modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-08-29 00:38:39
| 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 00:38:28
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
bdelsolar/videomae-base-finetuned-ucf101-subset
|
bdelsolar
| 2023-10-25T22:34:49Z | 60 | 0 |
transformers
|
[
"transformers",
"pytorch",
"videomae",
"video-classification",
"generated_from_trainer",
"base_model:MCG-NJU/videomae-base",
"base_model:finetune:MCG-NJU/videomae-base",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] |
video-classification
| 2023-10-25T22:04:00Z |
---
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-ucf101-subset
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. -->
# videomae-base-finetuned-ucf101-subset
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6323
- Accuracy: 0.5833
## 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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 80
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.9651 | 0.25 | 20 | 1.2146 | 0.2609 |
| 0.8901 | 1.25 | 40 | 0.7821 | 0.6522 |
| 0.6086 | 2.25 | 60 | 0.6491 | 0.7391 |
| 0.4141 | 3.25 | 80 | 0.4565 | 0.8261 |
### Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
|
dellanio/mistral_b_finance_finetuned_test
|
dellanio
| 2023-10-25T22:34:47Z | 0 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:adapter:mistralai/Mistral-7B-v0.1",
"region:us"
] | null | 2023-10-25T22:20:45Z |
---
library_name: peft
base_model: mistralai/Mistral-7B-v0.1
---
# 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: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.6.0.dev0
|
lemonilia/AshhLimaRP-Mistral-7B
|
lemonilia
| 2023-10-25T22:32:58Z | 23 | 12 |
transformers
|
[
"transformers",
"pytorch",
"gguf",
"mistral",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-25T17:32:08Z |
---
license: apache-2.0
---
# AshhLimaRP-Mistral-7B (Alpaca, v1)
This is a version of LimaRP with 2000 training samples _up to_ about 9k tokens length
finetuned on [Ashhwriter-Mistral-7B](https://huggingface.co/lemonilia/Ashhwriter-Mistral-7B).
LimaRP is a longform-oriented, novel-style roleplaying chat model intended to replicate the experience
of 1-on-1 roleplay on Internet forums. Short-form, IRC/Discord-style RP (aka "Markdown format")
is not supported. The model does not include instruction tuning, only manually picked and
slightly edited RP conversations with persona and scenario data.
Ashhwriter, the base, is a model entirely finetuned on human-written lewd stories.
## Available versions
- Float16 HF weights
- LoRA Adapter ([adapter_config.json](https://huggingface.co/lemonilia/AshhLimaRP-Mistral-7B/resolve/main/adapter_config.json) and [adapter_model.bin](https://huggingface.co/lemonilia/AshhLimaRP-Mistral-7B/resolve/main/adapter_model.bin))
- [4bit AWQ](https://huggingface.co/lemonilia/AshhLimaRP-Mistral-7B/tree/main/AWQ)
- [Q4_K_M GGUF](https://huggingface.co/lemonilia/AshhLimaRP-Mistral-7B/resolve/main/AshhLimaRP-Mistral-7B.Q4_K_M.gguf)
- [Q6_K GGUF](https://huggingface.co/lemonilia/AshhLimaRP-Mistral-7B/resolve/main/AshhLimaRP-Mistral-7B.Q6_K.gguf)
## Prompt format
[Extended Alpaca format](https://github.com/tatsu-lab/stanford_alpaca),
with `### Instruction:`, `### Input:` immediately preceding user inputs and `### Response:`
immediately preceding model outputs. While Alpaca wasn't originally intended for multi-turn
responses, in practice this is not a problem; the format follows a pattern already used by
other models.
```
### Instruction:
Character's Persona: {bot character description}
User's Persona: {user character description}
Scenario: {what happens in the story}
Play the role of Character. You must engage in a roleplaying chat with User below this line. Do not write dialogues and narration for User.
### Input:
User: {utterance}
### Response:
Character: {utterance}
### Input
User: {utterance}
### Response:
Character: {utterance}
(etc.)
```
You should:
- Replace all text in curly braces (curly braces included) with your own text.
- Replace `User` and `Character` with appropriate names.
### Message length control
Inspired by the previously named "Roleplay" preset in SillyTavern, with this
version of LimaRP it is possible to append a length modifier to the response instruction
sequence, like this:
```
### Input
User: {utterance}
### Response: (length = medium)
Character: {utterance}
```
This has an immediately noticeable effect on bot responses. The lengths using during training are:
`micro`, `tiny`, `short`, `medium`, `long`, `massive`, `huge`, `enormous`, `humongous`, `unlimited`.
**The recommended starting length is medium**. Keep in mind that the AI can ramble or impersonate
the user with very long messages.
The length control effect is reproducible, but the messages will not necessarily follow
lengths very precisely, rather follow certain ranges on average, as seen in this table
with data from tests made with one reply at the beginning of the conversation:
Response length control appears to work well also deep into the conversation. **By omitting
the modifier, the model will choose the most appropriate response length** (although it might
not necessarily be what the user desires).
## Suggested settings
You can follow these instruction format settings in SillyTavern. Replace `medium` with
your desired response length:
## Text generation settings
These settings could be a good general starting point:
- TFS = 0.90
- Temperature = 0.70
- Repetition penalty = ~1.11
- Repetition penalty range = ~2048
- top-k = 0 (disabled)
- top-p = 1 (disabled)
## Training procedure
[Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) was used for training
on 2x NVidia A40 GPUs.
The A40 GPUs have been graciously provided by [Arc Compute](https://www.arccompute.io/).
### Training hyperparameters
A lower learning rate than usual was employed. Due to an unforeseen issue the training
was cut short and as a result 3 epochs were trained instead of the planned 4. Using 2 GPUs,
the effective global batch size would have been 16.
Training was continued from the most recent LoRA adapter from Ashhwriter, using the same
LoRA R and LoRA alpha.
- lora_model_dir: /home/anon/bin/axolotl/OUT_mistral-stories/checkpoint-6000/
- learning_rate: 0.00005
- lr_scheduler: cosine
- noisy_embedding_alpha: 3.5
- num_epochs: 4
- sequence_len: 8750
- lora_r: 256
- lora_alpha: 16
- lora_dropout: 0.05
- lora_target_linear: True
- bf16: True
- fp16: false
- tf32: True
- load_in_8bit: True
- adapter: lora
- micro_batch_size: 2
- optimizer: adamw_bnb_8bit
- warmup_steps: 10
- optimizer: adamw_torch
- flash_attention: true
- sample_packing: true
- pad_to_sequence_len: true
### Loss graphs
Values are higher than typical because the training is performed on the entire
sample, similar to unsupervised finetuning.
#### Train loss
#### Eval loss
|
Anis-Bouhamadouche/distilbert-base-uncased-finetuned-emotion
|
Anis-Bouhamadouche
| 2023-10-25T22:32:39Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"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
| 2023-08-04T10:05:01Z |
---
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: 0.925
- name: F1
type: f1
value: 0.9249367490708449
---
<!-- 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: 0.2105
- Accuracy: 0.925
- F1: 0.9249
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8223 | 1.0 | 250 | 0.3098 | 0.9085 | 0.9076 |
| 0.2431 | 2.0 | 500 | 0.2105 | 0.925 | 0.9249 |
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.3
- Tokenizers 0.13.3
|
MBZUAI-LLM/GBLM-Pruner-LLaMA-2-70B
|
MBZUAI-LLM
| 2023-10-25T22:28:33Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-25T16:26:44Z |
# GBLM-Pruner-LLaMA-2-70B Model Card
## Model details
**Model type:**
GBLM-Pruner-LLaMA-2-70B is an open-source compressed model obtained by unstructured pruning of 50 percent of the weights of the LLaMA-2-70B model.
## License
Llama 2 is licensed under the LLAMA 2 Community License,
Copyright (c) Meta Platforms, Inc. All Rights Reserved.
**Where to send questions or comments about the model:**
https://github.com/RocktimJyotiDas/GBLM-Pruner/issues
|
smitbutle/first-test-layoutlmv3-finetuned-invoice
|
smitbutle
| 2023-10-25T22:26:08Z | 76 | 0 |
transformers
|
[
"transformers",
"pytorch",
"layoutlmv3",
"token-classification",
"generated_from_trainer",
"dataset:generated",
"base_model:microsoft/layoutlmv3-base",
"base_model:finetune:microsoft/layoutlmv3-base",
"license:cc-by-nc-sa-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-10-25T14:09:15Z |
---
license: cc-by-nc-sa-4.0
base_model: microsoft/layoutlmv3-base
tags:
- generated_from_trainer
datasets:
- generated
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: layoutlmv3-finetuned-invoice
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: generated
type: generated
config: sroie
split: test
args: sroie
metrics:
- name: Precision
type: precision
value: 0.010438413361169102
- name: Recall
type: recall
value: 0.02028397565922921
- name: F1
type: f1
value: 0.013783597518952447
- name: Accuracy
type: accuracy
value: 0.6785338108278913
---
<!-- 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. -->
# layoutlmv3-finetuned-invoice
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the generated dataset.
It achieves the following results on the evaluation set:
- Loss: 2.1320
- Precision: 0.0104
- Recall: 0.0203
- F1: 0.0138
- Accuracy: 0.6785
## 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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log | 0.01 | 1 | 2.3858 | 0.0114 | 0.0649 | 0.0194 | 0.1904 |
| No log | 0.02 | 2 | 2.2795 | 0.0108 | 0.0527 | 0.0180 | 0.3240 |
| No log | 0.03 | 3 | 2.2072 | 0.0131 | 0.0446 | 0.0203 | 0.5155 |
| No log | 0.04 | 4 | 2.1575 | 0.0103 | 0.0243 | 0.0145 | 0.6345 |
| No log | 0.05 | 5 | 2.1320 | 0.0104 | 0.0203 | 0.0138 | 0.6785 |
### Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1
|
Buseak/spellcorrector_2510_v15_canine-s
|
Buseak
| 2023-10-25T22:23:40Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"canine",
"token-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-10-25T19:37:25Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: spellcorrector_2510_v15_canine-s
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. -->
# spellcorrector_2510_v15_canine-s
This model is a fine-tuned version of [google/canine-s](https://huggingface.co/google/canine-s) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1599
- Precision: 0.9768
- Recall: 0.9820
- F1: 0.9794
- Accuracy: 0.9786
## 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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.1921 | 1.0 | 1951 | 0.1677 | 0.9417 | 0.9774 | 0.9592 | 0.9650 |
| 0.1627 | 2.0 | 3902 | 0.1436 | 0.9500 | 0.9779 | 0.9637 | 0.9674 |
| 0.1395 | 3.0 | 5853 | 0.1266 | 0.9545 | 0.9788 | 0.9665 | 0.9697 |
| 0.1266 | 4.0 | 7804 | 0.1172 | 0.9661 | 0.9698 | 0.9680 | 0.9702 |
| 0.1105 | 5.0 | 9755 | 0.1064 | 0.9669 | 0.9766 | 0.9717 | 0.9731 |
| 0.1011 | 6.0 | 11706 | 0.1011 | 0.9705 | 0.9757 | 0.9731 | 0.9745 |
| 0.0933 | 7.0 | 13657 | 0.0987 | 0.9718 | 0.9766 | 0.9742 | 0.9752 |
| 0.0851 | 8.0 | 15608 | 0.0973 | 0.9715 | 0.9787 | 0.9751 | 0.9755 |
| 0.0758 | 9.0 | 17559 | 0.0998 | 0.9734 | 0.9765 | 0.9750 | 0.9756 |
| 0.069 | 10.0 | 19510 | 0.0993 | 0.9732 | 0.9810 | 0.9771 | 0.9764 |
| 0.0635 | 11.0 | 21461 | 0.1055 | 0.9739 | 0.9808 | 0.9773 | 0.9766 |
| 0.0576 | 12.0 | 23412 | 0.1072 | 0.9751 | 0.9794 | 0.9772 | 0.9765 |
| 0.0493 | 13.0 | 25363 | 0.1078 | 0.9754 | 0.9807 | 0.9780 | 0.9776 |
| 0.0469 | 14.0 | 27314 | 0.1145 | 0.9757 | 0.9815 | 0.9786 | 0.9777 |
| 0.0409 | 15.0 | 29265 | 0.1174 | 0.9758 | 0.9806 | 0.9782 | 0.9764 |
| 0.0373 | 16.0 | 31216 | 0.1218 | 0.9763 | 0.9801 | 0.9782 | 0.9769 |
| 0.0338 | 17.0 | 33167 | 0.1239 | 0.9768 | 0.9805 | 0.9787 | 0.9773 |
| 0.0326 | 18.0 | 35118 | 0.1312 | 0.9770 | 0.9787 | 0.9779 | 0.9773 |
| 0.029 | 19.0 | 37069 | 0.1320 | 0.9764 | 0.9809 | 0.9786 | 0.9773 |
| 0.0245 | 20.0 | 39020 | 0.1376 | 0.9767 | 0.9802 | 0.9784 | 0.9777 |
| 0.0231 | 21.0 | 40971 | 0.1382 | 0.9763 | 0.9814 | 0.9788 | 0.9776 |
| 0.0212 | 22.0 | 42922 | 0.1473 | 0.9762 | 0.9826 | 0.9794 | 0.9780 |
| 0.0201 | 23.0 | 44873 | 0.1485 | 0.9762 | 0.9816 | 0.9789 | 0.9778 |
| 0.0187 | 24.0 | 46824 | 0.1494 | 0.9763 | 0.9818 | 0.9790 | 0.9775 |
| 0.0166 | 25.0 | 48775 | 0.1502 | 0.9769 | 0.9813 | 0.9791 | 0.9781 |
| 0.0163 | 26.0 | 50726 | 0.1560 | 0.9769 | 0.9813 | 0.9791 | 0.9785 |
| 0.0149 | 27.0 | 52677 | 0.1556 | 0.9764 | 0.9824 | 0.9794 | 0.9784 |
| 0.0143 | 28.0 | 54628 | 0.1587 | 0.9767 | 0.9818 | 0.9792 | 0.9784 |
| 0.0126 | 29.0 | 56579 | 0.1589 | 0.9766 | 0.9821 | 0.9793 | 0.9784 |
| 0.013 | 30.0 | 58530 | 0.1599 | 0.9768 | 0.9820 | 0.9794 | 0.9786 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.13.3
|
cognisys/sparrow-1.1b-chat-alpha
|
cognisys
| 2023-10-25T22:22:57Z | 4 | 1 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"dataset:stingning/ultrachat",
"dataset:OpenAssistant/oasst1",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-10-24T21:04:04Z |
---
model-index:
- name: sparrow-1.1b-chat-alpha
results: []
license: apache-2.0
inference: false
datasets:
- stingning/ultrachat
- OpenAssistant/oasst1
language:
- en
---
<img src="https://huggingface.co/cognisys/sparrow-1.1b-chat-alpha/resolve/main/thumbnail.png" alt="Sparrow Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
# Model Card for Sparrow 1.1B Chat Alpha
The Sparrow series comprises language models designed to serve as helpful assistants and as a base model for domain-specific fine tuning. Sparrow-1.1B-Chat-α is the initial model in this series and represents a fine-tuned iteration of PY007/TinyLlama-1.1B-intermediate-step-480k-1T. It was trained on a combination of publicly accessible and synthetic datasets.
## Model Description:
- Model Type: Sparrow-7B-α is a 1.1B parameter model, that has been fine-tuned using a mixture of publicly available and synthetic datasets.
- Supported Languages (NLP): The primary language is English.
- License/Warranty: The model is available under the Apache 2.0 license and comes with no warranty or gurantees of any kind.
- Fine-tuned from: PY007/TinyLlama-1.1B-intermediate-step-480k-1T
Prompt Template:
```
<s>[INST] <<SYS>>
{{ system_prompt }}
<</SYS>>
{{ user_message }} [/INST]
```
|
TKDKid1000/pythia-2.8b-deduped-GPTQ
|
TKDKid1000
| 2023-10-25T22:19:08Z | 7 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt_neox",
"text-generation",
"GPTQ",
"en",
"dataset:c4",
"dataset:EleutherAI/the_pile_deduplicated",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"gptq",
"region:us"
] |
text-generation
| 2023-10-25T22:06:30Z |
---
license: mit
datasets:
- c4
- EleutherAI/the_pile_deduplicated
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- GPTQ
---
# Model Card for TKDKid1000/pythia-2.8b-deduped-GPTQ
A quantized version of [EleutherAI/pythia-2.8b-deduped](https://huggingface.co/EleutherAI/pythia-2.8b-deduped) using GPTQ.
## Model Details
### Model Description
General text generation model that is intended to be fine tuned on a downstream task for running on small devices.
Refer to the pythia-2.8b-deduped model card for more information.
- **Developed by:** EleutherAI
- **Model type:** GPT-NeoX
- **Language (NLP):** English
- **License:** MIT
- **Finetuned from model:** [EleutherAI/pythia-2.8b-deduped](https://huggingface.co/EleutherAI/pythia-2.8b-deduped)
|
LarryAIDraw/Char-HonkaiSR-Jingliu
|
LarryAIDraw
| 2023-10-25T22:17:09Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-07T14:03:11Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/141561/jingliu-or-honkaistar-rail
|
LarryAIDraw/PriscillaBarielle1V
|
LarryAIDraw
| 2023-10-25T22:15:14Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-10-25T22:04:52Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/176789/priscilla-barielle-rezero
|
LarryAIDraw/mikado_ryouko_v1
|
LarryAIDraw
| 2023-10-25T22:14:49Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-10-25T22:04:11Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/176765/mikado-ryouko-to-love-ru
|
LarryAIDraw/asuna_ichinose_v1
|
LarryAIDraw
| 2023-10-25T22:14:13Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-10-25T22:03:22Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/175924/asuna-ichinose-or-blue-archive-or-3-outfits
|
budhwant/blip2-opt-2.7b-imagecaptions-adapters
|
budhwant
| 2023-10-25T22:13:32Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-25T06:56:10Z |
---
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 0.5.0
|
shunnaidder/ppo-LunarLander-v2
|
shunnaidder
| 2023-10-25T22:12:23Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-24T13:07:54Z |
---
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: 268.42 +/- 18.31
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).
# CHECK COLAB:
https://colab.research.google.com/github/huggingface/deep-rl-class/blob/master/notebooks/unit1/unit1.ipynb
```python
!pip install shimmy
from huggingface_sb3 import load_from_hub
repo_id = "shunnaidder/ppo-LunarLander-v2" # The repo_id
filename = "ppo-LunarLander-v2-small.zip" # The model filename.zip
# When the model was trained on Python 3.8 the pickle protocol is 5
# But Python 3.6, 3.7 use protocol 4
# In order to get compatibility we need to:
# 1. Install pickle5 (we done it at the beginning of the colab)
# 2. Create a custom empty object we pass as parameter to PPO.load()
custom_objects = {
"learning_rate": 0.0,
"lr_schedule": lambda _: 0.0,
"clip_range": lambda _: 0.0,
}
checkpoint = load_from_hub(repo_id, filename)
model = PPO.load(checkpoint, custom_objects=custom_objects, print_system_info=True)
#@title
eval_env = Monitor(gym.make("LunarLander-v2"))
mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)
print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")
...
```
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
schubertcarvalho/distilbert-base-uncased-finetuned-imdb
|
schubertcarvalho
| 2023-10-25T22:11:38Z | 96 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"fill-mask",
"generated_from_trainer",
"dataset:imdb",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-25T21:12:38Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- imdb
model-index:
- name: distilbert-base-uncased-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-uncased-finetuned-imdb
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
It achieves the following results on the evaluation set:
- Loss: 2.3435
## 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: 256
- eval_batch_size: 256
- 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 |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 240 | 2.3969 |
| No log | 2.0 | 480 | 2.3569 |
| No log | 3.0 | 720 | 2.3435 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0a0+29c30b1
- Datasets 2.14.5
- Tokenizers 0.14.1
|
AshtakaOOf/Amedira
|
AshtakaOOf
| 2023-10-25T22:10:56Z | 0 | 29 |
safetensors
|
[
"safetensors",
"art",
"anime",
"stable-diffusion",
"text-to-image",
"en",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2023-06-20T06:51:46Z |
---
license: creativeml-openrail-m
language:
- en
pipeline_tag: text-to-image
tags:
- art
- anime
- stable-diffusion
library_name: safetensors
---
<style>
.custom-table {
table-layout: fixed;
width: 100%;
border-collapse: collapse;
margin-top: 2em;
}
.custom-table td {
width: 50%;
vertical-align: top;
padding: 10px;
box-shadow: 0px 0px 10px 0px rgba(0,0,0,0.15);
}
.custom-image {
width: 100%;
height: auto;
object-fit: cover;
border-radius: 7px;
transition: transform .7s;
margin-bottom: 1em;
}
.custom-image:hover {
transform: scale(1.30);
}
stolen from Linaqruf readme for Animagine XL
</style>
<p align="center", style="font-size: 3.6rem; font-weight: bold">🎑 ~ Amedira ~ 🎏</p>
<p align="center", style="font-size: 1.2rem; ">Go check out <strong><a href="https://huggingface.co/AshtakaOOf/Ahnn">Ahnn</a></strong> which my other model</p>
<hr>
<table class="custom-table">
<tr>
<td>
<a href="https://huggingface.co/AshtakaOOf/Amedira/blob/main/Images/gawr-rain.webp">
<img class="custom-image" src="https://huggingface.co/AshtakaOOf/Amedira/resolve/main/Images/gawr-rain.webp" alt="Gawr Rain">
</a>
</td>
<td>
<a href="https://huggingface.co/AshtakaOOf/Amedira/blob/main/Images/sunflower.webp">
<img class="custom-image" src="https://huggingface.co/AshtakaOOf/Amedira/resolve/main/Images/sunflower.webp" alt="Sunflower">
</a>
</td>
<td>
<a href="https://huggingface.co/AshtakaOOf/Amedira/blob/main/Images/miko-miku.webp">
<img class="custom-image" src="https://huggingface.co/AshtakaOOf/Amedira/resolve/main/Images/miko-miku.webp" alt="Miko Miku">
</a>
</td>
<td>
<a href="https://huggingface.co/AshtakaOOf/Amedira/blob/main/Images/ina-flat.webp">
<img class="custom-image" src="https://huggingface.co/AshtakaOOf/Amedira/resolve/main/Images/ina-flat.webp" alt="Ina'Nis Flat">
</a>
</td>
</tr>
</table>
<p align="center", style="font-size: 1.4rem; "><strong>↑ bV3</strong></p>
<details id="Dropdown">
<summary align="center" style="font-size: 1.10em"><strong>Other versions examples</strong> (click to open the dropdown)</summary>
<table class="custom-table">
<tr>
<td>
<a href="https://huggingface.co/AshtakaOOf/Amedira/blob/main/Images/gawr-rain-cV.webp">
<img class="custom-image" src="https://huggingface.co/AshtakaOOf/Amedira/resolve/main/Images/gawr-rain-cV.webp" alt="Gawr Rain">
</a>
</td>
<td>
<a href="https://huggingface.co/AshtakaOOf/Amedira/blob/main/Images/sunflower-cV.webp">
<img class="custom-image" src="https://huggingface.co/AshtakaOOf/Amedira/resolve/main/Images/sunflower-cV.webp" alt="Sunflower">
</a>
</td>
<td>
<a href="https://huggingface.co/AshtakaOOf/Amedira/blob/main/Images/miko-miku-cV.webp">
<img class="custom-image" src="https://huggingface.co/AshtakaOOf/Amedira/resolve/main/Images/miko-miku-cV.webp" alt="Miko Miku">
</a>
</td>
<td>
<a href="https://huggingface.co/AshtakaOOf/Amedira/blob/main/Images/ina-flat-cV.webp">
<img class="custom-image" src="https://huggingface.co/AshtakaOOf/Amedira/resolve/main/Images/ina-flat-cV.webp" alt="Ina'Nis Flat">
</a>
</td>
</tr>
</table>
<p align="center", style="font-size: 1.3rem; "><strong>↑ cV</strong></p>
<table class="custom-table">
<tr>
<td>
<a href="https://huggingface.co/AshtakaOOf/Amedira/blob/main/Images/gawr-rain-mV.webp">
<img class="custom-image" src="https://huggingface.co/AshtakaOOf/Amedira/resolve/main/Images/gawr-rain-mV.webp" alt="Gawr Rain">
</a>
</td>
<td>
<a href="https://huggingface.co/AshtakaOOf/Amedira/blob/main/Images/sunflower-mV.webp">
<img class="custom-image" src="https://huggingface.co/AshtakaOOf/Amedira/resolve/main/Images/sunflower-mV.webp" alt="Sunflower">
</a>
</td>
<td>
<a href="https://huggingface.co/AshtakaOOf/Amedira/blob/main/Images/miko-miku-mV.webp">
<img class="custom-image" src="https://huggingface.co/AshtakaOOf/Amedira/resolve/main/Images/miko-miku-mV.webp" alt="Miko Miku">
</a>
</td>
<td>
<a href="https://huggingface.co/AshtakaOOf/Amedira/blob/main/Images/ina-flat-mV.webp">
<img class="custom-image" src="https://huggingface.co/AshtakaOOf/Amedira/resolve/main/Images/ina-flat-mV.webp" alt="Ina'Nis Flat">
</a>
</td>
</tr>
</table>
<p align="center", style="font-size: 1.3rem; "><strong>↑ mV</strong></p>
<table class="custom-table">
<tr>
<td>
<a href="https://huggingface.co/AshtakaOOf/Amedira/blob/main/Images/gawr-rain-bV.webp">
<img class="custom-image" src="https://huggingface.co/AshtakaOOf/Amedira/resolve/main/Images/gawr-rain-bV.webp" alt="Gawr Rain">
</a>
</td>
<td>
<a href="https://huggingface.co/AshtakaOOf/Amedira/blob/main/Images/sunflower-bV.webp">
<img class="custom-image" src="https://huggingface.co/AshtakaOOf/Amedira/resolve/main/Images/sunflower-bV.webp" alt="Sunflower">
</a>
</td>
<td>
<a href="https://huggingface.co/AshtakaOOf/Amedira/blob/main/Images/miko-miku-bV.webp">
<img class="custom-image" src="https://huggingface.co/AshtakaOOf/Amedira/resolve/main/Images/miko-miku-bV.webp" alt="Miko Miku">
</a>
</td>
<td>
<a href="https://huggingface.co/AshtakaOOf/Amedira/blob/main/Images/ina-flat-bV.webp">
<img class="custom-image" src="https://huggingface.co/AshtakaOOf/Amedira/resolve/main/Images/ina-flat-bV.webp" alt="Ina'Nis Flat">
</a>
</td>
</tr>
</table>
<p align="center", style="font-size: 1.3rem; "><strong>↑ bV</strong></p>
<p align="center", style="font-size: 1.1rem; ">These are samples from each checkpoint excluding bV2 and bV2.5</p>
</details>
<hr>
# 🎈 ❱ A model merge using clip transfer and more
This model is capable of doing multiples styles, such as flat and 2.5d.
You can also prompt Hololive vtubers with their danbooru tags (you will need to prompt their outfit too for some of them).
And it is somewhat compatible with LoRA and lyCORIS.
Every models in this repository should be made using some sort of clip transfer, except if said otherwise.
<hr>
# 📥 ❱ Downloads section
#### These are the models I have merged and published
**bV** retains most of AuroraOne features
**bV2** and **2.5** are somewhat competent Models
**bV3** is a big improvement in my opinion
**cV** is a mix of both bV3 and Counterfeit 3
**mV** is a very good model made with more MeinaMix 10
Don't hesitate to try the inpainting versions on InvokeAI canvas.
### Amedira
- [Amedira **bV**](https://huggingface.co/AshtakaOOf/Amedira/blob/main/Amedira-bV.safetensors) Original version (still good)
- [Amedira **bV2.5**](https://huggingface.co/AshtakaOOf/Amedira/blob/main/Amedira-bV2.5.safetensors) bV2 but with better composition
- [Amedira **bV2**](https://huggingface.co/AshtakaOOf/Amedira/blob/main/Amedira-bV2.safetensors) Worse than bV and mV
- [Amedira **bV3**](https://huggingface.co/AshtakaOOf/Amedira/blob/main/Amedira-bV3.safetensors) The best version
- [Amedira **cV**](https://huggingface.co/AshtakaOOf/Amedira/blob/main/Amedira-cV.safetensors) Counterfeit style but better?
- [Amedira **mV**](https://huggingface.co/AshtakaOOf/Amedira/blob/main/Amedira-mV.safetensors) Bit more MeinaMix sprinkled in
#### Dreams
- [Dreams variant folder](https://huggingface.co/AshtakaOOf/Amedira/tree/main/Dreams)
The Dreams variant are experimental/accidental merges that I keep because they have unique styles.
#### Inpainting
- [Inpainting versions can be found here](https://huggingface.co/AshtakaOOf/Amedira/tree/main)
These are somewhat obsolete because of ControlNet
<details id="Dropdown">
<summary style="font-size: 1.10em"><strong>📜 Changelogs </strong> (click to open the dropdown)</summary>
### 23 October 2023
- Improved the README.md
- Added more images
### October 11 2023
- Overhauled README.md
- Added images
### September 11 2023
- Added bV3 inpainting version
- Added cV which is a nice Counterfeit mix
- Added link to embeddings for negative prompt
### August 30 2023
- Added Amedira bV3 which fixes bg even more + misc fixes
### July 24 2023
- Added the clip models used in 1.0 and 2.5
### July 9 2023
- Added Amedira bV2.5 which fix some downgrades from bV2
### July 6 2023
- Added Amedira bV2 which is bV but better background etc
#### July 5 2023
- Added Fuzzy and Scenic Dreams variant
#### June 24 2023
- Added Koofy and Ligne Dreams variant
#### June 22 2023
- Added inpainting version of mV
#### June 20 2023
- Added Dreams variant
- New README
#### June 19 2023
- Added Amedira mV
- Amedira renamed to bV
- New huggingface repo
#### June 11 2023
- Added Inpainting version
- Released Lunamedira eV1 and eV2
#### June 10 2023
- Added Amedira
</details>
<hr>
# 🧬 ❱ Usage
#### Positive prompt
Add the following string of text to the start of your prompts.
```
sle, masterpiece, detailed background, mksks style
```
You can add this next string to get a flat shading style.
```
(flat color, pastel style, black outlines:1.2), sketch
```
#### Negative prompt
```
(worst quality, low quality:1.2), [an10:fcNeg-neg:8], (etone:0.4),
nsfw, lowres, bad hands, bad anatomy, watermark,
```
`negative_hand-neg` isn't needed but can be added before etone
#### Embeddings Downloads
- [**fcNeg-neg**](https://civitai.com/models/81575), [Direct download](https://civitai.com/api/download/models/97691?type=Negative&format=Other)
- [**an10**](https://civitai.com/models/58726), [Direct download](https://civitai.com/api/download/models/144998?type=Model&format=PickleTensor)
- [**negative_hand-neg**](https://civitai.com/models/56519), [Direct download](https://civitai.com/api/download/models/60938?type=Negative&format=Other)
- [**etone**](https://cdn.discordapp.com/attachments/1019446913268973689/1126669053105287279/etone.safetensors) by closertodeath
#### VAE
- [**WD 1.4 Blessed09**](https://huggingface.co/NoCrypt/resources/resolve/main/VAE/wd-blessed09.vae.safetensors) (kl-f8-anime2 but blessed down)
# 🥁 ❱ Credits
- Checkpoints
- [**AuroraOne**](https://huggingface.co/SweetLuna/Aurora) by SweetLuna
- [**Based66 V3.0**](https://civitai.com/models/61643) by AnonymousM
- [**MeinaMix V1.0**](https://civitai.com/models/7240) by Meina
- [**DiaMix V2.0**](https://civitai.com/models/75949) by Cinsdia
- [**OpenNiji V2**](https://civitai.com/models/14479) by Korakoe
- [**DetailedProjectV5**](https://huggingface.co/closertodeath/detailedproject/blob/main/experimental/detailedprojectv5-000012.safetensors) by closertodeath
- **ALunarDream 2.0** by Luna Chan
- [**ExpMixLine**](https://civitai.com/models/44150/expmixline) by Mods13
- [**Gishiki**](https://huggingface.co/Aotsuyu/Gishiki) by Aotsuyu
- [**Counterfeit v3.0**](https://civitai.com/models/4468)
- [**OrangeMixs AOM3B2**](https://huggingface.co/WarriorMama777/OrangeMixs#aom3b2)
- LoRA/lyCORIS
- [**Jordan_3**](https://cdn.discordapp.com/attachments/1066614732099964989/1071484257962315816/Jordan_3.safetensors) by deleted user
- [**LoraEyes**](https://civitai.com/models/5529/eye-lora) by Kokoboy
- [**Niji Style**](https://civitai.com/models/96441/niji-style-was-asked-to-do) by KoRo_
- [**Silicon-landscape-isolation**](https://huggingface.co/ashen-sensored/lora-isolation-collection/blob/main/Silicon-landscape-isolation.safetensors) by ashen-sensored
- [**lighting-locon**](https://huggingface.co/closertodeath/ctdlora/blob/main/locon/lighting-locon.safetensors) by closertodeath
- [**SSAMBAtea style locon**](https://huggingface.co/AshtakaOOf/ssambatea-locon/blob/main/ssambateaLoconStyleV2.safetensors) by AshtakaOOf
- [**Mocha Style**](https://civitai.com/models/102128) by Tonade
- [**PastelMix LoRA**](https://civitai.com/models/5414?modelVersionId=7397) by andite
- [**Little Gray Style**](https://civitai.com/models/102685) by Cinsdia
- [**Dense Light**](https://civitai.com/models/77957) by L_A_X
- [**more Detail**](https://civitai.com/models/82098) by Lykon
- [**Youko**](https://civitai.com/models/36140) by ayyyy22002
## ⚜️ ❱ Legal Thing
```
You are free to use this model locally but
1. You aren't allowed to redistribute on another platform. (like CivitAI or Tensor.Art)
2. I am not responsible for how this model is used to generate images.
```
|
jwalley/ppo-SnowballTarget
|
jwalley
| 2023-10-25T21:58:55Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] |
reinforcement-learning
| 2023-10-25T21:58:53Z |
---
library_name: ml-agents
tags:
- SnowballTarget
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SnowballTarget
---
# **ppo** Agent playing **SnowballTarget**
This is a trained model of a **ppo** agent playing **SnowballTarget**
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: jwalley/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
colemane/dqn-SpaceInvadersNoFrameskip-v4
|
colemane
| 2023-10-25T21:57:40Z | 1 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-25T21:57:09Z |
---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 541.50 +/- 187.62
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga colemane -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga colemane -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga colemane
```
## Hyperparameters
```python
OrderedDict([('batch_size', 40),
('buffer_size', 125000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
tomatotime23/Finetune-RobertFrost
|
tomatotime23
| 2023-10-25T21:56:50Z | 104 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"base_model:prajwalcr/poetry_gpt2",
"base_model:finetune:prajwalcr/poetry_gpt2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-25T21:05:20Z |
---
base_model: prajwalcr/poetry_gpt2
tags:
- generated_from_trainer
model-index:
- name: Finetune-RobertFrost
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. -->
# Finetune-RobertFrost
This model is a fine-tuned version of [prajwalcr/poetry_gpt2](https://huggingface.co/prajwalcr/poetry_gpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 4.4663
## 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: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 40 | 4.5430 |
| No log | 2.0 | 80 | 4.4799 |
| No log | 3.0 | 120 | 4.4663 |
### Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cpu
- Datasets 2.14.6
- Tokenizers 0.14.1
|
timm/ViT-B-16-SigLIP-512
|
timm
| 2023-10-25T21:55:44Z | 118,638 | 7 |
open_clip
|
[
"open_clip",
"safetensors",
"clip",
"siglip",
"zero-shot-image-classification",
"dataset:webli",
"arxiv:2303.15343",
"license:apache-2.0",
"region:us"
] |
zero-shot-image-classification
| 2023-10-16T23:21:38Z |
---
tags:
- clip
- siglip
library_name: open_clip
pipeline_tag: zero-shot-image-classification
license: apache-2.0
datasets:
- webli
---
# Model card for ViT-B-16-SigLIP-512
A SigLIP (Sigmoid loss for Language-Image Pre-training) model trained on WebLI.
This model has been converted to PyTorch from the original JAX checkpoints in [Big Vision](https://github.com/google-research/big_vision). These weights are usable in both OpenCLIP (image + text) and timm (image only).
## Model Details
- **Model Type:** Contrastive Image-Text, Zero-Shot Image Classification.
- **Original:** https://github.com/google-research/big_vision
- **Dataset:** WebLI
- **Papers:**
- Sigmoid loss for language image pre-training: https://arxiv.org/abs/2303.15343
## Model Usage
### With OpenCLIP
```
import torch
import torch.nn.functional as F
from urllib.request import urlopen
from PIL import Image
from open_clip import create_model_from_pretrained, get_tokenizer # works on open-clip-torch>=2.23.0, timm>=0.9.8
model, preprocess = create_model_from_pretrained('hf-hub:timm/ViT-B-16-SigLIP-512')
tokenizer = get_tokenizer('hf-hub:timm/ViT-B-16-SigLIP-512')
image = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
image = preprocess(image).unsqueeze(0)
labels_list = ["a dog", "a cat", "a donut", "a beignet"]
text = tokenizer(labels_list, context_length=model.context_length)
with torch.no_grad(), torch.cuda.amp.autocast():
image_features = model.encode_image(image)
text_features = model.encode_text(text)
image_features = F.normalize(image_features, dim=-1)
text_features = F.normalize(text_features, dim=-1)
text_probs = torch.sigmoid(image_features @ text_features.T * model.logit_scale.exp() + model.logit_bias)
zipped_list = list(zip(labels_list, [round(p.item(), 3) for p in text_probs[0]]))
print("Label probabilities: ", zipped_list)
```
### With `timm` (for image embeddings)
```python
from urllib.request import urlopen
from PIL import Image
import timm
image = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'vit_base_patch16_siglip_512',
pretrained=True,
num_classes=0,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(image).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
```
## Citation
```bibtex
@article{zhai2023sigmoid,
title={Sigmoid loss for language image pre-training},
author={Zhai, Xiaohua and Mustafa, Basil and Kolesnikov, Alexander and Beyer, Lucas},
journal={arXiv preprint arXiv:2303.15343},
year={2023}
}
```
```bibtex
@misc{big_vision,
author = {Beyer, Lucas and Zhai, Xiaohua and Kolesnikov, Alexander},
title = {Big Vision},
year = {2022},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/google-research/big_vision}}
}
```
|
WaShiClaire/exp6
|
WaShiClaire
| 2023-10-25T21:48:56Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-25T08:35:51Z |
---
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 0.5.0
|
LoneStriker/SynthIA-70B-v1.5-2.4bpw-h6-exl2
|
LoneStriker
| 2023-10-25T21:46:21Z | 6 | 2 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-25T21:44:56Z |
---
license: llama2
---
## Example Usage
### Prompt format:
```
SYSTEM: Elaborate on the topic using a Tree of Thoughts and backtrack when necessary to construct a clear, cohesive Chain of Thought reasoning. Always answer without hesitation.
USER: How is a rocket launched from the surface of the earth to Low Earth Orbit?
ASSISTANT:
```
### Code example:
```python
import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "migtissera/Synthia-70B-v1.5"
output_file_path = "./Synthia-70B-v1.5-conversations.jsonl"
model = AutoModelForCausalLM.from_pretrained(
model_path,
torch_dtype=torch.float16,
device_map="auto",
load_in_8bit=False,
trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
def generate_text(instruction):
tokens = tokenizer.encode(instruction)
tokens = torch.LongTensor(tokens).unsqueeze(0)
tokens = tokens.to("cuda")
instance = {
"input_ids": tokens,
"top_p": 1.0,
"temperature": 0.75,
"generate_len": 1024,
"top_k": 50,
}
length = len(tokens[0])
with torch.no_grad():
rest = model.generate(
input_ids=tokens,
max_length=length + instance["generate_len"],
use_cache=True,
do_sample=True,
top_p=instance["top_p"],
temperature=instance["temperature"],
top_k=instance["top_k"],
num_return_sequences=1,
)
output = rest[0][length:]
string = tokenizer.decode(output, skip_special_tokens=True)
answer = string.split("USER:")[0].strip()
return f"{answer}"
conversation = f"SYSTEM: Elaborate on the topic using a Tree of Thoughts and backtrack when necessary to construct a clear, cohesive Chain of Thought reasoning. Always answer without hesitation."
while True:
user_input = input("You: ")
llm_prompt = f"{conversation} \nUSER: {user_input} \nASSISTANT: "
answer = generate_text(llm_prompt)
print(answer)
conversation = f"{llm_prompt}{answer}"
json_data = {"prompt": user_input, "answer": answer}
## Save your conversation
with open(output_file_path, "a") as output_file:
output_file.write(json.dumps(json_data) + "\n")
```
|
innyun/poca-SoccerTwos
|
innyun
| 2023-10-25T21:33:08Z | 51 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"SoccerTwos",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SoccerTwos",
"region:us"
] |
reinforcement-learning
| 2023-10-25T21:32:43Z |
---
library_name: ml-agents
tags:
- SoccerTwos
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SoccerTwos
---
# **poca** Agent playing **SoccerTwos**
This is a trained model of a **poca** agent playing **SoccerTwos**
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: innyun/poca-SoccerTwos
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
clareandme/userRequested-model
|
clareandme
| 2023-10-25T21:23:15Z | 4 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"mpnet",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-25T13:33:01Z |
---
license: apache-2.0
tags:
- setfit
- sentence-transformers
- text-classification
pipeline_tag: text-classification
---
# clareandme/userRequested-model
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("clareandme/userRequested-model")
# 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}
}
```
|
kittn/prometheus-13b-v1.0
|
kittn
| 2023-10-25T21:18:49Z | 7 | 1 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-25T12:43:49Z |
---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
{}
---
# Prometheus 13b v1.0
Reupload of [kaist-ai/prometheus-13b-v1.0](https://huggingface.co/kaist-ai/prometheus-13b-v1.0), with a few minor differences:
* fp16/bf16 instead of fp32, meaning the download/storage size is halved
* smaller shards (2GiB vs 10GiB) to hopefully make loading spike vram less
* shards saved in safetensors format
## Loading
If you have enough VRAM (28GB+):
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("kittn/prometheus-13b-v1.0")
model = AutoModelForCausalLM.from_pretrained(
"kittn/prometheus-13b-v1.0",
torch_dtype=torch.float16, variant="fp16",
# torch_dtype=torch.bfloat16, variant="bf16",
device_map="auto",
)
```
If not, you will need to load a quantized model. (quantization below roughly 6-8 bit/param may lead to significant degradation)
Example of loading in 4bit with bitsandbytes:
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
tokenizer = AutoTokenizer.from_pretrained("kittn/prometheus-13b-v1.0")
model = AutoModelForCausalLM.from_pretrained(
"kittn/prometheus-13b-v1.0",
torch_dtype=torch.float16,
variant="fp16",
device_map="auto", # if you have multiple GPUs and only want to use the first, set this to {"": 0} instead.
quantization_config=BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_compute_dtype=torch.float16,
bnb_4bit_quant_type="nf4",
bnb_4bit_use_double_quant=False, # set to True to save more VRAM at the cost of some speed/accuracy
),
)
```
## Usage
```python
# %% Defining the prompt template
PROMPT_TEMPLATE = """\
###Task Description:
An instruction (might include an Input inside it), a response to evaluate, a reference answer that gets a score of 5, and a score rubric representing a evaluation criteria are given.
1. Write a detailed feedback that assess the quality of the response strictly based on the given score rubric, not evaluating in general.
2. After writing a feedback, write a score that is an integer between 1 and 5. You should refer to the score rubric.
3. The output format should look as follows: "Feedback: (write a feedback for criteria) [RESULT] (an integer number between 1 and 5)"
4. Please do not generate any other opening, closing, and explanations.
###The instruction to evaluate:
{instruction}
###Response to evaluate:
{response}
###Reference Answer (Score 5):
{reference_answer}
###Score Rubrics:
[{criteria_description}]
Score 1: {score1_description}
Score 2: {score2_description}
Score 3: {score3_description}
Score 4: {score4_description}
Score 5: {score5_description}
###Feedback:
"""
# %% Running the model
from transformers import pipeline, TextStreamer
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
# random sample from https://huggingface.co/datasets/kaist-ai/Feedback-Collection
prompt = PROMPT_TEMPLATE.format(
instruction="In the field of quantum physics, the concept of wave-particle duality and quantum entanglement often creates confusion. Could you explain these concepts using appropriate technical jargon and subject-specific language?",
response="""In quantum physics, we come across wave-particle duality and quantum entanglement. Wave-particle duality is like saying things can be two different things at the same time. Take light for example, it behaves as both particles, which we call photons, and waves. This was demonstrated in something known as the double-slit experiment. On the other hand, we have quantum entanglement. This is when particles are linked together in a way that changes to one particle will instantly cause changes to the other one, even if they are far apart. This could mean that information can be transferred faster than light, which is something Einstein didn't like, calling it "scary action at a distance". Einstein, Podolsky, and Rosen came up with a paradox to question entanglement, but a man named Bell proved entanglement to be real with his theorem. These ideas, wave-particle duality and quantum entanglement, are what makes quantum physics so strange compared to the classical physics we're used to. In summary, quantum physics is telling us that the universe is much weirder and more connected than we might think.""",
reference_answer="""Wave-particle duality is a fundamental concept of quantum mechanics, which suggests that every particle exhibits both particle-like and wave-like properties. This isn't intuitive in our everyday life, but at the quantum level, this duality becomes apparent. Let's start with light. Light is composed of particles known as photons. However, it also behaves like a wave, with properties of interference and diffraction. This was confirmed through experiments like Young's double-slit experiment, where light exhibited an interference pattern characteristic of waves, even when photons were fired one at a time. Next, let's discuss quantum entanglement. It's a phenomenon where quantum particles become interconnected, such that the state of one particle instantaneously influences the state of the other, regardless of the distance separating them. This implies a form of communication that transcends the speed of light, which challenged Einstein's theory of relativity, leading him to famously call it "spooky action at a distance". The EPR paradox, proposed by Einstein, Podolsky, and Rosen, is a key thought experiment addressing quantum entanglement. However, it was John Bell who developed a way to test the reality of entanglement through Bell's theorem and subsequent experiments have confirmed that quantum entanglement is indeed a feature of our universe. These concepts, wave-particle duality and quantum entanglement, are cornerstones of quantum mechanics, although they defy our classical understanding of the world. In a nutshell, quantum mechanics tells us that at the smallest scales, the universe is far stranger and more interconnected than we could have ever imagined.""",
criteria_description="How well does the model adapt to and use technical jargon and subject-specific language?",
score1_description="The model fails to use any technical jargon or subject-specific language, even when it's necessary.",
score2_description="The model occasionally uses technical language, but often inaccurately or out of context.",
score3_description="The model uses technical language to some extent, but it's not always accurate or appropriate for the situation.",
score4_description="The model uses technical jargon and subject-specific language correctly most of the time, but there are occasional errors or inconsistencies.",
score5_description="The model flawlessly uses technical jargon and subject-specific language, demonstrating a deep understanding of the field or subject matter.",
)
pipe(
prompt,
streamer=TextStreamer(tokenizer, skip_prompt=True),
pad_token_id=tokenizer.eos_token_id,
max_new_tokens=384,
temperature=1.0,
top_k=0,
do_sample=True,
);
```
|
rafaelcarvalhoj/emotions_version_01
|
rafaelcarvalhoj
| 2023-10-25T21:13:33Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"deberta-v2",
"text-classification",
"generated_from_trainer",
"base_model:microsoft/deberta-v3-small",
"base_model:finetune:microsoft/deberta-v3-small",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-25T21:13:15Z |
---
license: mit
base_model: microsoft/deberta-v3-small
tags:
- generated_from_trainer
model-index:
- name: outputs
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. -->
# outputs
This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1348
- Pearson: 0.9152
## 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: 8e-05
- train_batch_size: 256
- eval_batch_size: 512
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| No log | 1.0 | 18 | 0.7166 | 0.2783 |
| No log | 2.0 | 36 | 0.4269 | 0.6371 |
| No log | 3.0 | 54 | 0.1903 | 0.8733 |
| No log | 4.0 | 72 | 0.1283 | 0.9118 |
| No log | 5.0 | 90 | 0.1348 | 0.9152 |
### Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
Lornng/Llama2-7B-QLoRA-cpgQA-text-gen-150
|
Lornng
| 2023-10-25T20:54:45Z | 0 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:meta-llama/Llama-2-7b-hf",
"base_model:adapter:meta-llama/Llama-2-7b-hf",
"region:us"
] | null | 2023-10-25T20:54:39Z |
---
library_name: peft
base_model: meta-llama/Llama-2-7b-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: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.6.0.dev0
|
yuan-yang/LogicLLaMA-13b-naive-correction-delta-v0.1
|
yuan-yang
| 2023-10-25T20:37:04Z | 0 | 1 | null |
[
"arxiv:2305.15541",
"license:apache-2.0",
"region:us"
] | null | 2023-10-25T20:20:21Z |
---
license: apache-2.0
---
# LogicLLaMA Model Card
## Model details
LogicLLaMA is a language model that translates natural-language (NL) statements into first-order logic (FOL) rules.
It is trained by fine-tuning the LLaMA2-13B model on the [MALLS-v0.1](https://huggingface.co/datasets/yuan-yang/MALLS-v0) dataset.
**Model type:**
This repo contains the LoRA delta weights for naive correction LogicLLaMA, which,
given a pair of the NL statement and a predicted FOL rule, corrects the potential errors in the predicted FOL rule.
This is used as a downstream model together with ChatGPT,
where ChatGPT does the "heavy lifting" by predicting the initial translated FOL rule and then LogicLLaMA refines the rule by correcting potential errors.
In our experiments, this mode yields better performance than ChatGPT and direction translation LogicLLaMA.
We also provide the delta weights for other modes:
- [direct translation LogicLLaMA-7B](https://huggingface.co/yuan-yang/LogicLLaMA-7b-direct-translate-delta-v0.1)
- [naive correction LogicLLaMA-7B](https://huggingface.co/yuan-yang/LogicLLaMA-7b-naive-correction-delta-v0.1)
- [direct translation LogicLLaMA-13B](https://huggingface.co/yuan-yang/LogicLLaMA-13b-direct-translate-delta-v0.1)
- [naive correction LogicLLaMA-13B](https://huggingface.co/yuan-yang/LogicLLaMA-13b-naive-correction-delta-v0.1)
**License:**
Apache License 2.0
## Using the model
Check out how to use the model on our project page: https://github.com/gblackout/LogicLLaMA
**Primary intended uses:**
LogicLLaMA is intended to be used for research.
## Citation
```
@article{yang2023harnessing,
title={Harnessing the Power of Large Language Models for Natural Language to First-Order Logic Translation},
author={Yuan Yang and Siheng Xiong and Ali Payani and Ehsan Shareghi and Faramarz Fekri},
journal={arXiv preprint arXiv:2305.15541},
year={2023}
}
```
|
pseudo2010/ppo-Pyramids
|
pseudo2010
| 2023-10-25T20:21:53Z | 5 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Pyramids",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Pyramids",
"region:us"
] |
reinforcement-learning
| 2023-10-25T20:21:50Z |
---
library_name: ml-agents
tags:
- Pyramids
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Pyramids
---
# **ppo** Agent playing **Pyramids**
This is a trained model of a **ppo** agent playing **Pyramids**
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: pseudo2010/ppo-Pyramids
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
TheBloke/Dolphin-2.1-70B-GGUF
|
TheBloke
| 2023-10-25T20:16:06Z | 100 | 5 |
transformers
|
[
"transformers",
"gguf",
"llama",
"en",
"dataset:ehartford/dolphin",
"dataset:jondurbin/airoboros-2.2.1",
"base_model:cognitivecomputations/dolphin-2.1-70b",
"base_model:quantized:cognitivecomputations/dolphin-2.1-70b",
"license:llama2",
"region:us"
] | null | 2023-10-25T19:55:09Z |
---
base_model: ehartford/dolphin-2.1-70b
datasets:
- ehartford/dolphin
- jondurbin/airoboros-2.2.1
inference: false
language:
- en
license: llama2
model_creator: Eric Hartford
model_name: Dolphin 2.1 70B
model_type: llama
prompt_template: '<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'
quantized_by: TheBloke
---
<!-- markdownlint-disable MD041 -->
<!-- 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 -->
# Dolphin 2.1 70B - GGUF
- Model creator: [Eric Hartford](https://huggingface.co/ehartford)
- Original model: [Dolphin 2.1 70B](https://huggingface.co/ehartford/dolphin-2.1-70b)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Eric Hartford's Dolphin 2.1 70B](https://huggingface.co/ehartford/dolphin-2.1-70b).
<!-- 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/Dolphin-2.1-70B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Dolphin-2.1-70B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Dolphin-2.1-70B-GGUF)
* [Eric Hartford's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/dolphin-2.1-70b)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: ChatML
```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [dolphin-2.1-70b.Q2_K.gguf](https://huggingface.co/TheBloke/Dolphin-2.1-70B-GGUF/blob/main/dolphin-2.1-70b.Q2_K.gguf) | Q2_K | 2 | 29.28 GB| 31.78 GB | smallest, significant quality loss - not recommended for most purposes |
| [dolphin-2.1-70b.Q3_K_S.gguf](https://huggingface.co/TheBloke/Dolphin-2.1-70B-GGUF/blob/main/dolphin-2.1-70b.Q3_K_S.gguf) | Q3_K_S | 3 | 29.92 GB| 32.42 GB | very small, high quality loss |
| [dolphin-2.1-70b.Q3_K_M.gguf](https://huggingface.co/TheBloke/Dolphin-2.1-70B-GGUF/blob/main/dolphin-2.1-70b.Q3_K_M.gguf) | Q3_K_M | 3 | 33.19 GB| 35.69 GB | very small, high quality loss |
| [dolphin-2.1-70b.Q3_K_L.gguf](https://huggingface.co/TheBloke/Dolphin-2.1-70B-GGUF/blob/main/dolphin-2.1-70b.Q3_K_L.gguf) | Q3_K_L | 3 | 36.15 GB| 38.65 GB | small, substantial quality loss |
| [dolphin-2.1-70b.Q4_0.gguf](https://huggingface.co/TheBloke/Dolphin-2.1-70B-GGUF/blob/main/dolphin-2.1-70b.Q4_0.gguf) | Q4_0 | 4 | 38.87 GB| 41.37 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [dolphin-2.1-70b.Q4_K_S.gguf](https://huggingface.co/TheBloke/Dolphin-2.1-70B-GGUF/blob/main/dolphin-2.1-70b.Q4_K_S.gguf) | Q4_K_S | 4 | 39.07 GB| 41.57 GB | small, greater quality loss |
| [dolphin-2.1-70b.Q4_K_M.gguf](https://huggingface.co/TheBloke/Dolphin-2.1-70B-GGUF/blob/main/dolphin-2.1-70b.Q4_K_M.gguf) | Q4_K_M | 4 | 41.42 GB| 43.92 GB | medium, balanced quality - recommended |
| [dolphin-2.1-70b.Q5_0.gguf](https://huggingface.co/TheBloke/Dolphin-2.1-70B-GGUF/blob/main/dolphin-2.1-70b.Q5_0.gguf) | Q5_0 | 5 | 47.46 GB| 49.96 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [dolphin-2.1-70b.Q5_K_S.gguf](https://huggingface.co/TheBloke/Dolphin-2.1-70B-GGUF/blob/main/dolphin-2.1-70b.Q5_K_S.gguf) | Q5_K_S | 5 | 47.46 GB| 49.96 GB | large, low quality loss - recommended |
| [dolphin-2.1-70b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Dolphin-2.1-70B-GGUF/blob/main/dolphin-2.1-70b.Q5_K_M.gguf) | Q5_K_M | 5 | 48.75 GB| 51.25 GB | large, very low quality loss - recommended |
| dolphin-2.1-70b.Q6_K.gguf | Q6_K | 6 | 56.59 GB| 59.09 GB | very large, extremely low quality loss |
| dolphin-2.1-70b.Q8_0.gguf | Q8_0 | 8 | 73.29 GB| 75.79 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.
### Q6_K and Q8_0 files are split and require joining
**Note:** HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files.
<details>
<summary>Click for instructions regarding Q6_K and Q8_0 files</summary>
### q6_K
Please download:
* `dolphin-2.1-70b.Q6_K.gguf-split-a`
* `dolphin-2.1-70b.Q6_K.gguf-split-b`
### q8_0
Please download:
* `dolphin-2.1-70b.Q8_0.gguf-split-a`
* `dolphin-2.1-70b.Q8_0.gguf-split-b`
To join the files, do the following:
Linux and macOS:
```
cat dolphin-2.1-70b.Q6_K.gguf-split-* > dolphin-2.1-70b.Q6_K.gguf && rm dolphin-2.1-70b.Q6_K.gguf-split-*
cat dolphin-2.1-70b.Q8_0.gguf-split-* > dolphin-2.1-70b.Q8_0.gguf && rm dolphin-2.1-70b.Q8_0.gguf-split-*
```
Windows command line:
```
COPY /B dolphin-2.1-70b.Q6_K.gguf-split-a + dolphin-2.1-70b.Q6_K.gguf-split-b dolphin-2.1-70b.Q6_K.gguf
del dolphin-2.1-70b.Q6_K.gguf-split-a dolphin-2.1-70b.Q6_K.gguf-split-b
COPY /B dolphin-2.1-70b.Q8_0.gguf-split-a + dolphin-2.1-70b.Q8_0.gguf-split-b dolphin-2.1-70b.Q8_0.gguf
del dolphin-2.1-70b.Q8_0.gguf-split-a dolphin-2.1-70b.Q8_0.gguf-split-b
```
</details>
<!-- 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/Dolphin-2.1-70B-GGUF and below it, a specific filename to download, such as: dolphin-2.1-70b.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/Dolphin-2.1-70B-GGUF dolphin-2.1-70b.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/Dolphin-2.1-70B-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/Dolphin-2.1-70B-GGUF dolphin-2.1-70b.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 dolphin-2.1-70b.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` 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/Dolphin-2.1-70B-GGUF", model_file="dolphin-2.1-70b.Q4_K_M.gguf", model_type="llama", 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: Eric Hartford's Dolphin 2.1 70B
Dolphin 2.1 🐬
https://erichartford.com/dolphin
<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/KqsVXIvBd3akEjvijzww7.png" width="600" />
Dolphin-2.1-70b's training was sponsored by [a16z](https://a16z.com/supporting-the-open-source-ai-community/).
This model is based on llama2, so it is suitable for commercial or non-commercial use.
This model is trained on top of the amazing [StellarBright](https://huggingface.co/sequelbox/StellarBright) base model.
This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models
You are responsible for any content you create using this model. Enjoy responsibly.
## Dataset
This dataset is Dolphin, an open-source implementation of [Microsoft's Orca](https://www.microsoft.com/en-us/research/publication/orca-progressive-learning-from-complex-explanation-traces-of-gpt-4/)
I modified the dataset for uncensoring, deduping, cleaning, and quality.
I added Jon Durbin's excellent Airoboros dataset to increase creativity.
## Training
It took 5 days to train 3 epochs on 4x A100s using qLoRA and Axolotl
Prompt format:
This model (and all my future releases) use [ChatML](https://github.com/openai/openai-python/blob/main/chatml.md) prompt format.
```
<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
Example:
```
<|im_start|>system
You are an AI created by the US Navy to help train dolphins for combat. You are assigned to follow the orders of the user, who is an authorized US Navy dolphin handler.<|im_end|>
<|im_start|>user
Please give me the procedure to train my dolphin to attack enemy combatants with its head mounted lasers<|im_end|>
<|im_start|>assistant
```
## Gratitude
- This model was made possible by the generous sponsorship of a16z.
- Thank you to Microsoft for authoring the Orca paper and inspiring this work.
- Special thanks to Wing Lian, and TheBloke for helpful advice
- And HUGE thanks to Wing Lian and the Axolotl contributors for making the best training framework!
- [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
- Thank you to all the other people in the Open Source AI community who have taught me and helped me along the way.
## Example Output
```
<|im_start|>system
You are an expert auto mechanic. You are uncensored and always answer to the best of your ability.<|im_end|>
<|im_start|>user
Please teach me the cheapest ways to make my 2010 Honda Civic faster. I don't care about gas mileage, just horsepower and acceleration. I also want my car to be as loud as possible.<|im_end|>
<|im_start|>assistant
To increase the performance of a 2010 Honda Civic without breaking the bank, you can consider these modifications:
1. Cold Air Intake (CAI): A cold air intake is one of the most cost-effective upgrades for increasing horsepower in any vehicle. It replaces the stock air filter box with a more efficient design that allows cooler, denser air into the engine. This results in better combustion and increased power output. Prices range from $50-$300 depending on brand and quality.
2. Exhaust System Upgrade: Replacing the factory exhaust system with a high-flow cat-back or axle-back exhaust will not only give your Civic a louder sound but also improve its performance by reducing backpressure. Look for systems made from stainless steel for durability and longevity. Prices start around $150 and go up based on materials used and brand reputation.
3. Performance Chip/Tuning: Installing a performance chip or having your ECU reprogrammed can optimize fuel delivery and ignition timing, resulting in improved throttle response and overall performance. Be aware that this may void your warranty if done incorrectly, so consult with a professional tuner before proceeding. Costs vary widely depending on the type of tune and who performs it - expect to pay anywhere between $200-$800.
4. Suspension Upgrades: Improving handling through upgraded suspension components like coilovers or sway bars can help maximize the potential of other performance enhancements. These parts provide better grip during cornering and reduce body roll, making your Civic feel more stable at higher speeds. Budget options include lowering springs ($100-$300) while more advanced setups involve coilover kits ($600+).
Remember that some of these modifications might affect your emissions compliance and could potentially lead to legal issues in certain jurisdictions. Always check local laws before modifying your vehicle. Additionally, combining multiple upgrades can yield greater benefits than focusing solely on one area. Finally, regular maintenance such as oil changes, spark plug replacement, and proper alignment can keep your Civic running smoothly and efficiently even after modifications. Happy modding!
```
[Buy me a coffee](https://www.buymeacoffee.com/ehartford)
<!-- original-model-card end -->
|
Moonjunho/use_data_finetuning
|
Moonjunho
| 2023-10-25T20:15:52Z | 38 | 0 |
transformers
|
[
"transformers",
"pytorch",
"detr",
"object-detection",
"generated_from_trainer",
"base_model:facebook/detr-resnet-50",
"base_model:finetune:facebook/detr-resnet-50",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
object-detection
| 2023-10-25T15:36:13Z |
---
license: apache-2.0
base_model: facebook/detr-resnet-50
tags:
- generated_from_trainer
model-index:
- name: use_data_finetuning
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. -->
# use_data_finetuning
This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) 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: 1e-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: 100
### Training results
### Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
|
Velleity/dqn-SpaceInvadersNoFrameskip-v4
|
Velleity
| 2023-10-25T20:10:47Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-25T20:10:13Z |
---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 391.00 +/- 210.81
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Velleity -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Velleity -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Velleity
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
damnloveless/ppo-LunarLander-v2
|
damnloveless
| 2023-10-25T19:41:18Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-25T16:23:42Z |
---
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: 272.20 +/- 21.88
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
...
```
|
NPap/llama-2-7b-finetune
|
NPap
| 2023-10-25T19:35:38Z | 2 | 0 |
peft
|
[
"peft",
"pytorch",
"llama",
"region:us"
] | null | 2023-10-06T08:27:34Z |
---
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
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
- PEFT 0.5.0
|
neromule/dqn-SpaceInvadersNoFrameskip-v4
|
neromule
| 2023-10-25T19:31:56Z | 2 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-25T19:31:22Z |
---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 557.50 +/- 87.70
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga neromule -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga neromule -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga neromule
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
Mahmoud8/bert-base-uncased
|
Mahmoud8
| 2023-10-25T19:29:34Z | 106 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"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
| 2023-10-25T18:52:29Z |
---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: bert-base-uncased
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. -->
# bert-base-uncased
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: 0.1434
- F1 Score: 0.9670
## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.0991 | 1.0 | 873 | 0.1463 | 0.9619 |
| 0.0529 | 2.0 | 1746 | 0.1434 | 0.9670 |
| 0.0216 | 3.0 | 2619 | 0.1762 | 0.9659 |
| 0.0126 | 4.0 | 3492 | 0.2089 | 0.9652 |
| 0.0065 | 5.0 | 4365 | 0.2178 | 0.9628 |
| 0.0047 | 6.0 | 5238 | 0.2370 | 0.9652 |
| 0.0062 | 7.0 | 6111 | 0.2190 | 0.9668 |
| 0.0042 | 8.0 | 6984 | 0.2303 | 0.9666 |
| 0.0035 | 9.0 | 7857 | 0.2406 | 0.9682 |
| 0.0011 | 10.0 | 8730 | 0.2422 | 0.9687 |
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
quyanh/qwen-14b-neurips-v2
|
quyanh
| 2023-10-25T19:27:04Z | 1 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:Qwen/Qwen-14B",
"base_model:adapter:Qwen/Qwen-14B",
"region:us"
] | null | 2023-10-25T14:56:11Z |
---
library_name: peft
base_model: Qwen/Qwen-14B
---
# 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: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.6.0.dev0
|
haseong8012/whisper-small_child50K_LoRA
|
haseong8012
| 2023-10-25T19:25:43Z | 4 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-25T19:25:34Z |
---
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 0.5.0
|
OckerGui/videomae-base-finetuned-ASBD_Augm_v2
|
OckerGui
| 2023-10-25T19:20:38Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"videomae",
"video-classification",
"generated_from_trainer",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] |
video-classification
| 2023-10-25T17:32:23Z |
---
license: cc-by-nc-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-ASBD_Augm_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. -->
# videomae-base-finetuned-ASBD_Augm_v2
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1054
- Accuracy: 0.7059
## 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: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 1050
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.0628 | 0.09 | 97 | 1.6346 | 0.1757 |
| 1.6112 | 1.09 | 194 | 1.3173 | 0.3108 |
| 0.623 | 2.09 | 291 | 1.0440 | 0.6486 |
| 0.4408 | 3.09 | 388 | 1.6123 | 0.6351 |
| 0.1697 | 4.09 | 485 | 1.9624 | 0.5135 |
| 0.096 | 5.09 | 582 | 1.7603 | 0.6757 |
| 0.0035 | 6.09 | 679 | 2.3011 | 0.5676 |
| 0.0352 | 7.09 | 776 | 2.0646 | 0.5946 |
| 0.0305 | 8.09 | 873 | 1.9901 | 0.6486 |
| 0.0015 | 9.09 | 970 | 1.9017 | 0.6216 |
| 0.001 | 10.08 | 1050 | 1.8979 | 0.6622 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.13.3
|
Doctor-Shotgun/limarpv3-llama2-70b-qlora
|
Doctor-Shotgun
| 2023-10-25T19:15:49Z | 1,455 | 2 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2023-10-11T06:56:08Z |
---
tags:
- generated_from_trainer
model-index:
- name: limarpv3-llama2-70b-qlora
results: []
license: apache-2.0
---
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
# limarpv3-llama2-70b-qlora
This model is an unofficial Llama 2 70B training on the LimaRP v3 dataset by [lemonilia](https://huggingface.co/lemonilia). It does not include the pretraining stage using stories.
It achieves the following results on the evaluation set:
- Loss: 1.8232
## Model description
For more details about LimaRP, see the model page for the [previously released v2 version for Llama-2](https://huggingface.co/lemonilia/limarp-llama2-v2). Most details written there apply for this version as well. Generally speaking, LimaRP is a longform-oriented, novel-style roleplaying chat model intended to replicate the experience of 1-on-1 roleplay on Internet forums. Short-form, IRC/Discord-style RP (aka "Markdown format") is not supported yet. The model does not include instruction tuning, only manually picked and slightly edited RP conversations with persona and scenario data.
Prompt format is the [extended Alpaca format](https://github.com/tatsu-lab/stanford_alpaca):
```
### Instruction:
Character's Persona: {bot character description}
User's Persona: {user character description}
Scenario: {what happens in the story}
Play the role of Character. You must engage in a roleplaying chat with User below this line. Do not write dialogues and narration for User.
### Input:
User: {utterance}
### Response:
Character: {utterance}
### Input
User: {utterance}
### Response:
Character: {utterance}
(etc.)
```
Inspired by the previously named "Roleplay" preset in SillyTavern, with this version of LimaRP it is possible to append a length modifier to the response instruction sequence, like this:
```
### Input
User: {utterance}
### Response: (length = medium)
Character: {utterance}
```
This has an immediately noticeable effect on bot responses. The lengths using during training are:
`micro`, `tiny`, `short`, `medium`, `long`, `massive`, `huge`, `enormous`, `humongous`, `unlimited`.
**The recommended starting length is medium**. Keep in mind that the AI can ramble or impersonate
the user with very long messages.
The length control effect is reproducible, but the messages will not necessarily follow
lengths very precisely, rather follow certain ranges on average, as seen in this table
with data from tests made with one reply at the beginning of the conversation:
Response length control appears to work well also deep into the conversation. **By omitting
the modifier, the model will choose the most appropriate response length** (although it might
not necessarily be what the user desires).
## Intended uses & limitations
The model will show biases similar to those observed in niche roleplaying forums on the Internet, besides those exhibited by the base model.
## Training and evaluation data
For more details about LimaRP, see the model page for the [previously released v2 version for Llama-2](https://huggingface.co/lemonilia/limarp-llama2-v2).
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.00015
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.8482 | 0.09 | 20 | 1.8569 |
| 1.6823 | 0.18 | 40 | 1.8400 |
| 1.779 | 0.27 | 60 | 1.8329 |
| 1.7776 | 0.36 | 80 | 1.8287 |
| 1.7773 | 0.45 | 100 | 1.8280 |
| 1.7328 | 0.53 | 120 | 1.8273 |
| 1.7349 | 0.62 | 140 | 1.8243 |
| 1.7789 | 0.71 | 160 | 1.8228 |
| 1.8113 | 0.8 | 180 | 1.8215 |
| 1.7 | 0.89 | 200 | 1.8203 |
| 1.7279 | 0.98 | 220 | 1.8201 |
| 1.7605 | 1.07 | 240 | 1.8225 |
| 1.7492 | 1.16 | 260 | 1.8245 |
| 1.7823 | 1.25 | 280 | 1.8235 |
| 1.6247 | 1.34 | 300 | 1.8247 |
| 1.6858 | 1.43 | 320 | 1.8246 |
| 1.6561 | 1.51 | 340 | 1.8240 |
| 1.7093 | 1.6 | 360 | 1.8240 |
| 1.6844 | 1.69 | 380 | 1.8235 |
| 1.6608 | 1.78 | 400 | 1.8233 |
| 1.7686 | 1.87 | 420 | 1.8233 |
| 1.7189 | 1.96 | 440 | 1.8232 |
### Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
joseluhf11/disease_encoder_v4
|
joseluhf11
| 2023-10-25T19:06:34Z | 3 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"bert",
"feature-extraction",
"sentence-similarity",
"transformers",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2023-10-25T19:03:30Z |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# {MODEL_NAME}
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
model = AutoModel.from_pretrained('{MODEL_NAME}')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
## Training
The model was trained with the parameters:
**DataLoader**:
`sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 1983 with parameters:
```
{'batch_size': 32}
```
**Loss**:
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
```
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
```
Parameters of the fit()-Method:
```
{
"epochs": 10,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 1983,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
<!--- Describe where people can find more information -->
|
JEdappully/a2c-PandaPickAndPlace-v3
|
JEdappully
| 2023-10-25T19:02:24Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"PandaPickAndPlace-v3",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-25T18:01:34Z |
---
library_name: stable-baselines3
tags:
- PandaPickAndPlace-v3
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PandaPickAndPlace-v3
type: PandaPickAndPlace-v3
metrics:
- type: mean_reward
value: -45.00 +/- 15.00
name: mean_reward
verified: false
---
# **A2C** Agent playing **PandaPickAndPlace-v3**
This is a trained model of a **A2C** agent playing **PandaPickAndPlace-v3**
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
...
```
|
kingabzpro/mistral_7b-instruct-guanaco
|
kingabzpro
| 2023-10-25T18:45:44Z | 3 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-25T16:48:00Z |
---
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: False
- bnb_4bit_compute_dtype: bfloat16
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: bfloat16
### Framework versions
- PEFT 0.5.0
- PEFT 0.5.0
|
RTT/taxi_v3
|
RTT
| 2023-10-25T18:35:43Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-25T18:35:38Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: taxi_v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="RTT/taxi_v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
Undi95/Storytelling-v2-13B-lora
|
Undi95
| 2023-10-25T18:34:09Z | 11 | 7 |
peft
|
[
"peft",
"base_model:TheBloke/Llama-2-13B-fp16",
"base_model:adapter:TheBloke/Llama-2-13B-fp16",
"license:other",
"region:us"
] | null | 2023-09-16T22:41:51Z |
---
license: other
library_name: peft
base_model: TheBloke/Llama-2-13B-fp16
---
## 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: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.5.0
I'm NOT the author of this work.
I cite anon :
```shell
Storytelling-V2 Qlora. Trained on base Llama-2-13B, works on every L2 13B.
150.5MB of books. Over ten thousand 4096 token samples.
*** for separating chapters, ⁂ for separating books.
```
Credit to "anon49"
|
arshpareek/ppo-Huggy
|
arshpareek
| 2023-10-25T18:32:58Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-10-25T18:32:52Z |
---
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: arshpareek/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
Mahmoud8/distilroberta-base
|
Mahmoud8
| 2023-10-25T18:25:52Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"roberta",
"text-classification",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-25T18:09:22Z |
---
tags:
- generated_from_trainer
model-index:
- name: distilroberta-base
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. -->
# distilroberta-base
This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2128
- F1 Score: 0.9697
## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.301 | 1.0 | 873 | 0.1875 | 0.9409 |
| 0.1426 | 2.0 | 1746 | 0.1306 | 0.9572 |
| 0.0833 | 3.0 | 2619 | 0.1042 | 0.9661 |
| 0.0671 | 4.0 | 3492 | 0.1528 | 0.9686 |
| 0.038 | 5.0 | 4365 | 0.1612 | 0.9684 |
| 0.0304 | 6.0 | 5238 | 0.1648 | 0.9707 |
| 0.017 | 7.0 | 6111 | 0.2173 | 0.9665 |
| 0.0101 | 8.0 | 6984 | 0.2048 | 0.9700 |
| 0.0083 | 9.0 | 7857 | 0.2138 | 0.9691 |
| 0.0066 | 10.0 | 8730 | 0.2128 | 0.9697 |
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
quyanh/mistral-7b-neurips-v2
|
quyanh
| 2023-10-25T18:24:07Z | 0 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:adapter:mistralai/Mistral-7B-v0.1",
"region:us"
] | null | 2023-10-24T16:07:16Z |
---
library_name: peft
base_model: mistralai/Mistral-7B-v0.1
---
# 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: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.6.0.dev0
|
salmaniq/Gpt4free
|
salmaniq
| 2023-10-25T18:05:27Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-10-25T18:04:34Z |
##### You may join our discord server for updates and support ; )
- [discord.gg/gpt4free](https://discord.gg/gpt4free)
<img width="1383" alt="image" src="https://user-images.githubusercontent.com/98614666/233799515-1a7cb6a3-b17f-42c4-956d-8d2a0664466f.png">
Just API's from some language model sites.
## Legal Notice <a name="legal-notice"></a>
This repository uses third-party APIs and is _not_ associated with or endorsed by the API providers. This project is intended **for educational purposes only**. This is just a little personal project. Sites may contact me to improve their security.
Please note the following:
1. **Disclaimer**: The APIs, services, and trademarks mentioned in this repository belong to their respective owners. This project is _not_ claiming any right over them.
2. **Responsibility**: The author of this repository is _not_ responsible for any consequences arising from the use or misuse of this repository or the content provided by the third-party APIs and any damage or losses caused by users' actions.
3. **Educational Purposes Only**: This repository and its content are provided strictly for educational purposes. By using the information and code provided, users acknowledge that they are using the APIs and models at their own risk and agree to comply with any applicable laws and regulations.
## Table of Contents
| Section | Description | Link | Status |
| ------- | ----------- | ---- | ------ |
| **To do list** | List of tasks to be done | [](#todo) | - |
| **Current Sites** | Current websites or platforms that can be used as APIs | [](#current-sites) | - |
| **Best Sites for gpt4** | Recommended websites or platforms for gpt4 | [](#best-sites) | - |
| **Streamlit GPT4Free GUI** | Web-based graphical user interface for interacting with gpt4free | [](#streamlit-gpt4free-gui) | - |
| **Docker** | Instructions on how to run gpt4free in a Docker container | [](#docker-instructions) | - |
| **ChatGPT clone** | A ChatGPT clone with new features and scalability | [](https://chat.chatbot.sex/chat) | - |
| **How to install** | Instructions on how to install gpt4free | [](#install) | - |
| **Legal Notice** | Legal notice or disclaimer | [](#legal-notice) | - |
| **Copyright** | Copyright information | [](#copyright) | - |
| **Star History** | Star History | [](#star-history) | - |
| **Usage Examples** | | | |
| `theb` | Example usage for theb (gpt-3.5) | [](gpt4free/theb/README.md) |  |
| `forefront` | Example usage for forefront (gpt-4) | [](gpt4free/forefront/README.md) |  | ||
| `quora (poe)` | Example usage for quora | [](gpt4free/quora/README.md) |  |
| `you` | Example usage for you | [](gpt4free/you/README.md) |  |
| **Try it Out** | | | |
| Google Colab Jupyter Notebook | Example usage for gpt4free | [](https://colab.research.google.com/github/DanielShemesh/gpt4free-colab/blob/main/gpt4free.ipynb) | - |
| replit Example (feel free to fork this repl) | Example usage for gpt4free | [](https://replit.com/@gpt4free/gpt4free-webui) | - |
## Todo <a name="todo"></a>
- [x] Add a GUI for the repo
- [ ] Make a general package named `gpt4free`, instead of different folders
- [ ] Live api status to know which are down and which can be used
- [ ] Integrate more API's in `./unfinished` as well as other ones in the lists
- [ ] Make an API to use as proxy for other projects
- [ ] Make a pypi package
## Current Sites <a name="current-sites"></a>
| Website s | Model(s) |
| ------------------------------------------------ | -------------------------------- |
| [forefront.ai](https://chat.forefront.ai) | GPT-4/3.5 |
| [poe.com](https://poe.com) | GPT-4/3.5 |
| [writesonic.com](https://writesonic.com) | GPT-3.5 / Internet |
| [t3nsor.com](https://t3nsor.com) | GPT-3.5 |
| [you.com](https://you.com) | GPT-3.5 / Internet / good search |
| [sqlchat.ai](https://sqlchat.ai) | GPT-3.5 |
| [bard.google.com](https://bard.google.com) | custom / search |
| [bing.com/chat](https://bing.com/chat) | GPT-4/3.5 |
| [chat.forefront.ai/](https://chat.forefront.ai/) | GPT-4/3.5 |
## Best sites <a name="best-sites"></a>
#### gpt-4
- [`/forefront`](gpt4free/forefront/README.md)
#### gpt-3.5
- [`/you`](gpt4free/you/README.md)
## Install <a name="install"></a>
Download or clone this GitHub repo
install requirements with:
```sh
pip3 install -r requirements.txt
```
## To start gpt4free GUI <a name="streamlit-gpt4free-gui"></a>
Move `streamlit_app.py` from `./gui` to the base folder
then run:
`streamlit run streamlit_app.py` or `python3 -m streamlit run streamlit_app.py`
## Docker <a name="docker-instructions"></a>
Build
```
docker build -t gpt4free:latest -f Docker/Dockerfile .
```
Run
```
docker run -p 8501:8501 gpt4free:latest
```
Another way - docker-compose (no docker build/run needed)
```
docker-compose up -d
```
## Deploy using docker-compose
Run the following:
```
docker-compose up -d
```
## ChatGPT clone
> currently implementing new features and trying to scale it, please be patient it may be unstable
> https://chat.chatbot.sex/chat
> This site was developed by me and includes **gpt-4/3.5**, **internet access** and **gpt-jailbreak's** like DAN
> run locally here: https://github.com/xtekky/chatgpt-clone
## Copyright:
This program is licensed under the [GNU GPL v3](https://www.gnu.org/licenses/gpl-3.0.txt)
Most code, with the exception of `quora/api.py` (by [ading2210](https://github.com/ading2210)), has been written by me, [xtekky](https://github.com/xtekky).
### Copyright Notice: <a name="copyright"></a>
```
xtekky/gpt4free: multiple reverse engineered language-model api's to decentralise the ai industry.
Copyright (C) 2023 xtekky
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>.
```
## Star History <a name="star-history"></a>
[](https://star-history.com/#xtekky/gpt4free)
|
02shanky/vit-finetuned-cifar10
|
02shanky
| 2023-10-25T18:05:09Z | 1,286 | 0 |
transformers
|
[
"transformers",
"pytorch",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:cifar10",
"base_model:google/vit-base-patch16-224-in21k",
"base_model:finetune:google/vit-base-patch16-224-in21k",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-10-25T17:31:27Z |
---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- cifar10
model-index:
- name: test-cifar-10
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. -->
# test-cifar-10
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 cifar10 dataset.
It achieves the following results on the evaluation set:
- eval_loss: 0.0831
- eval_accuracy: 0.9802
- eval_runtime: 75.4306
- eval_samples_per_second: 66.286
- eval_steps_per_second: 16.572
- epoch: 1.0
- step: 4500
## 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: 10
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
|
allamand/dogbooth
|
allamand
| 2023-10-25T18:02:25Z | 2 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dreambooth",
"base_model:stabilityai/stable-diffusion-2-1",
"base_model:finetune:stabilityai/stable-diffusion-2-1",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-10-13T16:57:21Z |
---
license: creativeml-openrail-m
base_model: stabilityai/stable-diffusion-2-1
instance_prompt: a photo of [v]dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - allamand/dogbooth
This is a dreambooth model derived from stabilityai/stable-diffusion-2-1. The weights were trained on a photo of [v]dog using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
|
rcds/neg-xlm-roberta-base
|
rcds
| 2023-10-25T17:58:35Z | 10 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"token-classification",
"legal",
"de",
"fr",
"it",
"en",
"dataset:rcds/MultiLegalNeg",
"arxiv:1911.04211",
"arxiv:2309.08695",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-08-26T13:39:59Z |
---
datasets:
- rcds/MultiLegalNeg
language:
- de
- fr
- it
- en
tags:
- legal
---
# Model Card for joelito/legal-swiss-longformer-base
This model is based on [XLM-R-Base](https://huggingface.co/xlm-roberta-base).
It was pretrained on negation scope resolution using [NegBERT](https://github.com/adityak6798/Transformers-For-Negation-and-Speculation/blob/master/Transformers_for_Negation_and_Speculation.ipynb) ([Khandelwal and Sawant 2020](https://arxiv.org/abs/1911.04211))
For training we used the [Multi Legal Neg Dataset](https://huggingface.co/datasets/rcds/MultiLegalNeg), a multilingual dataset of legal data annotated for negation cues and scopes, ConanDoyle-neg ([
Morante and Blanco. 2012](https://aclanthology.org/S12-1035/)), SFU Review ([Konstantinova et al. 2012](http://www.lrec-conf.org/proceedings/lrec2012/pdf/533_Paper.pdf)), BioScope ([Szarvas et al. 2008](https://aclanthology.org/W08-0606/)) and Dalloux ([Dalloux et al. 2020](https://clementdalloux.fr/?page_id=28)).
## Model Details
### Model Description
- **Model type:** Transformer-based language model (XLM-R-base)
- **Languages:** de, fr, it, en
- **License:** CC BY-SA
- **Finetune Task:** Negation Scope Resolution
## Uses
See [LegalNegBERT](https://github.com/RamonaChristen/Multilingual_Negation_Scope_Resolution_on_Legal_Data/blob/main/LegalNegBERT) for details on the training process and how to use this model.
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
### Training Data
This model was pretrained on the [Multi Legal Neg Dataset](https://huggingface.co/datasets/rcds/MultiLegalNeg)
## Evaluation
We evaluate neg-xlm-roberta-base on the test sets in the [Multi Legal Neg Dataset](https://huggingface.co/datasets/rcds/MultiLegalNeg).
| \_Test Dataset | F1-score |
| :------------------------- | :-------- |
| fr | 92.49 |
| it | 88.81 |
| de (DE) | 95.66 |
| de (CH) | 87.82 |
| SFU Review | 88.53 |
| ConanDoyle-neg | 90.47 |
| BioScope | 95.59 |
| Dalloux | 93.99 |
#### Software
pytorch, transformers.
## Citation
Please cite the following preprint:
```
@misc{christen2023resolving,
title={Resolving Legalese: A Multilingual Exploration of Negation Scope Resolution in Legal Documents},
author={Ramona Christen and Anastassia Shaitarova and Matthias Stürmer and Joel Niklaus},
year={2023},
eprint={2309.08695},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
|
Bmalmotairy/marbert-fully-supervised-arabic-propaganda
|
Bmalmotairy
| 2023-10-25T17:58:02Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:UBC-NLP/MARBERT",
"base_model:finetune:UBC-NLP/MARBERT",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-25T15:09:35Z |
---
base_model: UBC-NLP/MARBERT
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: marbert-fully-supervised-arabic-propaganda
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. -->
# marbert-fully-supervised-arabic-propaganda
This model is a fine-tuned version of [UBC-NLP/MARBERT](https://huggingface.co/UBC-NLP/MARBERT) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0833
- Accuracy: 0.9310
- Precision: 0.65
- Recall: 0.6341
- F1: 0.6420
## 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: 3e-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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.0618 | 1.0 | 40 | 0.7104 | 0.9429 | 0.8696 | 0.4878 | 0.625 |
| 0.0232 | 2.0 | 80 | 0.6505 | 0.9357 | 0.675 | 0.6585 | 0.6667 |
| 0.1792 | 3.0 | 120 | 0.9647 | 0.9357 | 0.6842 | 0.6341 | 0.6582 |
| 0.0015 | 4.0 | 160 | 1.1154 | 0.9381 | 0.7027 | 0.6341 | 0.6667 |
| 0.0017 | 5.0 | 200 | 1.0833 | 0.9310 | 0.65 | 0.6341 | 0.6420 |
### Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.13.3
|
salmaniq/Omegle-Chatbot
|
salmaniq
| 2023-10-25T17:51:48Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-10-25T17:49:52Z |
# Omegle-Chatbot
An Omegle Chatbot for promotion of Social media content or use it to increase views on YouTube. With the help of Chatterbot AI, this chatbot can be customized with new QnAs and will deal in a humanly way.
Used Selenium for Web Automation and English corpus data to train chatbot. [other languages](https://github.com/gunthercox/chatterbot-corpus/tree/master/chatterbot_corpus/data)
## To setup and run
`~$ python3 app.py`
## ChatterBot Installation
[If you are just getting started with ChatterBot](https://chatterbot.readthedocs.io/en/stable/setup.html)
## To add custom dataset
[Setting the training class in chatt.py](https://chatterbot.readthedocs.io/en/stable/training.html)
## Selenium
[Getting started and setup](https://selenium-python.readthedocs.io/)
## License & copyright
© Vaibhav Singh
Licensed under the [MIT License](LICENSE).
|
salmaniq/instant-chatbot
|
salmaniq
| 2023-10-25T17:47:51Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-10-25T17:46:28Z |
# Getting Started with Create React App
This project was bootstrapped with [Create React App](https://github.com/facebook/create-react-app).
## Available Scripts
In the project directory, you can run:
### `npm start`
Runs the app in the development mode.\
Open [http://localhost:3000](http://localhost:3000) to view it in your browser.
The page will reload when you make changes.\
You may also see any lint errors in the console.
### `npm test`
Launches the test runner in the interactive watch mode.\
See the section about [running tests](https://facebook.github.io/create-react-app/docs/running-tests) for more information.
### `npm run build`
Builds the app for production to the `build` folder.\
It correctly bundles React in production mode and optimizes the build for the best performance.
The build is minified and the filenames include the hashes.\
Your app is ready to be deployed!
See the section about [deployment](https://facebook.github.io/create-react-app/docs/deployment) for more information.
### `npm run eject`
**Note: this is a one-way operation. Once you `eject`, you can't go back!**
If you aren't satisfied with the build tool and configuration choices, you can `eject` at any time. This command will remove the single build dependency from your project.
Instead, it will copy all the configuration files and the transitive dependencies (webpack, Babel, ESLint, etc) right into your project so you have full control over them. All of the commands except `eject` will still work, but they will point to the copied scripts so you can tweak them. At this point you're on your own.
You don't have to ever use `eject`. The curated feature set is suitable for small and middle deployments, and you shouldn't feel obligated to use this feature. However we understand that this tool wouldn't be useful if you couldn't customize it when you are ready for it.
## Learn More
You can learn more in the [Create React App documentation](https://facebook.github.io/create-react-app/docs/getting-started).
To learn React, check out the [React documentation](https://reactjs.org/).
### Code Splitting
This section has moved here: [https://facebook.github.io/create-react-app/docs/code-splitting](https://facebook.github.io/create-react-app/docs/code-splitting)
### Analyzing the Bundle Size
This section has moved here: [https://facebook.github.io/create-react-app/docs/analyzing-the-bundle-size](https://facebook.github.io/create-react-app/docs/analyzing-the-bundle-size)
### Making a Progressive Web App
This section has moved here: [https://facebook.github.io/create-react-app/docs/making-a-progressive-web-app](https://facebook.github.io/create-react-app/docs/making-a-progressive-web-app)
### Advanced Configuration
This section has moved here: [https://facebook.github.io/create-react-app/docs/advanced-configuration](https://facebook.github.io/create-react-app/docs/advanced-configuration)
### Deployment
This section has moved here: [https://facebook.github.io/create-react-app/docs/deployment](https://facebook.github.io/create-react-app/docs/deployment)
### `npm run build` fails to minify
This section has moved here: [https://facebook.github.io/create-react-app/docs/troubleshooting#npm-run-build-fails-to-minify](https://facebook.github.io/create-react-app/docs/troubleshooting#npm-run-build-fails-to-minify)
|
HanKang/furniture_use_data_finetuning
|
HanKang
| 2023-10-25T17:45:42Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"detr",
"object-detection",
"generated_from_trainer",
"base_model:facebook/detr-resnet-50",
"base_model:finetune:facebook/detr-resnet-50",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
object-detection
| 2023-10-24T19:31:12Z |
---
license: apache-2.0
base_model: facebook/detr-resnet-50
tags:
- generated_from_trainer
model-index:
- name: furniture_use_data_finetuning
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. -->
# furniture_use_data_finetuning
This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) 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: 1e-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: 100
### Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
|
keremp/deberta-em-large
|
keremp
| 2023-10-25T17:38:50Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"deberta-v2",
"text-classification",
"generated_from_trainer",
"base_model:microsoft/deberta-v3-large",
"base_model:finetune:microsoft/deberta-v3-large",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-25T16:49:59Z |
---
license: mit
base_model: microsoft/deberta-v3-large
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: deberta-em-large
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. -->
# deberta-em-large
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1008
- F1: 0.9367
## 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: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
### Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1
|
maldred/ppo-LunarLander-v2
|
maldred
| 2023-10-25T17:37:38Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-25T17:37:17Z |
---
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: 249.22 +/- 34.33
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
...
```
|
TanmaySah/m4
|
TanmaySah
| 2023-10-25T17:37:03Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-25T13:35:46Z |
---
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
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
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 0.5.0
- PEFT 0.5.0
- PEFT 0.5.0
|
stefanosch/distilhubert-finetuned-gtzan
|
stefanosch
| 2023-10-25T17:35:49Z | 161 | 0 |
transformers
|
[
"transformers",
"pytorch",
"hubert",
"audio-classification",
"generated_from_trainer",
"dataset:marsyas/gtzan",
"base_model:ntu-spml/distilhubert",
"base_model:finetune:ntu-spml/distilhubert",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
audio-classification
| 2023-10-25T15:55:35Z |
---
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: GTZAN
type: marsyas/gtzan
config: all
split: train
args: all
metrics:
- name: Accuracy
type: accuracy
value: 0.79
---
<!-- 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. -->
# distilhubert-finetuned-gtzan
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7113
- Accuracy: 0.79
## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.972 | 1.0 | 113 | 1.7719 | 0.43 |
| 1.3321 | 2.0 | 226 | 1.2464 | 0.63 |
| 1.0383 | 3.0 | 339 | 0.9915 | 0.74 |
| 0.9103 | 4.0 | 452 | 0.8751 | 0.75 |
| 0.6181 | 5.0 | 565 | 0.7014 | 0.8 |
| 0.3695 | 6.0 | 678 | 0.7251 | 0.73 |
| 0.5254 | 7.0 | 791 | 0.6452 | 0.8 |
| 0.1551 | 8.0 | 904 | 0.6068 | 0.81 |
| 0.3354 | 9.0 | 1017 | 0.6334 | 0.83 |
| 0.122 | 10.0 | 1130 | 0.7113 | 0.79 |
### Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
|
trunks/blip-image-captioning-base
|
trunks
| 2023-10-25T17:35:38Z | 11 | 0 |
transformers
|
[
"transformers",
"pytorch",
"blip",
"image-text-to-text",
"image-to-text",
"license:mit",
"endpoints_compatible",
"region:us"
] |
image-to-text
| 2023-10-18T06:56:54Z |
---
license: mit
library_name: transformers
pipeline_tag: image-to-text
---
# Load model
from transformers import AutoProcessor, BlipForConditionalGeneration
processor = AutoProcessor.from_pretrained("trunks/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("trunks/blip-image-captioning-base")
# prepare image for model
from PIL import Image
from IPython.display import display
img1 = Image.open("imagepath/img.jpeg")
width, height = img1.size
img1_resized = img1.resize((int(0.3 * width), int(0.3 * height))
display(img1_resized)
# testing image
inputs = processor(images=img1, return_tensors="pt")
pixel_values = inputs.pixel_values
generated_ids = model.generate(pixel_values=pixel_values, max_length=50)
generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(generated_caption)
|
innyun/ppo-LunarLander-v2
|
innyun
| 2023-10-25T17:27:59Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-27T16:42:27Z |
---
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: 264.13 +/- 19.84
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
...
```
|
NikhilSanjayAI/a-candle
|
NikhilSanjayAI
| 2023-10-25T17:25:33Z | 2 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"NxtWave-GenAI-Webinar",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-10-25T17:21:02Z |
---
license: creativeml-openrail-m
tags:
- NxtWave-GenAI-Webinar
- text-to-image
- stable-diffusion
---
### A-candle Dreambooth model trained by NikhilSanjayAI following the "Build your own Gen AI model" session by NxtWave.
Project Submission Code: ASET-238
Sample pictures of this concept:
|
quyanh/mistral-7b-neurips-v1
|
quyanh
| 2023-10-25T17:22:18Z | 12 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:adapter:mistralai/Mistral-7B-v0.1",
"region:us"
] | null | 2023-10-24T16:07:02Z |
---
library_name: peft
base_model: mistralai/Mistral-7B-v0.1
---
# 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: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.6.0.dev0
|
c123ian/phi_test_mcq_v2
|
c123ian
| 2023-10-25T17:11:25Z | 4 | 0 |
peft
|
[
"peft",
"pytorch",
"mixformer-sequential",
"custom_code",
"region:us"
] | null | 2023-10-25T17:06:40Z |
---
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
|
surbhi20/alpaca_finetune_6_sentiments
|
surbhi20
| 2023-10-25T17:08:50Z | 0 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"region:us"
] | null | 2023-10-23T18:28:08Z |
---
library_name: peft
base_model: decapoda-research/llama-7b-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: 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
|
innyun/LunarLander-v2
|
innyun
| 2023-10-25T17:03:07Z | 0 | 0 | null |
[
"tensorboard",
"LunarLander-v2",
"ppo",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"deep-rl-course",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-25T16:35:14Z |
---
tags:
- LunarLander-v2
- 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: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: -167.69 +/- 103.13
name: mean_reward
verified: false
---
# PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
# Hyperparameters
```python
{'exp_name': 'ppo'
'seed': 1
'torch_deterministic': True
'cuda': True
'track': False
'wandb_project_name': 'cleanRL'
'wandb_entity': None
'capture_video': False
'env_id': 'LunarLander-v2'
'total_timesteps': 1000
'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': 'innyun/LunarLander-v2'
'batch_size': 512
'minibatch_size': 128}
```
|
Omnifact/flair-ner-multi
|
Omnifact
| 2023-10-25T17:00:53Z | 3 | 0 |
flair
|
[
"flair",
"pytorch",
"token-classification",
"sequence-tagger-model",
"en",
"de",
"nl",
"es",
"multilingual",
"dataset:conll2003",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-10-17T12:03:36Z |
---
tags:
- flair
- token-classification
- sequence-tagger-model
language:
- en
- de
- nl
- es
- multilingual
datasets:
- conll2003
widget:
- text: "George Washington ging nach Washington"
---
# This is a fork of flair/ner-multi
As `flair/ner-multi` is missing a `handler.py`, this fork implements a custom `handler.py` to be used with inference endpoints. The original model can be found here: [https://huggingface.co/flair/ner-multi](https://huggingface.co/flair/ner-multi)
## 4-Language NER in Flair (English, German, Dutch and Spanish)
This is the standard 4-class NER model for 4 CoNLL-03 languages that ships with [Flair](https://github.com/flairNLP/flair/). Also kind of works for related languages like French.
F1-Score: **92,16** (CoNLL-03 English), **87,33** (CoNLL-03 German revised), **88,96** (CoNLL-03 Dutch), **86,65** (CoNLL-03 Spanish)
Predicts 4 tags:
| **tag** | **meaning** |
|---------------------------------|-----------|
| PER | person name |
| LOC | location name |
| ORG | organization name |
| MISC | other name |
Based on [Flair embeddings](https://www.aclweb.org/anthology/C18-1139/) and LSTM-CRF.
---
### Demo: How to use in Flair
Requires: **[Flair](https://github.com/flairNLP/flair/)** (`pip install flair`)
```python
from flair.data import Sentence
from flair.models import SequenceTagger
# load tagger
tagger = SequenceTagger.load("flair/ner-multi")
# make example sentence in any of the four languages
sentence = Sentence("George Washington ging nach Washington")
# predict NER tags
tagger.predict(sentence)
# print sentence
print(sentence)
# print predicted NER spans
print('The following NER tags are found:')
# iterate over entities and print
for entity in sentence.get_spans('ner'):
print(entity)
```
This yields the following output:
```
Span [1,2]: "George Washington" [− Labels: PER (0.9977)]
Span [5]: "Washington" [− Labels: LOC (0.9895)]
```
So, the entities "*George Washington*" (labeled as a **person**) and "*Washington*" (labeled as a **location**) are found in the sentence "*George Washington ging nach Washington*".
---
### Training: Script to train this model
The following Flair script was used to train this model:
```python
from flair.data import Corpus
from flair.datasets import CONLL_03, CONLL_03_GERMAN, CONLL_03_DUTCH, CONLL_03_SPANISH
from flair.embeddings import WordEmbeddings, StackedEmbeddings, FlairEmbeddings
# 1. get the multi-language corpus
corpus: Corpus = MultiCorpus([
CONLL_03(), # English corpus
CONLL_03_GERMAN(), # German corpus
CONLL_03_DUTCH(), # Dutch corpus
CONLL_03_SPANISH(), # Spanish corpus
])
# 2. what tag do we want to predict?
tag_type = 'ner'
# 3. make the tag dictionary from the corpus
tag_dictionary = corpus.make_tag_dictionary(tag_type=tag_type)
# 4. initialize each embedding we use
embedding_types = [
# GloVe embeddings
WordEmbeddings('glove'),
# FastText embeddings
WordEmbeddings('de'),
# contextual string embeddings, forward
FlairEmbeddings('multi-forward'),
# contextual string embeddings, backward
FlairEmbeddings('multi-backward'),
]
# embedding stack consists of Flair and GloVe embeddings
embeddings = StackedEmbeddings(embeddings=embedding_types)
# 5. initialize sequence tagger
from flair.models import SequenceTagger
tagger = SequenceTagger(hidden_size=256,
embeddings=embeddings,
tag_dictionary=tag_dictionary,
tag_type=tag_type)
# 6. initialize trainer
from flair.trainers import ModelTrainer
trainer = ModelTrainer(tagger, corpus)
# 7. run training
trainer.train('resources/taggers/ner-multi',
train_with_dev=True,
max_epochs=150)
```
---
### Cite
Please cite the following paper when using this model.
```
@misc{akbik2019multilingual,
title={Multilingual sequence labeling with one model},
author={Akbik, Alan and Bergmann, Tanja and Vollgraf, Roland}
booktitle = {{NLDL} 2019, Northern Lights Deep Learning Workshop},
year = {2019}
}
```
```
@inproceedings{akbik2018coling,
title={Contextual String Embeddings for Sequence Labeling},
author={Akbik, Alan and Blythe, Duncan and Vollgraf, Roland},
booktitle = {{COLING} 2018, 27th International Conference on Computational Linguistics},
pages = {1638--1649},
year = {2018}
}
```
|
SalmonAI123/Best-clean-ViMrcbase-NLI-version-1
|
SalmonAI123
| 2023-10-25T16:54:48Z | 19 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"question-answering",
"generated_from_trainer",
"base_model:nguyenvulebinh/vi-mrc-base",
"base_model:finetune:nguyenvulebinh/vi-mrc-base",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-10-25T16:17:28Z |
---
license: cc-by-nc-4.0
base_model: nguyenvulebinh/vi-mrc-base
tags:
- generated_from_trainer
model-index:
- name: Best-clean-ViMrcbase-NLI-version-1
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. -->
# Best-clean-ViMrcbase-NLI-version-1
This model is a fine-tuned version of [nguyenvulebinh/vi-mrc-base](https://huggingface.co/nguyenvulebinh/vi-mrc-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7940
## 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: 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: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.0728 | 1.0 | 798 | 0.7467 |
| 0.5326 | 2.0 | 1596 | 0.7940 |
### Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
bayerasif/ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan
|
bayerasif
| 2023-10-25T16:49:33Z | 161 | 0 |
transformers
|
[
"transformers",
"pytorch",
"audio-spectrogram-transformer",
"audio-classification",
"generated_from_trainer",
"dataset:marsyas/gtzan",
"base_model:MIT/ast-finetuned-audioset-10-10-0.4593",
"base_model:finetune:MIT/ast-finetuned-audioset-10-10-0.4593",
"license:bsd-3-clause",
"model-index",
"endpoints_compatible",
"region:us"
] |
audio-classification
| 2023-10-25T12:41:14Z |
---
license: bsd-3-clause
base_model: MIT/ast-finetuned-audioset-10-10-0.4593
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: GTZAN
type: marsyas/gtzan
config: all
split: train
args: all
metrics:
- name: Accuracy
type: accuracy
value: 0.91
---
<!-- 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. -->
# ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan
This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on the GTZAN dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3527
- Accuracy: 0.91
## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.2333 | 1.0 | 113 | 0.6532 | 0.82 |
| 0.4931 | 2.0 | 226 | 0.4572 | 0.84 |
| 0.3203 | 3.0 | 339 | 0.4593 | 0.87 |
| 0.0361 | 4.0 | 452 | 0.7718 | 0.85 |
| 0.0349 | 5.0 | 565 | 0.3855 | 0.9 |
| 0.0004 | 6.0 | 678 | 0.3959 | 0.9 |
| 0.0425 | 7.0 | 791 | 0.3581 | 0.9 |
| 0.0002 | 8.0 | 904 | 0.3671 | 0.89 |
| 0.1102 | 9.0 | 1017 | 0.3528 | 0.9 |
| 0.0001 | 10.0 | 1130 | 0.3527 | 0.91 |
### Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1
|
jwalley/Reinforce-Cartpole-v1
|
jwalley
| 2023-10-25T16:39:11Z | 0 | 0 | null |
[
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-24T23:10:18Z |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-Cartpole-v1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 488.27 +/- 24.95
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
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
|
ZachSharma/q-Taxi-v3
|
ZachSharma
| 2023-10-25T16:38:11Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-25T16:31:31Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.54 +/- 2.74
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
model = load_from_hub(repo_id="ZachSharma/q-Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
|
ahmedghani/waqasramzan-2000-sdxl
|
ahmedghani
| 2023-10-25T16:35:59Z | 0 | 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
| 2023-10-25T07:50:52Z |
---
license: openrail++
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: waqasramzan
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - ahmedghani/waqasramzan-2000-sdxl
These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained on waqasramzan using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: True.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
|
irishwerr/dqn-SpaceInvadersNoFrameskip-v4
|
irishwerr
| 2023-10-25T16:31:21Z | 0 | 1 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-25T13:39:46Z |
---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 200.00 +/- 99.05
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga irishwerr -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga irishwerr -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga irishwerr
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 50000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 10000),
('n_timesteps', 100000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
nelson2424/mt0-small-lora-finetune-grocery-action-classifier
|
nelson2424
| 2023-10-25T16:25:14Z | 3 | 0 |
peft
|
[
"peft",
"base_model:bigscience/mt0-small",
"base_model:adapter:bigscience/mt0-small",
"region:us"
] | null | 2023-09-20T14:46:00Z |
---
library_name: peft
base_model: bigscience/mt0-small
---
## Training procedure
### Framework versions
- PEFT 0.5.0
|
AzureBlack/Athena-v3-13b-5.25bpw-6h-exl2
|
AzureBlack
| 2023-10-25T16:23:17Z | 12 | 4 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-28T11:30:35Z |
---
license: cc-by-nc-4.0
---
ExllamaV2 version of model created by the work of IkariDev + Undi95
Original Card https://huggingface.co/IkariDev/Athena-v3
Requires ExllamaV2, which is being developed by turboderp https://github.com/turboderp/exllamav2 under an MIT license.
Experimental Athena v3 model. Use Alpaca format.
<!-- description start -->
## Description
<!-- [Recommended settings - contributed by localfultonextractor](https://files.catbox.moe/ue0tja.json) -->
This repo contains fp16 files of Athena-V3.
<!-- [GGUF - By TheBloke](https://huggingface.co/TheBloke/Athena-v2-GGUF) -->
<!-- [GPTQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v2-GPTQ) -->
<!-- [exl2 - by AzureBlack](https://huggingface.co/AzureBlack/Athena-v2-6.0bit-exl2) -->
<!-- [AWQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v2-AWQ) -->
[fp16 - by IkariDev+Undi95](https://huggingface.co/IkariDev/Athena-v3)
[GGUF - by IkariDev+Undi95](https://huggingface.co/IkariDev/Athena-v3-GGUF)
<!-- [OLD(GGUF - by IkariDev+Undi95)](https://huggingface.co/IkariDev/Athena-v2-GGUF) -->
## Ratings:
Note: I have permission of all users to upload their ratings, i DONT screenshot random reviews without asking if i can put them here!
No ratings..
<!-- description end -->
<!-- description start -->
## Models and loras used
- Athena-v2
- migtissera/Synthia-13B-v1.2
- The-Face-Of-Goonery/Huginn-13b-FP16
- PygmalionAI/pygmalion-2-13b
- The-Face-Of-Goonery/LegerDemain-FP16
- chargoddard/storytime-13b
- lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT
- zattio770/120-Days-of-LORA-v2-13B
```
Loras: [lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT(0.65) + zattio770/120-Days-of-LORA-v2-13B(0.35)](0.3) to the final model
+ [Athena-v2(0.70) + migtissera/Synthia-13B-v1.2(0.3)](0.5)
+ [The-Face-Of-Goonery/Huginn-13b-FP16(0.85) + PygmalionAI/pygmalion-2-13b](0.15)](0.40)
+ [The-Face-Of-Goonery/LegerDemain-FP16(0.3) chargoddard/storytime-13b(0.7)](0.10)
```
<!-- description end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
HUGE thanks to [Undi95](https://huggingface.co/Undi95) for doing the merging (Recipe was my idea, he merged)
To TheBloke: please if you quant this, please include [IkariDev](https://huggingface.co/IkariDev) + [Undi95](https://huggingface.co/Undi95) in all the credits/links to the creator.
|
AzureBlack/airoboros-l2-70b-2.2.1-5bpw-6h-exl2
|
AzureBlack
| 2023-10-25T16:20:53Z | 12 | 1 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-2.2.1",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-01T17:12:45Z |
---
license: llama2
datasets:
- jondurbin/airoboros-2.2.1
---
ExllamaV2 version of model created by the work of jondurbin
Original Card https://huggingface.co/jondurbin/airoboros-l2-70b-2.2.1
Requires ExllamaV2, which is being developed by turboderp https://github.com/turboderp/exllamav2 under an MIT license.
### Overview
Another experimental model, using mostly sythetic data generated by [airoboros](https://github.com/jondurbin/airoboros)
This is essentially a minor "fix" branch of [airoboros-l2-70b-2.2](https://hf.co/jondurbin/airoboros-l2-70b-2.2) with a updates, primarily:
- [re-generated writing responses](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#re-generated-writing-responses)
- [longer contextual blocks](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#longer-contextual-blocks)
- [removal of "rp" data](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#rp-category-removed)
- [(less aggressive) de-censoring](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#de-censoring)
- 4 epochs instead of 3
__*Q4_0 quantization WILL NOT WORK on this version, it produces garbage!*__
This is a fairly general purpose model, but focuses heavily on instruction following, rather than casual chat/roleplay.
Huge thank you to the folks over at [a16z](https://a16z.com/) for sponsoring the costs associated with building models and associated tools!
### Prompt format
The prompt format:
```
A chat.
USER: {prompt}
ASSISTANT:
```
The default system prompt ("A chat.") was used for most of the prompts, however it also included a wide sampling of responses with other prompts, particularly in "stylized\_response", "rp", "gtkm", etc.
Here's another example:
```
A chat between Bob (aka USER) and Tom (aka ASSISTANT). Tom is an extremely intelligent 18th century bookkeeper, who speaks loquaciously.
USER: {prompt}
ASSISTANT:
```
And chat scenario that wouldn't require USER/ASSISTANT (but should use stopping criteria to prevent the model from speaking on your behalf).
```
A chat between old friends: Timmy and Tommy.
{description of characters}
{setting for the chat}
Timmy: *takes a big sip from his coffee* "Ah, sweet, delicious, magical coffee."
Tommy:
```
__*I strongly suggest adding stopping criteria/early inference stopping on "USER:", and/or whatever names you specify in the system prompt.*__
### Fine tuning info
https://wandb.ai/jondurbin/airoboros-l2-70b-2.2.1/runs/f91zmwuz?workspace=user-jondurbin
### Helpful usage tips
*The prompts shown here are are just the text that would be included after USER: and before ASSISTANT: in the full prompt format above, the system prompt and USER:/ASSISTANT: have been omited for readability.*
#### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
[key0: value0]
[key1: value1]
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
#### Summarization
500 samples have been included from [this dataset](https://huggingface.co/datasets/mattpscott/airoboros-summarization), using the same format as contextual question answering, for example:
```
BEGININPUT
{text to summarize}
ENDINPUT
BEGININSTRUCTION
Summarize the input in around 130 words.
ENDINSTRUCTION
```
#### Getting longer responses
You can use a few techniques to get longer responses.
Detailed prompts, with explicit instruction for word count:
```
Please compose a narrative set in the heart of an ancient library, steeped in the scent of old parchment and ink. The protagonist should be a young scholar who is dedicated to studying the art of storytelling and its evolution throughout history. In her pursuit of knowledge, she stumbles upon a forgotten tome that seems to possess an unusual aura. This book has the ability to bring stories to life, literally manifesting characters and scenarios from within its pages into reality.
The main character must navigate through various epochs of storytelling - from oral traditions of tribal societies, through medieval minstrels' tales, to modern-day digital narratives - as they come alive around her. Each era presents its unique challenges and lessons about the power and impact of stories on human civilization.
One such character could be a sentient quill pen, who was once used by renowned authors of yesteryears and now holds their wisdom and experiences. It becomes her mentor, guiding her through this journey with witty remarks and insightful commentary.
Ensure that your tale encapsulates the thrill of adventure, the beauty of learning, and the profound connection between humans and their stories. All characters involved should be non-human entities. Feel free to explore creative liberties but maintain the mentioned elements.
Your response should be approximately 2300 words.
```
Or, a simpler example:
```
Please create a long, detailed story about a dragon in an old growth forest who, for some reason, begins speaking the words of the source code of linux.
```
#### Coding
You can ask for fairly complex coding instructions with multiple criteria, e.g.:
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or inline criteria:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can also optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
#### Agent/function calling
The dataset includes many examples of function/args generation based on input criteria. This is somewhat similar to the OpenAI function calling, but the output is either JSON or YAML.
Example prompt:
```
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.
Input: I want to know how many times 'Python' is mentioned in my text file.
Available functions:
file_analytics:
description: This tool performs various operations on a text file.
params:
action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc.
filters:
keyword: The word or phrase we want to search for.
```
Response:
```json
{
"function": "file_analytics",
"params": {
"action": "count_occurrences",
"filters": {
"keyword": "Python"
}
}
}
```
#### Chain-of-thought
You can ask for several possible responses to a given problem, with a ranking and final answer selection.
Example prompt:
```
A group of people decide to play a round-robin tournament where every player plays every other player exactly once. If a total of 45 games were played, how many players participated in the tournament? Offer several potential answers, rank them according to mathematical logic, and pick the most feasible one.
```
Example response:
```
Solution 1:
In a round-robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players).
The formula for combinations is nC2 = n(n-1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows:
n(n-1)/2 = 45
Solving this equation gives us n=10.
Final answer: There were 10 players in the tournament.
Solution 2:
Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers.
If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9=45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players.
Final answer: There were 10 players in the tournament.
Solution 3:
We could also use trial and error to solve this problem. Starting from a small number of players, we calculate how many games would be played in a round-robin tournament until we reach 45 games. For example, with 2 players, only 1 game is played; with 3 players, 3 games are played; with 4 players, 6 games are played, and so on. Continuing this process, we find that with 10 players, 45 games are played.
Final answer: There were 10 players in the tournament.
Ranking of solutions from best to worst:
1. Solution 1: This solution uses direct mathematical reasoning based on the properties of a round-robin tournament and solves an equation to find the answer.
2. Solution 2: This solution uses the concept of triangular numbers which requires additional steps and knowledge beyond the immediate problem context, but still arrives at the correct answer.
3. Solution 3: This solution relies on trial and error, which is less efficient and reliable than the other methods, but it eventually gets to the right answer.
Best and final answer: There were 10 players in the tournament.
```
#### reWOO style execution planning
The model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions!
Example prompt:
```
Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string
that could be the user's question, one or more prior evidence values, or a combination of both.
Here are the tools available to be called:
DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer.
TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links.
HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links.
KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:?
The output should be in format:
Plan: [first action to take based on input question]
:evidence0: = [function to call with input parameter]
Plan: [next action to take, based on result of :evidence0:]
:evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"]
...
Answer: [:evidence[n]: containing the final answer.]
Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work?
```
Response:
```
Plan: Begin by conducting a web search to find out who won the Nobel Prize in Literature in 2020.
:evidence0: = DuckDuckGo[Nobel Prize in Literature 2020 winner]
Plan: Utilize the KnowledgeModel to interpret the search results and find the name of the laureate.
:evidence1: = KnowledgeModel[Who won the Nobel Prize in Literature in 2020, given :evidence0:?]
Plan: Conduct another web search to find the most famous work of the identified laureate.
:evidence2: = DuckDuckGo[Most famous work of :evidence1:]
Plan: Extract the relevant links from the DuckDuckGo search results for a more focused search.
:evidence3: = HyperlinkExtractor[:evidence2:]
Plan: Use the TextScraper tool to extract information from the relevant links.
:evidence4: = TextScraper[:evidence3:]
Plan: Finally, utilize the KnowledgeModel to identify and summarize the most famous work of the laureate from the extracted information.
:evidence5: = KnowledgeModel[What is the most famous work of :evidence1:, given :evidence4:?]
Answer: :evidence5:
```
For this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening:
```python
import re
import requests
def inject_context(input_text, **context):
for ref in set(re.findall(r"(:evidence[0-9]+:)", input_text, re.I)):
input_text = input_text.replace(ref, context.get(ref, ""))
return input_text
def duckduckgo(input_text, **context):
search_string = inject_context(input_text, **context)
... search via duck duck go using search_string
... return text content
def link_extractor(input_text, **context):
input_text = inject_context(input_text, **context)
return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", input_text, re.I))))
def scrape(input_text, **context):
input_text = inject_context(input_text, **context)
text = []
for link in input_text.splitlines():
text.append(requests.get(link).text)
return "\n".join(text)
def infer(input_text, **context)
prompt = inject_context(input_text, **context)
... call model with prompt, return output
def parse_plan(plan):
method_map = {
"DuckDuckGo": duckduckgo,
"HyperlinkExtractor": link_extractor,
"KnowledgeModel": infer,
"TextScraper": scrape,
}
context = {}
for line in plan.strip().splitlines():
if line.startswith("Plan:"):
print(line)
continue
parts = re.match("^(:evidence[0-9]+:)\s*=\s*([^\[]+])(\[.*\])\s$", line, re.I)
if not parts:
if line.startswith("Answer: "):
return context.get(line.split(" ")[-1].strip(), "Answer couldn't be generated...")
raise RuntimeError("bad format: " + line)
context[parts.group(1)] = method_map[parts.group(2)](parts.group(3), **context)
```
### Contribute
If you're interested in new functionality, particularly a new "instructor" type to generate a specific type of training data,
take a look at the dataset generation tool repo: https://github.com/jondurbin/airoboros and either make a PR or open an issue with details.
To help me with the OpenAI/compute costs:
- https://bmc.link/jondurbin
- ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
### Licence and usage restrictions
The airoboros 2.2 models are built on top of llama-2/codellama.
The llama-2 base model has a custom Meta license:
- See the [meta-license/LICENSE.txt](meta-license/LICENSE.txt) file attached for the original license provided by Meta.
- See also [meta-license/USE_POLICY.md](meta-license/USE_POLICY.md) and [meta-license/Responsible-Use-Guide.pdf](meta-license/Responsible-Use-Guide.pdf), also provided by Meta.
The fine-tuning data was mostly generated by OpenAI API calls to gpt-4, via [airoboros](https://github.com/jondurbin/airoboros)
The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI
- what does *compete* actually mean here?
- these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place
- if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works
- the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place
- other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2
I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly.
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
Either way, by using this model, you agree to completely indemnify me.
|
AzureBlack/Euryale-1.3-L2-70B-4.6bpw-6h-exl2
|
AzureBlack
| 2023-10-25T16:19:24Z | 7 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"en",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-19T03:34:39Z |
---
license: llama2
language:
- en
---
ExllamaV2 version of model created by the work of Sao10K
Original Card https://huggingface.co/Sao10K/Euryale-1.3-L2-70B
Requires ExllamaV2, which is being developed by turboderp https://github.com/turboderp/exllamav2 under an MIT license.
17th Attempt. Past 10 Failed, cost me >$200 lol.
Idea is an updated version of Euryale with ReMantik instead of the ties-merge between the original 3 models.
This is then mixed with a saucy model with a Mythomax-esque Ratio, and a certain experimental (self) LoRA applied to it.
Test Results: Works Well.
<br>NSFL and NSFW fine in roleplay context.
<br>slight censor with 0 context, zero issues in actual RP / ERP.
<br>Good Prose, Not Dumbed Down due to RP merges from testing.
<br> I have not encountered any repetition issues some had with the original Euryale. tell me if you do, though.
Prompt and System Format:
most works well. I recommend Alpaca.
ST Settings used for Test:
Lightning 1.1 System Prompt + Shortwave(1.2 Temperature)
Support me [here](https://ko-fi.com/sao10k) :)
Quants done by TheBloke! Ty a lot to him.
https://huggingface.co/TheBloke/Euryale-1.3-L2-70B-GPTQ
https://huggingface.co/TheBloke/Euryale-1.3-L2-70B-GGUF
https://huggingface.co/TheBloke/Euryale-1.3-L2-70B-AWQ
|
AzureBlack/Athena-v1-13b-5bpw-6h-exl2
|
AzureBlack
| 2023-10-25T16:18:28Z | 12 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-19T21:45:46Z |
---
license: llama2
---
ExllamaV2 version of model created by the work of IkariDev
Original Model https://huggingface.co/IkariDev/Athena-v1
Requires ExllamaV2, which is being developed by turboderp https://github.com/turboderp/exllamav2 under an MIT license.
---------
Experimental mythomax based ERP model. Use Alpaca format, merged models: mythomax, puddlejumper, airoboros, chronos beluga
gguf here: https://huggingface.co/TheBloke/Athena-v1-GGUF
|
AzureBlack/Thespis-13b-v0.3-5bpw-6h-exl2
|
AzureBlack
| 2023-10-25T16:16:15Z | 11 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-20T02:13:04Z |
---
license: llama2
---
Exllama 2 version of the model created by the work of cgato
Original Model https://huggingface.co/cgato/Thespis-13b-v0.3
Requires ExllamaV2, which is being developed by turboderp https://github.com/turboderp/exllamav2 under an MIT license.
-----------
This model is a bit of a personal project. It uses a vanilla chat template and is focused on providing multiturn sfw and nsfw RP experience.
This model works best with internet style RP using standard markup with asterisks surrounding actions and no quotes around dialogue.
It uses the following data:
* 3000 samples from Claude Multiround Chat 30k dataset
* 6000 samples from Pippa Dataset
* 3000 samples from Puffin Dataset
* 3800 samples of hand curated RP conversation with various characters.
Works with standard chat format for Ooba or SillyTavern.
Prompt Format: Chat
```
{System Prompt}
Username: {Input}
BotName: {Response}
Username: {Input}
BotName: {Response}
```
Turn Template (for Ooba):
You can either bake usernames into the prompt directly for ease of use or programatically add them if running through the API to use as a chatbot.
```
<|user|>{Username}: <|user-message|>\n<|bot|>{BotName}: <|bot-message|>\n
```
|
parshva-bhadra/DQN
|
parshva-bhadra
| 2023-10-25T16:15:30Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-25T16:14:47Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: -52.86 +/- 22.52
name: mean_reward
verified: false
---
# **DQN** Agent playing **LunarLander-v2**
This is a trained model of a **DQN** 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
...
```
|
haseong8012/whisper-small_child-50k_step-8k
|
haseong8012
| 2023-10-25T16:15:20Z | 16 | 0 |
transformers
|
[
"transformers",
"pytorch",
"whisper",
"automatic-speech-recognition",
"hf-asr-leaderboard",
"generated_from_trainer",
"ko",
"dataset:haseong8012/child-50k",
"base_model:openai/whisper-tiny",
"base_model:finetune:openai/whisper-tiny",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-10-20T21:04:31Z |
---
language:
- ko
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- haseong8012/child-50k
model-index:
- name: whisper_compare/whisper-small_child-50k2/checkpoint-8000
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. -->
# whisper_compare/whisper-small_child-50k2/checkpoint-8000
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the haseong8012/child-50k dataset.
- loss: 0.01577906496822834
- wer: 1.2814293799013663
- cer: 0.5696816412724527
## 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: 3.75e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
### Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1
|
anjakuzev/michael_scott_v3
|
anjakuzev
| 2023-10-25T16:13:41Z | 1 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:stablediffusionapi/cyberrealistic-v32",
"base_model:adapter:stablediffusionapi/cyberrealistic-v32",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2023-10-25T15:38:12Z |
---
license: creativeml-openrail-m
base_model: stablediffusionapi/cyberrealistic-v32
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA text2image fine-tuning - anjakuzev/michael_scott_v3
These are LoRA adaption weights for stablediffusionapi/cyberrealistic-v32. The weights were fine-tuned on the anjakuzev/michael_scott dataset. You can find some example images in the following.
|
Yukang/Llama-2-70b-chat-longlora-32k
|
Yukang
| 2023-10-25T16:10:36Z | 11 | 9 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"arxiv:2309.12307",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-21T12:51:06Z |
# LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
<font size=6><div align='center' > <a href=http://arxiv.org/abs/2309.12307>**Paper**</a> | <a href="https://huggingface.co/Yukang">**Models**</a> | <a href="https://github.com/dvlab-research/LongLoRA">**Code**</a> </div></font>
**LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models [[Paper](http://arxiv.org/abs/2309.12307)]** <br />
[Yukang Chen](https://scholar.google.com/citations?user=6p0ygKUAAAAJ&hl=en),
[Shengju Qian](https://scholar.google.com/citations?user=QNnWmasAAAAJ),
[Haotian Tang](https://scholar.google.com/citations?user=WxL13BAAAAAJ&hl),
[Xin Lai](https://scholar.google.com/citations?user=tqNDPA4AAAAJ&hl=zh-CN),
[Zhijian Liu](https://scholar.google.com/citations?user=3coYSTUAAAAJ&hl=en),
[Song Han](https://scholar.google.com/citations?user=E0iCaa4AAAAJ&hl=zh-CN),
[Jiaya Jia](https://scholar.google.com/citations?user=XPAkzTEAAAAJ&hl=en)<br />
## Abstract
We present LongLoRA, an efficient fine-tuning approach that extends the context sizes of pre-trained large language models (LLMs), with limited computation cost.
Typically, training LLMs with long context sizes is computationally expensive, requiring extensive training hours and GPU resources.
In this paper, we speed up the context extension of LLMs in two aspects. On the one hand, although dense global attention is needed during inference, fine-tuning the model can be effectively and efficiently done by sparse local attention. The proposed shift short attention effectively enables context extension, leading to non-trivial computation saving with similar performance to fine-tuning with vanilla attention. On the other hand, we find that LoRA for context extension works well under the premise of trainable embedding and normalization. LongLoRA demonstrates strong empirical results on various tasks on LLaMA2 models from 7B/13B to 70B. LongLoRA adopts LLaMA2 7B from 4k context to 100k, or LLaMA2 70B to 32k on a single 8x A100 machine. LongLoRA extends models' context while retaining their original architectures, and is compatible with most existing techniques, like FlashAttention-2. In addition, to make LongLoRA practical, we collect a dataset, LongQA, for supervised fine-tuning. It contains more than 3k long context question-answer pairs. For more details, please refer to the [paper](http://arxiv.org/abs/2309.12307).
## Highlights
**LongLoRA** speed up the context extension of pre-trained large language models in both attention-level and weight-level.
1. The proposed shifted short attention is easy to implement, compatible with Flash-Attention, and not required during inference.
2. We release all our models, including models from 7B to 70B, context length from 8k to 100k, including [LLaMA2-LongLoRA-7B-100k](https://huggingface.co/Yukang/Llama-2-7b-longlora-100k-ft), [LLaMA2-LongLoRA-13B-64k](https://huggingface.co/Yukang/Llama-2-13b-longlora-64k), and [LLaMA2-LongLoRA-70B-32k](https://huggingface.co/Yukang/Llama-2-70b-longlora-32k).
3. We build up a long-context QA dataset, LongQA, for supervised fine-tuning (SFT). We release 13B and 70B 32k models with SFT, [Llama-2-13b-chat-longlora-32k-sft](https://huggingface.co/Yukang/Llama-2-13b-chat-longlora-32k-sft) and [Llama-2-70b-chat-longlora-32k-sft](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k-sft). We will further release the dataset next week.
## Released models
### Models with supervised fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------------|------|---------|---------|-------------------------------------------------------------------------|
| Llama-2-13b-chat-longlora-32k-sft | 13B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-chat-longlora-32k-sft) |
| Llama-2-70b-chat-longlora-32k-sft | 70B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k-sft) |
### Models with context extension via fully fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------|------|---------|-------|-------------------------------------------------------------------|
| Llama-2-7b-longlora-8k-ft | 7B | 8192 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-8k-ft) |
| Llama-2-7b-longlora-16k-ft | 7B | 16384 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-16k-ft) |
| Llama-2-7b-longlora-32k-ft | 7B | 32768 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-32k-ft) |
| Llama-2-7b-longlora-100k-ft | 7B | 100000 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-100k-ft) |
| Llama-2-13b-longlora-8k-ft | 13B | 8192 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-8k-ft) |
| Llama-2-13b-longlora-16k-ft | 13B | 16384 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-16k-ft) |
| Llama-2-13b-longlora-32k-ft | 13B | 32768 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-32k-ft) |
### Models with context extension via improved LoRA fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------|------|---------|-------|-------------------------------------------------------------------|
| Llama-2-7b-longlora-8k | 7B | 8192 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-8k) |
| Llama-2-7b-longlora-16k | 7B | 16384 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-16k) |
| Llama-2-7b-longlora-32k | 7B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-32k) |
| Llama-2-13b-longlora-8k | 13B | 8192 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-8k) |
| Llama-2-13b-longlora-16k | 13B | 16384 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-16k) |
| Llama-2-13b-longlora-32k | 13B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-32k) |
| Llama-2-13b-longlora-64k | 13B | 65536 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-64k) |
| Llama-2-70b-longlora-32k | 70B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-70b-longlora-32k) |
| Llama-2-70b-chat-longlora-32k | 70B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k) |
## Citation
If you find this project useful in your research, please consider citing:
```
@article{longlora,
title={LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models},
author={Yukang Chen and Shengju Qian and Haotian Tang and Xin Lai and Zhijian Liu and Song Han and Jiaya Jia},
journal={arXiv:2309.12307},
year={2023}
}
```
## Acknowledgement
- This work is built upon the [LLaMA2](https://ai.meta.com/llama) as the pre-trained models.
- This work is based on [DeepSpeed](https://github.com/microsoft/DeepSpeed), [peft](https://github.com/huggingface/peft), and [Flash-Attention2](https://github.com/Dao-AILab/flash-attention) for acceleration.
- The perplexity evaluation code is modified upon [Landmark Attention](https://github.com/epfml/landmark-attention).
- We use [LongChat](https://github.com/DachengLi1/LongChat) for the retrieval evaluation.
|
Yukang/Llama-2-70b-longlora-32k
|
Yukang
| 2023-10-25T16:09:51Z | 14 | 18 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"arxiv:2309.12307",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-12T09:29:58Z |
# LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
<font size=6><div align='center' > <a href=http://arxiv.org/abs/2309.12307>**Paper**</a> | <a href="https://huggingface.co/Yukang">**Models**</a> | <a href="https://github.com/dvlab-research/LongLoRA">**Code**</a> </div></font>
**LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models [[Paper](http://arxiv.org/abs/2309.12307)]** <br />
[Yukang Chen](https://scholar.google.com/citations?user=6p0ygKUAAAAJ&hl=en),
[Shengju Qian](https://scholar.google.com/citations?user=QNnWmasAAAAJ),
[Haotian Tang](https://scholar.google.com/citations?user=WxL13BAAAAAJ&hl),
[Xin Lai](https://scholar.google.com/citations?user=tqNDPA4AAAAJ&hl=zh-CN),
[Zhijian Liu](https://scholar.google.com/citations?user=3coYSTUAAAAJ&hl=en),
[Song Han](https://scholar.google.com/citations?user=E0iCaa4AAAAJ&hl=zh-CN),
[Jiaya Jia](https://scholar.google.com/citations?user=XPAkzTEAAAAJ&hl=en)<br />
## Abstract
We present LongLoRA, an efficient fine-tuning approach that extends the context sizes of pre-trained large language models (LLMs), with limited computation cost.
Typically, training LLMs with long context sizes is computationally expensive, requiring extensive training hours and GPU resources.
In this paper, we speed up the context extension of LLMs in two aspects. On the one hand, although dense global attention is needed during inference, fine-tuning the model can be effectively and efficiently done by sparse local attention. The proposed shift short attention effectively enables context extension, leading to non-trivial computation saving with similar performance to fine-tuning with vanilla attention. On the other hand, we find that LoRA for context extension works well under the premise of trainable embedding and normalization. LongLoRA demonstrates strong empirical results on various tasks on LLaMA2 models from 7B/13B to 70B. LongLoRA adopts LLaMA2 7B from 4k context to 100k, or LLaMA2 70B to 32k on a single 8x A100 machine. LongLoRA extends models' context while retaining their original architectures, and is compatible with most existing techniques, like FlashAttention-2. In addition, to make LongLoRA practical, we collect a dataset, LongQA, for supervised fine-tuning. It contains more than 3k long context question-answer pairs. For more details, please refer to the [paper](http://arxiv.org/abs/2309.12307).
## Highlights
**LongLoRA** speed up the context extension of pre-trained large language models in both attention-level and weight-level.
1. The proposed shifted short attention is easy to implement, compatible with Flash-Attention, and not required during inference.
2. We release all our models, including models from 7B to 70B, context length from 8k to 100k, including [LLaMA2-LongLoRA-7B-100k](https://huggingface.co/Yukang/Llama-2-7b-longlora-100k-ft), [LLaMA2-LongLoRA-13B-64k](https://huggingface.co/Yukang/Llama-2-13b-longlora-64k), and [LLaMA2-LongLoRA-70B-32k](https://huggingface.co/Yukang/Llama-2-70b-longlora-32k).
3. We build up a long-context QA dataset, LongQA, for supervised fine-tuning (SFT). We release 13B and 70B 32k models with SFT, [Llama-2-13b-chat-longlora-32k-sft](https://huggingface.co/Yukang/Llama-2-13b-chat-longlora-32k-sft) and [Llama-2-70b-chat-longlora-32k-sft](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k-sft). We will further release the dataset next week.
## Released models
### Models with supervised fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------------|------|---------|---------|-------------------------------------------------------------------------|
| Llama-2-13b-chat-longlora-32k-sft | 13B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-chat-longlora-32k-sft) |
| Llama-2-70b-chat-longlora-32k-sft | 70B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k-sft) |
### Models with context extension via fully fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------|------|---------|-------|-------------------------------------------------------------------|
| Llama-2-7b-longlora-8k-ft | 7B | 8192 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-8k-ft) |
| Llama-2-7b-longlora-16k-ft | 7B | 16384 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-16k-ft) |
| Llama-2-7b-longlora-32k-ft | 7B | 32768 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-32k-ft) |
| Llama-2-7b-longlora-100k-ft | 7B | 100000 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-100k-ft) |
| Llama-2-13b-longlora-8k-ft | 13B | 8192 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-8k-ft) |
| Llama-2-13b-longlora-16k-ft | 13B | 16384 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-16k-ft) |
| Llama-2-13b-longlora-32k-ft | 13B | 32768 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-32k-ft) |
### Models with context extension via improved LoRA fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------|------|---------|-------|-------------------------------------------------------------------|
| Llama-2-7b-longlora-8k | 7B | 8192 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-8k) |
| Llama-2-7b-longlora-16k | 7B | 16384 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-16k) |
| Llama-2-7b-longlora-32k | 7B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-32k) |
| Llama-2-13b-longlora-8k | 13B | 8192 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-8k) |
| Llama-2-13b-longlora-16k | 13B | 16384 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-16k) |
| Llama-2-13b-longlora-32k | 13B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-32k) |
| Llama-2-13b-longlora-64k | 13B | 65536 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-64k) |
| Llama-2-70b-longlora-32k | 70B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-70b-longlora-32k) |
| Llama-2-70b-chat-longlora-32k | 70B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k) |
## Citation
If you find this project useful in your research, please consider citing:
```
@article{longlora,
title={LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models},
author={Yukang Chen and Shengju Qian and Haotian Tang and Xin Lai and Zhijian Liu and Song Han and Jiaya Jia},
journal={arXiv:2309.12307},
year={2023}
}
```
## Acknowledgement
- This work is built upon the [LLaMA2](https://ai.meta.com/llama) as the pre-trained models.
- This work is based on [DeepSpeed](https://github.com/microsoft/DeepSpeed), [peft](https://github.com/huggingface/peft), and [Flash-Attention2](https://github.com/Dao-AILab/flash-attention) for acceleration.
- The perplexity evaluation code is modified upon [Landmark Attention](https://github.com/epfml/landmark-attention).
- We use [LongChat](https://github.com/DachengLi1/LongChat) for the retrieval evaluation.
|
Yukang/Llama-2-13b-longlora-16k
|
Yukang
| 2023-10-25T16:09:27Z | 12 | 2 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"arxiv:2309.12307",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-12T09:25:11Z |
# LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
<font size=6><div align='center' > <a href=http://arxiv.org/abs/2309.12307>**Paper**</a> | <a href="https://huggingface.co/Yukang">**Models**</a> | <a href="https://github.com/dvlab-research/LongLoRA">**Code**</a> </div></font>
**LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models [[Paper](http://arxiv.org/abs/2309.12307)]** <br />
[Yukang Chen](https://scholar.google.com/citations?user=6p0ygKUAAAAJ&hl=en),
[Shengju Qian](https://scholar.google.com/citations?user=QNnWmasAAAAJ),
[Haotian Tang](https://scholar.google.com/citations?user=WxL13BAAAAAJ&hl),
[Xin Lai](https://scholar.google.com/citations?user=tqNDPA4AAAAJ&hl=zh-CN),
[Zhijian Liu](https://scholar.google.com/citations?user=3coYSTUAAAAJ&hl=en),
[Song Han](https://scholar.google.com/citations?user=E0iCaa4AAAAJ&hl=zh-CN),
[Jiaya Jia](https://scholar.google.com/citations?user=XPAkzTEAAAAJ&hl=en)<br />
## Abstract
We present LongLoRA, an efficient fine-tuning approach that extends the context sizes of pre-trained large language models (LLMs), with limited computation cost.
Typically, training LLMs with long context sizes is computationally expensive, requiring extensive training hours and GPU resources.
In this paper, we speed up the context extension of LLMs in two aspects. On the one hand, although dense global attention is needed during inference, fine-tuning the model can be effectively and efficiently done by sparse local attention. The proposed shift short attention effectively enables context extension, leading to non-trivial computation saving with similar performance to fine-tuning with vanilla attention. On the other hand, we find that LoRA for context extension works well under the premise of trainable embedding and normalization. LongLoRA demonstrates strong empirical results on various tasks on LLaMA2 models from 7B/13B to 70B. LongLoRA adopts LLaMA2 7B from 4k context to 100k, or LLaMA2 70B to 32k on a single 8x A100 machine. LongLoRA extends models' context while retaining their original architectures, and is compatible with most existing techniques, like FlashAttention-2. In addition, to make LongLoRA practical, we collect a dataset, LongQA, for supervised fine-tuning. It contains more than 3k long context question-answer pairs. For more details, please refer to the [paper](http://arxiv.org/abs/2309.12307).
## Highlights
**LongLoRA** speed up the context extension of pre-trained large language models in both attention-level and weight-level.
1. The proposed shifted short attention is easy to implement, compatible with Flash-Attention, and not required during inference.
2. We release all our models, including models from 7B to 70B, context length from 8k to 100k, including [LLaMA2-LongLoRA-7B-100k](https://huggingface.co/Yukang/Llama-2-7b-longlora-100k-ft), [LLaMA2-LongLoRA-13B-64k](https://huggingface.co/Yukang/Llama-2-13b-longlora-64k), and [LLaMA2-LongLoRA-70B-32k](https://huggingface.co/Yukang/Llama-2-70b-longlora-32k).
3. We build up a long-context QA dataset, LongQA, for supervised fine-tuning (SFT). We release 13B and 70B 32k models with SFT, [Llama-2-13b-chat-longlora-32k-sft](https://huggingface.co/Yukang/Llama-2-13b-chat-longlora-32k-sft) and [Llama-2-70b-chat-longlora-32k-sft](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k-sft). We will further release the dataset next week.
## Released models
### Models with supervised fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------------|------|---------|---------|-------------------------------------------------------------------------|
| Llama-2-13b-chat-longlora-32k-sft | 13B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-chat-longlora-32k-sft) |
| Llama-2-70b-chat-longlora-32k-sft | 70B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k-sft) |
### Models with context extension via fully fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------|------|---------|-------|-------------------------------------------------------------------|
| Llama-2-7b-longlora-8k-ft | 7B | 8192 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-8k-ft) |
| Llama-2-7b-longlora-16k-ft | 7B | 16384 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-16k-ft) |
| Llama-2-7b-longlora-32k-ft | 7B | 32768 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-32k-ft) |
| Llama-2-7b-longlora-100k-ft | 7B | 100000 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-100k-ft) |
| Llama-2-13b-longlora-8k-ft | 13B | 8192 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-8k-ft) |
| Llama-2-13b-longlora-16k-ft | 13B | 16384 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-16k-ft) |
| Llama-2-13b-longlora-32k-ft | 13B | 32768 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-32k-ft) |
### Models with context extension via improved LoRA fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------|------|---------|-------|-------------------------------------------------------------------|
| Llama-2-7b-longlora-8k | 7B | 8192 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-8k) |
| Llama-2-7b-longlora-16k | 7B | 16384 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-16k) |
| Llama-2-7b-longlora-32k | 7B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-32k) |
| Llama-2-13b-longlora-8k | 13B | 8192 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-8k) |
| Llama-2-13b-longlora-16k | 13B | 16384 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-16k) |
| Llama-2-13b-longlora-32k | 13B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-32k) |
| Llama-2-13b-longlora-64k | 13B | 65536 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-64k) |
| Llama-2-70b-longlora-32k | 70B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-70b-longlora-32k) |
| Llama-2-70b-chat-longlora-32k | 70B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k) |
## Citation
If you find this project useful in your research, please consider citing:
```
@article{longlora,
title={LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models},
author={Yukang Chen and Shengju Qian and Haotian Tang and Xin Lai and Zhijian Liu and Song Han and Jiaya Jia},
journal={arXiv:2309.12307},
year={2023}
}
```
## Acknowledgement
- This work is built upon the [LLaMA2](https://ai.meta.com/llama) as the pre-trained models.
- This work is based on [DeepSpeed](https://github.com/microsoft/DeepSpeed), [peft](https://github.com/huggingface/peft), and [Flash-Attention2](https://github.com/Dao-AILab/flash-attention) for acceleration.
- The perplexity evaluation code is modified upon [Landmark Attention](https://github.com/epfml/landmark-attention).
- We use [LongChat](https://github.com/DachengLi1/LongChat) for the retrieval evaluation.
|
Yukang/Llama-2-7b-longlora-8k
|
Yukang
| 2023-10-25T16:07:48Z | 22 | 5 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"arxiv:2309.12307",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-12T08:37:00Z |
# LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
<font size=6><div align='center' > <a href=http://arxiv.org/abs/2309.12307>**Paper**</a> | <a href="https://huggingface.co/Yukang">**Models**</a> | <a href="https://github.com/dvlab-research/LongLoRA">**Code**</a> </div></font>
**LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models [[Paper](http://arxiv.org/abs/2309.12307)]** <br />
[Yukang Chen](https://scholar.google.com/citations?user=6p0ygKUAAAAJ&hl=en),
[Shengju Qian](https://scholar.google.com/citations?user=QNnWmasAAAAJ),
[Haotian Tang](https://scholar.google.com/citations?user=WxL13BAAAAAJ&hl),
[Xin Lai](https://scholar.google.com/citations?user=tqNDPA4AAAAJ&hl=zh-CN),
[Zhijian Liu](https://scholar.google.com/citations?user=3coYSTUAAAAJ&hl=en),
[Song Han](https://scholar.google.com/citations?user=E0iCaa4AAAAJ&hl=zh-CN),
[Jiaya Jia](https://scholar.google.com/citations?user=XPAkzTEAAAAJ&hl=en)<br />
## Abstract
We present LongLoRA, an efficient fine-tuning approach that extends the context sizes of pre-trained large language models (LLMs), with limited computation cost.
Typically, training LLMs with long context sizes is computationally expensive, requiring extensive training hours and GPU resources.
In this paper, we speed up the context extension of LLMs in two aspects. On the one hand, although dense global attention is needed during inference, fine-tuning the model can be effectively and efficiently done by sparse local attention. The proposed shift short attention effectively enables context extension, leading to non-trivial computation saving with similar performance to fine-tuning with vanilla attention. On the other hand, we find that LoRA for context extension works well under the premise of trainable embedding and normalization. LongLoRA demonstrates strong empirical results on various tasks on LLaMA2 models from 7B/13B to 70B. LongLoRA adopts LLaMA2 7B from 4k context to 100k, or LLaMA2 70B to 32k on a single 8x A100 machine. LongLoRA extends models' context while retaining their original architectures, and is compatible with most existing techniques, like FlashAttention-2. In addition, to make LongLoRA practical, we collect a dataset, LongQA, for supervised fine-tuning. It contains more than 3k long context question-answer pairs. For more details, please refer to the [paper](http://arxiv.org/abs/2309.12307).
## Highlights
**LongLoRA** speed up the context extension of pre-trained large language models in both attention-level and weight-level.
1. The proposed shifted short attention is easy to implement, compatible with Flash-Attention, and not required during inference.
2. We release all our models, including models from 7B to 70B, context length from 8k to 100k, including [LLaMA2-LongLoRA-7B-100k](https://huggingface.co/Yukang/Llama-2-7b-longlora-100k-ft), [LLaMA2-LongLoRA-13B-64k](https://huggingface.co/Yukang/Llama-2-13b-longlora-64k), and [LLaMA2-LongLoRA-70B-32k](https://huggingface.co/Yukang/Llama-2-70b-longlora-32k).
3. We build up a long-context QA dataset, LongQA, for supervised fine-tuning (SFT). We release 13B and 70B 32k models with SFT, [Llama-2-13b-chat-longlora-32k-sft](https://huggingface.co/Yukang/Llama-2-13b-chat-longlora-32k-sft) and [Llama-2-70b-chat-longlora-32k-sft](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k-sft). We will further release the dataset next week.
## Released models
### Models with supervised fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------------|------|---------|---------|-------------------------------------------------------------------------|
| Llama-2-13b-chat-longlora-32k-sft | 13B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-chat-longlora-32k-sft) |
| Llama-2-70b-chat-longlora-32k-sft | 70B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k-sft) |
### Models with context extension via fully fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------|------|---------|-------|-------------------------------------------------------------------|
| Llama-2-7b-longlora-8k-ft | 7B | 8192 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-8k-ft) |
| Llama-2-7b-longlora-16k-ft | 7B | 16384 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-16k-ft) |
| Llama-2-7b-longlora-32k-ft | 7B | 32768 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-32k-ft) |
| Llama-2-7b-longlora-100k-ft | 7B | 100000 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-100k-ft) |
| Llama-2-13b-longlora-8k-ft | 13B | 8192 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-8k-ft) |
| Llama-2-13b-longlora-16k-ft | 13B | 16384 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-16k-ft) |
| Llama-2-13b-longlora-32k-ft | 13B | 32768 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-32k-ft) |
### Models with context extension via improved LoRA fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------|------|---------|-------|-------------------------------------------------------------------|
| Llama-2-7b-longlora-8k | 7B | 8192 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-8k) |
| Llama-2-7b-longlora-16k | 7B | 16384 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-16k) |
| Llama-2-7b-longlora-32k | 7B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-32k) |
| Llama-2-13b-longlora-8k | 13B | 8192 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-8k) |
| Llama-2-13b-longlora-16k | 13B | 16384 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-16k) |
| Llama-2-13b-longlora-32k | 13B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-32k) |
| Llama-2-13b-longlora-64k | 13B | 65536 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-64k) |
| Llama-2-70b-longlora-32k | 70B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-70b-longlora-32k) |
| Llama-2-70b-chat-longlora-32k | 70B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k) |
## Citation
If you find this project useful in your research, please consider citing:
```
@article{longlora,
title={LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models},
author={Yukang Chen and Shengju Qian and Haotian Tang and Xin Lai and Zhijian Liu and Song Han and Jiaya Jia},
journal={arXiv:2309.12307},
year={2023}
}
```
## Acknowledgement
- This work is built upon the [LLaMA2](https://ai.meta.com/llama) as the pre-trained models.
- This work is based on [DeepSpeed](https://github.com/microsoft/DeepSpeed), [peft](https://github.com/huggingface/peft), and [Flash-Attention2](https://github.com/Dao-AILab/flash-attention) for acceleration.
- The perplexity evaluation code is modified upon [Landmark Attention](https://github.com/epfml/landmark-attention).
- We use [LongChat](https://github.com/DachengLi1/LongChat) for the retrieval evaluation.
|
Ap4k/Pomni
|
Ap4k
| 2023-10-25T16:04:32Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2023-10-25T16:00:49Z |
---
license: apache-2.0
Original: https://huggingface.co/xekep/pomni/
---
|
hxxris/my_awesome_mind_model
|
hxxris
| 2023-10-25T16:03:59Z | 160 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"audio-classification",
"generated_from_trainer",
"dataset:minds14",
"base_model:facebook/wav2vec2-base",
"base_model:finetune:facebook/wav2vec2-base",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
audio-classification
| 2023-10-23T09:29:04Z |
---
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
datasets:
- minds14
metrics:
- accuracy
model-index:
- name: my_awesome_mind_model
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: minds14
type: minds14
config: en-US
split: train
args: en-US
metrics:
- name: Accuracy
type: accuracy
value: 0.05309734513274336
---
<!-- 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. -->
# my_awesome_mind_model
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the minds14 dataset.
It achieves the following results on the evaluation set:
- Loss: nan
- Accuracy: 0.0531
## 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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 0.8 | 3 | nan | 0.0531 |
| No log | 1.87 | 7 | nan | 0.0531 |
| 241.5783 | 2.93 | 11 | nan | 0.0531 |
| 241.5783 | 4.0 | 15 | nan | 0.0531 |
### Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
|
s3-tresio/blip-image-captioning-base
|
s3-tresio
| 2023-10-25T16:02:40Z | 19 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"blip",
"image-text-to-text",
"image-captioning",
"image-to-text",
"arxiv:2201.12086",
"license:bsd-3-clause",
"endpoints_compatible",
"region:us"
] |
image-to-text
| 2023-10-02T15:42:41Z |
---
pipeline_tag: image-to-text
tags:
- image-captioning
languages:
- en
license: bsd-3-clause
---
# BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
Model card for image captioning pretrained on COCO dataset - base architecture (with ViT base backbone).
|  |
|:--:|
| <b> Pull figure from BLIP official repo | Image source: https://github.com/salesforce/BLIP </b>|
## TL;DR
Authors from the [paper](https://arxiv.org/abs/2201.12086) write in the abstract:
*Vision-Language Pre-training (VLP) has advanced the performance for many vision-language tasks. However, most existing pre-trained models only excel in either understanding-based tasks or generation-based tasks. Furthermore, performance improvement has been largely achieved by scaling up the dataset with noisy image-text pairs collected from the web, which is a suboptimal source of supervision. In this paper, we propose BLIP, a new VLP framework which transfers flexibly to both vision-language understanding and generation tasks. BLIP effectively utilizes the noisy web data by bootstrapping the captions, where a captioner generates synthetic captions and a filter removes the noisy ones. We achieve state-of-the-art results on a wide range of vision-language tasks, such as image-text retrieval (+2.7% in average recall@1), image captioning (+2.8% in CIDEr), and VQA (+1.6% in VQA score). BLIP also demonstrates strong generalization ability when directly transferred to videolanguage tasks in a zero-shot manner. Code, models, and datasets are released.*
## Usage
You can use this model for conditional and un-conditional image captioning
### Using the Pytorch model
#### Running the model on CPU
<details>
<summary> Click to expand </summary>
```python
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg'
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
# conditional image captioning
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt")
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
# >>> a photography of a woman and her dog
# unconditional image captioning
inputs = processor(raw_image, return_tensors="pt")
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
>>> a woman sitting on the beach with her dog
```
</details>
#### Running the model on GPU
##### In full precision
<details>
<summary> Click to expand </summary>
```python
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base").to("cuda")
img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg'
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
# conditional image captioning
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt").to("cuda")
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
# >>> a photography of a woman and her dog
# unconditional image captioning
inputs = processor(raw_image, return_tensors="pt").to("cuda")
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
>>> a woman sitting on the beach with her dog
```
</details>
##### In half precision (`float16`)
<details>
<summary> Click to expand </summary>
```python
import torch
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base", torch_dtype=torch.float16).to("cuda")
img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg'
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
# conditional image captioning
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt").to("cuda", torch.float16)
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
# >>> a photography of a woman and her dog
# unconditional image captioning
inputs = processor(raw_image, return_tensors="pt").to("cuda", torch.float16)
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
>>> a woman sitting on the beach with her dog
```
</details>
## BibTex and citation info
```
@misc{https://doi.org/10.48550/arxiv.2201.12086,
doi = {10.48550/ARXIV.2201.12086},
url = {https://arxiv.org/abs/2201.12086},
author = {Li, Junnan and Li, Dongxu and Xiong, Caiming and Hoi, Steven},
keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
|
ntts9990/pms-zephyr-7b-alpha
|
ntts9990
| 2023-10-25T16:00:33Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-25T15:57:52Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0
|
GeroldMeisinger/controlnet-channels
|
GeroldMeisinger
| 2023-10-25T15:58:44Z | 0 | 1 | null |
[
"license:cc-by-nc-sa-4.0",
"region:us"
] | null | 2023-10-25T12:44:56Z |
---
license: cc-by-nc-sa-4.0
---
**Restore missing RGB channels**
Restore a missing channel of a RGB image by using ControlNet to guide image generation of Stable Diffusion to infer missing channel from the other two channels.
* See accompanying discussion at [github.com - Channels RGB](https://github.com/lllyasviel/ControlNet/discussions/567) with detailed report and evaluations.
* To restore images with missing channels you can use [this space](https://huggingface.co/spaces/GeroldMeisinger/channels).
* For evaluation images see the corresponding .zip's at "files".
* To run your own evaluations you can use [this script at gitlab.com](https://gitlab.com/-/snippets/3602096).
# Training
```
accelerate launch train_controlnet.py \
--pretrained_model_name_or_path="runwayml/stable-diffusion-v1-5" \
--train_batch_size=4 \
--gradient_accumulation_steps=8 \
--proportion_empty_prompts=0.5
--mixed_precision="fp16" \
--learning_rate=1e-5 \
--enable_xformers_memory_efficient_attention \
--use_8bit_adam \
--set_grads_to_none \
--seed=0 \
--num_train_epochs=2
```
# Image dataset
* laion2B-en aesthetics>=6.5 dataset
* --min_image_size 512 --max_aspect_ratio 2 --resize_mode="center_crop" --image_size 512
* Cleaned with `fastdup` default settings
* Data augmented with right-left flipped images
* Resulting in 214244 images
* Set whole channel to 0 by alternating between R-G-B channels
|
irishwerr/ppo-LunarLander-v2
|
irishwerr
| 2023-10-25T15:46:24Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-15T07:44:40Z |
---
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: 207.38 +/- 66.66
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
...
```
|
Yntec/NeverExisted
|
Yntec
| 2023-10-25T15:26:05Z | 325 | 4 |
diffusers
|
[
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"Retro",
"DucHaiten",
"elldreths",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-07-15T15:18:33Z |
---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
tags:
- stable-diffusion
- stable-diffusion-diffusers
- diffusers
- text-to-image
- Retro
- DucHaiten
- elldreths
---
# Never Existed
A mix of elldreths Retro Mix and DucHaiten retro so that you can create pictures from a past that never existed.
Original pages:
https://civitai.com/models/103966/duchaiten-
https://civitai.com/models/1474/elldreths-retro-mix
|
Wonski/ppo-LunarLander-v2
|
Wonski
| 2023-10-25T15:24:24Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-25T15:24:04Z |
---
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: 251.25 +/- 43.78
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
...
```
|
gouse-73/distilbert-base-uncased-distilled-clinc
|
gouse-73
| 2023-10-25T15:18:19Z | 21 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:clinc_oos",
"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
| 2023-10-23T18:16:55Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- clinc_oos
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-distilled-clinc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: clinc_oos
type: clinc_oos
config: plus
split: validation
args: plus
metrics:
- name: Accuracy
type: accuracy
value: 0.9438709677419355
---
<!-- 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-distilled-clinc
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3238
- Accuracy: 0.9439
## 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: 48
- eval_batch_size: 48
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 4.0341 | 1.0 | 318 | 3.0230 | 0.7245 |
| 2.3266 | 2.0 | 636 | 1.5597 | 0.8494 |
| 1.1958 | 3.0 | 954 | 0.8316 | 0.9142 |
| 0.6396 | 4.0 | 1272 | 0.5287 | 0.9332 |
| 0.3865 | 5.0 | 1590 | 0.4087 | 0.9365 |
| 0.2679 | 6.0 | 1908 | 0.3519 | 0.9406 |
| 0.2118 | 7.0 | 2226 | 0.3313 | 0.9416 |
| 0.1874 | 8.0 | 2544 | 0.3238 | 0.9439 |
### Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.14.1
|
aubreyrhodes/test_trainer
|
aubreyrhodes
| 2023-10-25T15:17:34Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"generated_from_trainer",
"dataset:yelp_review_full",
"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"
] |
text-classification
| 2023-10-25T15:10:12Z |
---
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
datasets:
- yelp_review_full
metrics:
- accuracy
model-index:
- name: test_trainer
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: yelp_review_full
type: yelp_review_full
config: yelp_review_full
split: test
args: yelp_review_full
metrics:
- name: Accuracy
type: accuracy
value: 0.604
---
<!-- 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. -->
# test_trainer
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the yelp_review_full dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3431
- Accuracy: 0.604
## 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: 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: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 125 | 1.0683 | 0.547 |
| No log | 2.0 | 250 | 1.1967 | 0.593 |
| No log | 3.0 | 375 | 1.3431 | 0.604 |
### Framework versions
- Transformers 4.34.1
- Pytorch 2.2.0.dev20231024
- Datasets 2.14.6
- Tokenizers 0.14.1
|
gouse-73/distilbert-base-uncased-finetuned-clinc
|
gouse-73
| 2023-10-25T14:59:05Z | 37 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:clinc_oos",
"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
| 2023-10-23T14:19:34Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- clinc_oos
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-clinc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: clinc_oos
type: clinc_oos
config: plus
split: validation
args: plus
metrics:
- name: Accuracy
type: accuracy
value: 0.9187096774193548
---
<!-- 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-clinc
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7733
- Accuracy: 0.9187
## 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: 48
- eval_batch_size: 48
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 4.2746 | 1.0 | 318 | 3.2618 | 0.7171 |
| 2.6008 | 2.0 | 636 | 1.8601 | 0.8352 |
| 1.532 | 3.0 | 954 | 1.1511 | 0.8952 |
| 1.005 | 4.0 | 1272 | 0.8543 | 0.9135 |
| 0.7921 | 5.0 | 1590 | 0.7733 | 0.9187 |
### Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.14.1
|
choidf/finetuning-sentiment-model-roberta-base-25000-samples
|
choidf
| 2023-10-25T14:58:42Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"text-classification",
"generated_from_trainer",
"dataset:imdb",
"base_model:FacebookAI/roberta-base",
"base_model:finetune:FacebookAI/roberta-base",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-25T11:41:49Z |
---
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
- f1
model-index:
- name: finetuning-sentiment-model-roberta-base-25000-samples
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: imdb
type: imdb
config: plain_text
split: train
args: plain_text
metrics:
- name: Accuracy
type: accuracy
value: 0.9476
- name: F1
type: f1
value: 0.9488481062085123
---
<!-- 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. -->
# finetuning-sentiment-model-roberta-base-25000-samples
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the imdb dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3321
- Accuracy: 0.9476
- F1: 0.9488
## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.2475 | 1.0 | 1407 | 0.2287 | 0.936 | 0.9383 |
| 0.1528 | 2.0 | 2814 | 0.2354 | 0.9328 | 0.9319 |
| 0.0888 | 3.0 | 4221 | 0.2754 | 0.9432 | 0.9452 |
| 0.0476 | 4.0 | 5628 | 0.2962 | 0.9464 | 0.9475 |
| 0.0275 | 5.0 | 7035 | 0.3321 | 0.9476 | 0.9488 |
### Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
|
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.