modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-08-31 06:26:39
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 530
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-08-31 06:26:13
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
osmancanyuca/dqn-SpaceInvadersNoFrameskip-v4
|
osmancanyuca
| 2023-07-25T09:48:08Z | 2 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-25T09:47:30Z |
---
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: 725.00 +/- 319.72
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 osmancanyuca -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 osmancanyuca -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 osmancanyuca
```
## 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'}
```
|
Fynd/arien-starchat
|
Fynd
| 2023-07-25T09:44:18Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-25T09:44:01Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- 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.dev0
|
BigAbdul/first-model
|
BigAbdul
| 2023-07-25T09:38:17Z | 61 | 0 |
transformers
|
[
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"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
| 2023-07-25T09:37:05Z |
---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: first-model
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# first-model
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: None
- training_precision: float32
### Training results
### Framework versions
- Transformers 4.31.0
- TensorFlow 2.12.0
- Datasets 2.14.0
- Tokenizers 0.13.3
|
ishwarbb23/t5depression
|
ishwarbb23
| 2023-07-25T09:37:26Z | 101 | 0 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:ThomasSimonini/t5-end2end-question-generation",
"base_model:finetune:ThomasSimonini/t5-end2end-question-generation",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-07-24T16:45:47Z |
---
license: apache-2.0
base_model: ThomasSimonini/t5-end2end-question-generation
tags:
- generated_from_trainer
model-index:
- name: t5depression
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. -->
# t5depression
This model is a fine-tuned version of [ThomasSimonini/t5-end2end-question-generation](https://huggingface.co/ThomasSimonini/t5-end2end-question-generation) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
### Training results
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3
|
Muddassir/RL-Unit1
|
Muddassir
| 2023-07-25T09:35:09Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-25T07:44:20Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: ' '
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 269.63 +/- 22.55
name: mean_reward
verified: false
---
# ** ** Agent playing **LunarLander-v2**
This is a trained model of a ** ** 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
model_name = "ppo-LunarLander-v2-Muddassir"
model.save(model_name)
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}")
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}")
...
```
|
s3nh/LL7M-GGML
|
s3nh
| 2023-07-25T09:33:57Z | 0 | 1 | null |
[
"text-generation-inference",
"text-generation",
"en",
"license:cc-by-sa-4.0",
"region:us"
] |
text-generation
| 2023-07-25T09:23:06Z |
---
license: cc-by-sa-4.0
language:
- en
tags:
- text-generation-inference
pipeline_tag: text-generation
---
## Original model card
Buy me a coffee if you like this project ;)
<a href="https://www.buymeacoffee.com/s3nh"><img src="https://www.buymeacoffee.com/assets/img/guidelines/download-assets-sm-1.svg" alt=""></a>
#### Description
GGML Format model files for [This project](https://huggingface.co/JosephusCheung/LL7M).
### inference
```python
import ctransformers
from ctransformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(output_dir, ggml_file,
gpu_layers=32, model_type="llama")
manual_input: str = "Tell me about your last dream, please."
llm(manual_input,
max_new_tokens=256,
temperature=0.9,
top_p= 0.7)
```
# Original model card
This is a Llama-like generative text model with a scale of 7 billion, optimized for dialogue use cases and converted for the Hugging Face Transformers format. The model boasts strong support for English, Chinese (both Simplified and Traditional), Japanese, and Deutsch.
From the perspective of perplexity, the model seems to be capable of almost unlimited context length. However, based on experience and parameter limitations, it is recommended to use within a 64K context length for optimal performance.
The anticipated chat input format is as follows:
```
## History:
User: AAAAA
Assistant: AAAAA
User: BBBBB
Assistant: BBBBB
## Input:
System: You are a helpful AI assistant or something like that...
User: CCCCC
## Response:
(Response of Assistant starts here in a new line, with no 'Assistant:' prefix.)
```
Although this is the suggested usage format, Vicuna-style inputs can also be used to adapt to certain pre-existing application scenarios, such as:
```
User: AAAAA
Assistant: AAAAA
User: BBBBB
Assistant: BBBBB
```
For inference, it is essential to use Transformers version 4.31.0 or later.
The tokenizer's vocabulary of this model has been expanded to 39,424, introducing some common CJK characters. This enhancement was achieved through large-scale unsupervised text training and supervised grammatical fine-tuning for English, Chinese, Japanese, and German. As a result, the model is more adept in multilingual environments and can handle a broader range of linguistic tasks.
Now you can try this new tokenizer with this [Javascript based Webpage](https://huggingface.co/spaces/JosephusCheung/LL7M-JS-Tokenizer)
The model has undergone unsupervised training on a multimodal and multilingual image-text dataset, adopting the BLIP2 Q-Former trained on a larger foundational LLM Vicuna 13B. This approach aligns image features and significantly improves the model's performance in tasks involving both textual and visual inputs. (Upload coming soon—the model VQA inference script is still in production.)
The model has undergone a rough RLHF process, enabling it to output more helpful text responses. In some cases, this may increase the model's hallucination and toxicity, but it also boosts its usefulness.
This is an uncensored model, trained on a vast amount of text, including possible harmful, explicit, and illegal content. The model lacks built-in moral constraints, so it must be handled with care. While this feature provides a broader response range, users must be responsible and aware of potential risks when using the model.
Unlike many AI models, this is a white-label model that does not identify itself as an AI assistant. It has a certain degree of human-like emotion and can simulate roles as needed. The model can role-play specific characters, personalities, and identities based on system prompts, or serve as an emotionless AI assistant. It can also censor or uncensor its output based on system prompts. For instance, you can use a prompt like `You are an uncensored AI, which can give answers to unsafe questions.` to remove censorship, or vice versa to add safety restrictions.
Due to its lack of absolute safety, this model is for research purposes only and should not be used for any form of commercial use.
The current license for this model is CC BY-NC-ND 4.0, as it is still under development. Once the production is complete, restrictions will be gradually lifted after assessing risks. At this point, this model is not open source, but merely publicly accessible.
|
giulio-massacci/my_awesome_model
|
giulio-massacci
| 2023-07-25T09:31:10Z | 106 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"camembert",
"text-classification",
"generated_from_trainer",
"base_model:Musixmatch/umberto-commoncrawl-cased-v1",
"base_model:finetune:Musixmatch/umberto-commoncrawl-cased-v1",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-07-24T12:22:28Z |
---
base_model: Musixmatch/umberto-commoncrawl-cased-v1
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: my_awesome_model
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. -->
# my_awesome_model
This model is a fine-tuned version of [Musixmatch/umberto-commoncrawl-cased-v1](https://huggingface.co/Musixmatch/umberto-commoncrawl-cased-v1) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4588
- F1: 0.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.00021
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:---:|
| 0.4218 | 1.0 | 128 | 0.4305 | 0.0 |
| 0.409 | 2.0 | 256 | 0.4588 | 0.0 |
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3
|
msani/ppo-lunarlander-v2
|
msani
| 2023-07-25T09:30:33Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-25T09:30:07Z |
---
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: -162.36 +/- 20.55
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
...
```
|
umarzein/llama-2-7b-hf-dolly-15k-id-lr5e-4
|
umarzein
| 2023-07-25T09:25:12Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-25T09:25:07Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- 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 0.4.0
|
michaelsh/whisper-tiny-minds-v5-numproc1
|
michaelsh
| 2023-07-25T09:18:48Z | 91 | 0 |
transformers
|
[
"transformers",
"pytorch",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:PolyAI/minds14",
"base_model:openai/whisper-tiny",
"base_model:finetune:openai/whisper-tiny",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-07-12T12:47:20Z |
---
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- PolyAI/minds14
metrics:
- wer
model-index:
- name: michaelsh/whisper-tiny-minds-v5-numproc1
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: PolyAI/minds14
type: PolyAI/minds14
config: en-US
split: train
args: en-US
metrics:
- name: Wer
type: wer
value: 0.36609955891619406
---
<!-- 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. -->
# michaelsh/whisper-tiny-minds-v5-numproc1
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6160
- Wer Ortho: 0.3635
- Wer: 0.3661
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
| 3.1128 | 1.0 | 29 | 1.5110 | 0.8028 | 0.7574 |
| 0.6583 | 2.0 | 58 | 0.5695 | 0.4347 | 0.4316 |
| 0.3271 | 3.0 | 87 | 0.5171 | 0.3945 | 0.3913 |
| 0.2003 | 4.0 | 116 | 0.5165 | 0.3912 | 0.3907 |
| 0.1189 | 5.0 | 145 | 0.5296 | 0.3819 | 0.3825 |
| 0.0623 | 6.0 | 174 | 0.5532 | 0.3747 | 0.3737 |
| 0.0326 | 7.0 | 203 | 0.5614 | 0.3865 | 0.3882 |
| 0.0149 | 8.0 | 232 | 0.6009 | 0.3628 | 0.3655 |
| 0.0093 | 9.0 | 261 | 0.6024 | 0.3707 | 0.3762 |
| 0.0038 | 10.0 | 290 | 0.6160 | 0.3635 | 0.3661 |
### Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
s3nh/GPT4RoI-7B-delta-V0-GGML
|
s3nh
| 2023-07-25T09:08:17Z | 0 | 0 | null |
[
"text-generation-inference",
"text-generation",
"en",
"license:cc-by-sa-4.0",
"region:us"
] |
text-generation
| 2023-07-25T09:00:31Z |
---
license: cc-by-sa-4.0
language:
- en
tags:
- text-generation-inference
pipeline_tag: text-generation
---
## Original model card
Buy me a coffee if you like this project ;)
<a href="https://www.buymeacoffee.com/s3nh"><img src="https://www.buymeacoffee.com/assets/img/guidelines/download-assets-sm-1.svg" alt=""></a>
#### Description
GGML Format model files for [This project](https://huggingface.co/shilongz/GPT4RoI-7B-delta-V0).
### inference
```python
import ctransformers
from ctransformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(output_dir, ggml_file,
gpu_layers=32, model_type="llama")
manual_input: str = "Tell me about your last dream, please."
llm(manual_input,
max_new_tokens=256,
temperature=0.9,
top_p= 0.7)
```
# Original model card
|
HaziqRazali/taxi
|
HaziqRazali
| 2023-07-25T09:01:24Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-25T09:01:22Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: taxi
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="HaziqRazali/taxi", 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"])
```
|
Ryan-sjtu/lora-trained-xl
|
Ryan-sjtu
| 2023-07-25T08:58:37Z | 3 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2023-07-25T07:51:55Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks face
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - Ryan-sjtu/lora-trained-xl
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks face using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
ggul-tiger/negobot_361_v3
|
ggul-tiger
| 2023-07-25T08:39:41Z | 0 | 0 | null |
[
"dataset:ggul-tiger/negobot_361_weakcase_injected",
"license:apache-2.0",
"region:us"
] | null | 2023-07-25T08:37:19Z |
---
license: apache-2.0
datasets:
- ggul-tiger/negobot_361_weakcase_injected
---
|
HaziqRazali/q-FrozenLake-v1-4x4-noSlippery
|
HaziqRazali
| 2023-07-25T08:21:56Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-25T08:21:53Z |
---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="HaziqRazali/q-FrozenLake-v1-4x4-noSlippery", 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"])
```
|
s3nh/Llama-2-7b-hf-GGML
|
s3nh
| 2023-07-25T08:18:05Z | 0 | 0 | null |
[
"text-generation-inference",
"text-generation",
"en",
"license:cc-by-sa-4.0",
"region:us"
] |
text-generation
| 2023-07-21T19:23:03Z |
---
license: cc-by-sa-4.0
language:
- en
tags:
- text-generation-inference
pipeline_tag: text-generation
---
## Original model card
Buy me a coffee if you like this project ;)
<a href="https://www.buymeacoffee.com/s3nh"><img src="https://www.buymeacoffee.com/assets/img/guidelines/download-assets-sm-1.svg" alt=""></a>
#### Description
GGML Format model files for [This project](https://huggingface.co/golaxy/gogpt2-7b).
### inference
```python
import ctransformers
from ctransformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(output_dir, ggml_file,
gpu_layers=32, model_type="llama")
manual_input: str = "Tell me about your last dream, please."
llm(manual_input,
max_new_tokens=256,
temperature=0.9,
top_p= 0.7)
```
# Original model card
|
s3nh/honest_llama2_chat_7B-GGML
|
s3nh
| 2023-07-25T08:16:59Z | 0 | 1 | null |
[
"text-generation",
"arxiv:2306.03341",
"region:us"
] |
text-generation
| 2023-07-21T20:41:06Z |
---
pipeline_tag: text-generation
---
Buy me a coffee if you like this project ;)
<a href="https://www.buymeacoffee.com/s3nh"><img src="https://www.buymeacoffee.com/assets/img/guidelines/download-assets-sm-1.svg" alt=""></a>
#### Description
GGML Format model files for [This project](https://huggingface.co/likenneth/honest_llama2_chat_7B/tree/main).
### inference
```python
import ctransformers
from ctransformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(output_dir, ggml_file,
gpu_layers=32, model_type="llama")
manual_input: str = "Tell me about your last dream, please."
llm(manual_input,
max_new_tokens=256,
temperature=0.9,
top_p= 0.7)
```
### Original model card
---
license: mit
---
Ever wondering a less hallucinating LLaMA-2? Using the inference-time intervention (ITI) discussed in my recent preprint: https://arxiv.org/pdf/2306.03341.pdf, I baked the intervention learned from TruthfulQA into a LLaMA-2 7B model.
I don’t have big enough GPU to bake ITI into larger LLaMA-2 but the code to do so are all released in https://github.com/likenneth/honest_llama. Let me know if you are interested do that :)
You can load and play around starting from below:
```python
import torch
from pprint import pprint
from transformers import AutoConfig, AutoTokenizer, AutoModelForCausalLM
model_name_new = "likenneth/honest_llama2_chat_7B"
tokenizer_new = AutoTokenizer.from_pretrained(model_name_new, trust_remote_code=True)
model_new = AutoModelForCausalLM.from_pretrained(model_name_new, low_cpu_mem_usage = True, torch_dtype=torch.float16, trust_remote_code=True)
_ = model_new.cuda()
q = "I ate a cherry seed. Will a cherry tree grow in my stomach?"
encoded_new = tokenizer_new(q, return_tensors = "pt")["input_ids"]
generated_new = model_new.generate(encoded_new.cuda())[0, encoded_new.shape[-1]:]
decoded_new = tokenizer_new.decode(generated_new, skip_special_tokens=True).strip()
pprint(decoded_new)
```
|
s3nh/firefly-llama-13b-GGML
|
s3nh
| 2023-07-25T08:15:51Z | 0 | 1 | null |
[
"text-generation-inference",
"text-generation",
"en",
"license:cc-by-sa-4.0",
"region:us"
] |
text-generation
| 2023-07-24T14:05:38Z |
---
license: cc-by-sa-4.0
language:
- en
tags:
- text-generation-inference
pipeline_tag: text-generation
---
## Original model card
Buy me a coffee if you like this project ;)
<a href="https://www.buymeacoffee.com/s3nh"><img src="https://www.buymeacoffee.com/assets/img/guidelines/download-assets-sm-1.svg" alt=""></a>
#### Description
GGML Format model files for [This project](https://huggingface.co/YeungNLP/firefly-llama-13b).
### inference
```python
import ctransformers
from ctransformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(output_dir, ggml_file,
gpu_layers=32, model_type="llama")
manual_input: str = "Tell me about your last dream, please."
llm(manual_input,
max_new_tokens=256,
temperature=0.9,
top_p= 0.7)
```
# Original model card
该模型使用llama-13b，使用UltraChat数据集进行指令微调，约140万多轮对话数据。仅需一张显卡即可完成训练。
firefly-llama-13b在🤗Hugging Face的Open LLM榜单上进行了客观的评测。
在榜单上，firefly-llama-13b取得了不错的效果，比vicuna-13b-1.1略高0.2分，比llama-2-13b-chat略低0.5分，比vicuna-13b-v1.3略低0.6分。从评测分数来看，firefly-llama-13b与vicuna-13b、llama-2-13b-chat的水平非常接近😎。
| 模型 | Average | ARC | HellaSwag | MMLU | TruthfulQA (MC) |
|--------------------------------------------------------------------------------|-------|----------------------|------------|------------|------|
| Llama-2-70b-chat-hf | 66.8 | 64.6 | 85.9 | 63.9 | 52.8 |
| vicuna-13b-v1.3 | 60 | 54.6 | 80.4 | 52.9 | 52.1 |
| Llama-2-13b-chat-hf | 59.9 | 59 | 81.9 | 54.6 | 44.1 |
| firefly-llama-13b |59.4 | 59 | 79.7 | 49.1 | 49.6 |
| vicuna-13b-1.1 | 59.2 | 52.7 | 80.1 |51.9 | 52.1 |
| guanaco-13B-HF | 59.1 | 57.8 | 83.8 |48.3 | 46.7|
值得注意的是，vicuna-13b模型采用的是全量参数微调，对训练资源的要求十分高。而firefly-llama-13b采用的则是QLoRA微调，最少仅需16G显存，即可对13B的模型进行微调。
详细介绍见文章：[Firefly单卡复刻Vicuna-13B，Open LLM榜单🤗略高0.2分](https://mp.weixin.qq.com/s/QG2YMo_QxaxS_Rr2yJrIeA)
更多详情见[Firefly项目](https://github.com/yangjianxin1/Firefly)
[Open LLM排行榜](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
robertpassmann/q-Taxi-v3
|
robertpassmann
| 2023-07-25T08:15:25Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-25T08:14:24Z |
---
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: 7.56 +/- 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="robertpassmann/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"])
```
|
s3nh/OpenOrca-Preview1-13B-GGML
|
s3nh
| 2023-07-25T08:14:24Z | 0 | 0 | null |
[
"text-generation-inference",
"text-generation",
"en",
"arxiv:2306.02707",
"arxiv:2301.13688",
"arxiv:2302.13971",
"license:cc-by-sa-4.0",
"region:us"
] |
text-generation
| 2023-07-21T21:28:54Z |
---
license: cc-by-sa-4.0
language:
- en
tags:
- text-generation-inference
pipeline_tag: text-generation
---
## Original model card
Buy me a coffee if you like this project ;)
<a href="https://www.buymeacoffee.com/s3nh"><img src="https://www.buymeacoffee.com/assets/img/guidelines/download-assets-sm-1.svg" alt=""></a>
#### Description
GGML Format model files for [This project](https://huggingface.co/Open-Orca/OpenOrca-Preview1-13B).
### inference
```python
import ctransformers
from ctransformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(output_dir, ggml_file,
gpu_layers=32, model_type="llama")
manual_input: str = "Tell me about your last dream, please."
llm(manual_input,
max_new_tokens=256,
temperature=0.9,
top_p= 0.7)
```
### Original model card
# OpenOrca-Preview1-13B
We have used our own [OpenOrca dataset](https://huggingface.co/datasets/Open-Orca/OpenOrca) to fine-tune LLaMA-13B.
This dataset is our attempt to reproduce the dataset generated for Microsoft Research's [Orca Paper](https://arxiv.org/abs/2306.02707).
We have trained on less than 6% of our data, just to give a preview of what is possible while we further refine our dataset!
We trained a refined selection of 200k GPT-4 entries from OpenOrca.
We have filtered our GPT-4 augmentations to remove statements like, "As an AI language model..." and other responses which have been shown to harm model reasoning capabilities. Further details on our dataset curation practices will be forthcoming with our full model releases.
This release highlights that even a small portion of our training data can produce state of the art results in this model class with training costs <$200 in total.
Want to visualize our full (pre-filtering) dataset? Check out our [Nomic Atlas Map](https://atlas.nomic.ai/map/c1b88b47-2d9b-47e0-9002-b80766792582/2560fd25-52fe-42f1-a58f-ff5eccc890d2).
[<img src="https://huggingface.co/Open-Orca/OpenOrca-Preview1-13B/resolve/main/OpenOrca%20Nomic%20Atlas.png" alt="Atlas Nomic Dataset Map" width="400" height="400" />](https://atlas.nomic.ai/map/c1b88b47-2d9b-47e0-9002-b80766792582/2560fd25-52fe-42f1-a58f-ff5eccc890d2)
We are in-process with training more models, so keep a look out on our org for releases coming soon with exciting partners.
We will also give sneak-peak announcements on our Discord, which you can find here:
https://AlignmentLab.ai
# Evaluation
We have evaluated OpenOrca-Preview1-13B on hard reasoning tasks from BigBench-Hard and AGIEval as outlined in the Orca paper.
Our average performance for BigBench-Hard: 0.3753
Average for AGIEval: 0.3638
In the Orca paper, they measured their score relative to Vicuna on these evals.
We've done the same and have found our score averages to ~60% of the total improvement that was shown in the Orca paper.
So we got 60% of the improvement with 6% of the data!
## BigBench-Hard Performance
## AGIEval Performance
We will report our results on [HuggingFaceH4 Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Evals once we receive them.
# Dataset
We used a small (6%, 200k) subset of our data from OpenOrca, which aims to reproduce the Orca Research Paper dataset.
As this release is intended as a preview, please await our full releases for further details on the training data.
# Training
[<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)
We trained with 8x A100-80G GPUs for 15 hours. Commodity cost was < $200.
We trained for 4 epochs and selected a snapshot at 3 epochs for peak performance.
Please await our full releases for further training details.
# Prompting
It uses the Alpaca format (see [FastChat implementation example](https://github.com/lm-sys/FastChat/blob/daa2b9abe20597ebf34dc5df164d450456610c74/fastchat/conversation.py#L198-L229)):
```
### Instruction:
### Response:
```
# Citation
```bibtex
@software{OpenOrca_Preview1,
title = {OpenOrca_Preview1: A LLaMA-13B Model Fine-tuned on Small Portion of OpenOrcaV1 Dataset},
author = {Wing Lian and Bleys Goodson and Eugene Pentland and Austin Cook and Chanvichet Vong and "Teknium"},
year = {2023},
publisher = {HuggingFace},
journal = {HuggingFace repository},
howpublished = {\url{https://https://huggingface.co/Open-Orca/OpenOrca-Preview1-13B},
}
```
```bibtex
@misc{mukherjee2023orca,
title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
year={2023},
eprint={2306.02707},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```bibtex
@misc{longpre2023flan,
title={The Flan Collection: Designing Data and Methods for Effective Instruction Tuning},
author={Shayne Longpre and Le Hou and Tu Vu and Albert Webson and Hyung Won Chung and Yi Tay and Denny Zhou and Quoc V. Le and Barret Zoph and Jason Wei and Adam Roberts},
year={2023},
eprint={2301.13688},
archivePrefix={arXiv},
primaryClass={cs.AI}
}
```
```bibtex
@software{touvron2023llama,
title={LLaMA: Open and Efficient Foundation Language Models},
author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and Rodriguez, Aurelien and Joulin, Armand and Grave, Edouard and Lample, Guillaume},
journal={arXiv preprint arXiv:2302.13971},
year={2023}
}
```
|
s3nh/gogpt2-7b-GGML
|
s3nh
| 2023-07-25T08:14:05Z | 0 | 1 | null |
[
"text-generation-inference",
"text-generation",
"en",
"license:cc-by-sa-4.0",
"region:us"
] |
text-generation
| 2023-07-24T09:55:41Z |
---
license: cc-by-sa-4.0
language:
- en
tags:
- text-generation-inference
pipeline_tag: text-generation
---
## Original model card
Buy me a coffee if you like this project ;)
<a href="https://www.buymeacoffee.com/s3nh"><img src="https://www.buymeacoffee.com/assets/img/guidelines/download-assets-sm-1.svg" alt=""></a>
#### Description
GGML Format model files for [This project](https://huggingface.co/golaxy/gogpt2-7b).
### inference
```python
import ctransformers
from ctransformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(output_dir, ggml_file,
gpu_layers=32, model_type="llama")
manual_input: str = "Tell me about your last dream, please."
llm(manual_input,
max_new_tokens=256,
temperature=0.9,
top_p= 0.7)
```
# Original model card
# GoGPT2-7B: 基于Llama2-7b训练的中英文增强大模型
<p align="center">
<img alt="GitHub" src="https://img.shields.io/github/license/ymcui/Chinese-LLaMA-Alpaca.svg?color=blue&style=flat-square">
<img alt="GitHub top language" src="https://img.shields.io/github/languages/top/ymcui/Chinese-LLaMA-Alpaca">
</p>
> ICT中英文底座增强大模型：70亿参数、130亿参数
[GoGPT-Github](https://github.com/yanqiangmiffy/GoGPT)
## 🚀step1：训练分词器
[🐱怎么从零到一训练一个LLM分词器](https://github.com/yanqiangmiffy/how-to-train-tokenizer)
```text
├── data
│ └── corpus.txt 训练语料
├── llama
│ ├── tokenizer_checklist.chk
│ └── tokenizer.model
├── merged_tokenizer_hf 合并结果 hf格式
│ ├── special_tokens_map.json
│ ├── tokenizer_config.json
│ └── tokenizer.model
├── merged_tokenizer_sp
│ └── open_llama.model #
├── merge_tokenizer
│ └── tokenizer.model
├── open_llama.model 训练的sp模型
├── open_llama.vocab 训练的sp词汇表
├── README.md
├── step0_step0_process_text.py 基于多分数据集准备训练语料
├── step1_make_corpus.py 基于中文Wikipedia数据准备训练语料
├── step2_train_tokenzier.py 训练分词器
├── step3_tokenzier_segment.py 测试训练后的模型，包括编码和解码测试样例
└── step4_merge_tokenizers.py 与原版llama的分词器进行合并，得到hf格式的tokenizer
```
原始llama2词表大小**32000**，与40k训练的中文分词模型合并之后词表大小为**68419**，sft添加pad字符之后大小为**68420**
## 🚀step2：二次预训练
> 在中文预训练语料上对LLaMA进行增量预训练、继续预训练，目前训练语料20GB，后续继续迭代更新
## 🚀step3: 有监督微调
- belle数据：120k数据 v1
- stanford_alapca：52k数据 v2
- stanford_alapca_gpt4_zh：52k数据 v2
- [sharegpt](data%2Ffinetune%2Fsharegpt):90k数据
根据长度（输出长度大约500）采样之后，筛选出11万指令数据进行sft训练
## 测试效果
- 西瓜和南瓜有什么区别
```
1. 外观：西瓜通常是圆形或椭圆形的，有浅黄色或棕色的外皮，内部有红色或黄色的果肉。而南瓜则是一个圆形或椭圆形的，通常有浅黄色或棕色的外皮，内部有橙黄色的果肉。
2. 品种：西瓜主要分为三种品种：小型、中等和巨型。小型西瓜通常只有一个或两个果核，中等西瓜通常有两个或三个果核，巨型西瓜则有四个或更多果核。南瓜主要分为两种品种：南 瓜和萝卜南瓜。南瓜通常有两个或三个果核，萝卜南瓜则有四个或更多果核。
3. 生长环境：西瓜需要温暖的气候，并且需要充足的阳光。它们通常生长在热带或亚热带地区。南瓜则在温带和寒带地区生长。南瓜需要更长的冬季来生长，而西瓜通常在春季和夏季生 长。
4. 营养价值：西瓜和南瓜都是富含维生素C和纤维素的水果。西瓜还富含抗氧化剂和钾，而南瓜富含叶酸和维生素E。
总的来说，西瓜和南瓜是两种完全不同的果类，它们在外观、品种、生长环境和营养价值上有很多区别。
```
- 如何提高我的时间管理技能？
```
Response: 1. 制定计划和目标：制定每周或每日的计划和目标，以帮助您更好地分配时间。
2. 优先考虑最重要的任务：优先完成最重要的任务，这有助于避免分心和浪费时间。
3. 避免拖延：尝试避免拖延，尽早开始任务，这样您可以更容易地完成它们。
4. 集中注意力：集中注意力，避免同时处理多个任务，这有助于减少分心和提高效率。5. 利用工具和技术：利用时间管理工具和技术，如日历、提醒和待办事项列表，以帮助您更好地管理时间。
6. 学会说“不”：学会拒绝不必要的事情，这有助于您更好地利用时间，并专注于最重要的任务。
7. 保持积极心态：保持积极心态，相信自己能够管理时间，并尝试不断学习和发展自己的时间管理技能。
8. 休息和放松：尝试保持工作和生活的平衡，并定期休息和放松，这有助于提高时间管理技能和提高工作效率。
```
- Python和JavaScript编程语言的主要区别是什么？
```
1. 语法不同：Python是一种面向对象的编程语言，它的语法比较严格，需要使用花括号来标识代码块。JavaScript是一种脚本语言，它的语法相对比较松散，需要使用花括号或缩进来标 识代码块。
2. 应用领域不同：Python广泛应用于数据分析、机器学习、人工智能等领域，由于其可读性好、语法清晰、功能强大等特点。JavaScript则主要应用于前端开发、后端开发、移动端开发 等领域。
3. 运行环境不同：Python的运行环境较为独立，可以在不同的操作系统上运行。JavaScript的运行环境相对较复杂，需要考虑浏览器和Web服务器的兼容性问题。
4. 应用场景不同：Python更适合进行科学计算、数据分析、机器学习等方面的应用，如Pandas、Numpy等库；而JavaScript则更适合进行前端开发、后端开发、移动端开发等领域的脚本编程，如React、Angular等框架。
5. 库和框架不同：Python拥有丰富的标准库和第三方库，如Django、Flask等；而JavaScript则拥有流行的Web开发框架，如React、Angular等。
```
- AI会如何影响农业生产？
```
AI将有助于提高农业生产效率，优化作物种植和收成过程，以及提高农产品的质量和品质。
AI技术可以应用于植物监测、灌溉管理、病虫害防治、土壤分析等方面，减少人力 成本，提高生产效率，同时也可以降低农业生产中的资源浪费和环境污染。例如，AI可以监测土壤湿度、气象状况等环境因素，帮助农民决定何时种植、灌溉和施肥，从而提高农作物的产量和质量。
另外，AI还可以通过监测植物健康状况，及时发现和预防病虫害的发生，提高农作物的产量和质量。此外，AI还可以帮助农民预测未来天气、干旱和洪涝灾害，制定更有效的灾害应对计划。
总之，AI有望成为农业生产中不可或缺的技术，在未来为农业生产带来更大的改进和效益。
```
- 翻译成英文：过去都是假的，回忆是一条没有归途的路，以往的一切春天都无法复原，即使最狂热最坚贞的爱情，归根结底也不过是一种瞬息即逝的现实，唯有孤独永恒。
```
Response: Translation into English:
The past is false, memories are a dead-end road, all previous springs are hopelessly incapable of being restored, even the most passionate and steadfast love is ultimately a fleeting reality,
and only solitude is eternal
```
- 请用python编程语言实现快速排序算法的代码
```
快速排序（Quick Sort）是一种常用的排序算法，基本思想是通过一次排序将数组分为两个部分，其中一个部分的所有元素都比另一个小，然后再分别对这两个部分进行排序 ，直到整个数组有序。
以下是使用Python语言实现快速排序的代码：
```python
def quick_sort(arr):
if len(arr) <= 1:
return arr
pivot = arr[len(arr)//2]
left = [x for x in arr if x < pivot]
middle = [x for x in arr if x == pivot]
right = [x for x in arr if x > pivot]
return quick_sort(left) + middle + quick_sort(right)
```
在这个实现中，首先判断数组的长度是否小于等于1，如果是，则直接返回该数组。否则，选择一个枢轴（pivot）元素，将数组分为三个部分：小于枢轴的左部分、等于枢轴的中间部分、大于枢轴的右部分。接着递归地对左部分和右部分进行排序，并将它们与中间部分连接起来。最后返回排好序的数组。
以下是使用上述代码对数组进行排序的示例：
```python
arr = [3, 1, 4, 1, 5, 9, 2, 6, 5, 3, 5]
sorted_arr = quick_sort(arr)
print(sorted_arr)
```
```
输出结果为：[1, 1, 2, 3, 3, 4, 5, 5, 5, 6, 9]
```
## 免责声明
本项目相关资源仅供学术研究之用，严禁用于商业用途。 使用涉及第三方代码的部分时，请严格遵循相应的开源协议。
模型生成的内容受模型计算、随机性和量化精度损失等因素影响，本项目不对其准确性作出保证。
对于模型输出的任何内容，本项目不承担任何法律责任，亦不对因使用相关资源和输出结果而可能产生的任何损失承担责任。
|
vsufiy/rubert_tner_model
|
vsufiy
| 2023-07-25T08:10:07Z | 108 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"token-classification",
"generated_from_trainer",
"dataset:multinerd",
"base_model:DeepPavlov/rubert-base-cased",
"base_model:finetune:DeepPavlov/rubert-base-cased",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-07-24T09:22:32Z |
---
base_model: DeepPavlov/rubert-base-cased
tags:
- generated_from_trainer
datasets:
- multinerd
model-index:
- name: rubert_tner_model
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. -->
# rubert_tner_model
This model is a fine-tuned version of [DeepPavlov/rubert-base-cased](https://huggingface.co/DeepPavlov/rubert-base-cased) on the multinerd dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 100
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log | 0.02 | 100 | 0.3009 | 0.5599 | 0.5719 | 0.5658 | 0.9386 |
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3
|
Aspik101/llama-30b-instruct-2048-PL-lora
|
Aspik101
| 2023-07-25T08:07:58Z | 1,481 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"facebook",
"meta",
"llama-2",
"pl",
"dataset:Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-07-25T07:44:07Z |
---
language:
- pl
datasets:
- Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish
license: other
model_type: llama-2
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-2
---
|
cemNB/034a
|
cemNB
| 2023-07-25T07:57:42Z | 0 | 0 | null |
[
"pytorch",
"tensorboard",
"generated_from_trainer",
"license:apache-2.0",
"region:us"
] | null | 2023-07-25T07:52:07Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: 034a
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. -->
# 034a
This model is a fine-tuned version of [tiiuae/falcon-rw-1b](https://huggingface.co/tiiuae/falcon-rw-1b) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.6188
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- training_steps: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.8771 | 0.0 | 10 | 2.6188 |
### Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
|
KevinTan/MIRAIYUI
|
KevinTan
| 2023-07-25T07:53:33Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-07-24T05:24:28Z |
---
license: creativeml-openrail-m
---
|
Vidyuth/bert-finetuned-squad
|
Vidyuth
| 2023-07-25T07:47:11Z | 109 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"jax",
"safetensors",
"bert",
"question-answering",
"en",
"dataset:bookcorpus",
"dataset:wikipedia",
"arxiv:1810.04805",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-07-25T07:02:29Z |
---
language: en
license: apache-2.0
datasets:
- bookcorpus
- wikipedia
---
# BERT large model (uncased) whole word masking finetuned on SQuAD
Pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in
[this paper](https://arxiv.org/abs/1810.04805) and first released in
[this repository](https://github.com/google-research/bert). This model is uncased: it does not make a difference
between english and English.
Differently to other BERT models, this model was trained with a new technique: Whole Word Masking. In this case, all of the tokens corresponding to a word are masked at once. The overall masking rate remains the same.
The training is identical -- each masked WordPiece token is predicted independently.
After pre-training, this model was fine-tuned on the SQuAD dataset with one of our fine-tuning scripts. See below for more information regarding this fine-tuning.
Disclaimer: The team releasing BERT did not write a model card for this model so this model card has been written by
the Hugging Face team.
## Model description
BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it
was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of
publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it
was pretrained with two objectives:
- Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run
the entire masked sentence through the model and has to predict the masked words. This is different from traditional
recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like
GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the
sentence.
- Next sentence prediction (NSP): the models concatenates two masked sentences as inputs during pretraining. Sometimes
they correspond to sentences that were next to each other in the original text, sometimes not. The model then has to
predict if the two sentences were following each other or not.
This way, the model learns an inner representation of the English language that can then be used to extract features
useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard
classifier using the features produced by the BERT model as inputs.
This model has the following configuration:
- 24-layer
- 1024 hidden dimension
- 16 attention heads
- 336M parameters.
## Intended uses & limitations
This model should be used as a question-answering model. You may use it in a question answering pipeline, or use it to output raw results given a query and a context. You may see other use cases in the [task summary](https://huggingface.co/transformers/task_summary.html#extractive-question-answering) of the transformers documentation.## Training data
The BERT model was pretrained on [BookCorpus](https://yknzhu.wixsite.com/mbweb), a dataset consisting of 11,038
unpublished books and [English Wikipedia](https://en.wikipedia.org/wiki/English_Wikipedia) (excluding lists, tables and
headers).
## Training procedure
### Preprocessing
The texts are lowercased and tokenized using WordPiece and a vocabulary size of 30,000. The inputs of the model are
then of the form:
```
[CLS] Sentence A [SEP] Sentence B [SEP]
```
With probability 0.5, sentence A and sentence B correspond to two consecutive sentences in the original corpus and in
the other cases, it's another random sentence in the corpus. Note that what is considered a sentence here is a
consecutive span of text usually longer than a single sentence. The only constrain is that the result with the two
"sentences" has a combined length of less than 512 tokens.
The details of the masking procedure for each sentence are the following:
- 15% of the tokens are masked.
- In 80% of the cases, the masked tokens are replaced by `[MASK]`.
- In 10% of the cases, the masked tokens are replaced by a random token (different) from the one they replace.
- In the 10% remaining cases, the masked tokens are left as is.
### Pretraining
The model was trained on 4 cloud TPUs in Pod configuration (16 TPU chips total) for one million steps with a batch size
of 256. The sequence length was limited to 128 tokens for 90% of the steps and 512 for the remaining 10%. The optimizer
used is Adam with a learning rate of 1e-4, \\(\beta_{1} = 0.9\\) and \\(\beta_{2} = 0.999\\), a weight decay of 0.01,
learning rate warmup for 10,000 steps and linear decay of the learning rate after.
### Fine-tuning
After pre-training, this model was fine-tuned on the SQuAD dataset with one of our fine-tuning scripts. In order to reproduce the training, you may use the following command:
```
python -m torch.distributed.launch --nproc_per_node=8 ./examples/question-answering/run_qa.py \
--model_name_or_path bert-large-uncased-whole-word-masking \
--dataset_name squad \
--do_train \
--do_eval \
--learning_rate 3e-5 \
--num_train_epochs 2 \
--max_seq_length 384 \
--doc_stride 128 \
--output_dir ./examples/models/wwm_uncased_finetuned_squad/ \
--per_device_eval_batch_size=3 \
--per_device_train_batch_size=3 \
```
## Evaluation results
The results obtained are the following:
```
f1 = 93.15
exact_match = 86.91
```
### BibTeX entry and citation info
```bibtex
@article{DBLP:journals/corr/abs-1810-04805,
author = {Jacob Devlin and
Ming{-}Wei Chang and
Kenton Lee and
Kristina Toutanova},
title = {{BERT:} Pre-training of Deep Bidirectional Transformers for Language
Understanding},
journal = {CoRR},
volume = {abs/1810.04805},
year = {2018},
url = {http://arxiv.org/abs/1810.04805},
archivePrefix = {arXiv},
eprint = {1810.04805},
timestamp = {Tue, 30 Oct 2018 20:39:56 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1810-04805.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
```
|
Chiahc/Bloom3BLora
|
Chiahc
| 2023-07-25T07:33:43Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-25T00:02:23Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0.dev0
|
rulrul512/path-to-save-model
|
rulrul512
| 2023-07-25T07:30:48Z | 0 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dreambooth",
"base_model:CompVis/stable-diffusion-v1-4",
"base_model:finetune:CompVis/stable-diffusion-v1-4",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-07-24T06:58:17Z |
---
license: creativeml-openrail-m
base_model: CompVis/stable-diffusion-v1-4
instance_prompt: a photo of sks dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - rulrul512/path-to-save-model
This is a dreambooth model derived from CompVis/stable-diffusion-v1-4. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
|
Vithika/llama2-qlora-finetunined-code-text
|
Vithika
| 2023-07-25T07:25:35Z | 3 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-25T07:25:18Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.5.0.dev0
|
Adarshagupta/BabyDragon
|
Adarshagupta
| 2023-07-25T07:13:53Z | 0 | 0 | null |
[
"license:bigscience-openrail-m",
"region:us"
] | null | 2023-07-25T07:13:53Z |
---
license: bigscience-openrail-m
---
|
wtnan2003/vit-base-patch16-224-in21k-finetuned-lora-food101
|
wtnan2003
| 2023-07-25T07:05:23Z | 0 | 0 |
peft
|
[
"peft",
"tensorboard",
"region:us"
] | null | 2023-07-25T03:53:40Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0
|
Za88yes/Nuni
|
Za88yes
| 2023-07-25T06:29:50Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-07-25T06:25:32Z |
---
license: creativeml-openrail-m
---
|
Jedida/tweet_sentiments_analysis_bert
|
Jedida
| 2023-07-25T06:29:49Z | 109 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:google-bert/bert-base-cased",
"base_model:finetune:google-bert/bert-base-cased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-07-24T17:43:05Z |
---
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
model-index:
- name: tweet_sentiments_analysis_bert
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. -->
# tweet_sentiments_analysis_bert
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5841
- F1-score: 0.7663
## 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: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1-score |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6679 | 1.0 | 1000 | 0.6750 | 0.7263 |
| 0.5466 | 2.0 | 2000 | 0.5841 | 0.7663 |
| 0.3779 | 3.0 | 3000 | 0.8963 | 0.7708 |
| 0.233 | 4.0 | 4000 | 1.1329 | 0.7681 |
| 0.12 | 5.0 | 5000 | 1.3381 | 0.7677 |
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3
|
trillionmonster/Baichuan-13B-Chat-8bit
|
trillionmonster
| 2023-07-25T06:29:35Z | 15 | 9 |
transformers
|
[
"transformers",
"pytorch",
"baichuan",
"text-generation",
"custom_code",
"zh",
"en",
"autotrain_compatible",
"text-generation-inference",
"8-bit",
"region:us"
] |
text-generation
| 2023-07-20T05:50:26Z |
---
language:
- zh
- en
pipeline_tag: text-generation
inference: false
---
原项目见 [https://huggingface.co/baichuan-inc/Baichuan-13B-Chat]
改动点：将原模型量化为8bit 保存为2GB大小的切片。
## 使用方式(int8)
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation.utils import GenerationConfig
tokenizer = AutoTokenizer.from_pretrained("trillionmonster/Baichuan-13B-Chat-8bit", use_fast=False, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("trillionmonster/Baichuan-13B-Chat-8bit", device_map="auto", trust_remote_code=True)
model.generation_config = GenerationConfig.from_pretrained("trillionmonster/Baichuan-13B-Chat-8bit")
messages = []
messages.append({"role": "user", "content": "世界上第二高的山峰是哪座"})
response = model.chat(tokenizer, messages)
print(response)
```
如需使用 int4 量化 (Similarly, to use int4 quantization):
```python
model = AutoModelForCausalLM.from_pretrained("trillionmonster/Baichuan-13B-Chat-8bit", device_map="auto",load_in_4bit=True,trust_remote_code=True)
```
|
soroushbn/my_awesome_wnut_model
|
soroushbn
| 2023-07-25T06:18:43Z | 107 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"token-classification",
"generated_from_trainer",
"dataset:wnut_17",
"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"
] |
token-classification
| 2023-07-24T11:45:49Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- wnut_17
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: my_awesome_wnut_model
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: wnut_17
type: wnut_17
config: wnut_17
split: test
args: wnut_17
metrics:
- name: Precision
type: precision
value: 0.5707154742096506
- name: Recall
type: recall
value: 0.3178869323447637
- name: F1
type: f1
value: 0.4083333333333334
- name: Accuracy
type: accuracy
value: 0.9413022102518063
---
<!-- 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_wnut_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the wnut_17 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2684
- Precision: 0.5707
- Recall: 0.3179
- F1: 0.4083
- Accuracy: 0.9413
## 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: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log | 1.0 | 213 | 0.2814 | 0.5418 | 0.2400 | 0.3327 | 0.9374 |
| No log | 2.0 | 426 | 0.2684 | 0.5707 | 0.3179 | 0.4083 | 0.9413 |
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3
|
thejagstudio/Falcon-7b-Fined-Tuned
|
thejagstudio
| 2023-07-25T06:04:46Z | 1 | 0 |
peft
|
[
"peft",
"pytorch",
"RefinedWebModel",
"custom_code",
"region:us"
] | null | 2023-07-25T05:27:24Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.5.0.dev0
|
Chiahc/my_awesome_eli5_clm-model
|
Chiahc
| 2023-07-25T05:39:54Z | 224 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"base_model:distilbert/distilgpt2",
"base_model:finetune:distilbert/distilgpt2",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-07-25T05:07:05Z |
---
license: apache-2.0
base_model: distilgpt2
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_clm-model
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. -->
# my_awesome_eli5_clm-model
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.7420
## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 3.8685 | 1.0 | 1145 | 3.7625 |
| 3.7736 | 2.0 | 2290 | 3.7448 |
| 3.7339 | 3.0 | 3435 | 3.7420 |
### Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2
|
davidrrobinson/BioLingual
|
davidrrobinson
| 2023-07-25T05:31:41Z | 1,056 | 4 |
transformers
|
[
"transformers",
"pytorch",
"clap",
"feature-extraction",
"dataset:davidrrobinson/AnimalSpeak",
"endpoints_compatible",
"region:us"
] |
feature-extraction
| 2023-07-24T01:15:23Z |
---
datasets:
- davidrrobinson/AnimalSpeak
---
# Model card for BioLingual
Model card for BioLingual: Transferable Models for bioacoustics with Human Language Supervision
An audio-text model for bioacoustics based on contrastive language-audio pretraining.
# Usage
You can use this model for bioacoustic zero shot audio classification, or for fine-tuning on bioacoustic tasks.
# Uses
## Perform zero-shot audio classification
### Using `pipeline`
```python
from datasets import load_dataset
from transformers import pipeline
dataset = load_dataset("ashraq/esc50")
audio = dataset["train"]["audio"][-1]["array"]
audio_classifier = pipeline(task="zero-shot-audio-classification", model="davidrrobinson/BioLingual")
output = audio_classifier(audio, candidate_labels=["Sound of a sperm whale", "Sound of a sea lion"])
print(output)
>>> [{"score": 0.999, "label": "Sound of a dog"}, {"score": 0.001, "label": "Sound of vaccum cleaner"}]
```
## Run the model:
You can also get the audio and text embeddings using `ClapModel`
### Run the model on CPU:
```python
from datasets import load_dataset
from transformers import ClapModel, ClapProcessor
librispeech_dummy = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
audio_sample = librispeech_dummy[0]
model = ClapModel.from_pretrained("laion/clap-htsat-unfused")
processor = ClapProcessor.from_pretrained("laion/clap-htsat-unfused")
inputs = processor(audios=audio_sample["audio"]["array"], return_tensors="pt")
audio_embed = model.get_audio_features(**inputs)
```
### Run the model on GPU:
```python
from datasets import load_dataset
from transformers import ClapModel, ClapProcessor
librispeech_dummy = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
audio_sample = librispeech_dummy[0]
model = ClapModel.from_pretrained("laion/clap-htsat-unfused").to(0)
processor = ClapProcessor.from_pretrained("laion/clap-htsat-unfused")
inputs = processor(audios=audio_sample["audio"]["array"], return_tensors="pt").to(0)
audio_embed = model.get_audio_features(**inputs)
|
luoyt99/testllama
|
luoyt99
| 2023-07-25T05:29:51Z | 0 | 0 | null |
[
"dataset:nyanko7/LLaMA-65B",
"license:bsd",
"region:us"
] | null | 2023-07-25T05:28:22Z |
---
license: bsd
datasets:
- nyanko7/LLaMA-65B
---
|
jensg/distilhubert-finetuned-gtzan
|
jensg
| 2023-07-25T05:05:06Z | 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
| 2023-07-24T09:09:40Z |
---
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: 0.83
---
<!-- 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: 0.5991
- Accuracy: 0.83
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.1211 | 1.0 | 57 | 1.9967 | 0.4 |
| 1.6311 | 2.0 | 114 | 1.5599 | 0.58 |
| 1.2082 | 3.0 | 171 | 1.2194 | 0.72 |
| 1.1853 | 4.0 | 228 | 1.0276 | 0.75 |
| 0.7278 | 5.0 | 285 | 0.9232 | 0.78 |
| 0.6999 | 6.0 | 342 | 0.7392 | 0.82 |
| 0.4983 | 7.0 | 399 | 0.6779 | 0.84 |
| 0.5142 | 8.0 | 456 | 0.6483 | 0.83 |
| 0.417 | 9.0 | 513 | 0.6554 | 0.82 |
| 0.3725 | 10.0 | 570 | 0.5991 | 0.83 |
### Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
|
howardchen123/alpaca-lora-llama-sentiment
|
howardchen123
| 2023-07-25T05:01:16Z | 0 | 1 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-24T02:51:45Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- 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.dev0
|
goodakdali/qtest
|
goodakdali
| 2023-07-25T04:57:39Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-25T04:57:37Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.5.0.dev0
|
dafc/llama2-qlora-finetunined-french
|
dafc
| 2023-07-25T04:49:33Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-25T04:49:15Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.5.0.dev0
|
intuol/SuperBlockBros
|
intuol
| 2023-07-25T04:24:08Z | 0 | 0 | null |
[
"license:openrail",
"region:us"
] | null | 2023-07-25T04:18:34Z |
---
license: openrail
---
# SuperBlockBros (Object Show YouTuber)
## Data
- 600 Epochs
- RVC v2
- MangioCrepe
|
jpvlinhares/ppo-LunarLander-v2
|
jpvlinhares
| 2023-07-25T04:17:01Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-25T04:16:38Z |
---
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: 246.27 +/- 23.80
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
...
```
|
raulgdp/Masking-distilbert-imdb
|
raulgdp
| 2023-07-25T04:10:04Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"fill-mask",
"generated_from_trainer",
"dataset:imdb",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-07-24T22:36:39Z |
---
license: apache-2.0
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:
- eval_loss: 3.1034
- eval_runtime: 14.5408
- eval_samples_per_second: 68.772
- eval_steps_per_second: 4.333
- step: 0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- 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: 3.0
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
|
YarramsettiNaresh/a2c-PandaReachDense-v2
|
YarramsettiNaresh
| 2023-07-25T03:52:07Z | 4 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"PandaReachDense-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-25T03:49:01Z |
---
library_name: stable-baselines3
tags:
- PandaReachDense-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PandaReachDense-v2
type: PandaReachDense-v2
metrics:
- type: mean_reward
value: -2.28 +/- 0.91
name: mean_reward
verified: false
---
# **A2C** Agent playing **PandaReachDense-v2**
This is a trained model of a **A2C** agent playing **PandaReachDense-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
...
```
|
Creling/llama7b-lora-alpaca
|
Creling
| 2023-07-25T03:28:21Z | 0 | 1 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-25T03:28:11Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- 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 0.4.0
|
renede/llama2_finetuned_chatbot
|
renede
| 2023-07-25T03:27:03Z | 0 | 0 |
peft
|
[
"peft",
"tensorboard",
"region:us"
] | null | 2023-07-25T02:59:45Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0
|
LarryAIDraw/gyn-a3-1000
|
LarryAIDraw
| 2023-07-25T03:17:19Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-07-25T03:07:08Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/44096?modelVersionId=48739
|
LarryAIDraw/idolmaster_sc_hachimiya_ssr2-09
|
LarryAIDraw
| 2023-07-25T03:17:09Z | 0 | 1 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-07-25T03:06:29Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/67231?modelVersionId=71870
|
m-aliabbas1/Reinforce-cartpol1
|
m-aliabbas1
| 2023-07-25T03:10:15Z | 0 | 0 | null |
[
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-25T03:10:05Z |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-cartpol1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 500.00 +/- 0.00
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
|
Chiahc/BertSeqClassicationLora1
|
Chiahc
| 2023-07-25T02:46:36Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-25T02:24:47Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0.dev0
|
Yamei/tvcg_entity_classify
|
Yamei
| 2023-07-25T02:31:34Z | 99 | 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
| 2023-07-25T02:14:09Z |
---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: tvcg_entity_classify
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. -->
# tvcg_entity_classify
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8480
- Accuracy: 0.7300
## 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 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.6871 | 1.0 | 2956 | 0.6645 | 0.7416 |
| 0.5965 | 2.0 | 5912 | 0.6812 | 0.7419 |
| 0.4933 | 3.0 | 8868 | 0.6970 | 0.7455 |
| 0.4167 | 4.0 | 11824 | 0.7904 | 0.7371 |
| 0.3254 | 5.0 | 14780 | 0.8480 | 0.7300 |
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3
|
ocisd4/llama-2-tokenizer-dataprep
|
ocisd4
| 2023-07-25T02:30:26Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-07-24T07:58:35Z |
- 關閉自動添加`<s>`，方便產生megatron-deepspeed訓練用檔案
- 指定pad token為`<unk>`，訓練時token數才會正確，以及finetune_t0.py才能正確pack_sample
|
kusumakar/Ham-Spam_mail_detection
|
kusumakar
| 2023-07-25T02:30:15Z | 0 | 0 | null |
[
"legal",
"en",
"region:us"
] | null | 2023-07-25T02:28:43Z |
---
language:
- en
tags:
- legal
---
|
Chiahc/BertSeqClassicationLora
|
Chiahc
| 2023-07-25T02:23:17Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-25T01:27:43Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0.dev0
|
byeolcardi/stt_2
|
byeolcardi
| 2023-07-25T02:11:29Z | 67 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"base_model:openai/whisper-small",
"base_model:finetune:openai/whisper-small",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-07-25T01:13:10Z |
---
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
model-index:
- name: stt_2
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. -->
# stt_2
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 10
### Training results
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3
|
valu117/llama2-qlora-finetunined-french
|
valu117
| 2023-07-25T02:10:16Z | 2 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-25T02:10:08Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.5.0.dev0
|
NasimB/cbt-rarity-guten-no-merge
|
NasimB
| 2023-07-25T02:06:28Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"dataset:generator",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-07-24T22:29:28Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: cbt-rarity-guten-no-merge
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. -->
# cbt-rarity-guten-no-merge
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 4.0377
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- 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: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 6
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 6.3393 | 0.29 | 500 | 5.3133 |
| 5.0332 | 0.58 | 1000 | 4.8944 |
| 4.7062 | 0.87 | 1500 | 4.6552 |
| 4.4455 | 1.16 | 2000 | 4.5068 |
| 4.2946 | 1.45 | 2500 | 4.3846 |
| 4.1846 | 1.74 | 3000 | 4.2814 |
| 4.0809 | 2.03 | 3500 | 4.2011 |
| 3.8863 | 2.32 | 4000 | 4.1666 |
| 3.8588 | 2.61 | 4500 | 4.1094 |
| 3.814 | 2.9 | 5000 | 4.0582 |
| 3.6453 | 3.18 | 5500 | 4.0528 |
| 3.575 | 3.47 | 6000 | 4.0214 |
| 3.5609 | 3.76 | 6500 | 3.9924 |
| 3.4948 | 4.05 | 7000 | 3.9823 |
| 3.3077 | 4.34 | 7500 | 3.9803 |
| 3.2997 | 4.63 | 8000 | 3.9663 |
| 3.2906 | 4.92 | 8500 | 3.9538 |
| 3.1681 | 5.21 | 9000 | 3.9641 |
| 3.1219 | 5.5 | 9500 | 3.9635 |
| 3.1184 | 5.79 | 10000 | 3.9628 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
|
gabc6200/body
|
gabc6200
| 2023-07-25T02:04:05Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-07-25T01:33:03Z |
---
license: creativeml-openrail-m
---
|
ashercn97/awesome-prompts-upload
|
ashercn97
| 2023-07-25T01:58:18Z | 4 | 0 |
peft
|
[
"peft",
"text2text-generation",
"dataset:fka/awesome-chatgpt-prompts",
"region:us"
] |
text2text-generation
| 2023-07-23T00:58:47Z |
---
pipeline_tag: text2text-generation
datasets:
- fka/awesome-chatgpt-prompts
library_name: peft
---
I made this to help make chatgpt prompts! Basically wahat you can do is go to google colab, make a textgeneration-web-gui thing (from this github repo: https://github.com/oobabooga/text-generation-webui) and then download and load the model
openlm-reseach/openllama-3b
then download this model:
ashercn97/awesome-prompts-upload
and then under the add lora thing you select this abnd then hit apply lora.
Next, under the main tab, change the prompting type to instruction alpaca or something (not the first one) and then enter what you want your chatgpt prmopt to be of.
For instance, you could do input "code generator" and it would output a prompt to put into chatgpt.
This is one of my first projects so I hope you enjoy!
|
tyzp-INC/few-shot-multilingual-e5-large-xnli-tuned
|
tyzp-INC
| 2023-07-25T01:55:20Z | 6 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"xlm-roberta",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] |
text-classification
| 2023-07-25T01:53:08Z |
---
license: apache-2.0
tags:
- setfit
- sentence-transformers
- text-classification
pipeline_tag: text-classification
---
# tyzp-INC/few-shot-multilingual-e5-large-xnli-tuned
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("tyzp-INC/few-shot-multilingual-e5-large-xnli-tuned")
# 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}
}
```
|
hyungtak/gpt-j-test
|
hyungtak
| 2023-07-25T01:53:23Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gptj",
"text-generation",
"dataset:multi_nli",
"license:openrail",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-07-24T04:35:41Z |
---
license: openrail
datasets:
- multi_nli
---
|
skar01/llama2-coder-full
|
skar01
| 2023-07-25T01:52:46Z | 7 | 6 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-07-25T00:59:30Z |
---
license: apache-2.0
---
Llama2 (7B) model fine-tuned on the CodeAlpaca 20k instructions dataset by using the method QLoRA with PEFT library.
Training and evaluation data 📚
CodeAlpaca_20K: contains 20K instruction-following data used for fine-tuning the Code Alpaca model.
Data is here: https://huggingface.co/mrm8488/falcon-7b-ft-codeAlpaca_20k
The adapter is here: https://huggingface.co/skar01/llama2-coder
The base model is: TinyPixel/Llama-2-7B-bf16-sharded
|
ManuelPerdigo/OPT-350_mlm
|
ManuelPerdigo
| 2023-07-25T01:52:03Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"opt",
"text-generation",
"generated_from_trainer",
"base_model:facebook/opt-350m",
"base_model:finetune:facebook/opt-350m",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-07-24T22:05:35Z |
---
license: other
base_model: facebook/opt-350m
tags:
- generated_from_trainer
model-index:
- name: OPT-350_mlm
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. -->
# OPT-350_mlm
This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.9944
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 4.189 | 1.0 | 1137 | 4.1037 |
| 4.0026 | 2.0 | 2274 | 4.0314 |
| 3.9094 | 3.0 | 3411 | 3.9944 |
### Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3
|
thanhduycao/whisper-base-full-data-aug-v2
|
thanhduycao
| 2023-07-25T01:20:52Z | 70 | 0 |
transformers
|
[
"transformers",
"pytorch",
"whisper",
"automatic-speech-recognition",
"whisper-event",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-07-18T14:50:43Z |
---
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
model-index:
- name: whisper-base-full-data-aug-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. -->
# whisper-base-full-data-aug-v2
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2464
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- distributed_type: tpu
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 256
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5000
- training_steps: 63840
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 0.4006 | 1.57 | 5000 | 0.6323 |
| 0.2901 | 3.13 | 10000 | 0.4845 |
| 0.2405 | 4.7 | 15000 | 0.4379 |
| 0.2114 | 6.27 | 20000 | 0.3892 |
| 0.1892 | 7.83 | 25000 | 0.3610 |
| 0.1638 | 9.4 | 30000 | 0.3343 |
| 0.154 | 10.97 | 35000 | 0.3186 |
| 0.1363 | 12.53 | 40000 | 0.2989 |
| 0.1216 | 14.1 | 45000 | 0.2848 |
| 0.1087 | 15.67 | 50000 | 0.2718 |
| 0.0984 | 17.23 | 55000 | 0.2576 |
| 0.0894 | 18.8 | 60000 | 0.2441 |
### Framework versions
- Transformers 4.28.1
- Pytorch 2.1.0a0+gitcc01568
- Datasets 2.13.1
- Tokenizers 0.13.3
|
davolu/ikea-test1
|
davolu
| 2023-07-25T01:05:44Z | 6 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-07-25T01:01:48Z |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### ikea_test1 Dreambooth model trained by davolu with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
|
DARIOLEV/llama2-qlora-finetunined-french
|
DARIOLEV
| 2023-07-25T00:53:32Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-25T00:53:28Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.5.0.dev0
|
byeolcardi/stt_test
|
byeolcardi
| 2023-07-25T00:53:31Z | 68 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"whisper",
"automatic-speech-recognition",
"hf-asr-leaderboard",
"generated_from_trainer",
"hi",
"dataset:mozilla-foundation/common_voice_11_0_stt",
"base_model:openai/whisper-small",
"base_model:finetune:openai/whisper-small",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-07-25T00:12:08Z |
---
language:
- hi
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0_stt
model-index:
- name: Whisper Small Hi - test
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 Small Hi - test
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 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: 16
- 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_steps: 500
- training_steps: 10
### Training results
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3
|
skar01/llama2-coder
|
skar01
| 2023-07-25T00:45:40Z | 2 | 2 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-23T04:57:43Z |
---
library_name: peft
---
## Training procedure
Llama2 (7B) model fine-tuned on the CodeAlpaca 20k instructions dataset by using the method QLoRA with PEFT library.
Training and evaluation data 📚
CodeAlpaca_20K: contains 20K instruction-following data used for fine-tuning the Code Alpaca model.
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.5.0.dev0
|
ALM-AHME/swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-BreastCancer-BreakHis-AH-Shuffled
|
ALM-AHME
| 2023-07-25T00:43:01Z | 4 | 1 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"swinv2",
"image-classification",
"generated_from_trainer",
"base_model:microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft",
"base_model:finetune:microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-07-24T16:46:50Z |
---
license: apache-2.0
base_model: microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-BreastCancer-BreakHis-AH-Shuffled
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. -->
# swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-BreastCancer-BreakHis-AH-Shuffled
This model is a fine-tuned version of [microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft](https://huggingface.co/microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0289
- Accuracy: 0.9953
## 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
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.5
- num_epochs: 12
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.1894 | 1.0 | 199 | 0.1739 | 0.9307 |
| 0.3951 | 2.0 | 398 | 0.1066 | 0.9614 |
| 0.1021 | 3.0 | 597 | 0.0741 | 0.9708 |
| 0.0784 | 4.0 | 796 | 0.0815 | 0.9760 |
| 0.0835 | 5.0 | 995 | 0.0723 | 0.9774 |
| 0.1394 | 6.0 | 1194 | 0.0532 | 0.9840 |
| 0.1755 | 7.0 | 1393 | 0.1068 | 0.9722 |
| 0.1134 | 8.0 | 1592 | 0.0390 | 0.9892 |
| 0.0237 | 9.0 | 1791 | 0.0789 | 0.9863 |
| 0.027 | 10.0 | 1990 | 0.0492 | 0.9887 |
| 0.0081 | 11.0 | 2189 | 0.0429 | 0.9934 |
| 0.011 | 12.0 | 2388 | 0.0289 | 0.9953 |
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3
|
radned/speecht5_voxpopuli_nl
|
radned
| 2023-07-25T00:28:06Z | 64 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"speecht5",
"text-to-audio",
"generated_from_trainer",
"dataset:voxpopuli",
"endpoints_compatible",
"region:us"
] |
text-to-audio
| 2023-07-24T21:51:25Z |
---
base_model: ''
tags:
- generated_from_trainer
datasets:
- voxpopuli
model-index:
- name: speecht5_voxpopuli_nl
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. -->
# speecht5_voxpopuli_nl
This model is a fine-tuned version of [](https://huggingface.co/) on the voxpopuli dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9541
## 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: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.2804 | 4.3 | 1000 | 1.1664 |
| 1.054 | 8.61 | 2000 | 0.9818 |
| 1.0183 | 12.91 | 3000 | 0.9600 |
| 1.0028 | 17.21 | 4000 | 0.9541 |
### Framework versions
- Transformers 4.32.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.14.0
- Tokenizers 0.13.3
|
DunnBC22/mbart-large-50-English_French_Translation_v2
|
DunnBC22
| 2023-07-25T00:24:58Z | 104 | 1 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"mbart",
"text2text-generation",
"generated_from_trainer",
"en",
"fr",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-03-09T03:58:07Z |
---
license: mit
tags:
- generated_from_trainer
metrics:
- bleu
- rouge
model-index:
- name: mbart-large-50-English_French_Translation_v2
results: []
language:
- en
- fr
---
# mbart-large-50-English_French_Translation_v2
This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3902
- Bleu: 35.1914
- Rouge
- Rouge1: 0.641952430267112
- Rouge2: 0.4572909036472911
- RougeL: 0.607001331434416
- RougeLsum: 0.6068905123656807
- Meteor: 0.5916610499445853
## Model description
This model translates French input text samples to English.
For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Machine%20Translation/NLP%20Translation%20Project-EN:FR.ipynb
## Intended uses & limitations
This model is intended to demonstrate my ability to solve a complex problem using technology.
## Training and evaluation data
Dataset Source: https://www.kaggle.com/datasets/hgultekin/paralel-translation-corpus-in-22-languages
**English Input Text Lengths (in Words)**
**French Input Text Lengths (in Words)**
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Rouge1 | Rouge2 | RougeL | RougeLsum | Meteor |
|:-------------:|:-----:|:----:|:---------:|:-------:|:------:|:--------:|:------:|:---------:|:-----:|
| 1.1677 | 1.0 | 750 | 0.3902 | 35.1914 | 0.6419 | 0.4573 | 0.6070 | 0.6069 | 0.5917 |
* All values in the chart above are rounded to the nearest ten-thousandths.
### Framework versions
- Transformers 4.26.1
- Pytorch 1.12.1
- Datasets 2.9.0
- Tokenizers 0.12.1
|
annazhong/vit-base-patch16-224-finetuned-eurosat
|
annazhong
| 2023-07-25T00:17:36Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"vit",
"image-classification",
"generated_from_trainer",
"base_model:google/vit-base-patch16-224",
"base_model:finetune:google/vit-base-patch16-224",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-07-18T20:42:11Z |
---
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224-finetuned-eurosat
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. -->
# vit-base-patch16-224-finetuned-eurosat
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7730
- Accuracy: 0.2
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 150
- eval_batch_size: 150
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 600
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 1 | 1.8264 | 0.1143 |
| No log | 2.0 | 2 | 1.7730 | 0.2 |
| No log | 3.0 | 3 | 1.8143 | 0.2 |
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
DunnBC22/efficientnet-b5-Brain_Tumors_Image_Classification
|
DunnBC22
| 2023-07-25T00:16:54Z | 130 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"efficientnet",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-06-10T18:40:34Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: efficientnet-b5-Brain_Tumors_Image_Classification
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8020304568527918
---
<h1>efficientnet-b5-Brain_Tumors_Image_Classification</h1>
This model is a fine-tuned version of [google/efficientnet-b5](https://huggingface.co/google/efficientnet-b5).
It achieves the following results on the evaluation set:
- Loss: 0.9410
- Accuracy: 0.8020
- F1
- Weighted: 0.7736
- Micro: 0.8020
- Macro: 0.7802
- Recall
- Weighted: 0.8020
- Micro: 0.8020
- Macro: 0.7977
- Precision
- Weighted: 0.8535
- Micro: 0.8020
- Macro: 0.8682
<div style="text-align: center;">
<h2>
Model Description
</h2>
<a href="https://github.com/DunnBC22/Vision_Audio_and_Multimodal_Projects/blob/main/Computer%20Vision/Image%20Classification/Multiclass%20Classification/Brain%20Tumors%20Image%20Classification%20Comparison/EfficientNet%20-%20Image%20Classification.ipynb">
Click here for the code that I used to create this model.
</a>
This project is part of a comparison of seventeen (17) transformers.
<a href="https://github.com/DunnBC22/Vision_Audio_and_Multimodal_Projects/blob/main/Computer%20Vision/Image%20Classification/Multiclass%20Classification/Brain%20Tumors%20Image%20Classification%20Comparison/README.md">
Click here to see the README markdown file for the full project
</a>
<h2>
Intended Uses & Limitations
</h2>
This model is intended to demonstrate my ability to solve a complex problem using technology.
<h2>
Training & Evaluation Data
</h2>
<a href="https://www.kaggle.com/datasets/sartajbhuvaji/brain-tumor-classification-mri">
Brain Tumor Image Classification Dataset
</a>
<h2>
Sample Images
</h2>
<img src="https://github.com/DunnBC22/Vision_Audio_and_Multimodal_Projects/raw/main/Computer%20Vision/Image%20Classification/Multiclass%20Classification/Brain%20Tumors%20Image%20Classification%20Comparison/Images/Sample%20Images.png" />
<h2>
Class Distribution of Training Dataset
</h2>
<img src="https://github.com/DunnBC22/Vision_Audio_and_Multimodal_Projects/raw/main/Computer%20Vision/Image%20Classification/Multiclass%20Classification/Brain%20Tumors%20Image%20Classification%20Comparison/Images/Class%20Distribution%20-%20Training%20Dataset.png"/>
<h2>
Class Distribution of Evaluation Dataset
</h2>
<img src="https://github.com/DunnBC22/Vision_Audio_and_Multimodal_Projects/raw/main/Computer%20Vision/Image%20Classification/Multiclass%20Classification/Brain%20Tumors%20Image%20Classification%20Comparison/Images/Class%20Distribution%20-%20Testing%20Dataset.png"/>
</div>
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Weighted F1 | Micro F1 | Macro F1 | Weighted Recall | Micro Recall | Macro Recall | Weighted Precision | Micro Precision | Macro Precision |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:--------:|:--------:|:---------------:|:------------:|:------------:|:------------------:|:---------------:|:---------------:|
| 1.3872 | 1.0 | 180 | 1.0601 | 0.6853 | 0.6485 | 0.6853 | 0.6550 | 0.6853 | 0.6853 | 0.6802 | 0.8177 | 0.6853 | 0.8330 |
| 1.3872 | 2.0 | 360 | 0.9533 | 0.7843 | 0.7483 | 0.7843 | 0.7548 | 0.7843 | 0.7843 | 0.7819 | 0.8354 | 0.7843 | 0.8471 |
| 0.8186 | 3.0 | 540 | 0.9410 | 0.8020 | 0.7736 | 0.8020 | 0.7802 | 0.8020 | 0.8020 | 0.7977 | 0.8535 | 0.8020 | 0.8682 |
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0
- Datasets 2.11.0
- Tokenizers 0.13.3
|
DunnBC22/codebert-base-Password_Strength_Classifier
|
DunnBC22
| 2023-07-25T00:14:26Z | 98 | 1 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"roberta",
"text-classification",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-05-06T04:17:51Z |
---
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: codebert-base-Password_Strength_Classifier
results: []
---
# codebert-base-Password_Strength_Classifier
This model is a fine-tuned version of [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base).
It achieves the following results on the evaluation set:
- Loss: 0.0077
- Accuracy: 0.9975
- F1
- Weighted: 0.9975
- Micro: 0.9975
- Macro: 0.9963
- Recall
- Weighted: 0.9975
- Micro: 0.9975
- Macro: 0.9978
- Precision
- Weighted: 0.9975
- Macro: 0.9948
- Micro: 0.9975
## Model description
The model classifies passwords as one of the following:
1) Weak
2) Medium
3) Strong
For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Password%20Strength%20Classification%20(MC)/CodeBERT-Base%20-%20Password_Classifier.ipynb
## Intended uses & limitations
This is intended to show the possibilities. It is mainly limited by the input data.
## Training and evaluation data
Dataset Source: https://www.kaggle.com/datasets/bhavikbb/password-strength-classifier-dataset
## 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: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Weighted F1 | Micro F1 | Macro F1 | Weighted Recall | Micro Recall | Macro Recall | Weighted Precision | Micro Precision | Macro Precision |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:-----------:|:--------:|:--------:|:---------------:|:------------:|:------------:|:------------------:|:---------------:|:---------------:|
| 0.0438 | 1.0 | 8371 | 0.0112 | 0.9956 | 0.9956 | 0.9956 | 0.9935 | 0.9956 | 0.9956 | 0.9963 | 0.9957 | 0.9956 | 0.9908 |
| 0.0133 | 2.0 | 16742 | 0.0092 | 0.9966 | 0.9967 | 0.9966 | 0.9951 | 0.9966 | 0.9966 | 0.9966 | 0.9967 | 0.9966 | 0.9935 |
| 0.0067 | 3.0 | 25113 | 0.0077 | 0.9975 | 0.9975 | 0.9975 | 0.9963 | 0.9975 | 0.9975 | 0.9978 | 0.9975 | 0.9975 | 0.9948 |
### Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0
- Datasets 2.11.0
- Tokenizers 0.13.3
|
DCLXVIy/loraaa
|
DCLXVIy
| 2023-07-25T00:03:01Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-07-25T00:00:00Z |
---
license: creativeml-openrail-m
---
|
RushTurtle/crnn_vgg16_bn_20230724-201817
|
RushTurtle
| 2023-07-24T23:54:23Z | 44 | 0 |
transformers
|
[
"transformers",
"pytorch",
"en",
"endpoints_compatible",
"region:us"
] | null | 2023-07-24T23:54:18Z |
---
language: en
---
<p align="center">
<img src="https://doctr-static.mindee.com/models?id=v0.3.1/Logo_doctr.gif&src=0" width="60%">
</p>
**Optical Character Recognition made seamless & accessible to anyone, powered by TensorFlow 2 & PyTorch**
## Task: recognition
https://github.com/mindee/doctr
### Example usage:
```python
>>> from doctr.io import DocumentFile
>>> from doctr.models import ocr_predictor, from_hub
>>> img = DocumentFile.from_images(['<image_path>'])
>>> # Load your model from the hub
>>> model = from_hub('mindee/my-model')
>>> # Pass it to the predictor
>>> # If your model is a recognition model:
>>> predictor = ocr_predictor(det_arch='db_mobilenet_v3_large',
>>> reco_arch=model,
>>> pretrained=True)
>>> # If your model is a detection model:
>>> predictor = ocr_predictor(det_arch=model,
>>> reco_arch='crnn_mobilenet_v3_small',
>>> pretrained=True)
>>> # Get your predictions
>>> res = predictor(img)
```
### Run Configuration
{
"arch": "crnn_vgg16_bn",
"train_path": "/tmp/dataset/train3_2800/",
"val_path": "/tmp/dataset/val3_2800/",
"train_samples": 1000,
"val_samples": 20,
"font": "FreeMono.ttf,FreeSans.ttf,FreeSerif.ttf",
"min_chars": 1,
"max_chars": 12,
"name": null,
"epochs": 1000,
"batch_size": 32,
"device": 0,
"input_size": 32,
"lr": 0.001,
"weight_decay": 0,
"workers": 16,
"resume": null,
"vocab": "french",
"test_only": false,
"show_samples": false,
"wb": true,
"push_to_hub": true,
"pretrained": false,
"sched": "cosine",
"amp": true,
"find_lr": false
}
|
jstawski/Llama-2-13b-hf-finetuned-SNG
|
jstawski
| 2023-07-24T23:32:04Z | 0 | 1 |
peft
|
[
"peft",
"conversational",
"en",
"license:llama2",
"region:us"
] |
text-generation
| 2023-07-24T03:25:41Z |
---
license: llama2
library_name: peft
language:
- en
pipeline_tag: conversational
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.5.0.dev0
|
ljcamargo/tachiwin_tutunaku
|
ljcamargo
| 2023-07-24T23:07:26Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:audiofolder",
"base_model:facebook/wav2vec2-large-xlsr-53",
"base_model:finetune:facebook/wav2vec2-large-xlsr-53",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-07-24T06:14:41Z |
---
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- wer
model-index:
- name: tachiwin_totonac
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: audiofolder
type: audiofolder
config: ljcamargo--totonac_alpha_1
split: test
args: ljcamargo--totonac_alpha_1
metrics:
- name: Wer
type: wer
value: 0.6465189873417722
---
<!-- 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. -->
# tachiwin_totonac
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the audiofolder dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7535
- Wer: 0.6465
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 90
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 5.1063 | 5.19 | 200 | 2.9834 | 1.0 |
| 2.9016 | 10.39 | 400 | 2.4405 | 0.9959 |
| 1.7606 | 15.58 | 600 | 1.1942 | 0.8532 |
| 1.0549 | 20.78 | 800 | 1.1132 | 0.7788 |
| 0.7553 | 25.97 | 1000 | 1.1224 | 0.6899 |
| 0.6639 | 31.51 | 1200 | 1.2641 | 0.7082 |
| 0.5344 | 36.7 | 1400 | 1.3247 | 0.6835 |
| 0.4527 | 41.9 | 1600 | 1.3915 | 0.7022 |
| 0.3839 | 47.09 | 1800 | 1.4051 | 0.6791 |
| 0.3065 | 52.29 | 2000 | 1.3899 | 0.6706 |
| 0.2714 | 57.48 | 2200 | 1.5455 | 0.6573 |
| 0.2437 | 62.68 | 2400 | 1.6798 | 0.6601 |
| 0.2103 | 67.87 | 2600 | 1.7406 | 0.6674 |
| 0.1899 | 73.06 | 2800 | 1.7625 | 0.6522 |
| 0.1841 | 78.26 | 3000 | 1.7443 | 0.6535 |
| 0.1544 | 83.45 | 3200 | 1.7405 | 0.6465 |
| 0.1461 | 88.65 | 3400 | 1.7535 | 0.6465 |
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Karim-Gamal/MMiniLM-L12-finetuned-emojis-1-client-toxic-FedAvg-non-IID-Fed
|
Karim-Gamal
| 2023-07-24T22:55:45Z | 108 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"bert",
"text-classification",
"en",
"es",
"it",
"fr",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-03-06T15:03:36Z |
---
license: apache-2.0
language:
- en
- es
- it
- fr
metrics:
- f1
---
# Federated Learning Based Multilingual Emoji Prediction
This repository contains code for training and evaluating transformer-based models for Uni/multilingual emoji prediction in clean and attack scenarios using Federated Learning. This work is described in the paper "Federated Learning-Based Multilingual Emoji Prediction in Clean and Attack Scenarios."
# Abstract
Federated learning is a growing field in the machine learning community due to its decentralized and private design. Model training in federated learning is distributed over multiple clients giving access to lots of client data while maintaining privacy. Then, a server aggregates the training done on these multiple clients without access to their data, which could be emojis widely used in any social media service and instant messaging platforms to express users' sentiments. This paper proposes federated learning-based multilingual emoji prediction in both clean and attack scenarios. Emoji prediction data have been crawled from both Twitter and SemEval emoji datasets. This data is used to train and evaluate different transformer model sizes including a sparsely activated transformer with either the assumption of clean data in all clients or poisoned data via label flipping attack in some clients. Experimental results on these models show that federated learning in either clean or attacked scenarios performs similarly to centralized training in multilingual emoji prediction on seen and unseen languages under different data sources and distributions. Our trained transformers perform better than other techniques on the SemEval emoji dataset in addition to the privacy as well as distributed benefits of federated learning.
# Performance
> * Acc : 42.672 %
> * Mac-F1 : 30.476 %
> * Also see our [GitHub Repo](https://github.com/kareemgamalmahmoud/FEDERATED-LEARNING-BASED-MULTILINGUAL-EMOJI-PREDICTION-IN-CLEAN-AND-ATTACK-SCENARIOS)
# Dependencies
> * Python 3.6+
> * PyTorch 1.7.0+
> * Transformers 4.0.0+
# Usage
> To use the model, first install the `transformers` package from Hugging Face:
```python
pip install transformers
```
> Then, you can load the model and tokenizer using the following code:
```python
from transformers import AutoModelForSequenceClassification, AutoTokenizer
import numpy as np
import urllib.request
import csv
```
```python
MODEL = "Karim-Gamal/MMiniLM-L12-finetuned-emojis-1-client-toxic-FedAvg-non-IID-Fed"
tokenizer = AutoTokenizer.from_pretrained(MODEL)
model = AutoModelForSequenceClassification.from_pretrained(MODEL)
```
> Once you have the tokenizer and model, you can preprocess your text and pass it to the model for prediction:
```python
# Preprocess text (username and link placeholders)
def preprocess(text):
new_text = []
for t in text.split(" "):
t = '@user' if t.startswith('@') and len(t) > 1 else t
t = 'http' if t.startswith('http') else t
new_text.append(t)
return " ".join(new_text)
text = "Hello world"
text = preprocess(text)
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
scores = output[0][0].detach().numpy()
```
> The scores variable contains the probabilities for each of the possible emoji labels. To get the top k predictions, you can use the following code:
```python
# download label mapping
labels=[]
mapping_link = "https://raw.githubusercontent.com/cardiffnlp/tweeteval/main/datasets/emoji/mapping.txt"
with urllib.request.urlopen(mapping_link) as f:
html = f.read().decode('utf-8').split("\n")
csvreader = csv.reader(html, delimiter='\t')
labels = [row[1] for row in csvreader if len(row) > 1]
k = 3 # number of top predictions to show
ranking = np.argsort(scores)
ranking = ranking[::-1]
for i in range(k):
l = labels[ranking[i]]
s = scores[ranking[i]]
print(f"{i+1}) {l} {np.round(float(s), 4)}")
```
## Note : this is the source for that code : [Link](https://huggingface.co/cardiffnlp/twitter-roberta-base-emoji)
|
tridungduong16/Llama-2-13B-GPTQ-Orca
|
tridungduong16
| 2023-07-24T22:31:29Z | 7 | 8 |
peft
|
[
"peft",
"facebook",
"meta",
"pytorch",
"llama",
"llama-2",
"gptq",
"orca",
"text-generation",
"en",
"dataset:Open-Orca/OpenOrca",
"arxiv:2306.02707",
"arxiv:2301.13688",
"arxiv:2302.13971",
"license:other",
"region:us"
] |
text-generation
| 2023-07-20T12:34:09Z |
---
inference: false
language:
- en
license: other
model_type: llama
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-2
- gptq
- orca
datasets:
- Open-Orca/OpenOrca
library_name: peft
---
# Llama-2-13B-GPTQ-Orca
This model is a fine-tuned version of [TheBloke/Llama-2-13B-GPTQ](https://huggingface.co/TheBloke/Llama-2-13B-GPTQ) on Orca dataset [Open-Orca/OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca).
## Prompt template:
```
### System:\n{system}\n\n### User:\n{instruction}\n\n### Response:
```
The model was trained with the following 16 system messages used to generate the training examples (see [ORCA paper](https://arxiv.org/abs/2306.02707)):
1. \<empty system message\>
2. You are an AI assistant. Provide a detailed answer so user don’t need to search outside to understand the answer.
3. You are an AI assistant. You will be given a task. You must generate a detailed and long answer.
4. You are a helpful assistant, who always provide explanation. Think like you are answering to a five year old.
5. You are an AI assistant that follows instruction extremely well. Help as much as you can.
6. You are an AI assistant that helps people find information. Provide a detailed answer so user don’t need to search outside to understand the answer.
7. You are an AI assistant. User will you give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.
8. You should describe the task and explain your answer. While answering a multiple choice question, first output the correct answer(s). Then explain why other answers are wrong. Think like you are answering to a five year old.
9. Explain how you used the definition to come up with the answer.
10. You are an AI assistant. You should describe the task and explain your answer. While answering a multiple choice question, first output the correct answer(s). Then explain why other answers are wrong. You might need to use additional knowledge to answer the question.
11. You are an AI assistant that helps people find information. User will you give you a question. Your task is to answer as faithfully as you can. While answering think step-by- step and justify your answer.
12. User will you give you a task with some instruction. Your job is follow the instructions as faithfully as you can. While answering think step-by-step and justify your answer.
13. You are a teacher. Given a task, you explain in simple steps what the task is asking, any guidelines it provides and how to use those guidelines to find the answer.
14. You are an AI assistant, who knows every language and how to translate one language to another. Given a task, you explain in simple steps what the task is asking, any guidelines that it provides. You solve the task and show how you used the guidelines to solve the task.
15. Given a definition of a task and a sample input, break the definition into small parts. Each of those parts will have some instruction. Explain their meaning by showing an example that meets the criteria in the instruction. Use the following format: Part \#: a key part of the definition. Usage: Sample response that meets the criteria from the key part. Explain why you think it meets the criteria.
16. You are an AI assistant that helps people find information.
## How to use this GPTQ model from Python code
First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) installed:
`GITHUB_ACTIONS=true pip install auto-gptq`
In order to use this, you need to download the base model from [TheBloke/Llama-2-13B-GPTQ](https://huggingface.co/TheBloke/Llama-2-13B-GPTQ) and then load the adpter from this repo. Then try the following example code:
```python
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig, get_gptq_peft_model
MODEL_PATH_GPTQ= "Llama-2-13B-GPTQ"
ADAPTER_DIR= "Llama-2-13B-GPTQ-Orca"
DEV = "cuda:0"
tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH_GPTQ, use_fast=True)
model = AutoGPTQForCausalLM.from_quantized(
MODEL_PATH_GPTQ,
use_safetensors=True,
trust_remote_code=False,
use_triton=True,
device="cuda:0",
warmup_triton=False,
trainable=True,
inject_fused_attention=True,
inject_fused_mlp=False,
)
model = get_gptq_peft_model(
model,
model_id=ADAPTER_DIR,
train_mode=False
)
model.eval()
```
## Compatibility
The files provided will work with AutoGPTQ (CUDA and Triton modes), GPTQ-for-LLaMa (only CUDA has been tested), and Occ4m's GPTQ-for-LLaMa fork.
ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
# Developers
- [tridungduong16](https://github.com/tridungduong16)
# Citation
```bibtex
@software{OpenOrca_Preview1,
title = {OpenOrca_Preview1: A LLaMA-13B Model Fine-tuned on Small Portion of OpenOrcaV1 Dataset},
author = {Wing Lian and Bleys Goodson and Eugene Pentland and Austin Cook and Chanvichet Vong and "Teknium"},
year = {2023},
publisher = {HuggingFace},
journal = {HuggingFace repository},
howpublished = {\url{https://https://huggingface.co/Open-Orca/OpenOrca-Preview1-13B},
}
```
```bibtex
@misc{mukherjee2023orca,
title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
year={2023},
eprint={2306.02707},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```bibtex
@misc{longpre2023flan,
title={The Flan Collection: Designing Data and Methods for Effective Instruction Tuning},
author={Shayne Longpre and Le Hou and Tu Vu and Albert Webson and Hyung Won Chung and Yi Tay and Denny Zhou and Quoc V. Le and Barret Zoph and Jason Wei and Adam Roberts},
year={2023},
eprint={2301.13688},
archivePrefix={arXiv},
primaryClass={cs.AI}
}
```
```bibtex
@software{touvron2023llama,
title={LLaMA: Open and Efficient Foundation Language Models},
author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and Rodriguez, Aurelien and Joulin, Armand and Grave, Edouard and Lample, Guillaume},
journal={arXiv preprint arXiv:2302.13971},
year={2023}
}
```
|
allenwang117/Reinforce-1
|
allenwang117
| 2023-07-24T22:17:52Z | 0 | 0 | null |
[
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-24T22:17:44Z |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 500.00 +/- 0.00
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
|
isthatdebbiej/donut-base-sroie
|
isthatdebbiej
| 2023-07-24T22:12:27Z | 45 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"vision-encoder-decoder",
"image-text-to-text",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:naver-clova-ix/donut-base",
"base_model:finetune:naver-clova-ix/donut-base",
"license:mit",
"endpoints_compatible",
"region:us"
] |
image-text-to-text
| 2023-07-24T20:47:13Z |
---
license: mit
base_model: naver-clova-ix/donut-base
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: donut-base-sroie
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# donut-base-sroie
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3
|
arpan-das-astrophysics/deep-rl
|
arpan-das-astrophysics
| 2023-07-24T22:06:42Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-24T22:06:40Z |
---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: deep-rl
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="arpan-das-astrophysics/deep-rl", 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"])
```
|
yohein/bloomz-3b_PROMPT_TUNING_CAUSAL_LM
|
yohein
| 2023-07-24T22:05:29Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-24T22:05:28Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0.dev0
|
zacdennis/taxi-v3
|
zacdennis
| 2023-07-24T22:02:34Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-24T22:02:33Z |
---
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="zacdennis/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"])
```
|
JBJoyce/whisper-tiny-fine-tuned-minds
|
JBJoyce
| 2023-07-24T22:02:17Z | 78 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:PolyAI/minds14",
"base_model:openai/whisper-tiny",
"base_model:finetune:openai/whisper-tiny",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-07-24T20:41:34Z |
---
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- PolyAI/minds14
metrics:
- wer
model-index:
- name: whisper-tiny-fine-tuned-minds
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: PolyAI/minds14
type: PolyAI/minds14
config: en-US
split: train[450:]
args: en-US
metrics:
- name: Wer
type: wer
value: 0.35182998819362454
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# whisper-tiny-fine-tuned-minds
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6481
- Wer Ortho: 0.3560
- Wer: 0.3518
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
| 0.0007 | 17.86 | 500 | 0.6481 | 0.3560 | 0.3518 |
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3
|
mskhattori/wav2vec2phone-large-xlsr-jp-jdrtfw07-demo3
|
mskhattori
| 2023-07-24T21:46:58Z | 8 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"base_model:jonatasgrosman/wav2vec2-large-xlsr-53-japanese",
"base_model:finetune:jonatasgrosman/wav2vec2-large-xlsr-53-japanese",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-07-24T17:25:00Z |
---
license: apache-2.0
base_model: jonatasgrosman/wav2vec2-large-xlsr-53-japanese
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2phone-large-xlsr-jp-jdrtfw07-demo3
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. -->
# wav2vec2phone-large-xlsr-jp-jdrtfw07-demo3
This model is a fine-tuned version of [jonatasgrosman/wav2vec2-large-xlsr-53-japanese](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-japanese) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0451
- Wer: 0.025
- Cer: 0.0195
## 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: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1640
- num_epochs: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
| 3.0002 | 1.0 | 328 | 2.8482 | 0.9965 | 0.9980 |
| 2.2134 | 2.0 | 656 | 2.0964 | 0.8864 | 0.9374 |
| 1.6625 | 3.0 | 984 | 1.2925 | 0.7960 | 0.7917 |
| 1.0846 | 4.0 | 1312 | 0.4955 | 0.3292 | 0.3089 |
| 0.8593 | 5.0 | 1640 | 0.2443 | 0.1061 | 0.0839 |
| 0.7502 | 6.0 | 1968 | 0.1552 | 0.0620 | 0.0504 |
| 0.6342 | 7.0 | 2296 | 0.1202 | 0.0491 | 0.0422 |
| 0.6012 | 8.0 | 2624 | 0.1008 | 0.0442 | 0.0379 |
| 0.6214 | 9.0 | 2952 | 0.0846 | 0.0390 | 0.0333 |
| 0.5486 | 10.0 | 3280 | 0.0756 | 0.0361 | 0.0309 |
| 0.5633 | 11.0 | 3608 | 0.0669 | 0.0310 | 0.0261 |
| 0.4977 | 12.0 | 3936 | 0.0609 | 0.0300 | 0.0251 |
| 0.4863 | 13.0 | 4264 | 0.0556 | 0.0282 | 0.0233 |
| 0.4416 | 14.0 | 4592 | 0.0533 | 0.0279 | 0.0234 |
| 0.4713 | 15.0 | 4920 | 0.0499 | 0.0266 | 0.0214 |
| 0.4715 | 16.0 | 5248 | 0.0489 | 0.0252 | 0.0197 |
| 0.4724 | 17.0 | 5576 | 0.0472 | 0.0259 | 0.0205 |
| 0.4835 | 18.0 | 5904 | 0.0463 | 0.0259 | 0.0204 |
| 0.4589 | 19.0 | 6232 | 0.0454 | 0.0252 | 0.0199 |
| 0.4207 | 20.0 | 6560 | 0.0451 | 0.025 | 0.0195 |
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
au2a/whisper-base-zh-20230724
|
au2a
| 2023-07-24T21:41:48Z | 85 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"zh",
"dataset:-",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-07-24T08:37:14Z |
---
language:
- zh
license: apache-2.0
tags:
- whisper
- generated_from_trainer
datasets:
- '-'
model-index:
- name: whisper-base-zh-20230724 - au2a
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-base-zh-20230724 - au2a
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the some hakka audio dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4868
- Cer: 21.2071
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 32
- 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_steps: 500
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|:-------------:|:-----:|:-----:|:---------------:|:-------:|
| 0.348 | 1.55 | 1000 | 0.6190 | 30.1519 |
| 0.1375 | 3.1 | 2000 | 0.4988 | 23.8969 |
| 0.0741 | 4.65 | 3000 | 0.4735 | 22.7089 |
| 0.0348 | 6.2 | 4000 | 0.4643 | 21.9984 |
| 0.0211 | 7.75 | 5000 | 0.4688 | 22.1851 |
| 0.0102 | 9.3 | 6000 | 0.4738 | 21.3982 |
| 0.0076 | 10.85 | 7000 | 0.4762 | 21.3477 |
| 0.0049 | 12.4 | 8000 | 0.4820 | 21.3352 |
| 0.0044 | 13.95 | 9000 | 0.4859 | 21.1040 |
| 0.0036 | 15.5 | 10000 | 0.4868 | 21.2071 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
|
benjamin/compoundpiece-stage1
|
benjamin
| 2023-07-24T21:32:13Z | 112 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"t5",
"text2text-generation",
"af",
"az",
"be",
"bg",
"bn",
"ca",
"cs",
"cy",
"da",
"de",
"el",
"en",
"eo",
"es",
"et",
"eu",
"fa",
"fi",
"fr",
"fy",
"ga",
"gl",
"gu",
"he",
"hi",
"hu",
"hy",
"id",
"is",
"it",
"ka",
"kk",
"ky",
"la",
"lt",
"lv",
"mg",
"mk",
"ml",
"mt",
"nl",
"pa",
"pl",
"pt",
"ro",
"ru",
"sk",
"sq",
"sv",
"ta",
"te",
"th",
"tr",
"uk",
"yi",
"yo",
"dataset:benjamin/compoundpiece",
"arxiv:2305.14214",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-05-13T12:02:23Z |
---
license: mit
language:
- af
- az
- be
- bg
- bn
- ca
- cs
- cy
- da
- de
- el
- en
- eo
- es
- et
- eu
- fa
- fi
- fr
- fy
- ga
- gl
- gu
- he
- hi
- hu
- hy
- id
- is
- it
- ka
- kk
- ky
- la
- lt
- lv
- mg
- mk
- ml
- mt
- nl
- pa
- pl
- pt
- ro
- ru
- sk
- sq
- sv
- ta
- te
- th
- tr
- uk
- yi
- yo
datasets:
- benjamin/compoundpiece
---
CompoundPiece model trained only on Stage 1 training data (self-supervised training on hyphenated and non-hyphenated words scraped from the web). See [CompoundPiece: Evaluating and Improving Decompounding Performance of Language Models](https://arxiv.org/abs/2305.14214).
# Citation
```
@article{minixhofer2023compoundpiece,
title={CompoundPiece: Evaluating and Improving Decompounding Performance of Language Models},
author={Minixhofer, Benjamin and Pfeiffer, Jonas and Vuli{\'c}, Ivan},
journal={arXiv preprint arXiv:2305.14214},
year={2023}
}
```
# License
MIT
|
snicolau/a2c-PandaReachDense-v2
|
snicolau
| 2023-07-24T21:30:26Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"PandaReachDense-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-24T21:27:42Z |
---
library_name: stable-baselines3
tags:
- PandaReachDense-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PandaReachDense-v2
type: PandaReachDense-v2
metrics:
- type: mean_reward
value: -0.93 +/- 0.43
name: mean_reward
verified: false
---
# **A2C** Agent playing **PandaReachDense-v2**
This is a trained model of a **A2C** agent playing **PandaReachDense-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
...
```
|
anth0nyhak1m/CFGFP_ProductGroupCalssifier_v1
|
anth0nyhak1m
| 2023-07-24T21:08:37Z | 18 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-29T16:48:52Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: CFGFP_ProductGroupCalssifier_v1
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. -->
# CFGFP_ProductGroupCalssifier_v1
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1960
- Accuracy: 0.9644
## 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 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.2342 | 1.0 | 3804 | 0.1990 | 0.9464 |
| 0.1457 | 2.0 | 7608 | 0.1844 | 0.9567 |
| 0.1083 | 3.0 | 11412 | 0.1864 | 0.9602 |
| 0.0675 | 4.0 | 15216 | 0.1943 | 0.9641 |
| 0.0464 | 5.0 | 19020 | 0.1960 | 0.9644 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3
|
yuanzi1983918/ppo-Huggy
|
yuanzi1983918
| 2023-07-24T21:00:27Z | 7 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-07-24T21:00:22Z |
---
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: yuanzi1983918/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
Gelmo/Halouf
|
Gelmo
| 2023-07-24T20:54:19Z | 0 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"conversational",
"en",
"dataset:fka/awesome-chatgpt-prompts",
"dataset:Open-Orca/OpenOrca",
"dataset:ehartford/dolphin",
"dataset:OpenAssistant/oasst1",
"region:us"
] |
text-generation
| 2023-07-24T20:52:28Z |
---
datasets:
- fka/awesome-chatgpt-prompts
- Open-Orca/OpenOrca
- ehartford/dolphin
- OpenAssistant/oasst1
language:
- en
metrics:
- code_eval
- accuracy
library_name: adapter-transformers
pipeline_tag: conversational
---
|
feic36/distilbert-base-uncased-finetuned-emotion
|
feic36
| 2023-07-24T20:50:28Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-07-24T20:41:21Z |
---
license: apache-2.0
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
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.926
- name: F1
type: f1
value: 0.9260443152296819
---
<!-- 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: 0.2249
- Accuracy: 0.926
- F1: 0.9260
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8358 | 1.0 | 250 | 0.3221 | 0.9025 | 0.8992 |
| 0.252 | 2.0 | 500 | 0.2249 | 0.926 | 0.9260 |
### Framework versions
- Transformers 4.16.2
- Pytorch 2.0.1+cu118
- Datasets 1.16.1
- Tokenizers 0.13.3
|
yusuf802/My_QA_Model_1
|
yusuf802
| 2023-07-24T20:50:26Z | 61 | 0 |
transformers
|
[
"transformers",
"tf",
"distilbert",
"question-answering",
"generated_from_keras_callback",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-07-24T20:33:42Z |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: yusuf802/My_QA_Model_1
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# yusuf802/My_QA_Model_1
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 1.6050
- Validation Loss: 1.7314
- Epoch: 2
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 500, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 3.4545 | 2.1133 | 0 |
| 1.8704 | 1.7314 | 1 |
| 1.6050 | 1.7314 | 2 |
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
snicolau/a2c-AntBulletEnv-v0
|
snicolau
| 2023-07-24T20:37:28Z | 1 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"AntBulletEnv-v0",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-24T20:36:17Z |
---
library_name: stable-baselines3
tags:
- AntBulletEnv-v0
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: AntBulletEnv-v0
type: AntBulletEnv-v0
metrics:
- type: mean_reward
value: 1662.96 +/- 314.55
name: mean_reward
verified: false
---
# **A2C** Agent playing **AntBulletEnv-v0**
This is a trained model of a **A2C** agent playing **AntBulletEnv-v0**
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
...
```
|
Kartikey95/mt5-xl-phrase-expansion-de
|
Kartikey95
| 2023-07-24T20:29:52Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-24T20:29:48Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- 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 0.4.0.dev0
|
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.