | 12 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"textual_inversion",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-10-10T08:58:54Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- textual_inversion
inference: true
---
# Textual inversion text2image fine-tuning - alexofntu/textual_inversion_Carla_day1
These are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.
|
Tommert25/multibert1010_lrate7.5b32
|
Tommert25
| 2023-10-10T11:44:56Z | 118 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"token-classification",
"generated_from_trainer",
"base_model:google-bert/bert-base-multilingual-uncased",
"base_model:finetune:google-bert/bert-base-multilingual-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-10-10T09:10:56Z |
---
license: apache-2.0
base_model: bert-base-multilingual-uncased
tags:
- generated_from_trainer
metrics:
- recall
- accuracy
model-index:
- name: multibert1010_lrate7.5b32
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# multibert1010_lrate7.5b32
This model is a fine-tuned version of [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5515
- Precisions: 0.8551
- Recall: 0.8069
- F-measure: 0.8283
- Accuracy: 0.9171
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 7.5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 14
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precisions | Recall | F-measure | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:----------:|:------:|:---------:|:--------:|
| 0.6054 | 1.0 | 118 | 0.4021 | 0.8661 | 0.6558 | 0.6767 | 0.8698 |
| 0.316 | 2.0 | 236 | 0.4039 | 0.8167 | 0.6935 | 0.7317 | 0.8800 |
| 0.1896 | 3.0 | 354 | 0.3480 | 0.8183 | 0.7792 | 0.7780 | 0.9003 |
| 0.1318 | 4.0 | 472 | 0.3930 | 0.8529 | 0.7703 | 0.7983 | 0.8965 |
| 0.0846 | 5.0 | 590 | 0.4027 | 0.8348 | 0.8010 | 0.8141 | 0.9047 |
| 0.0652 | 6.0 | 708 | 0.4824 | 0.8298 | 0.7555 | 0.7855 | 0.9002 |
| 0.0398 | 7.0 | 826 | 0.5446 | 0.8697 | 0.7766 | 0.8110 | 0.9017 |
| 0.0335 | 8.0 | 944 | 0.4761 | 0.8402 | 0.8013 | 0.8192 | 0.9054 |
| 0.0228 | 9.0 | 1062 | 0.5232 | 0.8547 | 0.7921 | 0.8156 | 0.9085 |
| 0.0181 | 10.0 | 1180 | 0.5477 | 0.8560 | 0.7968 | 0.8226 | 0.9133 |
| 0.0106 | 11.0 | 1298 | 0.5207 | 0.8370 | 0.8050 | 0.8199 | 0.9142 |
| 0.0075 | 12.0 | 1416 | 0.5381 | 0.8469 | 0.8025 | 0.8229 | 0.9156 |
| 0.0038 | 13.0 | 1534 | 0.5573 | 0.8538 | 0.8061 | 0.8269 | 0.9165 |
| 0.0047 | 14.0 | 1652 | 0.5515 | 0.8551 | 0.8069 | 0.8283 | 0.9171 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Helsinki-NLP/opus-mt-tc-big-zle-gmq
|
Helsinki-NLP
| 2023-10-10T11:42:54Z | 121 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"tc",
"big",
"zle",
"gmq",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-03-24T11:31:46Z |
---
language:
- da
- gmq
- nb
- false
- ru
- sv
- uk
- zle
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-zle-gmq
results:
- task:
name: Translation rus-dan
type: translation
args: rus-dan
dataset:
name: flores101-devtest
type: flores_101
args: rus dan devtest
metrics:
- name: BLEU
type: bleu
value: 28.0
- task:
name: Translation rus-nob
type: translation
args: rus-nob
dataset:
name: flores101-devtest
type: flores_101
args: rus nob devtest
metrics:
- name: BLEU
type: bleu
value: 20.6
- task:
name: Translation rus-swe
type: translation
args: rus-swe
dataset:
name: flores101-devtest
type: flores_101
args: rus swe devtest
metrics:
- name: BLEU
type: bleu
value: 26.4
- task:
name: Translation ukr-dan
type: translation
args: ukr-dan
dataset:
name: flores101-devtest
type: flores_101
args: ukr dan devtest
metrics:
- name: BLEU
type: bleu
value: 30.3
- task:
name: Translation ukr-nob
type: translation
args: ukr-nob
dataset:
name: flores101-devtest
type: flores_101
args: ukr nob devtest
metrics:
- name: BLEU
type: bleu
value: 21.1
- task:
name: Translation ukr-swe
type: translation
args: ukr-swe
dataset:
name: flores101-devtest
type: flores_101
args: ukr swe devtest
metrics:
- name: BLEU
type: bleu
value: 28.8
- task:
name: Translation rus-dan
type: translation
args: rus-dan
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: rus-dan
metrics:
- name: BLEU
type: bleu
value: 59.6
- task:
name: Translation rus-nob
type: translation
args: rus-nob
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: rus-nob
metrics:
- name: BLEU
type: bleu
value: 46.1
- task:
name: Translation rus-swe
type: translation
args: rus-swe
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: rus-swe
metrics:
- name: BLEU
type: bleu
value: 53.3
---
# opus-mt-tc-big-zle-gmq
Neural machine translation model for translating from East Slavic languages (zle) to North Germanic languages (gmq).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Model info
* Release: 2022-03-14
* source language(s): rus ukr
* target language(s): dan nob nor swe
* valid target language labels: >>dan<< >>nob<< >>nor<< >>swe<<
* model: transformer-big
* data: opusTCv20210807+pft ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
* tokenization: SentencePiece (spm32k,spm32k)
* original model: [opusTCv20210807+pft_transformer-big_2022-03-14.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/zle-gmq/opusTCv20210807+pft_transformer-big_2022-03-14.zip)
* more information released models: [OPUS-MT zle-gmq README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/zle-gmq/README.md)
* more information about the model: [MarianMT](https://huggingface.co/docs/transformers/model_doc/marian)
This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>dan<<`
## Usage
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
">>dan<< Заўтра ўжо чацвер.",
">>swe<< Том грав з Мері в кішки-мишки."
]
model_name = "pytorch-models/opus-mt-tc-big-zle-gmq"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# I morgen er det torsdag.
# Tom lekte med Mary i katt-möss.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-zle-gmq")
print(pipe(">>dan<< Заўтра ўжо чацвер."))
# expected output: I morgen er det torsdag.
```
## Benchmarks
* test set translations: [opusTCv20210807+pft_transformer-big_2022-03-14.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/zle-gmq/opusTCv20210807+pft_transformer-big_2022-03-14.test.txt)
* test set scores: [opusTCv20210807+pft_transformer-big_2022-03-14.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/zle-gmq/opusTCv20210807+pft_transformer-big_2022-03-14.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| rus-dan | tatoeba-test-v2021-08-07 | 0.74307 | 59.6 | 1713 | 11746 |
| rus-nob | tatoeba-test-v2021-08-07 | 0.66376 | 46.1 | 1277 | 11672 |
| rus-swe | tatoeba-test-v2021-08-07 | 0.69608 | 53.3 | 1282 | 8449 |
| bel-dan | flores101-devtest | 0.47621 | 13.9 | 1012 | 24638 |
| bel-nob | flores101-devtest | 0.44966 | 10.8 | 1012 | 23873 |
| bel-swe | flores101-devtest | 0.47274 | 13.2 | 1012 | 23121 |
| rus-dan | flores101-devtest | 0.55917 | 28.0 | 1012 | 24638 |
| rus-nob | flores101-devtest | 0.50724 | 20.6 | 1012 | 23873 |
| rus-swe | flores101-devtest | 0.55812 | 26.4 | 1012 | 23121 |
| ukr-dan | flores101-devtest | 0.57829 | 30.3 | 1012 | 24638 |
| ukr-nob | flores101-devtest | 0.52271 | 21.1 | 1012 | 23873 |
| ukr-swe | flores101-devtest | 0.57499 | 28.8 | 1012 | 23121 |
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 1bdabf7
* port time: Wed Mar 23 23:13:54 EET 2022
* port machine: LM0-400-22516.local
|
Helsinki-NLP/opus-mt-tc-big-zle-zls
|
Helsinki-NLP
| 2023-10-10T11:34:02Z | 121 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"tc",
"big",
"zle",
"zls",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-03-24T12:10:45Z |
---
language:
- be
- bg
- hr
- ru
- sh
- sl
- sr_Cyrl
- sr_Latn
- uk
- zle
- zls
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-zle-zls
results:
- task:
name: Translation rus-bul
type: translation
args: rus-bul
dataset:
name: flores101-devtest
type: flores_101
args: rus bul devtest
metrics:
- name: BLEU
type: bleu
value: 28.9
- task:
name: Translation rus-hrv
type: translation
args: rus-hrv
dataset:
name: flores101-devtest
type: flores_101
args: rus hrv devtest
metrics:
- name: BLEU
type: bleu
value: 23.2
- task:
name: Translation rus-mkd
type: translation
args: rus-mkd
dataset:
name: flores101-devtest
type: flores_101
args: rus mkd devtest
metrics:
- name: BLEU
type: bleu
value: 24.3
- task:
name: Translation rus-slv
type: translation
args: rus-slv
dataset:
name: flores101-devtest
type: flores_101
args: rus slv devtest
metrics:
- name: BLEU
type: bleu
value: 23.1
- task:
name: Translation rus-srp_Cyrl
type: translation
args: rus-srp_Cyrl
dataset:
name: flores101-devtest
type: flores_101
args: rus srp_Cyrl devtest
metrics:
- name: BLEU
type: bleu
value: 24.1
- task:
name: Translation ukr-bul
type: translation
args: ukr-bul
dataset:
name: flores101-devtest
type: flores_101
args: ukr bul devtest
metrics:
- name: BLEU
type: bleu
value: 30.8
- task:
name: Translation ukr-hrv
type: translation
args: ukr-hrv
dataset:
name: flores101-devtest
type: flores_101
args: ukr hrv devtest
metrics:
- name: BLEU
type: bleu
value: 24.6
- task:
name: Translation ukr-mkd
type: translation
args: ukr-mkd
dataset:
name: flores101-devtest
type: flores_101
args: ukr mkd devtest
metrics:
- name: BLEU
type: bleu
value: 26.2
- task:
name: Translation ukr-slv
type: translation
args: ukr-slv
dataset:
name: flores101-devtest
type: flores_101
args: ukr slv devtest
metrics:
- name: BLEU
type: bleu
value: 24.2
- task:
name: Translation ukr-srp_Cyrl
type: translation
args: ukr-srp_Cyrl
dataset:
name: flores101-devtest
type: flores_101
args: ukr srp_Cyrl devtest
metrics:
- name: BLEU
type: bleu
value: 26.2
- task:
name: Translation rus-bul
type: translation
args: rus-bul
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: rus-bul
metrics:
- name: BLEU
type: bleu
value: 53.7
- task:
name: Translation rus-hbs
type: translation
args: rus-hbs
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: rus-hbs
metrics:
- name: BLEU
type: bleu
value: 49.4
- task:
name: Translation rus-slv
type: translation
args: rus-slv
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: rus-slv
metrics:
- name: BLEU
type: bleu
value: 21.5
- task:
name: Translation rus-srp_Cyrl
type: translation
args: rus-srp_Cyrl
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: rus-srp_Cyrl
metrics:
- name: BLEU
type: bleu
value: 46.1
- task:
name: Translation rus-srp_Latn
type: translation
args: rus-srp_Latn
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: rus-srp_Latn
metrics:
- name: BLEU
type: bleu
value: 51.7
- task:
name: Translation ukr-bul
type: translation
args: ukr-bul
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: ukr-bul
metrics:
- name: BLEU
type: bleu
value: 61.3
- task:
name: Translation ukr-hbs
type: translation
args: ukr-hbs
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: ukr-hbs
metrics:
- name: BLEU
type: bleu
value: 52.1
- task:
name: Translation ukr-hrv
type: translation
args: ukr-hrv
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: ukr-hrv
metrics:
- name: BLEU
type: bleu
value: 50.1
- task:
name: Translation ukr-srp_Cyrl
type: translation
args: ukr-srp_Cyrl
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: ukr-srp_Cyrl
metrics:
- name: BLEU
type: bleu
value: 54.7
- task:
name: Translation ukr-srp_Latn
type: translation
args: ukr-srp_Latn
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: ukr-srp_Latn
metrics:
- name: BLEU
type: bleu
value: 53.4
---
# opus-mt-tc-big-zle-zls
Neural machine translation model for translating from East Slavic languages (zle) to South Slavic languages (zls).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Model info
* Release: 2022-03-23
* source language(s): bel rus ukr
* target language(s): bul hbs hrv slv srp_Cyrl srp_Latn
* valid target language labels: >>bul<< >>hbs<< >>hrv<< >>slv<< >>srp_Cyrl<< >>srp_Latn<<
* model: transformer-big
* data: opusTCv20210807+bt ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
* tokenization: SentencePiece (spm32k,spm32k)
* original model: [opusTCv20210807+bt_transformer-big_2022-03-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/zle-zls/opusTCv20210807+bt_transformer-big_2022-03-23.zip)
* more information released models: [OPUS-MT zle-zls README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/zle-zls/README.md)
* more information about the model: [MarianMT](https://huggingface.co/docs/transformers/model_doc/marian)
This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>bul<<`
## Usage
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
">>bul<< Новы каранавірус вельмі заразны.",
">>srp_Latn<< Моє ім'я — Саллі."
]
model_name = "pytorch-models/opus-mt-tc-big-zle-zls"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# Короната е силно заразна.
# Zovem se Sali.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-zle-zls")
print(pipe(">>bul<< Новы каранавірус вельмі заразны."))
# expected output: Короната е силно заразна.
```
## Benchmarks
* test set translations: [opusTCv20210807+bt_transformer-big_2022-03-23.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/zle-zls/opusTCv20210807+bt_transformer-big_2022-03-23.test.txt)
* test set scores: [opusTCv20210807+bt_transformer-big_2022-03-23.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/zle-zls/opusTCv20210807+bt_transformer-big_2022-03-23.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| rus-bul | tatoeba-test-v2021-08-07 | 0.71515 | 53.7 | 1247 | 8272 |
| rus-hbs | tatoeba-test-v2021-08-07 | 0.69192 | 49.4 | 2500 | 14736 |
| rus-slv | tatoeba-test-v2021-08-07 | 0.38051 | 21.5 | 657 | 3969 |
| rus-srp_Cyrl | tatoeba-test-v2021-08-07 | 0.66622 | 46.1 | 881 | 5407 |
| rus-srp_Latn | tatoeba-test-v2021-08-07 | 0.70990 | 51.7 | 1483 | 8552 |
| ukr-bul | tatoeba-test-v2021-08-07 | 0.77283 | 61.3 | 1020 | 5181 |
| ukr-hbs | tatoeba-test-v2021-08-07 | 0.69401 | 52.1 | 942 | 5130 |
| ukr-hrv | tatoeba-test-v2021-08-07 | 0.67202 | 50.1 | 389 | 2302 |
| ukr-srp_Cyrl | tatoeba-test-v2021-08-07 | 0.70064 | 54.7 | 205 | 1112 |
| ukr-srp_Latn | tatoeba-test-v2021-08-07 | 0.72405 | 53.4 | 348 | 1716 |
| bel-bul | flores101-devtest | 0.49528 | 16.1 | 1012 | 24700 |
| bel-hrv | flores101-devtest | 0.46308 | 12.4 | 1012 | 22423 |
| bel-mkd | flores101-devtest | 0.48608 | 13.5 | 1012 | 24314 |
| bel-slv | flores101-devtest | 0.44452 | 12.2 | 1012 | 23425 |
| bel-srp_Cyrl | flores101-devtest | 0.44424 | 12.6 | 1012 | 23456 |
| rus-bul | flores101-devtest | 0.58653 | 28.9 | 1012 | 24700 |
| rus-hrv | flores101-devtest | 0.53494 | 23.2 | 1012 | 22423 |
| rus-mkd | flores101-devtest | 0.55184 | 24.3 | 1012 | 24314 |
| rus-slv | flores101-devtest | 0.52201 | 23.1 | 1012 | 23425 |
| rus-srp_Cyrl | flores101-devtest | 0.53038 | 24.1 | 1012 | 23456 |
| ukr-bul | flores101-devtest | 0.59625 | 30.8 | 1012 | 24700 |
| ukr-hrv | flores101-devtest | 0.54530 | 24.6 | 1012 | 22423 |
| ukr-mkd | flores101-devtest | 0.56822 | 26.2 | 1012 | 24314 |
| ukr-slv | flores101-devtest | 0.53092 | 24.2 | 1012 | 23425 |
| ukr-srp_Cyrl | flores101-devtest | 0.54618 | 26.2 | 1012 | 23456 |
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 1bdabf7
* port time: Thu Mar 24 00:46:26 EET 2022
* port machine: LM0-400-22516.local
|
Helsinki-NLP/opus-mt-tc-big-itc-eu
|
Helsinki-NLP
| 2023-10-10T11:33:00Z | 113 | 2 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"es",
"eu",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-08-12T16:30:35Z |
---
language:
- es
- eu
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-itc-eu
results:
- task:
name: Translation spa-eus
type: translation
args: spa-eus
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: spa-eus
metrics:
- name: BLEU
type: bleu
value: 32.4
- name: chr-F
type: chrf
value: 0.60699
---
# opus-mt-tc-big-itc-eu
## Table of Contents
- [Model Details](#model-details)
- [Uses](#uses)
- [Risks, Limitations and Biases](#risks-limitations-and-biases)
- [How to Get Started With the Model](#how-to-get-started-with-the-model)
- [Training](#training)
- [Evaluation](#evaluation)
- [Citation Information](#citation-information)
- [Acknowledgements](#acknowledgements)
## Model Details
Neural machine translation model for translating from Italic languages (itc) to Basque (eu).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
**Model Description:**
- **Developed by:** Language Technology Research Group at the University of Helsinki
- **Model Type:** Translation (transformer-big)
- **Release**: 2022-07-23
- **License:** CC-BY-4.0
- **Language(s):**
- Source Language(s): fra ita spa
- Target Language(s): eus
- Language Pair(s): spa-eus
- Valid Target Language Labels:
- **Original Model**: [opusTCv20210807_transformer-big_2022-07-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/itc-eus/opusTCv20210807_transformer-big_2022-07-23.zip)
- **Resources for more information:**
- [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
- More information about released models for this language pair: [OPUS-MT itc-eus README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/itc-eus/README.md)
- [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian)
- [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/
## Uses
This model can be used for translation and text-to-text generation.
## Risks, Limitations and Biases
**CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain content that is disturbing, offensive, and can propagate historical and current stereotypes.**
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
## How to Get Started With the Model
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
"Il est riche.",
"¿Correcto?"
]
model_name = "pytorch-models/opus-mt-tc-big-itc-eu"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# Aberatsa da.
# Zuzena?
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-itc-eu")
print(pipe("Il est riche."))
# expected output: Aberatsa da.
```
## Training
- **Data**: opusTCv20210807 ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
- **Pre-processing**: SentencePiece (spm32k,spm32k)
- **Model Type:** transformer-big
- **Original MarianNMT Model**: [opusTCv20210807_transformer-big_2022-07-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/itc-eus/opusTCv20210807_transformer-big_2022-07-23.zip)
- **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
## Evaluation
* test set translations: [opusTCv20210807_transformer-big_2022-07-23.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/itc-eus/opusTCv20210807_transformer-big_2022-07-23.test.txt)
* test set scores: [opusTCv20210807_transformer-big_2022-07-23.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/itc-eus/opusTCv20210807_transformer-big_2022-07-23.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| spa-eus | tatoeba-test-v2021-08-07 | 0.60699 | 32.4 | 1850 | 10945 |
## Citation Information
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 8b9f0b0
* port time: Sat Aug 13 00:08:07 EEST 2022
* port machine: LM0-400-22516.local
|
Helsinki-NLP/opus-mt-tc-big-gmq-zlw
|
Helsinki-NLP
| 2023-10-10T11:28:52Z | 113 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"cs",
"da",
"nb",
"pl",
"sv",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-08-12T12:46:57Z |
---
language:
- cs
- da
- nb
- pl
- sv
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-gmq-zlw
results:
- task:
name: Translation dan-ces
type: translation
args: dan-ces
dataset:
name: flores101-devtest
type: flores_101
args: dan ces devtest
metrics:
- name: BLEU
type: bleu
value: 26.7
- name: chr-F
type: chrf
value: 0.54065
- task:
name: Translation dan-pol
type: translation
args: dan-pol
dataset:
name: flores101-devtest
type: flores_101
args: dan pol devtest
metrics:
- name: BLEU
type: bleu
value: 18.8
- name: chr-F
type: chrf
value: 0.48389
- task:
name: Translation isl-ces
type: translation
args: isl-ces
dataset:
name: flores101-devtest
type: flores_101
args: isl ces devtest
metrics:
- name: BLEU
type: bleu
value: 17.7
- name: chr-F
type: chrf
value: 0.43582
- task:
name: Translation isl-pol
type: translation
args: isl-pol
dataset:
name: flores101-devtest
type: flores_101
args: isl pol devtest
metrics:
- name: BLEU
type: bleu
value: 13.9
- name: chr-F
type: chrf
value: 0.41929
- task:
name: Translation nob-ces
type: translation
args: nob-ces
dataset:
name: flores101-devtest
type: flores_101
args: nob ces devtest
metrics:
- name: BLEU
type: bleu
value: 22.3
- name: chr-F
type: chrf
value: 0.50336
- task:
name: Translation nob-pol
type: translation
args: nob-pol
dataset:
name: flores101-devtest
type: flores_101
args: nob pol devtest
metrics:
- name: BLEU
type: bleu
value: 16.3
- name: chr-F
type: chrf
value: 0.46130
- task:
name: Translation swe-ces
type: translation
args: swe-ces
dataset:
name: flores101-devtest
type: flores_101
args: swe ces devtest
metrics:
- name: BLEU
type: bleu
value: 25.7
- name: chr-F
type: chrf
value: 0.53188
- task:
name: Translation swe-pol
type: translation
args: swe-pol
dataset:
name: flores101-devtest
type: flores_101
args: swe pol devtest
metrics:
- name: BLEU
type: bleu
value: 18.6
- name: chr-F
type: chrf
value: 0.48163
- task:
name: Translation swe-pol
type: translation
args: swe-pol
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: swe-pol
metrics:
- name: BLEU
type: bleu
value: 46.2
- name: chr-F
type: chrf
value: 0.66326
---
# opus-mt-tc-big-gmq-zlw
## Table of Contents
- [Model Details](#model-details)
- [Uses](#uses)
- [Risks, Limitations and Biases](#risks-limitations-and-biases)
- [How to Get Started With the Model](#how-to-get-started-with-the-model)
- [Training](#training)
- [Evaluation](#evaluation)
- [Citation Information](#citation-information)
- [Acknowledgements](#acknowledgements)
## Model Details
Neural machine translation model for translating from North Germanic languages (gmq) to West Slavic languages (zlw).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
**Model Description:**
- **Developed by:** Language Technology Research Group at the University of Helsinki
- **Model Type:** Translation (transformer-big)
- **Release**: 2022-08-03
- **License:** CC-BY-4.0
- **Language(s):**
- Source Language(s): dan nob nor swe
- Target Language(s): ces pol
- Language Pair(s): dan-ces nob-ces swe-ces swe-pol
- Valid Target Language Labels: >>ces<< >>csb<< >>czk<< >>dsb<< >>hsb<< >>pol<< >>pox<< >>slk<< >>szl<<
- **Original Model**: [opusTCv20210807_transformer-big_2022-08-03.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-zlw/opusTCv20210807_transformer-big_2022-08-03.zip)
- **Resources for more information:**
- [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
- More information about released models for this language pair: [OPUS-MT gmq-zlw README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/gmq-zlw/README.md)
- [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian)
- [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/
This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>ces<<`
## Uses
This model can be used for translation and text-to-text generation.
## Risks, Limitations and Biases
**CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain content that is disturbing, offensive, and can propagate historical and current stereotypes.**
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
## How to Get Started With the Model
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
">>ces<< Normalt er jeg hjemme hele weekenden.",
">>pol<< Lev ditt liv."
]
model_name = "pytorch-models/opus-mt-tc-big-gmq-zlw"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# Většinou jsem doma celý víkend.
# Żyj swoim życiem.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-gmq-zlw")
print(pipe(">>ces<< Normalt er jeg hjemme hele weekenden."))
# expected output: Většinou jsem doma celý víkend.
```
## Training
- **Data**: opusTCv20210807 ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
- **Pre-processing**: SentencePiece (spm32k,spm32k)
- **Model Type:** transformer-big
- **Original MarianNMT Model**: [opusTCv20210807_transformer-big_2022-08-03.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-zlw/opusTCv20210807_transformer-big_2022-08-03.zip)
- **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
## Evaluation
* test set translations: [opusTCv20210807_transformer-big_2022-08-03.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-zlw/opusTCv20210807_transformer-big_2022-08-03.test.txt)
* test set scores: [opusTCv20210807_transformer-big_2022-08-03.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-zlw/opusTCv20210807_transformer-big_2022-08-03.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| swe-pol | tatoeba-test-v2021-08-07 | 0.66326 | 46.2 | 1392 | 8157 |
| dan-ces | flores101-devtest | 0.54065 | 26.7 | 1012 | 22101 |
| dan-pol | flores101-devtest | 0.48389 | 18.8 | 1012 | 22520 |
| isl-ces | flores101-devtest | 0.43582 | 17.7 | 1012 | 22101 |
| isl-pol | flores101-devtest | 0.41929 | 13.9 | 1012 | 22520 |
| nob-ces | flores101-devtest | 0.50336 | 22.3 | 1012 | 22101 |
| nob-pol | flores101-devtest | 0.46130 | 16.3 | 1012 | 22520 |
| swe-ces | flores101-devtest | 0.53188 | 25.7 | 1012 | 22101 |
| swe-pol | flores101-devtest | 0.48163 | 18.6 | 1012 | 22520 |
## Citation Information
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 8b9f0b0
* port time: Sat Aug 13 00:02:29 EEST 2022
* port machine: LM0-400-22516.local
|
Helsinki-NLP/opus-mt-tc-big-gmq-ar
|
Helsinki-NLP
| 2023-10-10T11:26:33Z | 117 | 1 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"ar",
"da",
"sv",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-08-12T14:35:33Z |
---
language:
- ar
- da
- sv
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-gmq-ar
results:
- task:
name: Translation dan-ara
type: translation
args: dan-ara
dataset:
name: flores101-devtest
type: flores_101
args: dan ara devtest
metrics:
- name: BLEU
type: bleu
value: 19.9
- name: chr-F
type: chrf
value: 0.52841
- task:
name: Translation nob-ara
type: translation
args: nob-ara
dataset:
name: flores101-devtest
type: flores_101
args: nob ara devtest
metrics:
- name: BLEU
type: bleu
value: 16.8
- name: chr-F
type: chrf
value: 0.49670
- task:
name: Translation swe-ara
type: translation
args: swe-ara
dataset:
name: flores101-devtest
type: flores_101
args: swe ara devtest
metrics:
- name: BLEU
type: bleu
value: 19.3
- name: chr-F
type: chrf
value: 0.51882
---
# opus-mt-tc-big-gmq-ar
## Table of Contents
- [Model Details](#model-details)
- [Uses](#uses)
- [Risks, Limitations and Biases](#risks-limitations-and-biases)
- [How to Get Started With the Model](#how-to-get-started-with-the-model)
- [Training](#training)
- [Evaluation](#evaluation)
- [Citation Information](#citation-information)
- [Acknowledgements](#acknowledgements)
## Model Details
Neural machine translation model for translating from North Germanic languages (gmq) to Arabic (ar).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
**Model Description:**
- **Developed by:** Language Technology Research Group at the University of Helsinki
- **Model Type:** Translation (transformer-big)
- **Release**: 2022-07-27
- **License:** CC-BY-4.0
- **Language(s):**
- Source Language(s): dan swe
- Target Language(s): ara
- Language Pair(s): dan-ara swe-ara
- Valid Target Language Labels: >>apc<< >>ara<< >>arq<< >>arz<<
- **Original Model**: [opusTCv20210807_transformer-big_2022-07-27.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-ara/opusTCv20210807_transformer-big_2022-07-27.zip)
- **Resources for more information:**
- [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
- More information about released models for this language pair: [OPUS-MT gmq-ara README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/gmq-ara/README.md)
- [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian)
- [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/
This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>><<`
## Uses
This model can be used for translation and text-to-text generation.
## Risks, Limitations and Biases
**CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain content that is disturbing, offensive, and can propagate historical and current stereotypes.**
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
## How to Get Started With the Model
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
">>ara<< Jeg elsker semitiske sprog.",
">>ara<< Vad handlar boken om?"
]
model_name = "pytorch-models/opus-mt-tc-big-gmq-ar"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# أحبّ اللغات الساميّة.
# عن ماذا يتحدث الكتاب؟
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-gmq-ar")
print(pipe(">>ara<< Jeg elsker semitiske sprog."))
# expected output: أحبّ اللغات الساميّة.
```
## Training
- **Data**: opusTCv20210807 ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
- **Pre-processing**: SentencePiece (spm32k,spm32k)
- **Model Type:** transformer-big
- **Original MarianNMT Model**: [opusTCv20210807_transformer-big_2022-07-27.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-ara/opusTCv20210807_transformer-big_2022-07-27.zip)
- **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
## Evaluation
* test set translations: [opusTCv20210807_transformer-big_2022-07-27.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-ara/opusTCv20210807_transformer-big_2022-07-27.test.txt)
* test set scores: [opusTCv20210807_transformer-big_2022-07-27.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-ara/opusTCv20210807_transformer-big_2022-07-27.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| dan-ara | flores101-devtest | 0.52841 | 19.9 | 1012 | 21357 |
| nob-ara | flores101-devtest | 0.49670 | 16.8 | 1012 | 21357 |
| swe-ara | flores101-devtest | 0.51882 | 19.3 | 1012 | 21357 |
## Citation Information
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 8b9f0b0
* port time: Sat Aug 13 00:05:06 EEST 2022
* port machine: LM0-400-22516.local
|
Helsinki-NLP/opus-mt-tc-big-zls-zle
|
Helsinki-NLP
| 2023-10-10T11:25:27Z | 127 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"tc",
"big",
"zls",
"zle",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-03-24T12:47:28Z |
---
language:
- be
- bg
- hr
- ru
- sh
- sl
- sr_Cyrl
- sr_Latn
- uk
- zle
- zls
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-zls-zle
results:
- task:
name: Translation bul-rus
type: translation
args: bul-rus
dataset:
name: flores101-devtest
type: flores_101
args: bul rus devtest
metrics:
- name: BLEU
type: bleu
value: 24.6
- task:
name: Translation bul-ukr
type: translation
args: bul-ukr
dataset:
name: flores101-devtest
type: flores_101
args: bul ukr devtest
metrics:
- name: BLEU
type: bleu
value: 22.9
- task:
name: Translation hrv-rus
type: translation
args: hrv-rus
dataset:
name: flores101-devtest
type: flores_101
args: hrv rus devtest
metrics:
- name: BLEU
type: bleu
value: 23.5
- task:
name: Translation hrv-ukr
type: translation
args: hrv-ukr
dataset:
name: flores101-devtest
type: flores_101
args: hrv ukr devtest
metrics:
- name: BLEU
type: bleu
value: 21.9
- task:
name: Translation mkd-rus
type: translation
args: mkd-rus
dataset:
name: flores101-devtest
type: flores_101
args: mkd rus devtest
metrics:
- name: BLEU
type: bleu
value: 24.3
- task:
name: Translation mkd-ukr
type: translation
args: mkd-ukr
dataset:
name: flores101-devtest
type: flores_101
args: mkd ukr devtest
metrics:
- name: BLEU
type: bleu
value: 22.5
- task:
name: Translation slv-rus
type: translation
args: slv-rus
dataset:
name: flores101-devtest
type: flores_101
args: slv rus devtest
metrics:
- name: BLEU
type: bleu
value: 22.0
- task:
name: Translation slv-ukr
type: translation
args: slv-ukr
dataset:
name: flores101-devtest
type: flores_101
args: slv ukr devtest
metrics:
- name: BLEU
type: bleu
value: 20.2
- task:
name: Translation srp_Cyrl-rus
type: translation
args: srp_Cyrl-rus
dataset:
name: flores101-devtest
type: flores_101
args: srp_Cyrl rus devtest
metrics:
- name: BLEU
type: bleu
value: 25.7
- task:
name: Translation srp_Cyrl-ukr
type: translation
args: srp_Cyrl-ukr
dataset:
name: flores101-devtest
type: flores_101
args: srp_Cyrl ukr devtest
metrics:
- name: BLEU
type: bleu
value: 24.4
- task:
name: Translation bul-rus
type: translation
args: bul-rus
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: bul-rus
metrics:
- name: BLEU
type: bleu
value: 52.6
- task:
name: Translation bul-ukr
type: translation
args: bul-ukr
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: bul-ukr
metrics:
- name: BLEU
type: bleu
value: 53.3
- task:
name: Translation hbs-rus
type: translation
args: hbs-rus
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: hbs-rus
metrics:
- name: BLEU
type: bleu
value: 58.5
- task:
name: Translation hbs-ukr
type: translation
args: hbs-ukr
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: hbs-ukr
metrics:
- name: BLEU
type: bleu
value: 52.3
- task:
name: Translation hrv-ukr
type: translation
args: hrv-ukr
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: hrv-ukr
metrics:
- name: BLEU
type: bleu
value: 50.0
- task:
name: Translation slv-rus
type: translation
args: slv-rus
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: slv-rus
metrics:
- name: BLEU
type: bleu
value: 27.3
- task:
name: Translation srp_Cyrl-rus
type: translation
args: srp_Cyrl-rus
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: srp_Cyrl-rus
metrics:
- name: BLEU
type: bleu
value: 56.2
- task:
name: Translation srp_Cyrl-ukr
type: translation
args: srp_Cyrl-ukr
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: srp_Cyrl-ukr
metrics:
- name: BLEU
type: bleu
value: 51.8
- task:
name: Translation srp_Latn-rus
type: translation
args: srp_Latn-rus
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: srp_Latn-rus
metrics:
- name: BLEU
type: bleu
value: 60.1
- task:
name: Translation srp_Latn-ukr
type: translation
args: srp_Latn-ukr
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: srp_Latn-ukr
metrics:
- name: BLEU
type: bleu
value: 55.8
---
# opus-mt-tc-big-zls-zle
Neural machine translation model for translating from South Slavic languages (zls) to East Slavic languages (zle).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Model info
* Release: 2022-03-23
* source language(s): bul hbs hrv slv srp_Cyrl srp_Latn
* target language(s): bel rus ukr
* valid target language labels: >>bel<< >>rus<< >>ukr<<
* model: transformer-big
* data: opusTCv20210807+bt ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
* tokenization: SentencePiece (spm32k,spm32k)
* original model: [opusTCv20210807+bt_transformer-big_2022-03-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/zls-zle/opusTCv20210807+bt_transformer-big_2022-03-23.zip)
* more information released models: [OPUS-MT zls-zle README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/zls-zle/README.md)
* more information about the model: [MarianMT](https://huggingface.co/docs/transformers/model_doc/marian)
This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>bel<<`
## Usage
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
">>rus<< Gdje je brigadir?",
">>ukr<< Zovem se Seli."
]
model_name = "pytorch-models/opus-mt-tc-big-zls-zle"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# Где бригадир?
# Мене звати Саллі.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-zls-zle")
print(pipe(">>rus<< Gdje je brigadir?"))
# expected output: Где бригадир?
```
## Benchmarks
* test set translations: [opusTCv20210807+bt_transformer-big_2022-03-23.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/zls-zle/opusTCv20210807+bt_transformer-big_2022-03-23.test.txt)
* test set scores: [opusTCv20210807+bt_transformer-big_2022-03-23.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/zls-zle/opusTCv20210807+bt_transformer-big_2022-03-23.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| bul-rus | tatoeba-test-v2021-08-07 | 0.71467 | 52.6 | 1247 | 7870 |
| bul-ukr | tatoeba-test-v2021-08-07 | 0.71757 | 53.3 | 1020 | 4932 |
| hbs-rus | tatoeba-test-v2021-08-07 | 0.74593 | 58.5 | 2500 | 14213 |
| hbs-ukr | tatoeba-test-v2021-08-07 | 0.70244 | 52.3 | 942 | 4961 |
| hrv-ukr | tatoeba-test-v2021-08-07 | 0.68931 | 50.0 | 389 | 2232 |
| slv-rus | tatoeba-test-v2021-08-07 | 0.42255 | 27.3 | 657 | 4056 |
| srp_Cyrl-rus | tatoeba-test-v2021-08-07 | 0.74112 | 56.2 | 881 | 5117 |
| srp_Cyrl-ukr | tatoeba-test-v2021-08-07 | 0.68915 | 51.8 | 205 | 1061 |
| srp_Latn-rus | tatoeba-test-v2021-08-07 | 0.75340 | 60.1 | 1483 | 8311 |
| srp_Latn-ukr | tatoeba-test-v2021-08-07 | 0.73106 | 55.8 | 348 | 1668 |
| bul-rus | flores101-devtest | 0.54226 | 24.6 | 1012 | 23295 |
| bul-ukr | flores101-devtest | 0.53382 | 22.9 | 1012 | 22810 |
| hrv-rus | flores101-devtest | 0.51726 | 23.5 | 1012 | 23295 |
| hrv-ukr | flores101-devtest | 0.51011 | 21.9 | 1012 | 22810 |
| mkd-bel | flores101-devtest | 0.40885 | 10.7 | 1012 | 24829 |
| mkd-rus | flores101-devtest | 0.52509 | 24.3 | 1012 | 23295 |
| mkd-ukr | flores101-devtest | 0.52021 | 22.5 | 1012 | 22810 |
| slv-rus | flores101-devtest | 0.50349 | 22.0 | 1012 | 23295 |
| slv-ukr | flores101-devtest | 0.49156 | 20.2 | 1012 | 22810 |
| srp_Cyrl-rus | flores101-devtest | 0.53656 | 25.7 | 1012 | 23295 |
| srp_Cyrl-ukr | flores101-devtest | 0.53623 | 24.4 | 1012 | 22810 |
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 1bdabf7
* port time: Thu Mar 24 04:08:51 EET 2022
* port machine: LM0-400-22516.local
|
Helsinki-NLP/opus-mt-tc-big-zle-es
|
Helsinki-NLP
| 2023-10-10T11:24:23Z | 120 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"be",
"es",
"ru",
"rue",
"uk",
"zle",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-03-24T12:05:31Z |
---
language:
- be
- es
- ru
- rue
- uk
- zle
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-zle-es
results:
- task:
name: Translation rus-spa
type: translation
args: rus-spa
dataset:
name: flores101-devtest
type: flores_101
args: rus spa devtest
metrics:
- name: BLEU
type: bleu
value: 22.5
- task:
name: Translation ukr-spa
type: translation
args: ukr-spa
dataset:
name: flores101-devtest
type: flores_101
args: ukr spa devtest
metrics:
- name: BLEU
type: bleu
value: 22.7
- task:
name: Translation bel-spa
type: translation
args: bel-spa
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: bel-spa
metrics:
- name: BLEU
type: bleu
value: 46.3
- task:
name: Translation rus-spa
type: translation
args: rus-spa
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: rus-spa
metrics:
- name: BLEU
type: bleu
value: 52.3
- task:
name: Translation ukr-spa
type: translation
args: ukr-spa
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: ukr-spa
metrics:
- name: BLEU
type: bleu
value: 51.6
- task:
name: Translation rus-spa
type: translation
args: rus-spa
dataset:
name: newstest2012
type: wmt-2012-news
args: rus-spa
metrics:
- name: BLEU
type: bleu
value: 29.0
- task:
name: Translation rus-spa
type: translation
args: rus-spa
dataset:
name: newstest2013
type: wmt-2013-news
args: rus-spa
metrics:
- name: BLEU
type: bleu
value: 31.7
---
# opus-mt-tc-big-zle-es
Neural machine translation model for translating from East Slavic languages (zle) to Spanish (es).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Model info
* Release: 2022-03-23
* source language(s): bel rue rus ukr
* target language(s): spa
* model: transformer-big
* data: opusTCv20210807 ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
* tokenization: SentencePiece (spm32k,spm32k)
* original model: [opusTCv20210807_transformer-big_2022-03-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/zle-spa/opusTCv20210807_transformer-big_2022-03-23.zip)
* more information released models: [OPUS-MT zle-spa README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/zle-spa/README.md)
## Usage
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
"Том був п'яничкою.",
"Он достаточно взрослый, чтобы путешествовать одному."
]
model_name = "pytorch-models/opus-mt-tc-big-zle-es"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# Tom era un borracho.
# Es lo suficientemente mayor como para viajar solo.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-zle-es")
print(pipe("Том був п'яничкою."))
# expected output: Tom era un borracho.
```
## Benchmarks
* test set translations: [opusTCv20210807_transformer-big_2022-03-23.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/zle-spa/opusTCv20210807_transformer-big_2022-03-23.test.txt)
* test set scores: [opusTCv20210807_transformer-big_2022-03-23.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/zle-spa/opusTCv20210807_transformer-big_2022-03-23.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| bel-spa | tatoeba-test-v2021-08-07 | 0.65523 | 46.3 | 205 | 1412 |
| rus-spa | tatoeba-test-v2021-08-07 | 0.69933 | 52.3 | 10506 | 75246 |
| ukr-spa | tatoeba-test-v2021-08-07 | 0.68862 | 51.6 | 10115 | 59284 |
| bel-spa | flores101-devtest | 0.44744 | 14.1 | 1012 | 29199 |
| rus-spa | flores101-devtest | 0.50880 | 22.5 | 1012 | 29199 |
| ukr-spa | flores101-devtest | 0.50943 | 22.7 | 1012 | 29199 |
| rus-spa | newstest2012 | 0.55185 | 29.0 | 3003 | 79006 |
| rus-spa | newstest2013 | 0.56826 | 31.7 | 3000 | 70528 |
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 1bdabf7
* port time: Thu Mar 24 00:12:49 EET 2022
* port machine: LM0-400-22516.local
|
Azma-AI/bart-conversation-summarizer
|
Azma-AI
| 2023-10-10T11:24:01Z | 427 | 6 |
transformers
|
[
"transformers",
"pytorch",
"bart",
"text2text-generation",
"summarization",
"dataset:samsum",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
summarization
| 2023-10-10T11:21:55Z |
---
datasets:
- samsum
pipeline_tag: summarization
widget:
- text: >
Laurie: So, what are your plans for this weekend?
Christie: I don’t know. Do you want to get together or something?
Sarah: How about going to see a movie? Cinemax 26 on Carson Boulevard is showing Enchanted.
Laurie: That sounds like a good idea. Maybe we should go out to eat beforehand.
Sarah: It is fine with me. Where do you want to meet?
Christie: Let’s meet at Summer Pizza House. I have not gone there for a long time.
Laurie: Good idea again. I heard they just came up with a new pizza. It should be good because Summer Pizza House always has the best pizza in town.
Sarah: When should we meet?
Christie: Well, the movie is shown at 2:00PM, 4:00PM, 6:00PM and 8:00PM.
Laurie: Why don’t we go to the 2:00PM show? We can meet at Summer Pizza House at noon. That will give us plenty of time to enjoy our pizza.
Sarah: My cousin Karen is in town. Can I bring her along? I hate to leave her home alone.
Christie: Karen is in town? Yes, bring her along. Laurie, you remember Karen? We met her at Sara’s high school graduation party two years ago.
Laurie: I do not quite remember her. What does she look like?
Sarah: She has blond hair, she is kind of slender, and she is about your height.
Laurie: She wears eyeglasses, right?
Sarah: Yes, and she was playing the piano off and on during the party.
Laurie: I remember her now. Yes, do bring her along Sara. She is such a nice person, and funny too.
Sarah: She will be happy to meet both of you again.
Christie: What is she doing these days?
Sarah: She graduated last June, and she will start her teaching career next week when the new school term begins.
Laurie: What grade is she going to teach?
Sarah: She will teach kindergarten. She loves working with kids, and she always has such a good rapport with them
Christie: Kindergarten? She must be a very patient person. I always think kindergarten is the most difficult class to teach. Most of the kids have never been to school, and they have
e never been away from mommy for long.
Sarah: I think Karen will do fine. She knows how to handle young children
Laurie: I think the first few weeks will be tough. However, once the routine is set, it should not be too difficult to teach kindergarten.
Christie: You are right. The kids might even look forward to going to school since they have so many friends to play with.
Sarah: There are so many new things for them to do at school too. They do a lot of crafts in kindergarten. I am always amazed by the things kindergarten teachers do.
Laurie: Yes, I have seen my niece come home with so many neat stuff.
Christie: Maybe we can ask Karen to show us some of the things that we can do for this Halloween.
Laurie: Maybe we can stop by the craft store after the movie. What do you think, Sara?
Sarah: I will talk to her. I think she will like that. It will help her with school projects when Halloween comes.
Christie: Michael’s is a good store for crafts. It always carries a variety of things, and you can find almost anything there.
Laurie: There is a Michaels store not far away from Cinemax 26. I believe it is just around the corner, on Pioneer Avenue. We can even walk over there.
Sarah: So, we plan to meet for pizza at noon, go to the movies at two, and shop at Michael’s afterward. Right?
Laurie and Christie: Yes.
model-index:
- name: bart-large-cnn-samsum
results:
- task:
type: summarization
name: Conversation Summarization
dataset:
name: >-
SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive
Summarization
type: samsum
metrics:
- type: rogue-1
value: 54.8764
name: Validation ROGUE-1
- type: rogue-2
value: 29.6869,
name: Validation ROGUE-2
- type: rogue-l
value: 44.9874
name: Validation ROGUE-L
- type: loss
value: 1.47812
name: loss
---
|
Helsinki-NLP/opus-mt-tc-big-zle-fr
|
Helsinki-NLP
| 2023-10-10T11:23:15Z | 120 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"be",
"fr",
"ru",
"uk",
"zle",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-03-24T10:22:19Z |
---
language:
- be
- fr
- ru
- uk
- zle
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-zle-fr
results:
- task:
name: Translation bel-fra
type: translation
args: bel-fra
dataset:
name: tatoeba-test-v2020-07-28-v2021-08-07
type: tatoeba_mt
args: bel-fra
metrics:
- name: BLEU
type: bleu
value: 46.4
- task:
name: Translation multi-fra
type: translation
args: multi-fra
dataset:
name: tatoeba-test-v2020-07-28-v2021-08-07
type: tatoeba_mt
args: multi-fra
metrics:
- name: BLEU
type: bleu
value: 52.4
- task:
name: Translation rus-fra
type: translation
args: rus-fra
dataset:
name: tatoeba-test-v2020-07-28-v2021-08-07
type: tatoeba_mt
args: rus-fra
metrics:
- name: BLEU
type: bleu
value: 51.8
- task:
name: Translation ukr-fra
type: translation
args: ukr-fra
dataset:
name: tatoeba-test-v2020-07-28-v2021-08-07
type: tatoeba_mt
args: ukr-fra
metrics:
- name: BLEU
type: bleu
value: 50.7
- task:
name: Translation rus-fra
type: translation
args: rus-fra
dataset:
name: newstest2012
type: wmt-2012-news
args: rus-fra
metrics:
- name: BLEU
type: bleu
value: 25.3
- task:
name: Translation rus-fra
type: translation
args: rus-fra
dataset:
name: newstest2013
type: wmt-2013-news
args: rus-fra
metrics:
- name: BLEU
type: bleu
value: 29.7
---
# opus-mt-tc-big-zle-fr
Neural machine translation model for translating from East Slavic languages (zle) to French (fr).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Model info
* Release: 2022-03-23
* source language(s): bel rus ukr
* target language(s): fra
* model: transformer-big
* data: opusTCv20210807 ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
* tokenization: SentencePiece (spm32k,spm32k)
* original model: [opusTCv20210807_transformer-big_2022-03-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/zle-fra/opusTCv20210807_transformer-big_2022-03-23.zip)
* more information released models: [OPUS-MT zle-fra README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/zle-fra/README.md)
## Usage
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
"Подавай блюдо на тарелке.",
"Операція не може чекати."
]
model_name = "pytorch-models/opus-mt-tc-big-zle-fr"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# Servez le plat dans l'assiette.
# L'opération ne peut pas attendre.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-zle-fr")
print(pipe("Подавай блюдо на тарелке."))
# expected output: Servez le plat dans l'assiette.
```
## Benchmarks
* test set translations: [opusTCv20210807_transformer-big_2022-03-23.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/zle-fra/opusTCv20210807_transformer-big_2022-03-23.test.txt)
* test set scores: [opusTCv20210807_transformer-big_2022-03-23.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/zle-fra/opusTCv20210807_transformer-big_2022-03-23.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| bel-fra | tatoeba-test-v2020-07-28-v2021-08-07 | 0.65415 | 46.4 | 283 | 2005 |
| multi-fra | tatoeba-test-v2020-07-28-v2021-08-07 | 0.68422 | 52.4 | 10000 | 66671 |
| rus-fra | tatoeba-test-v2020-07-28-v2021-08-07 | 0.68699 | 51.8 | 11490 | 80573 |
| ukr-fra | tatoeba-test-v2020-07-28-v2021-08-07 | 0.67887 | 50.7 | 10035 | 63222 |
| rus-fra | newstest2012 | 0.53679 | 25.3 | 3003 | 78011 |
| rus-fra | newstest2013 | 0.56211 | 29.7 | 3000 | 70037 |
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 1bdabf7
* port time: Wed Mar 23 22:45:20 EET 2022
* port machine: LM0-400-22516.local
|
Helsinki-NLP/opus-mt-tc-big-he-itc
|
Helsinki-NLP
| 2023-10-10T11:22:11Z | 110 | 1 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"ca",
"es",
"fr",
"gl",
"he",
"it",
"pt",
"ro",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-08-12T15:35:46Z |
---
language:
- ca
- es
- fr
- gl
- he
- it
- pt
- ro
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-he-itc
results:
- task:
name: Translation heb-cat
type: translation
args: heb-cat
dataset:
name: flores101-devtest
type: flores_101
args: heb cat devtest
metrics:
- name: BLEU
type: bleu
value: 30.4
- name: chr-F
type: chrf
value: 0.56398
- task:
name: Translation heb-fra
type: translation
args: heb-fra
dataset:
name: flores101-devtest
type: flores_101
args: heb fra devtest
metrics:
- name: BLEU
type: bleu
value: 33.7
- name: chr-F
type: chrf
value: 0.59254
- task:
name: Translation heb-glg
type: translation
args: heb-glg
dataset:
name: flores101-devtest
type: flores_101
args: heb glg devtest
metrics:
- name: BLEU
type: bleu
value: 24.5
- name: chr-F
type: chrf
value: 0.51861
- task:
name: Translation heb-ita
type: translation
args: heb-ita
dataset:
name: flores101-devtest
type: flores_101
args: heb ita devtest
metrics:
- name: BLEU
type: bleu
value: 20.8
- name: chr-F
type: chrf
value: 0.50540
- task:
name: Translation heb-por
type: translation
args: heb-por
dataset:
name: flores101-devtest
type: flores_101
args: heb por devtest
metrics:
- name: BLEU
type: bleu
value: 33.1
- name: chr-F
type: chrf
value: 0.58818
- task:
name: Translation heb-ron
type: translation
args: heb-ron
dataset:
name: flores101-devtest
type: flores_101
args: heb ron devtest
metrics:
- name: BLEU
type: bleu
value: 22.3
- name: chr-F
type: chrf
value: 0.51480
- task:
name: Translation heb-spa
type: translation
args: heb-spa
dataset:
name: flores101-devtest
type: flores_101
args: heb spa devtest
metrics:
- name: BLEU
type: bleu
value: 21.6
- name: chr-F
type: chrf
value: 0.49786
- task:
name: Translation heb-fra
type: translation
args: heb-fra
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: heb-fra
metrics:
- name: BLEU
type: bleu
value: 47.5
- name: chr-F
type: chrf
value: 0.64713
- task:
name: Translation heb-ita
type: translation
args: heb-ita
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: heb-ita
metrics:
- name: BLEU
type: bleu
value: 42.1
- name: chr-F
type: chrf
value: 0.64836
- task:
name: Translation heb-por
type: translation
args: heb-por
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: heb-por
metrics:
- name: BLEU
type: bleu
value: 41.2
- name: chr-F
type: chrf
value: 0.61428
- task:
name: Translation heb-spa
type: translation
args: heb-spa
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: heb-spa
metrics:
- name: BLEU
type: bleu
value: 51.3
- name: chr-F
type: chrf
value: 0.69210
---
# opus-mt-tc-big-he-itc
## Table of Contents
- [Model Details](#model-details)
- [Uses](#uses)
- [Risks, Limitations and Biases](#risks-limitations-and-biases)
- [How to Get Started With the Model](#how-to-get-started-with-the-model)
- [Training](#training)
- [Evaluation](#evaluation)
- [Citation Information](#citation-information)
- [Acknowledgements](#acknowledgements)
## Model Details
Neural machine translation model for translating from Hebrew (he) to Italic languages (itc).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
**Model Description:**
- **Developed by:** Language Technology Research Group at the University of Helsinki
- **Model Type:** Translation (transformer-big)
- **Release**: 2022-07-25
- **License:** CC-BY-4.0
- **Language(s):**
- Source Language(s): heb
- Target Language(s): cat fra glg ita por ron spa
- Language Pair(s): heb-cat heb-fra heb-glg heb-ita heb-por heb-ron heb-spa
- Valid Target Language Labels: >>acf<< >>aoa<< >>arg<< >>ast<< >>cat<< >>cbk<< >>ccd<< >>cks<< >>cos<< >>cri<< >>crs<< >>dlm<< >>drc<< >>egl<< >>ext<< >>fab<< >>fax<< >>fra<< >>frc<< >>frm<< >>fro<< >>frp<< >>fur<< >>gcf<< >>gcf_Latn<< >>gcr<< >>glg<< >>hat<< >>idb<< >>ist<< >>ita<< >>itk<< >>kea<< >>kmv<< >>lad<< >>lad_Latn<< >>lat<< >>lat_Latn<< >>lij<< >>lld<< >>lmo<< >>lou<< >>mcm<< >>mfe<< >>mol<< >>mwl<< >>mxi<< >>mzs<< >>nap<< >>nrf<< >>oci<< >>osc<< >>osp<< >>osp_Latn<< >>pap<< >>pcd<< >>pln<< >>pms<< >>pob<< >>por<< >>pov<< >>pre<< >>pro<< >>qbb<< >>qhr<< >>rcf<< >>rgn<< >>roh<< >>ron<< >>ruo<< >>rup<< >>ruq<< >>scf<< >>scn<< >>sdc<< >>sdn<< >>spa<< >>spq<< >>spx<< >>src<< >>srd<< >>sro<< >>tmg<< >>tvy<< >>vec<< >>vkp<< >>wln<< >>xfa<< >>xum<<
- **Original Model**: [opusTCv20210807_transformer-big_2022-07-25.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/heb-itc/opusTCv20210807_transformer-big_2022-07-25.zip)
- **Resources for more information:**
- [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
- More information about released models for this language pair: [OPUS-MT heb-itc README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/heb-itc/README.md)
- [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian)
- [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/
This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>fra<<`
## Uses
This model can be used for translation and text-to-text generation.
## Risks, Limitations and Biases
**CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain content that is disturbing, offensive, and can propagate historical and current stereotypes.**
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
## How to Get Started With the Model
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
">>cat<< מרי פמיניסטית.",
">>spa<< תתרמו לטטואבה."
]
model_name = "pytorch-models/opus-mt-tc-big-he-itc"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# Mary és feminista.
# Donen a Tatoeba.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-he-itc")
print(pipe(">>cat<< מרי פמיניסטית."))
# expected output: Mary és feminista.
```
## Training
- **Data**: opusTCv20210807 ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
- **Pre-processing**: SentencePiece (spm32k,spm32k)
- **Model Type:** transformer-big
- **Original MarianNMT Model**: [opusTCv20210807_transformer-big_2022-07-25.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/heb-itc/opusTCv20210807_transformer-big_2022-07-25.zip)
- **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
## Evaluation
* test set translations: [opusTCv20210807_transformer-big_2022-07-25.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/heb-itc/opusTCv20210807_transformer-big_2022-07-25.test.txt)
* test set scores: [opusTCv20210807_transformer-big_2022-07-25.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/heb-itc/opusTCv20210807_transformer-big_2022-07-25.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| heb-fra | tatoeba-test-v2021-08-07 | 0.64713 | 47.5 | 3281 | 26123 |
| heb-ita | tatoeba-test-v2021-08-07 | 0.64836 | 42.1 | 1706 | 11464 |
| heb-por | tatoeba-test-v2021-08-07 | 0.61428 | 41.2 | 719 | 5335 |
| heb-spa | tatoeba-test-v2021-08-07 | 0.69210 | 51.3 | 1849 | 14213 |
| heb-cat | flores101-devtest | 0.56398 | 30.4 | 1012 | 27304 |
| heb-fra | flores101-devtest | 0.59254 | 33.7 | 1012 | 28343 |
| heb-glg | flores101-devtest | 0.51861 | 24.5 | 1012 | 26582 |
| heb-ita | flores101-devtest | 0.50540 | 20.8 | 1012 | 27306 |
| heb-por | flores101-devtest | 0.58818 | 33.1 | 1012 | 26519 |
| heb-ron | flores101-devtest | 0.51480 | 22.3 | 1012 | 26799 |
| heb-spa | flores101-devtest | 0.49786 | 21.6 | 1012 | 29199 |
## Citation Information
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 8b9f0b0
* port time: Sat Aug 13 00:06:50 EEST 2022
* port machine: LM0-400-22516.local
|
Helsinki-NLP/opus-mt-tc-big-he-gmq
|
Helsinki-NLP
| 2023-10-10T11:21:10Z | 107 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"da",
"he",
"nb",
"sv",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-08-12T16:14:29Z |
---
language:
- da
- he
- nb
- sv
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-he-gmq
results:
- task:
name: Translation heb-dan
type: translation
args: heb-dan
dataset:
name: flores101-devtest
type: flores_101
args: heb dan devtest
metrics:
- name: BLEU
type: bleu
value: 31.4
- name: chr-F
type: chrf
value: 0.58023
- task:
name: Translation heb-isl
type: translation
args: heb-isl
dataset:
name: flores101-devtest
type: flores_101
args: heb isl devtest
metrics:
- name: BLEU
type: bleu
value: 14.0
- name: chr-F
type: chrf
value: 0.41998
- task:
name: Translation heb-nob
type: translation
args: heb-nob
dataset:
name: flores101-devtest
type: flores_101
args: heb nob devtest
metrics:
- name: BLEU
type: bleu
value: 23.7
- name: chr-F
type: chrf
value: 0.53086
- task:
name: Translation heb-swe
type: translation
args: heb-swe
dataset:
name: flores101-devtest
type: flores_101
args: heb swe devtest
metrics:
- name: BLEU
type: bleu
value: 29.6
- name: chr-F
type: chrf
value: 0.56881
---
# opus-mt-tc-big-he-gmq
## Table of Contents
- [Model Details](#model-details)
- [Uses](#uses)
- [Risks, Limitations and Biases](#risks-limitations-and-biases)
- [How to Get Started With the Model](#how-to-get-started-with-the-model)
- [Training](#training)
- [Evaluation](#evaluation)
- [Citation Information](#citation-information)
- [Acknowledgements](#acknowledgements)
## Model Details
Neural machine translation model for translating from Hebrew (he) to North Germanic languages (gmq).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
**Model Description:**
- **Developed by:** Language Technology Research Group at the University of Helsinki
- **Model Type:** Translation (transformer-big)
- **Release**: 2022-07-23
- **License:** CC-BY-4.0
- **Language(s):**
- Source Language(s): heb
- Target Language(s): dan nob nor swe
- Language Pair(s): heb-dan heb-nob heb-swe
- Valid Target Language Labels: >>dan<< >>fao<< >>isl<< >>jut<< >>nno<< >>nob<< >>non<< >>nrn<< >>ovd<< >>qer<< >>rmg<< >>swe<<
- **Original Model**: [opusTCv20210807_transformer-big_2022-07-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/heb-gmq/opusTCv20210807_transformer-big_2022-07-23.zip)
- **Resources for more information:**
- [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
- More information about released models for this language pair: [OPUS-MT heb-gmq README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/heb-gmq/README.md)
- [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian)
- [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/
This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>dan<<`
## Uses
This model can be used for translation and text-to-text generation.
## Risks, Limitations and Biases
**CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain content that is disturbing, offensive, and can propagate historical and current stereotypes.**
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
## How to Get Started With the Model
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
">>dan<< כל שלושת הילדים של אליעזר לודוויג זמנהוף נרצחו בשואה.",
">>swe<< הסתבר שטום היה מרגל."
]
model_name = "pytorch-models/opus-mt-tc-big-he-gmq"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# Alle tre børn af Eliezer Ludwig Zamenhof blev dræbt i Holocaust.
# Det visade sig att Tom var en spion.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-he-gmq")
print(pipe(">>dan<< כל שלושת הילדים של אליעזר לודוויג זמנהוף נרצחו בשואה."))
# expected output: Alle tre børn af Eliezer Ludwig Zamenhof blev dræbt i Holocaust.
```
## Training
- **Data**: opusTCv20210807 ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
- **Pre-processing**: SentencePiece (spm32k,spm32k)
- **Model Type:** transformer-big
- **Original MarianNMT Model**: [opusTCv20210807_transformer-big_2022-07-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/heb-gmq/opusTCv20210807_transformer-big_2022-07-23.zip)
- **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
## Evaluation
* test set translations: [opusTCv20210807_transformer-big_2022-07-23.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/heb-gmq/opusTCv20210807_transformer-big_2022-07-23.test.txt)
* test set scores: [opusTCv20210807_transformer-big_2022-07-23.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/heb-gmq/opusTCv20210807_transformer-big_2022-07-23.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| heb-dan | flores101-devtest | 0.58023 | 31.4 | 1012 | 24638 |
| heb-isl | flores101-devtest | 0.41998 | 14.0 | 1012 | 22834 |
| heb-nob | flores101-devtest | 0.53086 | 23.7 | 1012 | 23873 |
| heb-swe | flores101-devtest | 0.56881 | 29.6 | 1012 | 23121 |
## Citation Information
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 8b9f0b0
* port time: Sat Aug 13 00:07:45 EEST 2022
* port machine: LM0-400-22516.local
|
Helsinki-NLP/opus-mt-tc-big-itc-he
|
Helsinki-NLP
| 2023-10-10T11:20:10Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"ca",
"es",
"fr",
"gl",
"he",
"it",
"pt",
"ro",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-08-12T12:28:06Z |
---
language:
- ca
- es
- fr
- gl
- he
- it
- pt
- ro
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-itc-he
results:
- task:
name: Translation cat-heb
type: translation
args: cat-heb
dataset:
name: flores101-devtest
type: flores_101
args: cat heb devtest
metrics:
- name: BLEU
type: bleu
value: 23.0
- name: chr-F
type: chrf
value: 0.52457
- task:
name: Translation fra-heb
type: translation
args: fra-heb
dataset:
name: flores101-devtest
type: flores_101
args: fra heb devtest
metrics:
- name: BLEU
type: bleu
value: 23.2
- name: chr-F
type: chrf
value: 0.52953
- task:
name: Translation glg-heb
type: translation
args: glg-heb
dataset:
name: flores101-devtest
type: flores_101
args: glg heb devtest
metrics:
- name: BLEU
type: bleu
value: 20.8
- name: chr-F
type: chrf
value: 0.50918
- task:
name: Translation ita-heb
type: translation
args: ita-heb
dataset:
name: flores101-devtest
type: flores_101
args: ita heb devtest
metrics:
- name: BLEU
type: bleu
value: 18.3
- name: chr-F
type: chrf
value: 0.49007
- task:
name: Translation por-heb
type: translation
args: por-heb
dataset:
name: flores101-devtest
type: flores_101
args: por heb devtest
metrics:
- name: BLEU
type: bleu
value: 24.4
- name: chr-F
type: chrf
value: 0.53906
- task:
name: Translation ron-heb
type: translation
args: ron-heb
dataset:
name: flores101-devtest
type: flores_101
args: ron heb devtest
metrics:
- name: BLEU
type: bleu
value: 22.1
- name: chr-F
type: chrf
value: 0.52103
- task:
name: Translation spa-heb
type: translation
args: spa-heb
dataset:
name: flores101-devtest
type: flores_101
args: spa heb devtest
metrics:
- name: BLEU
type: bleu
value: 16.5
- name: chr-F
type: chrf
value: 0.47646
- task:
name: Translation fra-heb
type: translation
args: fra-heb
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: fra-heb
metrics:
- name: BLEU
type: bleu
value: 39.6
- name: chr-F
type: chrf
value: 0.60539
- task:
name: Translation ita-heb
type: translation
args: ita-heb
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: ita-heb
metrics:
- name: BLEU
type: bleu
value: 40.0
- name: chr-F
type: chrf
value: 0.60264
- task:
name: Translation por-heb
type: translation
args: por-heb
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: por-heb
metrics:
- name: BLEU
type: bleu
value: 44.4
- name: chr-F
type: chrf
value: 0.63087
- task:
name: Translation spa-heb
type: translation
args: spa-heb
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: spa-heb
metrics:
- name: BLEU
type: bleu
value: 44.5
- name: chr-F
type: chrf
value: 0.63883
---
# opus-mt-tc-big-itc-he
## Table of Contents
- [Model Details](#model-details)
- [Uses](#uses)
- [Risks, Limitations and Biases](#risks-limitations-and-biases)
- [How to Get Started With the Model](#how-to-get-started-with-the-model)
- [Training](#training)
- [Evaluation](#evaluation)
- [Citation Information](#citation-information)
- [Acknowledgements](#acknowledgements)
## Model Details
Neural machine translation model for translating from Italic languages (itc) to Hebrew (he).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
**Model Description:**
- **Developed by:** Language Technology Research Group at the University of Helsinki
- **Model Type:** Translation (transformer-big)
- **Release**: 2022-08-03
- **License:** CC-BY-4.0
- **Language(s):**
- Source Language(s): cat fra glg ita lad_Latn por ron spa
- Target Language(s): heb
- Language Pair(s): cat-heb fra-heb glg-heb ita-heb por-heb ron-heb spa-heb
- Valid Target Language Labels:
- **Original Model**: [opusTCv20210807_transformer-big_2022-08-03.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/itc-heb/opusTCv20210807_transformer-big_2022-08-03.zip)
- **Resources for more information:**
- [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
- More information about released models for this language pair: [OPUS-MT itc-heb README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/itc-heb/README.md)
- [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian)
- [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/
## Uses
This model can be used for translation and text-to-text generation.
## Risks, Limitations and Biases
**CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain content that is disturbing, offensive, and can propagate historical and current stereotypes.**
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
## How to Get Started With the Model
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
"La María és feminista.",
"Contribuyan en Tatoeba."
]
model_name = "pytorch-models/opus-mt-tc-big-itc-he"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# מרי היא פמיניסטית.
# תרום לטאטואבה.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-itc-he")
print(pipe("La María és feminista."))
# expected output: מרי היא פמיניסטית.
```
## Training
- **Data**: opusTCv20210807 ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
- **Pre-processing**: SentencePiece (spm32k,spm32k)
- **Model Type:** transformer-big
- **Original MarianNMT Model**: [opusTCv20210807_transformer-big_2022-08-03.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/itc-heb/opusTCv20210807_transformer-big_2022-08-03.zip)
- **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
## Evaluation
* test set translations: [opusTCv20210807_transformer-big_2022-08-03.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/itc-heb/opusTCv20210807_transformer-big_2022-08-03.test.txt)
* test set scores: [opusTCv20210807_transformer-big_2022-08-03.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/itc-heb/opusTCv20210807_transformer-big_2022-08-03.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| fra-heb | tatoeba-test-v2021-08-07 | 0.60539 | 39.6 | 3281 | 20655 |
| ita-heb | tatoeba-test-v2021-08-07 | 0.60264 | 40.0 | 1706 | 9796 |
| por-heb | tatoeba-test-v2021-08-07 | 0.63087 | 44.4 | 719 | 4423 |
| spa-heb | tatoeba-test-v2021-08-07 | 0.63883 | 44.5 | 1849 | 12112 |
| cat-heb | flores101-devtest | 0.52457 | 23.0 | 1012 | 20749 |
| fra-heb | flores101-devtest | 0.52953 | 23.2 | 1012 | 20749 |
| glg-heb | flores101-devtest | 0.50918 | 20.8 | 1012 | 20749 |
| ita-heb | flores101-devtest | 0.49007 | 18.3 | 1012 | 20749 |
| por-heb | flores101-devtest | 0.53906 | 24.4 | 1012 | 20749 |
| ron-heb | flores101-devtest | 0.52103 | 22.1 | 1012 | 20749 |
| spa-heb | flores101-devtest | 0.47646 | 16.5 | 1012 | 20749 |
## Citation Information
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 8b9f0b0
* port time: Sat Aug 13 00:02:03 EEST 2022
* port machine: LM0-400-22516.local
|
Helsinki-NLP/opus-mt-tc-big-cel-en
|
Helsinki-NLP
| 2023-10-10T11:19:09Z | 114 | 1 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"br",
"cel",
"cy",
"en",
"ga",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-04-13T15:36:34Z |
---
language:
- br
- cel
- cy
- en
- ga
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-cel-en
results:
- task:
name: Translation cym-eng
type: translation
args: cym-eng
dataset:
name: flores101-devtest
type: flores_101
args: cym eng devtest
metrics:
- name: BLEU
type: bleu
value: 50.2
- task:
name: Translation gle-eng
type: translation
args: gle-eng
dataset:
name: flores101-devtest
type: flores_101
args: gle eng devtest
metrics:
- name: BLEU
type: bleu
value: 37.4
- task:
name: Translation bre-eng
type: translation
args: bre-eng
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: bre-eng
metrics:
- name: BLEU
type: bleu
value: 36.1
- task:
name: Translation cym-eng
type: translation
args: cym-eng
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: cym-eng
metrics:
- name: BLEU
type: bleu
value: 53.6
- task:
name: Translation gle-eng
type: translation
args: gle-eng
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: gle-eng
metrics:
- name: BLEU
type: bleu
value: 57.7
---
# opus-mt-tc-big-cel-en
Neural machine translation model for translating from Celtic languages (cel) to English (en).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Model info
* Release: 2022-03-13
* source language(s): bre cym gle
* target language(s): eng
* model: transformer-big
* data: opusTCv20210807+bt ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
* tokenization: SentencePiece (spm32k,spm32k)
* original model: [opusTCv20210807+bt_transformer-big_2022-03-13.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/cel-eng/opusTCv20210807+bt_transformer-big_2022-03-13.zip)
* more information released models: [OPUS-MT cel-eng README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/cel-eng/README.md)
## Usage
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
"A-du emaoc’h?",
"Ta'n ushtey glen."
]
model_name = "pytorch-models/opus-mt-tc-big-cel-en"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# Is that you?
# Ta'n ushtey glen.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-cel-en")
print(pipe("A-du emaoc’h?"))
# expected output: Is that you?
```
## Benchmarks
* test set translations: [opusTCv20210807+bt_transformer-big_2022-03-13.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/cel-eng/opusTCv20210807+bt_transformer-big_2022-03-13.test.txt)
* test set scores: [opusTCv20210807+bt_transformer-big_2022-03-13.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/cel-eng/opusTCv20210807+bt_transformer-big_2022-03-13.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| bre-eng | tatoeba-test-v2021-08-07 | 0.53712 | 36.1 | 383 | 2065 |
| cym-eng | tatoeba-test-v2021-08-07 | 0.69239 | 53.6 | 818 | 5563 |
| gle-eng | tatoeba-test-v2021-08-07 | 0.72087 | 57.7 | 1913 | 11190 |
| cym-eng | flores101-devtest | 0.71379 | 50.2 | 1012 | 24721 |
| gle-eng | flores101-devtest | 0.63946 | 37.4 | 1012 | 24721 |
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 3405783
* port time: Wed Apr 13 18:36:25 EEST 2022
* port machine: LM0-400-22516.local
|
Helsinki-NLP/opus-mt-tc-big-es-zle
|
Helsinki-NLP
| 2023-10-10T11:16:04Z | 121 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"be",
"es",
"ru",
"uk",
"zle",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-03-24T12:43:19Z |
---
language:
- be
- es
- ru
- uk
- zle
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-es-zle
results:
- task:
name: Translation spa-rus
type: translation
args: spa-rus
dataset:
name: flores101-devtest
type: flores_101
args: spa rus devtest
metrics:
- name: BLEU
type: bleu
value: 20.2
- task:
name: Translation spa-bel
type: translation
args: spa-bel
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: spa-bel
metrics:
- name: BLEU
type: bleu
value: 27.5
- task:
name: Translation spa-rus
type: translation
args: spa-rus
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: spa-rus
metrics:
- name: BLEU
type: bleu
value: 49.0
- task:
name: Translation spa-ukr
type: translation
args: spa-ukr
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: spa-ukr
metrics:
- name: BLEU
type: bleu
value: 42.3
- task:
name: Translation spa-rus
type: translation
args: spa-rus
dataset:
name: newstest2012
type: wmt-2012-news
args: spa-rus
metrics:
- name: BLEU
type: bleu
value: 24.6
- task:
name: Translation spa-rus
type: translation
args: spa-rus
dataset:
name: newstest2013
type: wmt-2013-news
args: spa-rus
metrics:
- name: BLEU
type: bleu
value: 26.9
---
# opus-mt-tc-big-es-zle
Neural machine translation model for translating from Spanish (es) to East Slavic languages (zle).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Model info
* Release: 2022-03-23
* source language(s): spa
* target language(s): bel rus ukr
* valid target language labels: >>bel<< >>rus<< >>ukr<<
* model: transformer-big
* data: opusTCv20210807 ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
* tokenization: SentencePiece (spm32k,spm32k)
* original model: [opusTCv20210807_transformer-big_2022-03-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/spa-zle/opusTCv20210807_transformer-big_2022-03-23.zip)
* more information released models: [OPUS-MT spa-zle README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/spa-zle/README.md)
* more information about the model: [MarianMT](https://huggingface.co/docs/transformers/model_doc/marian)
This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>bel<<`
## Usage
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
">>rus<< Su novela se vendió bien.",
">>ukr<< Quiero ir a Corea del Norte."
]
model_name = "pytorch-models/opus-mt-tc-big-es-zle"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# Его роман хорошо продавался.
# Я хочу поїхати до Північної Кореї.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-es-zle")
print(pipe(">>rus<< Su novela se vendió bien."))
# expected output: Его роман хорошо продавался.
```
## Benchmarks
* test set translations: [opusTCv20210807_transformer-big_2022-03-23.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/spa-zle/opusTCv20210807_transformer-big_2022-03-23.test.txt)
* test set scores: [opusTCv20210807_transformer-big_2022-03-23.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/spa-zle/opusTCv20210807_transformer-big_2022-03-23.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| spa-bel | tatoeba-test-v2021-08-07 | 0.54506 | 27.5 | 205 | 1259 |
| spa-rus | tatoeba-test-v2021-08-07 | 0.68523 | 49.0 | 10506 | 69242 |
| spa-ukr | tatoeba-test-v2021-08-07 | 0.63502 | 42.3 | 10115 | 54544 |
| spa-rus | flores101-devtest | 0.49913 | 20.2 | 1012 | 23295 |
| spa-ukr | flores101-devtest | 0.47772 | 17.4 | 1012 | 22810 |
| spa-rus | newstest2012 | 0.52436 | 24.6 | 3003 | 64790 |
| spa-rus | newstest2013 | 0.54249 | 26.9 | 3000 | 58560 |
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 1bdabf7
* port time: Thu Mar 24 03:35:13 EET 2022
* port machine: LM0-400-22516.local
|
Helsinki-NLP/opus-mt-tc-big-zle-zlw
|
Helsinki-NLP
| 2023-10-10T11:13:51Z | 119 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"be",
"cs",
"pl",
"ru",
"uk",
"zle",
"zlw",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-03-24T12:13:49Z |
---
language:
- be
- cs
- pl
- ru
- uk
- zle
- zlw
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-zle-zlw
results:
- task:
name: Translation rus-ces
type: translation
args: rus-ces
dataset:
name: flores101-devtest
type: flores_101
args: rus ces devtest
metrics:
- name: BLEU
type: bleu
value: 23.1
- task:
name: Translation ukr-ces
type: translation
args: ukr-ces
dataset:
name: flores101-devtest
type: flores_101
args: ukr ces devtest
metrics:
- name: BLEU
type: bleu
value: 25.1
- task:
name: Translation bel-pol
type: translation
args: bel-pol
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: bel-pol
metrics:
- name: BLEU
type: bleu
value: 47.1
- task:
name: Translation rus-ces
type: translation
args: rus-ces
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: rus-ces
metrics:
- name: BLEU
type: bleu
value: 53.4
- task:
name: Translation rus-pol
type: translation
args: rus-pol
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: rus-pol
metrics:
- name: BLEU
type: bleu
value: 53.7
- task:
name: Translation ukr-ces
type: translation
args: ukr-ces
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: ukr-ces
metrics:
- name: BLEU
type: bleu
value: 58.0
- task:
name: Translation ukr-pol
type: translation
args: ukr-pol
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: ukr-pol
metrics:
- name: BLEU
type: bleu
value: 57.0
- task:
name: Translation rus-ces
type: translation
args: rus-ces
dataset:
name: newstest2013
type: wmt-2013-news
args: rus-ces
metrics:
- name: BLEU
type: bleu
value: 26.0
---
# opus-mt-tc-big-zle-zlw
Neural machine translation model for translating from East Slavic languages (zle) to West Slavic languages (zlw).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Model info
* Release: 2022-03-23
* source language(s): bel rus ukr
* target language(s): ces pol
* valid target language labels: >>ces<< >>pol<<
* model: transformer-big
* data: opusTCv20210807+bt ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
* tokenization: SentencePiece (spm32k,spm32k)
* original model: [opusTCv20210807+bt_transformer-big_2022-03-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/zle-zlw/opusTCv20210807+bt_transformer-big_2022-03-23.zip)
* more information released models: [OPUS-MT zle-zlw README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/zle-zlw/README.md)
* more information about the model: [MarianMT](https://huggingface.co/docs/transformers/model_doc/marian)
This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>ces<<`
## Usage
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
">>pol<< Это метафора.",
">>pol<< Что вы делали?"
]
model_name = "pytorch-models/opus-mt-tc-big-zle-zlw"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# To metafora.
# Co robiliście?
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-zle-zlw")
print(pipe(">>pol<< Это метафора."))
# expected output: To metafora.
```
## Benchmarks
* test set translations: [opusTCv20210807+bt_transformer-big_2022-03-23.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/zle-zlw/opusTCv20210807+bt_transformer-big_2022-03-23.test.txt)
* test set scores: [opusTCv20210807+bt_transformer-big_2022-03-23.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/zle-zlw/opusTCv20210807+bt_transformer-big_2022-03-23.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| bel-pol | tatoeba-test-v2021-08-07 | 0.65517 | 47.1 | 287 | 1706 |
| rus-ces | tatoeba-test-v2021-08-07 | 0.69695 | 53.4 | 2934 | 16831 |
| rus-pol | tatoeba-test-v2021-08-07 | 0.72176 | 53.7 | 3543 | 21505 |
| ukr-ces | tatoeba-test-v2021-08-07 | 0.73149 | 58.0 | 1787 | 8550 |
| ukr-pol | tatoeba-test-v2021-08-07 | 0.74649 | 57.0 | 2519 | 13201 |
| bel-ces | flores101-devtest | 0.41248 | 11.1 | 1012 | 22101 |
| bel-pol | flores101-devtest | 0.42240 | 10.2 | 1012 | 22520 |
| rus-ces | flores101-devtest | 0.50971 | 23.1 | 1012 | 22101 |
| rus-pol | flores101-devtest | 0.48672 | 18.4 | 1012 | 22520 |
| ukr-ces | flores101-devtest | 0.52482 | 25.1 | 1012 | 22101 |
| ukr-pol | flores101-devtest | 0.48790 | 18.8 | 1012 | 22520 |
| rus-ces | newstest2012 | 0.45834 | 18.8 | 3003 | 65456 |
| rus-ces | newstest2013 | 0.52364 | 26.0 | 3000 | 57250 |
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 1bdabf7
* port time: Thu Mar 24 00:50:29 EET 2022
* port machine: LM0-400-22516.local
|
Helsinki-NLP/opus-mt-tc-big-fr-zle
|
Helsinki-NLP
| 2023-10-10T11:11:18Z | 121 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"be",
"fr",
"ru",
"uk",
"zle",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-03-24T12:29:13Z |
---
language:
- be
- fr
- ru
- uk
- zle
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-fr-zle
results:
- task:
name: Translation fra-rus
type: translation
args: fra-rus
dataset:
name: flores101-devtest
type: flores_101
args: fra rus devtest
metrics:
- name: BLEU
type: bleu
value: 25.8
- task:
name: Translation fra-ukr
type: translation
args: fra-ukr
dataset:
name: flores101-devtest
type: flores_101
args: fra ukr devtest
metrics:
- name: BLEU
type: bleu
value: 23.1
- task:
name: Translation fra-bel
type: translation
args: fra-bel
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: fra-bel
metrics:
- name: BLEU
type: bleu
value: 31.1
- task:
name: Translation fra-rus
type: translation
args: fra-rus
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: fra-rus
metrics:
- name: BLEU
type: bleu
value: 46.1
- task:
name: Translation fra-ukr
type: translation
args: fra-ukr
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: fra-ukr
metrics:
- name: BLEU
type: bleu
value: 39.9
- task:
name: Translation fra-rus
type: translation
args: fra-rus
dataset:
name: newstest2012
type: wmt-2012-news
args: fra-rus
metrics:
- name: BLEU
type: bleu
value: 23.1
- task:
name: Translation fra-rus
type: translation
args: fra-rus
dataset:
name: newstest2013
type: wmt-2013-news
args: fra-rus
metrics:
- name: BLEU
type: bleu
value: 24.8
---
# opus-mt-tc-big-fr-zle
Neural machine translation model for translating from French (fr) to East Slavic languages (zle).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Model info
* Release: 2022-03-23
* source language(s): fra
* target language(s): bel rus ukr
* valid target language labels: >>bel<< >>rus<< >>ukr<<
* model: transformer-big
* data: opusTCv20210807 ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
* tokenization: SentencePiece (spm32k,spm32k)
* original model: [opusTCv20210807_transformer-big_2022-03-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/fra-zle/opusTCv20210807_transformer-big_2022-03-23.zip)
* more information released models: [OPUS-MT fra-zle README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/fra-zle/README.md)
* more information about the model: [MarianMT](https://huggingface.co/docs/transformers/model_doc/marian)
This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>bel<<`
## Usage
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
">>rus<< Ils ont acheté un très bon appareil photo.",
">>ukr<< Il s'est soudain mis à pleuvoir."
]
model_name = "pytorch-models/opus-mt-tc-big-fr-zle"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# Они купили очень хорошую камеру.
# Раптом почався дощ.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-fr-zle")
print(pipe(">>rus<< Ils ont acheté un très bon appareil photo."))
# expected output: Они купили очень хорошую камеру.
```
## Benchmarks
* test set translations: [opusTCv20210807_transformer-big_2022-03-23.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/fra-zle/opusTCv20210807_transformer-big_2022-03-23.test.txt)
* test set scores: [opusTCv20210807_transformer-big_2022-03-23.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/fra-zle/opusTCv20210807_transformer-big_2022-03-23.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| fra-bel | tatoeba-test-v2021-08-07 | 0.52711 | 31.1 | 283 | 1703 |
| fra-rus | tatoeba-test-v2021-08-07 | 0.66502 | 46.1 | 11490 | 70123 |
| fra-ukr | tatoeba-test-v2021-08-07 | 0.61860 | 39.9 | 10035 | 54372 |
| fra-rus | flores101-devtest | 0.54106 | 25.8 | 1012 | 23295 |
| fra-ukr | flores101-devtest | 0.52733 | 23.1 | 1012 | 22810 |
| fra-rus | newstest2012 | 0.51254 | 23.1 | 3003 | 64790 |
| fra-rus | newstest2013 | 0.52342 | 24.8 | 3000 | 58560 |
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 1bdabf7
* port time: Thu Mar 24 02:05:04 EET 2022
* port machine: LM0-400-22516.local
|
Helsinki-NLP/opus-mt-tc-big-fi-zls
|
Helsinki-NLP
| 2023-10-10T11:08:02Z | 119 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"bg",
"fi",
"hr",
"sl",
"sr",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-08-12T16:46:33Z |
---
language:
- bg
- fi
- hr
- sl
- sr
language_bcp47:
- sr_Cyrl
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-fi-zls
results:
- task:
name: Translation fin-bul
type: translation
args: fin-bul
dataset:
name: flores101-devtest
type: flores_101
args: fin bul devtest
metrics:
- name: BLEU
type: bleu
value: 26.2
- name: chr-F
type: chrf
value: 0.54912
- task:
name: Translation fin-hrv
type: translation
args: fin-hrv
dataset:
name: flores101-devtest
type: flores_101
args: fin hrv devtest
metrics:
- name: BLEU
type: bleu
value: 21.3
- name: chr-F
type: chrf
value: 0.51468
- task:
name: Translation fin-slv
type: translation
args: fin-slv
dataset:
name: flores101-devtest
type: flores_101
args: fin slv devtest
metrics:
- name: BLEU
type: bleu
value: 22.3
- name: chr-F
type: chrf
value: 0.51226
- task:
name: Translation fin-srp_Cyrl
type: translation
args: fin-srp_Cyrl
dataset:
name: flores101-devtest
type: flores_101
args: fin srp_Cyrl devtest
metrics:
- name: BLEU
type: bleu
value: 21.8
- name: chr-F
type: chrf
value: 0.50774
---
# opus-mt-tc-big-fi-zls
## Table of Contents
- [Model Details](#model-details)
- [Uses](#uses)
- [Risks, Limitations and Biases](#risks-limitations-and-biases)
- [How to Get Started With the Model](#how-to-get-started-with-the-model)
- [Training](#training)
- [Evaluation](#evaluation)
- [Citation Information](#citation-information)
- [Acknowledgements](#acknowledgements)
## Model Details
Neural machine translation model for translating from Finnish (fi) to South Slavic languages (zls).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
**Model Description:**
- **Developed by:** Language Technology Research Group at the University of Helsinki
- **Model Type:** Translation (transformer-big)
- **Release**: 2022-07-23
- **License:** CC-BY-4.0
- **Language(s):**
- Source Language(s): fin
- Target Language(s): bul hrv slv srp_Cyrl
- Language Pair(s): fin-bul fin-hrv fin-slv fin-srp_Cyrl
- Valid Target Language Labels: >>bos<< >>bos_Cyrl<< >>bos_Latn<< >>bul<< >>chu<< >>hbs<< >>hbs_Cyrl<< >>hrv<< >>kjv<< >>mkd<< >>slv<< >>srp<< >>srp_Cyrl<< >>srp_Latn<< >>svm<<
- **Original Model**: [opusTCv20210807_transformer-big_2022-07-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/fin-zls/opusTCv20210807_transformer-big_2022-07-23.zip)
- **Resources for more information:**
- [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
- More information about released models for this language pair: [OPUS-MT fin-zls README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/fin-zls/README.md)
- [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian)
- [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/
This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>slv<<`
## Uses
This model can be used for translation and text-to-text generation.
## Risks, Limitations and Biases
**CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain content that is disturbing, offensive, and can propagate historical and current stereotypes.**
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
## How to Get Started With the Model
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
">>bul<< Ajattelen vain sinua.",
">>slv<< Virtahevot rakastavat vettä."
]
model_name = "pytorch-models/opus-mt-tc-big-fi-zls"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# Мисля само за теб.
# Povodni konji obožujejo vodo.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-fi-zls")
print(pipe(">>bul<< Ajattelen vain sinua."))
# expected output: Мисля само за теб.
```
## Training
- **Data**: opusTCv20210807 ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
- **Pre-processing**: SentencePiece (spm32k,spm32k)
- **Model Type:** transformer-big
- **Original MarianNMT Model**: [opusTCv20210807_transformer-big_2022-07-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/fin-zls/opusTCv20210807_transformer-big_2022-07-23.zip)
- **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
## Evaluation
* test set translations: [opusTCv20210807_transformer-big_2022-07-23.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/fin-zls/opusTCv20210807_transformer-big_2022-07-23.test.txt)
* test set scores: [opusTCv20210807_transformer-big_2022-07-23.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/fin-zls/opusTCv20210807_transformer-big_2022-07-23.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| fin-bul | flores101-devtest | 0.54912 | 26.2 | 1012 | 24700 |
| fin-hrv | flores101-devtest | 0.51468 | 21.3 | 1012 | 22423 |
| fin-slv | flores101-devtest | 0.51226 | 22.3 | 1012 | 23425 |
| fin-srp_Cyrl | flores101-devtest | 0.50774 | 21.8 | 1012 | 23456 |
## Citation Information
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 8b9f0b0
* port time: Sat Aug 13 00:08:29 EEST 2022
* port machine: LM0-400-22516.local
|
Helsinki-NLP/opus-mt-tc-big-de-zle
|
Helsinki-NLP
| 2023-10-10T11:06:58Z | 120 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"be",
"de",
"ru",
"uk",
"zle",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-03-24T12:19:23Z |
---
language:
- be
- de
- ru
- uk
- zle
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-de-zle
results:
- task:
name: Translation deu-rus
type: translation
args: deu-rus
dataset:
name: flores101-devtest
type: flores_101
args: deu rus devtest
metrics:
- name: BLEU
type: bleu
value: 26.3
- task:
name: Translation deu-ukr
type: translation
args: deu-ukr
dataset:
name: flores101-devtest
type: flores_101
args: deu ukr devtest
metrics:
- name: BLEU
type: bleu
value: 24.2
- task:
name: Translation deu-bel
type: translation
args: deu-bel
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: deu-bel
metrics:
- name: BLEU
type: bleu
value: 29.5
- task:
name: Translation deu-rus
type: translation
args: deu-rus
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: deu-rus
metrics:
- name: BLEU
type: bleu
value: 46.1
- task:
name: Translation deu-ukr
type: translation
args: deu-ukr
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: deu-ukr
metrics:
- name: BLEU
type: bleu
value: 40.7
- task:
name: Translation deu-rus
type: translation
args: deu-rus
dataset:
name: newstest2012
type: wmt-2012-news
args: deu-rus
metrics:
- name: BLEU
type: bleu
value: 20.8
- task:
name: Translation deu-rus
type: translation
args: deu-rus
dataset:
name: newstest2013
type: wmt-2013-news
args: deu-rus
metrics:
- name: BLEU
type: bleu
value: 24.9
---
# opus-mt-tc-big-de-zle
Neural machine translation model for translating from German (de) to East Slavic languages (zle).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Model info
* Release: 2022-03-23
* source language(s): deu
* target language(s): bel rus ukr
* valid target language labels: >>bel<< >>rus<< >>ukr<<
* model: transformer-big
* data: opusTCv20210807 ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
* tokenization: SentencePiece (spm32k,spm32k)
* original model: [opusTCv20210807_transformer-big_2022-03-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/deu-zle/opusTCv20210807_transformer-big_2022-03-23.zip)
* more information released models: [OPUS-MT deu-zle README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/deu-zle/README.md)
* more information about the model: [MarianMT](https://huggingface.co/docs/transformers/model_doc/marian)
This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>bel<<`
## Usage
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
">>ukr<< Der Soldat hat mir Wasser gegeben.",
">>ukr<< Ich will hier nicht essen."
]
model_name = "pytorch-models/opus-mt-tc-big-de-zle"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# Солдат дав мені воду.
# Я не хочу тут їсти.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-de-zle")
print(pipe(">>ukr<< Der Soldat hat mir Wasser gegeben."))
# expected output: Солдат дав мені воду.
```
## Benchmarks
* test set translations: [opusTCv20210807_transformer-big_2022-03-23.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/deu-zle/opusTCv20210807_transformer-big_2022-03-23.test.txt)
* test set scores: [opusTCv20210807_transformer-big_2022-03-23.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/deu-zle/opusTCv20210807_transformer-big_2022-03-23.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| deu-bel | tatoeba-test-v2021-08-07 | 0.53128 | 29.5 | 551 | 3601 |
| deu-rus | tatoeba-test-v2021-08-07 | 0.67143 | 46.1 | 12800 | 87296 |
| deu-ukr | tatoeba-test-v2021-08-07 | 0.62737 | 40.7 | 10319 | 56287 |
| deu-rus | flores101-devtest | 0.54152 | 26.3 | 1012 | 23295 |
| deu-ukr | flores101-devtest | 0.53286 | 24.2 | 1012 | 22810 |
| deu-rus | newstest2012 | 0.49409 | 20.8 | 3003 | 64790 |
| deu-rus | newstest2013 | 0.52631 | 24.9 | 3000 | 58560 |
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 1bdabf7
* port time: Thu Mar 24 01:29:09 EET 2022
* port machine: LM0-400-22516.local
|
Azma-AI/roberta-base-emotion-classifier
|
Azma-AI
| 2023-10-10T11:05:56Z | 108 | 1 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"text-classification",
"emotions",
"multi-class-classification",
"multi-label-classification",
"en",
"dataset:go_emotions",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-10T11:02:32Z |
---
language: en
tags:
- text-classification
- pytorch
- roberta
- emotions
- multi-class-classification
- multi-label-classification
datasets:
- go_emotions
license: mit
widget:
- text: "I am not having a great day."
---
Model trained from [roberta-base](https://huggingface.co/roberta-base) on the [go_emotions](https://huggingface.co/datasets/go_emotions) dataset for multi-label classification.
[go_emotions](https://huggingface.co/datasets/go_emotions) is based on Reddit data and has 28 labels. It is a multi-label dataset where one or multiple labels may apply for any given input text, hence this model is a multi-label classification model with 28 'probability' float outputs for any given input text. Typically a threshold of 0.5 is applied to the probabilities for the prediction for each label.
The model was trained using `AutoModelForSequenceClassification.from_pretrained` with `problem_type="multi_label_classification"` for 3 epochs with a learning rate of 2e-5 and weight decay of 0.01.
Evaluation (of the 28 dim output via a threshold of 0.5 to binarize each) using the dataset test split gives:
- Micro F1 0.585
- ROC AUC 0.751
- Accuracy 0.474
But the metrics would be more meaningful when measured per label given the multi-label nature.
Additionally some labels (E.g. `gratitude`) when considered independently perform very strongly with F1 around 0.9, whilst others (E.g. `relief`) perform very poorly. This is a challenging dataset. Labels such as `relief` do have much fewer examples in the training data (less than 100 out of the 40k+), but there is also some ambiguity and/or labelling errors visible in the training data of `go_emotions` that is suspected to constrain the performance.
|
Helsinki-NLP/opus-mt-tc-big-gmq-gmq
|
Helsinki-NLP
| 2023-10-10T11:05:51Z | 124 | 1 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"da",
"is",
"nb",
"nn",
"sv",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-08-12T10:30:28Z |
---
language:
- da
- is
- nb
- nn
- sv
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-gmq-gmq
results:
- task:
name: Translation isl-swe
type: translation
args: isl-swe
dataset:
name: europeana2021
type: europeana2021
args: isl-swe
metrics:
- name: BLEU
type: bleu
value: 22.2
- name: chr-F
type: chrf
value: 0.45562
- task:
name: Translation nob-isl
type: translation
args: nob-isl
dataset:
name: europeana2021
type: europeana2021
args: nob-isl
metrics:
- name: BLEU
type: bleu
value: 29.7
- name: chr-F
type: chrf
value: 0.54171
- task:
name: Translation nob-swe
type: translation
args: nob-swe
dataset:
name: europeana2021
type: europeana2021
args: nob-swe
metrics:
- name: BLEU
type: bleu
value: 54.0
- name: chr-F
type: chrf
value: 0.73891
- task:
name: Translation dan-isl
type: translation
args: dan-isl
dataset:
name: flores101-devtest
type: flores_101
args: dan isl devtest
metrics:
- name: BLEU
type: bleu
value: 22.2
- name: chr-F
type: chrf
value: 0.50227
- task:
name: Translation dan-nob
type: translation
args: dan-nob
dataset:
name: flores101-devtest
type: flores_101
args: dan nob devtest
metrics:
- name: BLEU
type: bleu
value: 28.6
- name: chr-F
type: chrf
value: 0.58445
- task:
name: Translation dan-swe
type: translation
args: dan-swe
dataset:
name: flores101-devtest
type: flores_101
args: dan swe devtest
metrics:
- name: BLEU
type: bleu
value: 38.5
- name: chr-F
type: chrf
value: 0.65000
- task:
name: Translation isl-dan
type: translation
args: isl-dan
dataset:
name: flores101-devtest
type: flores_101
args: isl dan devtest
metrics:
- name: BLEU
type: bleu
value: 27.2
- name: chr-F
type: chrf
value: 0.53630
- task:
name: Translation isl-nob
type: translation
args: isl-nob
dataset:
name: flores101-devtest
type: flores_101
args: isl nob devtest
metrics:
- name: BLEU
type: bleu
value: 20.5
- name: chr-F
type: chrf
value: 0.49434
- task:
name: Translation isl-swe
type: translation
args: isl-swe
dataset:
name: flores101-devtest
type: flores_101
args: isl swe devtest
metrics:
- name: BLEU
type: bleu
value: 26.0
- name: chr-F
type: chrf
value: 0.53373
- task:
name: Translation nob-dan
type: translation
args: nob-dan
dataset:
name: flores101-devtest
type: flores_101
args: nob dan devtest
metrics:
- name: BLEU
type: bleu
value: 31.7
- name: chr-F
type: chrf
value: 0.59657
- task:
name: Translation nob-isl
type: translation
args: nob-isl
dataset:
name: flores101-devtest
type: flores_101
args: nob isl devtest
metrics:
- name: BLEU
type: bleu
value: 18.9
- name: chr-F
type: chrf
value: 0.47432
- task:
name: Translation nob-swe
type: translation
args: nob-swe
dataset:
name: flores101-devtest
type: flores_101
args: nob swe devtest
metrics:
- name: BLEU
type: bleu
value: 31.3
- name: chr-F
type: chrf
value: 0.60030
- task:
name: Translation swe-dan
type: translation
args: swe-dan
dataset:
name: flores101-devtest
type: flores_101
args: swe dan devtest
metrics:
- name: BLEU
type: bleu
value: 39.0
- name: chr-F
type: chrf
value: 0.64340
- task:
name: Translation swe-isl
type: translation
args: swe-isl
dataset:
name: flores101-devtest
type: flores_101
args: swe isl devtest
metrics:
- name: BLEU
type: bleu
value: 21.7
- name: chr-F
type: chrf
value: 0.49590
- task:
name: Translation swe-nob
type: translation
args: swe-nob
dataset:
name: flores101-devtest
type: flores_101
args: swe nob devtest
metrics:
- name: BLEU
type: bleu
value: 28.9
- name: chr-F
type: chrf
value: 0.58336
- task:
name: Translation dan-nob
type: translation
args: dan-nob
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: dan-nob
metrics:
- name: BLEU
type: bleu
value: 78.2
- name: chr-F
type: chrf
value: 0.87556
- task:
name: Translation dan-swe
type: translation
args: dan-swe
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: dan-swe
metrics:
- name: BLEU
type: bleu
value: 72.5
- name: chr-F
type: chrf
value: 0.83556
- task:
name: Translation nno-nob
type: translation
args: nno-nob
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: nno-nob
metrics:
- name: BLEU
type: bleu
value: 78.9
- name: chr-F
type: chrf
value: 0.88349
- task:
name: Translation nob-dan
type: translation
args: nob-dan
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: nob-dan
metrics:
- name: BLEU
type: bleu
value: 73.9
- name: chr-F
type: chrf
value: 0.85345
- task:
name: Translation nob-nno
type: translation
args: nob-nno
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: nob-nno
metrics:
- name: BLEU
type: bleu
value: 55.2
- name: chr-F
type: chrf
value: 0.74571
- task:
name: Translation nob-swe
type: translation
args: nob-swe
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: nob-swe
metrics:
- name: BLEU
type: bleu
value: 73.9
- name: chr-F
type: chrf
value: 0.84747
- task:
name: Translation swe-dan
type: translation
args: swe-dan
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: swe-dan
metrics:
- name: BLEU
type: bleu
value: 72.6
- name: chr-F
type: chrf
value: 0.83392
- task:
name: Translation swe-nob
type: translation
args: swe-nob
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: swe-nob
metrics:
- name: BLEU
type: bleu
value: 76.3
- name: chr-F
type: chrf
value: 0.85815
---
# opus-mt-tc-big-gmq-gmq
## Table of Contents
- [Model Details](#model-details)
- [Uses](#uses)
- [Risks, Limitations and Biases](#risks-limitations-and-biases)
- [How to Get Started With the Model](#how-to-get-started-with-the-model)
- [Training](#training)
- [Evaluation](#evaluation)
- [Citation Information](#citation-information)
- [Acknowledgements](#acknowledgements)
## Model Details
Neural machine translation model for translating from North Germanic languages (gmq) to North Germanic languages (gmq).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
**Model Description:**
- **Developed by:** Language Technology Research Group at the University of Helsinki
- **Model Type:** Translation (transformer-big)
- **Release**: 2022-07-29
- **License:** CC-BY-4.0
- **Language(s):**
- Source Language(s): dan fao isl nno nob nor swe
- Target Language(s): dan isl nno nob nor swe
- Language Pair(s): dan-isl dan-nob dan-swe isl-dan isl-nob isl-swe nno-nob nob-dan nob-isl nob-nno nob-swe swe-dan swe-isl swe-nob
- Valid Target Language Labels: >>dan<< >>fao<< >>isl<< >>jut<< >>nno<< >>nob<< >>non<< >>nrn<< >>ovd<< >>qer<< >>rmg<< >>swe<<
- **Original Model**: [opusTCv20210807_transformer-big_2022-07-29.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-gmq/opusTCv20210807_transformer-big_2022-07-29.zip)
- **Resources for more information:**
- [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
- More information about released models for this language pair: [OPUS-MT gmq-gmq README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/gmq-gmq/README.md)
- [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian)
- [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/
This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>dan<<`
## Uses
This model can be used for translation and text-to-text generation.
## Risks, Limitations and Biases
**CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain content that is disturbing, offensive, and can propagate historical and current stereotypes.**
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
## How to Get Started With the Model
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
">>fao<< Jeg er bange for kakerlakker.",
">>nob<< Vladivostok är en stad i Ryssland."
]
model_name = "pytorch-models/opus-mt-tc-big-gmq-gmq"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# Tað eru uml.
# Vladivostok er en by i Russland.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-gmq-gmq")
print(pipe(">>fao<< Jeg er bange for kakerlakker."))
# expected output: Tað eru uml.
```
## Training
- **Data**: opusTCv20210807 ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
- **Pre-processing**: SentencePiece (spm32k,spm32k)
- **Model Type:** transformer-big
- **Original MarianNMT Model**: [opusTCv20210807_transformer-big_2022-07-29.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-gmq/opusTCv20210807_transformer-big_2022-07-29.zip)
- **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
## Evaluation
* test set translations: [opusTCv20210807_transformer-big_2022-07-29.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-gmq/opusTCv20210807_transformer-big_2022-07-29.test.txt)
* test set scores: [opusTCv20210807_transformer-big_2022-07-29.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-gmq/opusTCv20210807_transformer-big_2022-07-29.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| dan-nob | tatoeba-test-v2021-08-07 | 0.87556 | 78.2 | 1299 | 9620 |
| dan-swe | tatoeba-test-v2021-08-07 | 0.83556 | 72.5 | 1549 | 10060 |
| nno-nob | tatoeba-test-v2021-08-07 | 0.88349 | 78.9 | 467 | 3129 |
| nob-dan | tatoeba-test-v2021-08-07 | 0.85345 | 73.9 | 1299 | 9794 |
| nob-nno | tatoeba-test-v2021-08-07 | 0.74571 | 55.2 | 466 | 3141 |
| nob-swe | tatoeba-test-v2021-08-07 | 0.84747 | 73.9 | 563 | 3698 |
| swe-dan | tatoeba-test-v2021-08-07 | 0.83392 | 72.6 | 1549 | 10239 |
| swe-nob | tatoeba-test-v2021-08-07 | 0.85815 | 76.3 | 563 | 3708 |
| isl-swe | europeana2021 | 0.45562 | 22.2 | 563 | 10293 |
| nob-isl | europeana2021 | 0.54171 | 29.7 | 538 | 9932 |
| nob-swe | europeana2021 | 0.73891 | 54.0 | 538 | 9885 |
| dan-isl | flores101-devtest | 0.50227 | 22.2 | 1012 | 22834 |
| dan-nob | flores101-devtest | 0.58445 | 28.6 | 1012 | 23873 |
| dan-swe | flores101-devtest | 0.65000 | 38.5 | 1012 | 23121 |
| isl-dan | flores101-devtest | 0.53630 | 27.2 | 1012 | 24638 |
| isl-nob | flores101-devtest | 0.49434 | 20.5 | 1012 | 23873 |
| isl-swe | flores101-devtest | 0.53373 | 26.0 | 1012 | 23121 |
| nob-dan | flores101-devtest | 0.59657 | 31.7 | 1012 | 24638 |
| nob-isl | flores101-devtest | 0.47432 | 18.9 | 1012 | 22834 |
| nob-swe | flores101-devtest | 0.60030 | 31.3 | 1012 | 23121 |
| swe-dan | flores101-devtest | 0.64340 | 39.0 | 1012 | 24638 |
| swe-isl | flores101-devtest | 0.49590 | 21.7 | 1012 | 22834 |
| swe-nob | flores101-devtest | 0.58336 | 28.9 | 1012 | 23873 |
## Citation Information
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 8b9f0b0
* port time: Fri Aug 12 23:59:02 EEST 2022
* port machine: LM0-400-22516.local
|
Helsinki-NLP/opus-mt-tc-big-itc-tr
|
Helsinki-NLP
| 2023-10-10T11:04:52Z | 113 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"ca",
"es",
"fr",
"gl",
"it",
"oc",
"pt",
"ro",
"tr",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-08-12T13:25:33Z |
---
language:
- ca
- es
- fr
- gl
- it
- oc
- pt
- ro
- tr
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-itc-tr
results:
- task:
name: Translation cat-tur
type: translation
args: cat-tur
dataset:
name: flores101-devtest
type: flores_101
args: cat tur devtest
metrics:
- name: BLEU
type: bleu
value: 21.7
- name: chr-F
type: chrf
value: 0.54892
- task:
name: Translation fra-tur
type: translation
args: fra-tur
dataset:
name: flores101-devtest
type: flores_101
args: fra tur devtest
metrics:
- name: BLEU
type: bleu
value: 21.7
- name: chr-F
type: chrf
value: 0.55342
- task:
name: Translation glg-tur
type: translation
args: glg-tur
dataset:
name: flores101-devtest
type: flores_101
args: glg tur devtest
metrics:
- name: BLEU
type: bleu
value: 20.6
- name: chr-F
type: chrf
value: 0.53936
- task:
name: Translation ita-tur
type: translation
args: ita-tur
dataset:
name: flores101-devtest
type: flores_101
args: ita tur devtest
metrics:
- name: BLEU
type: bleu
value: 18.4
- name: chr-F
type: chrf
value: 0.52842
- task:
name: Translation oci-tur
type: translation
args: oci-tur
dataset:
name: flores101-devtest
type: flores_101
args: oci tur devtest
metrics:
- name: BLEU
type: bleu
value: 17.6
- name: chr-F
type: chrf
value: 0.50618
- task:
name: Translation por-tur
type: translation
args: por-tur
dataset:
name: flores101-devtest
type: flores_101
args: por tur devtest
metrics:
- name: BLEU
type: bleu
value: 23.5
- name: chr-F
type: chrf
value: 0.56396
- task:
name: Translation ron-tur
type: translation
args: ron-tur
dataset:
name: flores101-devtest
type: flores_101
args: ron tur devtest
metrics:
- name: BLEU
type: bleu
value: 21.5
- name: chr-F
type: chrf
value: 0.55409
- task:
name: Translation spa-tur
type: translation
args: spa-tur
dataset:
name: flores101-devtest
type: flores_101
args: spa tur devtest
metrics:
- name: BLEU
type: bleu
value: 16.5
- name: chr-F
type: chrf
value: 0.51066
- task:
name: Translation fra-tur
type: translation
args: fra-tur
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: fra-tur
metrics:
- name: BLEU
type: bleu
value: 34.8
- name: chr-F
type: chrf
value: 0.63006
- task:
name: Translation ita-tur
type: translation
args: ita-tur
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: ita-tur
metrics:
- name: BLEU
type: bleu
value: 34.9
- name: chr-F
type: chrf
value: 0.59991
- task:
name: Translation por-tur
type: translation
args: por-tur
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: por-tur
metrics:
- name: BLEU
type: bleu
value: 40.1
- name: chr-F
type: chrf
value: 0.67836
- task:
name: Translation ron-tur
type: translation
args: ron-tur
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: ron-tur
metrics:
- name: BLEU
type: bleu
value: 35.5
- name: chr-F
type: chrf
value: 0.64031
- task:
name: Translation spa-tur
type: translation
args: spa-tur
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: spa-tur
metrics:
- name: BLEU
type: bleu
value: 45.2
- name: chr-F
type: chrf
value: 0.71524
---
# opus-mt-tc-big-itc-tr
## Table of Contents
- [Model Details](#model-details)
- [Uses](#uses)
- [Risks, Limitations and Biases](#risks-limitations-and-biases)
- [How to Get Started With the Model](#how-to-get-started-with-the-model)
- [Training](#training)
- [Evaluation](#evaluation)
- [Citation Information](#citation-information)
- [Acknowledgements](#acknowledgements)
## Model Details
Neural machine translation model for translating from Italic languages (itc) to Turkish (tr).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
**Model Description:**
- **Developed by:** Language Technology Research Group at the University of Helsinki
- **Model Type:** Translation (transformer-big)
- **Release**: 2022-07-28
- **License:** CC-BY-4.0
- **Language(s):**
- Source Language(s): cat fra glg ita lad lad_Latn oci por ron spa
- Target Language(s): tur
- Language Pair(s): cat-tur fra-tur glg-tur ita-tur oci-tur por-tur ron-tur spa-tur
- Valid Target Language Labels:
- **Original Model**: [opusTCv20210807_transformer-big_2022-07-28.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/itc-tur/opusTCv20210807_transformer-big_2022-07-28.zip)
- **Resources for more information:**
- [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
- More information about released models for this language pair: [OPUS-MT itc-tur README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/itc-tur/README.md)
- [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian)
- [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/
## Uses
This model can be used for translation and text-to-text generation.
## Risks, Limitations and Biases
**CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain content that is disturbing, offensive, and can propagate historical and current stereotypes.**
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
## How to Get Started With the Model
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
""Di che nazionalità sono le tue dottoresse?" "Malese."",
""Di che nazionalità sono i nostri amici?" "Maltese.""
]
model_name = "pytorch-models/opus-mt-tc-big-itc-tr"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# "Doktorların hangi milletten?" "Malezyalı."
# "Arkadaşlarımız hangi milletten?" "Maltalı."
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-itc-tr")
print(pipe(""Di che nazionalità sono le tue dottoresse?" "Malese.""))
# expected output: "Doktorların hangi milletten?" "Malezyalı."
```
## Training
- **Data**: opusTCv20210807 ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
- **Pre-processing**: SentencePiece (spm32k,spm32k)
- **Model Type:** transformer-big
- **Original MarianNMT Model**: [opusTCv20210807_transformer-big_2022-07-28.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/itc-tur/opusTCv20210807_transformer-big_2022-07-28.zip)
- **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
## Evaluation
* test set translations: [opusTCv20210807_transformer-big_2022-07-28.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/itc-tur/opusTCv20210807_transformer-big_2022-07-28.test.txt)
* test set scores: [opusTCv20210807_transformer-big_2022-07-28.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/itc-tur/opusTCv20210807_transformer-big_2022-07-28.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| fra-tur | tatoeba-test-v2021-08-07 | 0.63006 | 34.8 | 2582 | 14307 |
| ita-tur | tatoeba-test-v2021-08-07 | 0.59991 | 34.9 | 10000 | 75807 |
| por-tur | tatoeba-test-v2021-08-07 | 0.67836 | 40.1 | 1794 | 9312 |
| ron-tur | tatoeba-test-v2021-08-07 | 0.64031 | 35.5 | 2460 | 13788 |
| spa-tur | tatoeba-test-v2021-08-07 | 0.71524 | 45.2 | 10615 | 56099 |
| cat-tur | flores101-devtest | 0.54892 | 21.7 | 1012 | 20253 |
| fra-tur | flores101-devtest | 0.55342 | 21.7 | 1012 | 20253 |
| glg-tur | flores101-devtest | 0.53936 | 20.6 | 1012 | 20253 |
| ita-tur | flores101-devtest | 0.52842 | 18.4 | 1012 | 20253 |
| oci-tur | flores101-devtest | 0.50618 | 17.6 | 1012 | 20253 |
| por-tur | flores101-devtest | 0.56396 | 23.5 | 1012 | 20253 |
| ron-tur | flores101-devtest | 0.55409 | 21.5 | 1012 | 20253 |
| spa-tur | flores101-devtest | 0.51066 | 16.5 | 1012 | 20253 |
## Citation Information
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 8b9f0b0
* port time: Sat Aug 13 00:03:26 EEST 2022
* port machine: LM0-400-22516.local
|
Helsinki-NLP/opus-mt-tc-big-de-es
|
Helsinki-NLP
| 2023-10-10T11:03:48Z | 207 | 1 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"de",
"es",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-08-12T15:21:06Z |
---
language:
- de
- es
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-de-es
results:
- task:
name: Translation deu-spa
type: translation
args: deu-spa
dataset:
name: flores101-devtest
type: flores_101
args: deu spa devtest
metrics:
- name: BLEU
type: bleu
value: 24.9
- name: chr-F
type: chrf
value: 0.53208
- task:
name: Translation deu-spa
type: translation
args: deu-spa
dataset:
name: news-test2008
type: news-test2008
args: deu-spa
metrics:
- name: BLEU
type: bleu
value: 26.6
- name: chr-F
type: chrf
value: 0.54400
- task:
name: Translation deu-spa
type: translation
args: deu-spa
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: deu-spa
metrics:
- name: BLEU
type: bleu
value: 50.8
- name: chr-F
type: chrf
value: 0.69105
- task:
name: Translation deu-spa
type: translation
args: deu-spa
dataset:
name: newstest2009
type: wmt-2009-news
args: deu-spa
metrics:
- name: BLEU
type: bleu
value: 25.9
- name: chr-F
type: chrf
value: 0.53934
- task:
name: Translation deu-spa
type: translation
args: deu-spa
dataset:
name: newstest2010
type: wmt-2010-news
args: deu-spa
metrics:
- name: BLEU
type: bleu
value: 33.8
- name: chr-F
type: chrf
value: 0.60102
- task:
name: Translation deu-spa
type: translation
args: deu-spa
dataset:
name: newstest2011
type: wmt-2011-news
args: deu-spa
metrics:
- name: BLEU
type: bleu
value: 31.3
- name: chr-F
type: chrf
value: 0.57133
- task:
name: Translation deu-spa
type: translation
args: deu-spa
dataset:
name: newstest2012
type: wmt-2012-news
args: deu-spa
metrics:
- name: BLEU
type: bleu
value: 32.6
- name: chr-F
type: chrf
value: 0.58119
- task:
name: Translation deu-spa
type: translation
args: deu-spa
dataset:
name: newstest2013
type: wmt-2013-news
args: deu-spa
metrics:
- name: BLEU
type: bleu
value: 32.4
- name: chr-F
type: chrf
value: 0.57559
---
# opus-mt-tc-big-de-es
## Table of Contents
- [Model Details](#model-details)
- [Uses](#uses)
- [Risks, Limitations and Biases](#risks-limitations-and-biases)
- [How to Get Started With the Model](#how-to-get-started-with-the-model)
- [Training](#training)
- [Evaluation](#evaluation)
- [Citation Information](#citation-information)
- [Acknowledgements](#acknowledgements)
## Model Details
Neural machine translation model for translating from German (de) to Spanish (es).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
**Model Description:**
- **Developed by:** Language Technology Research Group at the University of Helsinki
- **Model Type:** Translation (transformer-big)
- **Release**: 2022-07-26
- **License:** CC-BY-4.0
- **Language(s):**
- Source Language(s): deu
- Target Language(s): spa
- Language Pair(s): deu-spa
- Valid Target Language Labels:
- **Original Model**: [opusTCv20210807_transformer-big_2022-07-26.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/deu-spa/opusTCv20210807_transformer-big_2022-07-26.zip)
- **Resources for more information:**
- [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
- More information about released models for this language pair: [OPUS-MT deu-spa README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/deu-spa/README.md)
- [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian)
- [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/
## Uses
This model can be used for translation and text-to-text generation.
## Risks, Limitations and Biases
**CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain content that is disturbing, offensive, and can propagate historical and current stereotypes.**
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
## How to Get Started With the Model
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
"Ich verstehe nicht, worüber ihr redet.",
"Die Vögel singen in den Bäumen."
]
model_name = "pytorch-models/opus-mt-tc-big-de-es"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# No entiendo de qué están hablando.
# Los pájaros cantan en los árboles.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-de-es")
print(pipe("Ich verstehe nicht, worüber ihr redet."))
# expected output: No entiendo de qué están hablando.
```
## Training
- **Data**: opusTCv20210807 ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
- **Pre-processing**: SentencePiece (spm32k,spm32k)
- **Model Type:** transformer-big
- **Original MarianNMT Model**: [opusTCv20210807_transformer-big_2022-07-26.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/deu-spa/opusTCv20210807_transformer-big_2022-07-26.zip)
- **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
## Evaluation
* test set translations: [opusTCv20210807_transformer-big_2022-07-26.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/deu-spa/opusTCv20210807_transformer-big_2022-07-26.test.txt)
* test set scores: [opusTCv20210807_transformer-big_2022-07-26.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/deu-spa/opusTCv20210807_transformer-big_2022-07-26.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| deu-spa | tatoeba-test-v2021-08-07 | 0.69105 | 50.8 | 10521 | 82570 |
| deu-spa | flores101-devtest | 0.53208 | 24.9 | 1012 | 29199 |
| deu-spa | newssyscomb2009 | 0.55547 | 28.3 | 502 | 12503 |
| deu-spa | news-test2008 | 0.54400 | 26.6 | 2051 | 52586 |
| deu-spa | newstest2009 | 0.53934 | 25.9 | 2525 | 68111 |
| deu-spa | newstest2010 | 0.60102 | 33.8 | 2489 | 65480 |
| deu-spa | newstest2011 | 0.57133 | 31.3 | 3003 | 79476 |
| deu-spa | newstest2012 | 0.58119 | 32.6 | 3003 | 79006 |
| deu-spa | newstest2013 | 0.57559 | 32.4 | 3000 | 70528 |
## Citation Information
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 8b9f0b0
* port time: Sat Aug 13 00:06:19 EEST 2022
* port machine: LM0-400-22516.local
|
Helsinki-NLP/opus-mt-tc-big-fa-itc
|
Helsinki-NLP
| 2023-10-10T11:01:36Z | 120 | 1 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"fa",
"fr",
"pt",
"ro",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-08-12T17:02:21Z |
---
language:
- fa
- fr
- pt
- ro
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-fa-itc
results:
- task:
name: Translation fas-fra
type: translation
args: fas-fra
dataset:
name: flores101-devtest
type: flores_101
args: fas fra devtest
metrics:
- name: BLEU
type: bleu
value: 28.9
- name: chr-F
type: chrf
value: 0.55883
- task:
name: Translation fas-ita
type: translation
args: fas-ita
dataset:
name: flores101-devtest
type: flores_101
args: fas ita devtest
metrics:
- name: BLEU
type: bleu
value: 19.7
- name: chr-F
type: chrf
value: 0.49512
- task:
name: Translation fas-por
type: translation
args: fas-por
dataset:
name: flores101-devtest
type: flores_101
args: fas por devtest
metrics:
- name: BLEU
type: bleu
value: 27.6
- name: chr-F
type: chrf
value: 0.54829
- task:
name: Translation fas-ron
type: translation
args: fas-ron
dataset:
name: flores101-devtest
type: flores_101
args: fas ron devtest
metrics:
- name: BLEU
type: bleu
value: 19.7
- name: chr-F
type: chrf
value: 0.48821
- task:
name: Translation fas-spa
type: translation
args: fas-spa
dataset:
name: flores101-devtest
type: flores_101
args: fas spa devtest
metrics:
- name: BLEU
type: bleu
value: 19.4
- name: chr-F
type: chrf
value: 0.47722
- task:
name: Translation fas-fra
type: translation
args: fas-fra
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: fas-fra
metrics:
- name: BLEU
type: bleu
value: 37.5
- name: chr-F
type: chrf
value: 0.57949
---
# opus-mt-tc-big-fa-itc
## Table of Contents
- [Model Details](#model-details)
- [Uses](#uses)
- [Risks, Limitations and Biases](#risks-limitations-and-biases)
- [How to Get Started With the Model](#how-to-get-started-with-the-model)
- [Training](#training)
- [Evaluation](#evaluation)
- [Citation Information](#citation-information)
- [Acknowledgements](#acknowledgements)
## Model Details
Neural machine translation model for translating from Persian (fa) to Italic languages (itc).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
**Model Description:**
- **Developed by:** Language Technology Research Group at the University of Helsinki
- **Model Type:** Translation (transformer-big)
- **Release**: 2022-07-23
- **License:** CC-BY-4.0
- **Language(s):**
- Source Language(s): fas
- Target Language(s): fra ita por ron spa
- Language Pair(s): fas-fra fas-por fas-ron
- Valid Target Language Labels: >>acf<< >>aoa<< >>arg<< >>ast<< >>cat<< >>cbk<< >>ccd<< >>cks<< >>cos<< >>cri<< >>crs<< >>dlm<< >>drc<< >>egl<< >>ext<< >>fab<< >>fax<< >>fra<< >>frc<< >>frm<< >>fro<< >>frp<< >>fur<< >>gcf<< >>gcr<< >>glg<< >>hat<< >>idb<< >>ist<< >>ita<< >>itk<< >>kea<< >>kmv<< >>lad<< >>lad_Latn<< >>lat<< >>lat_Latn<< >>lij<< >>lld<< >>lmo<< >>lou<< >>mcm<< >>mfe<< >>mol<< >>mwl<< >>mxi<< >>mzs<< >>nap<< >>nrf<< >>oci<< >>osc<< >>osp<< >>pap<< >>pcd<< >>pln<< >>pms<< >>pob<< >>por<< >>pov<< >>pre<< >>pro<< >>qbb<< >>qhr<< >>rcf<< >>rgn<< >>roh<< >>ron<< >>ruo<< >>rup<< >>ruq<< >>scf<< >>scn<< >>sdc<< >>sdn<< >>spa<< >>spq<< >>spx<< >>src<< >>srd<< >>sro<< >>tmg<< >>tvy<< >>vec<< >>vkp<< >>wln<< >>xfa<< >>xum<<
- **Original Model**: [opusTCv20210807_transformer-big_2022-07-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/fas-itc/opusTCv20210807_transformer-big_2022-07-23.zip)
- **Resources for more information:**
- [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
- More information about released models for this language pair: [OPUS-MT fas-itc README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/fas-itc/README.md)
- [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian)
- [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/
This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>fra<<`
## Uses
This model can be used for translation and text-to-text generation.
## Risks, Limitations and Biases
**CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain content that is disturbing, offensive, and can propagate historical and current stereotypes.**
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
## How to Get Started With the Model
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
">>lad<< اسلام زیباست.",
">>spa<< ورود به کتابخانه رایگان است."
]
model_name = "pytorch-models/opus-mt-tc-big-fa-itc"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# O Islam é lindo.
# La entrada a la biblioteca es gratuita.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-fa-itc")
print(pipe(">>lad<< اسلام زیباست."))
# expected output: O Islam é lindo.
```
## Training
- **Data**: opusTCv20210807 ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
- **Pre-processing**: SentencePiece (spm32k,spm32k)
- **Model Type:** transformer-big
- **Original MarianNMT Model**: [opusTCv20210807_transformer-big_2022-07-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/fas-itc/opusTCv20210807_transformer-big_2022-07-23.zip)
- **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
## Evaluation
* test set translations: [opusTCv20210807_transformer-big_2022-07-23.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/fas-itc/opusTCv20210807_transformer-big_2022-07-23.test.txt)
* test set scores: [opusTCv20210807_transformer-big_2022-07-23.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/fas-itc/opusTCv20210807_transformer-big_2022-07-23.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| fas-fra | tatoeba-test-v2021-08-07 | 0.57949 | 37.5 | 376 | 3377 |
| fas-fra | flores101-devtest | 0.55883 | 28.9 | 1012 | 28343 |
| fas-ita | flores101-devtest | 0.49512 | 19.7 | 1012 | 27306 |
| fas-por | flores101-devtest | 0.54829 | 27.6 | 1012 | 26519 |
| fas-ron | flores101-devtest | 0.48821 | 19.7 | 1012 | 26799 |
| fas-spa | flores101-devtest | 0.47722 | 19.4 | 1012 | 29199 |
## Citation Information
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 8b9f0b0
* port time: Sat Aug 13 00:08:53 EEST 2022
* port machine: LM0-400-22516.local
|
Helsinki-NLP/opus-mt-tc-big-fa-gmq
|
Helsinki-NLP
| 2023-10-10T10:58:23Z | 119 | 1 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"da",
"fa",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-08-12T17:17:15Z |
---
language:
- da
- fa
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-fa-gmq
results:
- task:
name: Translation fas-dan
type: translation
args: fas-dan
dataset:
name: flores101-devtest
type: flores_101
args: fas dan devtest
metrics:
- name: BLEU
type: bleu
value: 22.7
- name: chr-F
type: chrf
value: 0.50857
---
# opus-mt-tc-big-fa-gmq
## Table of Contents
- [Model Details](#model-details)
- [Uses](#uses)
- [Risks, Limitations and Biases](#risks-limitations-and-biases)
- [How to Get Started With the Model](#how-to-get-started-with-the-model)
- [Training](#training)
- [Evaluation](#evaluation)
- [Citation Information](#citation-information)
- [Acknowledgements](#acknowledgements)
## Model Details
Neural machine translation model for translating from Persian (fa) to North Germanic languages (gmq).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
**Model Description:**
- **Developed by:** Language Technology Research Group at the University of Helsinki
- **Model Type:** Translation (transformer-big)
- **Release**: 2022-07-23
- **License:** CC-BY-4.0
- **Language(s):**
- Source Language(s): fas
- Target Language(s): dan
- Language Pair(s): fas-dan
- Valid Target Language Labels:
- **Original Model**: [opusTCv20210807_transformer-big_2022-07-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/fas-gmq/opusTCv20210807_transformer-big_2022-07-23.zip)
- **Resources for more information:**
- [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
- More information about released models for this language pair: [OPUS-MT fas-gmq README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/fas-gmq/README.md)
- [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian)
- [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/
This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>><<`
## Uses
This model can be used for translation and text-to-text generation.
## Risks, Limitations and Biases
**CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain content that is disturbing, offensive, and can propagate historical and current stereotypes.**
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
## How to Get Started With the Model
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
"از سوسک میترسم.",
"از سوسک میترسم."
]
model_name = "pytorch-models/opus-mt-tc-big-fa-gmq"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# Jeg er bange for kakerlakker.
# Jeg er bange for kakerlakker.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-fa-gmq")
print(pipe("از سوسک میترسم."))
# expected output: Jeg er bange for kakerlakker.
```
## Training
- **Data**: opusTCv20210807 ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
- **Pre-processing**: SentencePiece (spm32k,spm32k)
- **Model Type:** transformer-big
- **Original MarianNMT Model**: [opusTCv20210807_transformer-big_2022-07-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/fas-gmq/opusTCv20210807_transformer-big_2022-07-23.zip)
- **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
## Evaluation
* test set translations: [opusTCv20210807_transformer-big_2022-07-23.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/fas-gmq/opusTCv20210807_transformer-big_2022-07-23.test.txt)
* test set scores: [opusTCv20210807_transformer-big_2022-07-23.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/fas-gmq/opusTCv20210807_transformer-big_2022-07-23.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| fas-dan | flores101-devtest | 0.50857 | 22.7 | 1012 | 24638 |
## Citation Information
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 8b9f0b0
* port time: Sat Aug 13 00:09:16 EEST 2022
* port machine: LM0-400-22516.local
|
Helsinki-NLP/opus-mt-tc-big-zls-de
|
Helsinki-NLP
| 2023-10-10T10:57:17Z | 142 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"bg",
"de",
"hr",
"mk",
"sh",
"sl",
"sr",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-08-12T14:51:09Z |
---
language:
- bg
- de
- hr
- mk
- sh
- sl
- sr
language_bcp47:
- sr_Cyrl
- sr_Latn
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-zls-de
results:
- task:
name: Translation bul-deu
type: translation
args: bul-deu
dataset:
name: flores101-devtest
type: flores_101
args: bul deu devtest
metrics:
- name: BLEU
type: bleu
value: 28.4
- name: chr-F
type: chrf
value: 0.57688
- task:
name: Translation hrv-deu
type: translation
args: hrv-deu
dataset:
name: flores101-devtest
type: flores_101
args: hrv deu devtest
metrics:
- name: BLEU
type: bleu
value: 27.4
- name: chr-F
type: chrf
value: 0.56674
- task:
name: Translation mkd-deu
type: translation
args: mkd-deu
dataset:
name: flores101-devtest
type: flores_101
args: mkd deu devtest
metrics:
- name: BLEU
type: bleu
value: 29.3
- name: chr-F
type: chrf
value: 0.57688
- task:
name: Translation slv-deu
type: translation
args: slv-deu
dataset:
name: flores101-devtest
type: flores_101
args: slv deu devtest
metrics:
- name: BLEU
type: bleu
value: 26.7
- name: chr-F
type: chrf
value: 0.56258
- task:
name: Translation srp_Cyrl-deu
type: translation
args: srp_Cyrl-deu
dataset:
name: flores101-devtest
type: flores_101
args: srp_Cyrl deu devtest
metrics:
- name: BLEU
type: bleu
value: 30.7
- name: chr-F
type: chrf
value: 0.59271
- task:
name: Translation bul-deu
type: translation
args: bul-deu
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: bul-deu
metrics:
- name: BLEU
type: bleu
value: 54.5
- name: chr-F
type: chrf
value: 0.71220
- task:
name: Translation hbs-deu
type: translation
args: hbs-deu
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: hbs-deu
metrics:
- name: BLEU
type: bleu
value: 54.8
- name: chr-F
type: chrf
value: 0.71283
- task:
name: Translation hrv-deu
type: translation
args: hrv-deu
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: hrv-deu
metrics:
- name: BLEU
type: bleu
value: 53.1
- name: chr-F
type: chrf
value: 0.69448
- task:
name: Translation slv-deu
type: translation
args: slv-deu
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: slv-deu
metrics:
- name: BLEU
type: bleu
value: 21.1
- name: chr-F
type: chrf
value: 0.36339
- task:
name: Translation srp_Latn-deu
type: translation
args: srp_Latn-deu
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: srp_Latn-deu
metrics:
- name: BLEU
type: bleu
value: 56.0
- name: chr-F
type: chrf
value: 0.72489
---
# opus-mt-tc-big-zls-de
## Table of Contents
- [Model Details](#model-details)
- [Uses](#uses)
- [Risks, Limitations and Biases](#risks-limitations-and-biases)
- [How to Get Started With the Model](#how-to-get-started-with-the-model)
- [Training](#training)
- [Evaluation](#evaluation)
- [Citation Information](#citation-information)
- [Acknowledgements](#acknowledgements)
## Model Details
Neural machine translation model for translating from South Slavic languages (zls) to German (de).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
**Model Description:**
- **Developed by:** Language Technology Research Group at the University of Helsinki
- **Model Type:** Translation (transformer-big)
- **Release**: 2022-07-26
- **License:** CC-BY-4.0
- **Language(s):**
- Source Language(s): bos_Latn bul hbs hrv mkd slv srp_Cyrl srp_Latn
- Target Language(s): deu
- Language Pair(s): bul-deu hbs-deu hrv-deu mkd-deu slv-deu srp_Cyrl-deu srp_Latn-deu
- Valid Target Language Labels:
- **Original Model**: [opusTCv20210807_transformer-big_2022-07-26.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/zls-deu/opusTCv20210807_transformer-big_2022-07-26.zip)
- **Resources for more information:**
- [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
- More information about released models for this language pair: [OPUS-MT zls-deu README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/zls-deu/README.md)
- [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian)
- [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/
## Uses
This model can be used for translation and text-to-text generation.
## Risks, Limitations and Biases
**CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain content that is disturbing, offensive, and can propagate historical and current stereotypes.**
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
## How to Get Started With the Model
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
"Jesi li ti student?",
"Dve stvari deca treba da dobiju od svojih roditelja: korene i krila."
]
model_name = "pytorch-models/opus-mt-tc-big-zls-de"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# Sind Sie Student?
# Zwei Dinge sollten Kinder von ihren Eltern bekommen: Wurzeln und Flügel.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-zls-de")
print(pipe("Jesi li ti student?"))
# expected output: Sind Sie Student?
```
## Training
- **Data**: opusTCv20210807 ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
- **Pre-processing**: SentencePiece (spm32k,spm32k)
- **Model Type:** transformer-big
- **Original MarianNMT Model**: [opusTCv20210807_transformer-big_2022-07-26.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/zls-deu/opusTCv20210807_transformer-big_2022-07-26.zip)
- **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
## Evaluation
* test set translations: [opusTCv20210807_transformer-big_2022-07-26.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/zls-deu/opusTCv20210807_transformer-big_2022-07-26.test.txt)
* test set scores: [opusTCv20210807_transformer-big_2022-07-26.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/zls-deu/opusTCv20210807_transformer-big_2022-07-26.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| bul-deu | tatoeba-test-v2021-08-07 | 0.71220 | 54.5 | 314 | 2224 |
| hbs-deu | tatoeba-test-v2021-08-07 | 0.71283 | 54.8 | 1959 | 15559 |
| hrv-deu | tatoeba-test-v2021-08-07 | 0.69448 | 53.1 | 782 | 5734 |
| slv-deu | tatoeba-test-v2021-08-07 | 0.36339 | 21.1 | 492 | 3003 |
| srp_Latn-deu | tatoeba-test-v2021-08-07 | 0.72489 | 56.0 | 986 | 8500 |
| bul-deu | flores101-devtest | 0.57688 | 28.4 | 1012 | 25094 |
| hrv-deu | flores101-devtest | 0.56674 | 27.4 | 1012 | 25094 |
| mkd-deu | flores101-devtest | 0.57688 | 29.3 | 1012 | 25094 |
| slv-deu | flores101-devtest | 0.56258 | 26.7 | 1012 | 25094 |
| srp_Cyrl-deu | flores101-devtest | 0.59271 | 30.7 | 1012 | 25094 |
## Citation Information
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 8b9f0b0
* port time: Sat Aug 13 00:05:30 EEST 2022
* port machine: LM0-400-22516.local
|
Subsets and Splits
Filtered Qwen2.5 Distill Models
Identifies specific configurations of models by filtering cards that contain 'distill', 'qwen2.5', '7b' while excluding certain base models and incorrect model ID patterns, uncovering unique model variants.
Filtered Model Cards Count
Finds the count of entries with specific card details that include 'distill', 'qwen2.5', '7b' but exclude certain base models, revealing valuable insights about the dataset's content distribution.
Filtered Distill Qwen 7B Models
Filters for specific card entries containing 'distill', 'qwen', and '7b', excluding certain strings and patterns, to identify relevant model configurations.
Filtered Qwen-7b Model Cards
The query performs a detailed filtering based on specific keywords and excludes certain entries, which could be useful for identifying a specific subset of cards but does not provide deeper insights or trends.
Filtered Qwen 7B Model Cards
The query filters for specific terms related to "distilled" or "distill", "qwen", and "7b" in the 'card' column but excludes certain base models, providing a limited set of entries for further inspection.
Qwen 7B Distilled Models
The query provides a basic filtering of records to find specific card names that include keywords related to distilled Qwen 7b models, excluding a particular base model, which gives limited insight but helps in focusing on relevant entries.
Qwen 7B Distilled Model Cards
The query filters data based on specific keywords in the modelId and card fields, providing limited insight primarily useful for locating specific entries rather than revealing broad patterns or trends.
Qwen 7B Distilled Models
Finds all entries containing the terms 'distilled', 'qwen', and '7b' in a case-insensitive manner, providing a filtered set of records but without deeper analysis.
Distilled Qwen 7B Models
The query filters for specific model IDs containing 'distilled', 'qwen', and '7b', providing a basic retrieval of relevant entries but without deeper analysis or insight.
Filtered Model Cards with Distill Qwen2.
Filters and retrieves records containing specific keywords in the card description while excluding certain phrases, providing a basic count of relevant entries.
Filtered Model Cards with Distill Qwen 7
The query filters specific variations of card descriptions containing 'distill', 'qwen', and '7b' while excluding a particular base model, providing limited but specific data retrieval.
Distill Qwen 7B Model Cards
The query filters and retrieves rows where the 'card' column contains specific keywords ('distill', 'qwen', and '7b'), providing a basic filter result that can help in identifying specific entries.