modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-09-24 00:43:13
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 573
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-09-24 00:37:34
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
anirbankgec/anirban_qa_model
|
anirbankgec
| 2023-07-04T06:21:39Z | 104 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-07-04T05:47:43Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: anirban_qa_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. -->
# anirban_qa_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5705
## 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
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 250 | 2.2741 |
| 2.6748 | 2.0 | 500 | 1.6251 |
| 2.6748 | 3.0 | 750 | 1.5705 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Pranjal-666/Reinforce-pixelcopter
|
Pranjal-666
| 2023-07-04T06:10:20Z | 0 | 0 | null |
[
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-03T08:35:18Z |
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-pixelcopter
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 21.80 +/- 13.98
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
nic70/dqn-SpaceInvadersNoFrameskip-v4
|
nic70
| 2023-07-04T05:49:04Z | 1 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-04T05:48:23Z |
---
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: 625.50 +/- 109.99
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 nic70 -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 nic70 -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 nic70
```
## 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'}
```
|
l3cube-pune/marathi-sentiment-subtitles
|
l3cube-pune
| 2023-07-04T05:24:38Z | 109 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"bert",
"text-classification",
"mr",
"dataset:L3Cube-MahaSent-MD",
"arxiv:2306.13888",
"arxiv:2205.14728",
"license:cc-by-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-04T07:58:17Z |
---
language: mr
tags:
- bert
license: cc-by-4.0
datasets:
- L3Cube-MahaSent-MD
widget:
- text: "I like you. </s></s> I love you."
---
## MahaSent-ST
MahaSent-ST is a MahaBERT(l3cube-pune/marathi-bert-v2) model fine-tuned on L3Cube-MahaSent-ST Corpus, a subtitles domain, Marathi sentiment analysis dataset. <br>
This dataset is a part of L3Cube-MahaSent-MD, a multi-domain Marathi sentiment analysis dataset. <br>
The MahaSent-MD dataset contains domains like movie reviews, generic tweets, subtitles, and political tweets. This model is trained specifically on the subtitles domain. <br>
The recommended multi-domain version of this model covering all domains is shared here: <a href="https://huggingface.co/l3cube-pune/marathi-sentiment-md"> marathi-sentiment-md </a> <br>
[dataset link] (https://github.com/l3cube-pune/MarathiNLP) <br>
More details on the dataset, models, and baseline results can be found in our [paper] (https://arxiv.org/abs/2306.13888)
<br>
Citing:
```
@article{pingle2023l3cube,
title={L3Cube-MahaSent-MD: A Multi-domain Marathi Sentiment Analysis Dataset and Transformer Models},
author={Pingle, Aabha and Vyawahare, Aditya and Joshi, Isha and Tangsali, Rahul and Joshi, Raviraj},
journal={arXiv preprint arXiv:2306.13888},
year={2023}
}
```
```
@article{joshi2022l3cube,
title={L3cube-mahanlp: Marathi natural language processing datasets, models, and library},
author={Joshi, Raviraj},
journal={arXiv preprint arXiv:2205.14728},
year={2022}
}
```
Other Marathi Sentiment models from the MahaSent family are shared here:<br>
<a href="https://huggingface.co/l3cube-pune/marathi-sentiment-md"> MahaSent-MD (multi domain) </a> <br>
<a href="https://huggingface.co/l3cube-pune/marathi-sentiment-tweets"> MahaSent-GT (generic tweets) </a> <br>
<a href="https://huggingface.co/l3cube-pune/marathi-sentiment-movie-reviews"> MahaSent-MR (movie reviews) </a> <br>
<a href="https://huggingface.co/l3cube-pune/marathi-sentiment-political-tweets"> MahaSent-PT (political tweets) </a> <br>
<a href="https://huggingface.co/l3cube-pune/marathi-sentiment-subtitles"> MahaSent-ST (TV subtitles) </a> <br>
<a href="https://huggingface.co/l3cube-pune/MarathiSentiment"> MahaSent v1 (political tweets) </a> <br>
|
nolestock/RedPajama-INCITE-Base-3B-v1-SFT-guanaco-lora
|
nolestock
| 2023-07-04T05:02:36Z | 0 | 0 |
keras
|
[
"keras",
"en",
"arxiv:1910.09700",
"license:mit",
"region:us"
] | null | 2023-07-04T05:02:24Z |
---
language: en
license: mit
library_name: keras
---
# Model Card for RedPajama-INCITE-Base-3B-v1-SFT-guanaco-lora"
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
this model does this and that
- **Developed by:** Nate Raw
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** en
- **License:** mit
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** nolestock/RedPajama-INCITE-Base-3B-v1-SFT-guanaco-lora
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
saintzeno/reinforce-CartPole-v1
|
saintzeno
| 2023-07-04T04:39:55Z | 0 | 0 | null |
[
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-04T04:39:47Z |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: reinforce-CartPole-v1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 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
|
bobobert4/q-FrozenLake-v1-4x4-noSlippery
|
bobobert4
| 2023-07-04T04:38:26Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-04T04:38:24Z |
---
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="bobobert4/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"])
```
|
emya/outputs_200
|
emya
| 2023-07-04T04:38:26Z | 6 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dreambooth",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-07-03T05:52:40Z |
---
license: creativeml-openrail-m
base_model: outputs_200
instance_prompt: app icon, company logo for Booking.com, letter B as motif in the center, font color white, background color solid blue, minimal, simple
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - emya/outputs_200
This is a dreambooth model derived from outputs_200. The weights were trained on app icon, company logo for Booking.com, letter B as motif in the center, font color white, background color solid blue, minimal, simple using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
|
Pru06/ppo-LunarLander-v2
|
Pru06
| 2023-07-04T04:16:55Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-04T04:16:36Z |
---
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: 256.57 +/- 24.25
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
...
```
|
giuseppebs/ppo-Huggy
|
giuseppebs
| 2023-07-04T04:11:48Z | 12 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-07-04T04:11:43Z |
---
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: giuseppebs/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
anonderpling/horde_colab
|
anonderpling
| 2023-07-04T04:10:17Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-05-12T00:14:39Z |
Just wheels for the horde colab, built natively
Dunno why I even did this, tbh, when most of the processing is on the gpu...
I was *trying* to cross-compile build native packages with similar optimizations for my tablet, but I can't figure it out. Cross compiling is a pitfa.
```
%cd /content/
!rm -rf /content/AI-Horde-Worker /content/pip
!git clone https://github.com/db0/AI-Horde-Worker.git
%cd /content/AI-Horde-Worker
#!apt install nano aria2 libcairo2-dev libjpeg-dev libgif-dev htop llvm clang
!CFLAGS='-mtune=native -march=native -mcpu=native O3 -g -DNDEBUG' MAX_JOBS=4 pip wheel -r requirements.txt --wheel-dir=/content/pip
!CFLAGS='-mtune=native -march=native -mcpu=native O3 -g -DNDEBUG' MAX_JOBS=4 pip install -r requirements.txt --no-index --find-links /content/pip
```
That's it. It really does depend on the colab machines being exactly the same.
|
rsilg/ppo-LunarLander-v2
|
rsilg
| 2023-07-04T04:03:47Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-04T03:30:44Z |
---
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: 243.91 +/- 21.29
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
...
```
|
tiagotogas/SirKazzio
|
tiagotogas
| 2023-07-04T03:24:03Z | 0 | 0 | null |
[
"pt",
"license:openrail",
"region:us"
] | null | 2023-07-04T03:22:26Z |
---
license: openrail
language:
- pt
---
|
MariTonini/ppo-Huggy
|
MariTonini
| 2023-07-04T03:00:44Z | 15 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-07-04T03:00:38Z |
---
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: MariTonini/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
xunnylee/byakuyaTogami
|
xunnylee
| 2023-07-04T02:59:03Z | 0 | 0 | null |
[
"license:openrail",
"region:us"
] | null | 2023-07-04T02:57:09Z |
---
license: openrail
---
hi! thank you for using my model!
if you use it, please credit @xunnylee on youtube and discord!
have fun! :D
|
xian79/q-FrozenLake-v1-4x4-noSlippery
|
xian79
| 2023-07-04T02:51:50Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-04T02:51:47Z |
---
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="xian79/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"])
```
|
MDelan/ppo-Huggy
|
MDelan
| 2023-07-04T02:46:36Z | 15 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-07-03T19:29:26Z |
---
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: MDelan/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
ibibek/vicuna-13B-gptq
|
ibibek
| 2023-07-04T02:43:14Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-04T02:43:09Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
andres-gv/cmi-topics-3
|
andres-gv
| 2023-07-04T02:36:23Z | 4 | 0 |
bertopic
|
[
"bertopic",
"text-classification",
"region:us"
] |
text-classification
| 2023-07-04T02:34:49Z |
---
library_name: bertopic
pipeline_tag: text-classification
---
|
alibaba-pai/pai-diffusion-anime-large-zh
|
alibaba-pai
| 2023-07-04T02:28:21Z | 32 | 0 |
diffusers
|
[
"diffusers",
"pytorch",
"text-to-image",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-07-03T03:00:49Z |
---
license: apache-2.0
tags:
- pytorch
- diffusers
- text-to-image
---
# Chinese Diffusion Model (Anime, 512 Resolution)
## 简介 Brief Introduction
我们开源了一个中文 Diffusion 模型，您可以直接输入中文提示词，我们为您呈现精美的动漫风格图片。本模型的默认分辨率是 768*512（竖图）。
We release a Chinese diffusion model, which is able to generate high-quality anime images according to the prompts you input. The default resolution of this model is 768*512.
* Github: [EasyNLP](https://github.com/alibaba/EasyNLP)
## 使用 Usage
本模型支持 `diffusers`，可以参考以下范例代码：
This model supports `diffusers`. Please refer to the following code:
```python
from diffusers import StableDiffusionPipeline
model_id = "alibaba-pai/pai-diffusion-anime-large-zh"
pipe = StableDiffusionPipeline.from_pretrained(model_id)
pipe = pipe.to("cuda")
prompt = "1个女孩，玫瑰，猫，蕾丝，音符，轻粒子"
image = pipe(prompt, height=768, width=512).images[0]
image.save("result.png")
```
## 作品展示 Gallery
| prompt: 1个女孩，单人，高分辨率，腮红，看着观众，微笑，张开嘴，刘海 | prompt: 1个女孩，高分辨率，金发，坐着，紫色的眼睛，蝴蝶结 |
| --- | --- |
|  |  |
| prompt: 1个女孩，蓝眼睛，白色裙子，大腿，银色头发，百褶裙，天空 | prompt: 1个女孩，玫瑰，猫，蕾丝，音符，轻粒子 |
| --- | --- |
|  |  |
## 使用须知 Notice for Use
使用上述模型需遵守[AIGC模型开源特别条款](https://terms.alicdn.com/legal-agreement/terms/common_platform_service/20230505180457947/20230505180457947.html)。
If you want to use this model, please read this [document](https://terms.alicdn.com/legal-agreement/terms/common_platform_service/20230505180457947/20230505180457947.html) carefully and abide by the terms.
|
Ahmed007/Copilot_for_poors_v2
|
Ahmed007
| 2023-07-04T02:19:10Z | 108 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2022-12-22T22:02:47Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: Copilot_for_poors_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. -->
# Copilot_for_poors_v2
This model is a fine-tuned version of [Ahmed007/Copilot_for_poors](https://huggingface.co/Ahmed007/Copilot_for_poors) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5072
## 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: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 14 | 1.5951 |
| No log | 2.0 | 28 | 1.5887 |
| No log | 3.0 | 42 | 1.5792 |
| No log | 4.0 | 56 | 1.5684 |
| No log | 5.0 | 70 | 1.5601 |
| No log | 6.0 | 84 | 1.5525 |
| No log | 7.0 | 98 | 1.5462 |
| No log | 8.0 | 112 | 1.5401 |
| No log | 9.0 | 126 | 1.5335 |
| No log | 10.0 | 140 | 1.5293 |
| No log | 11.0 | 154 | 1.5257 |
| No log | 12.0 | 168 | 1.5220 |
| No log | 13.0 | 182 | 1.5182 |
| No log | 14.0 | 196 | 1.5151 |
| No log | 15.0 | 210 | 1.5124 |
| No log | 16.0 | 224 | 1.5110 |
| No log | 17.0 | 238 | 1.5096 |
| No log | 18.0 | 252 | 1.5083 |
| No log | 19.0 | 266 | 1.5074 |
| No log | 20.0 | 280 | 1.5072 |
### Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1
|
TalesLF/ppo-SnowballTarget
|
TalesLF
| 2023-07-04T02:16:46Z | 14 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] |
reinforcement-learning
| 2023-07-04T02:16:43Z |
---
library_name: ml-agents
tags:
- SnowballTarget
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SnowballTarget
---
# **ppo** Agent playing **SnowballTarget**
This is a trained model of a **ppo** agent playing **SnowballTarget**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: TalesLF/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
ysige/distilbert-base-uncased-distilled-clinc
|
ysige
| 2023-07-04T02:00:50Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:clinc_oos",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-07-04T00:49:56Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- clinc_oos
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-distilled-clinc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: clinc_oos
type: clinc_oos
config: plus
split: validation
args: plus
metrics:
- name: Accuracy
type: accuracy
value: 0.925483870967742
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-distilled-clinc
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0007
- Accuracy: 0.9255
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 48
- eval_batch_size: 48
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 318 | 0.0101 | 0.6877 |
| 0.0186 | 2.0 | 636 | 0.0036 | 0.8432 |
| 0.0186 | 3.0 | 954 | 0.0019 | 0.8913 |
| 0.0038 | 4.0 | 1272 | 0.0012 | 0.9148 |
| 0.0018 | 5.0 | 1590 | 0.0010 | 0.92 |
| 0.0018 | 6.0 | 1908 | 0.0008 | 0.9252 |
| 0.0013 | 7.0 | 2226 | 0.0008 | 0.9248 |
| 0.0011 | 8.0 | 2544 | 0.0007 | 0.9255 |
### Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cpu
- Datasets 2.11.0
- Tokenizers 0.13.3
|
wwkiyyx/yolo
|
wwkiyyx
| 2023-07-04T01:27:46Z | 0 | 0 | null |
[
"object-detection",
"zh",
"license:mit",
"region:us"
] |
object-detection
| 2023-07-04T01:24:32Z |
---
license: mit
language:
- zh
pipeline_tag: object-detection
---
|
Nams139/ppo-Huggy
|
Nams139
| 2023-07-04T01:18:03Z | 11 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-07-04T01:17:53Z |
---
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: Nams139/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
djifg/grow_classification_kcbert
|
djifg
| 2023-07-04T01:09:18Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-07-04T00:48:48Z |
---
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: grow_classification_kcbert
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. -->
# grow_classification_kcbert
This model is a fine-tuned version of [beomi/kcbert-large](https://huggingface.co/beomi/kcbert-large) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4473
- Accuracy: 0.9307
- F1: 0.9293
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 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: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.171 | 1.0 | 436 | 0.3674 | 0.9127 | 0.9113 |
| 0.0295 | 2.0 | 872 | 0.4799 | 0.9171 | 0.9150 |
| 0.0141 | 3.0 | 1308 | 0.4577 | 0.9285 | 0.9266 |
| 0.0087 | 4.0 | 1744 | 0.4352 | 0.9304 | 0.9291 |
| 0.0073 | 5.0 | 2180 | 0.4473 | 0.9307 | 0.9293 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
guimrtns/distilbert-base-uncased-finetuned-cola
|
guimrtns
| 2023-07-04T00:54:26Z | 61 | 0 |
transformers
|
[
"transformers",
"tf",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-07-03T23:52:10Z |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: guimrtns/distilbert-base-uncased-finetuned-cola
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. -->
# guimrtns/distilbert-base-uncased-finetuned-cola
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: 0.1983
- Validation Loss: 0.5310
- Train Matthews Correlation: 0.5094
- 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': 1602, '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 | Train Matthews Correlation | Epoch |
|:----------:|:---------------:|:--------------------------:|:-----:|
| 0.5196 | 0.4838 | 0.4297 | 0 |
| 0.3302 | 0.4419 | 0.5227 | 1 |
| 0.1983 | 0.5310 | 0.5094 | 2 |
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Allenpai/alpaca-lora2
|
Allenpai
| 2023-07-04T00:47:29Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-02T11:32:59Z |
---
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
|
mazeinmouse/ppo-PyramidsTarget
|
mazeinmouse
| 2023-07-04T00:38:00Z | 2 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Pyramids",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Pyramids",
"region:us"
] |
reinforcement-learning
| 2023-07-04T00:36:21Z |
---
library_name: ml-agents
tags:
- Pyramids
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Pyramids
---
# **ppo** Agent playing **Pyramids**
This is a trained model of a **ppo** agent playing **Pyramids**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: mazeinmouse/ppo-PyramidsTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
kato96/yicbip
|
kato96
| 2023-07-04T00:33:44Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-07-04T00:28:13Z |
---
license: creativeml-openrail-m
---
|
AkshayShetty/detr-resnet-50_finetuned_cppe5
|
AkshayShetty
| 2023-07-04T00:28:34Z | 188 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"detr",
"object-detection",
"generated_from_trainer",
"dataset:imagefolder",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
object-detection
| 2023-07-02T22:49:15Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: detr-resnet-50_finetuned_cppe5
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. -->
# detr-resnet-50_finetuned_cppe5
This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) 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: 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: 1000
### Training results
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
ysmaicon/ppo-Huggy
|
ysmaicon
| 2023-07-04T00:25:06Z | 11 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-07-04T00:25:02Z |
---
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: ysmaicon/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-fp16
|
bhenrym14
| 2023-07-04T00:23:36Z | 1,405 | 4 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-gpt4-1.4.1",
"arxiv:2306.15595",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-07-03T22:09:52Z |
---
datasets:
- jondurbin/airoboros-gpt4-1.4.1
---
# RoPE Scaled QLoRA Finetune of airoboros-33b-gpt4-1.4.1 (fp16)
LoRA Weights can be found here: https://huggingface.co/bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-LoRA
GPTQ quantized weights can be found here: https://huggingface.co/bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-GPTQ
## Overview
This is [Jon Durbin's Airoboros 33B GPT4 1.4](https://huggingface.co/jondurbin/airoboros-33b-gpt4-1.4) (merged model - fp16 weights) with several key modifications:
- Context length extended to 8192 by RoPE Scaled Embeddings, but NOT via the superHOT LoRA. I started with base Llama-33b.
- Training sequences beyond 2048 have the target truncated to equal 2048.
- Used airoboros-gpt4-1.4.1 dataset instead of airoboros-gpt4-1.4
Otherwise, I emulated the training process as closely as possible (rank 64 QLoRA) It was trained on 1x RTX 6000 Ada for ~43 hours.
## How to Use
The easiest way is to use the GPTQ weights (linked above) with [oobabooga text-generation-webui](https://github.com/oobabooga/text-generation-webui) and ExLlama. You'll need to set max_seq_len to 8192 and compress_pos_emb to 4.
**IMPORTANT: To use these weights you'll need to patch in the appropriate RoPE scaling module. see: [replace_llama_rope_with_scaled_rope](https://github.com/bhenrym14/qlora-airoboros-longcontext/blob/main/scaledllama/llama_rope_scaled_monkey_patch.py)**
## Motivation
Recent advancements in extending context by RoPE scaling ([kaiokendev](https://kaiokendev.github.io/til#extending-context-to-8k) and [meta AI)](https://arxiv.org/abs/2306.15595)) demonstrate the ability to extend the context window without (total) retraining. Finetuning has shown to be necessary to properly leverage the longer context. The superHOT LoRA is an adapter that has been finetuned on longer context (8192 tokens); even when applied to models trained on dissimilar datasets, it successfully extends the context window to which the model can attend. While it's impressive this adapter is so flexible, how much does performance suffer relative to a model that has been finetuned with the scaled embeddings from the start? This is an experiment to explore this.
## Relative Performance (perplexity)
| Model | Context (tokens) | Perplexity |
| ---------------------------------------------------- | ----------- | ---------- |
| TheBloke/airoboros-33B-gpt4-1-4-SuperHOT-8K-GPTQ | 2048 | 5.15 |
| TheBloke/airoboros-33B-gpt4-1-4-SuperHOT-8K-GPTQ | 3072 | 5.04 |
| **bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-GPTQ** | **2048** | **4.32** |
| **bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-GPTQ** | **3072** | **4.26** |
- How does this reduction in perplexity translate into actual performance lift on downstream tasks? I'm not sure yet. I've done a few experiments and have been happy with the performance, but I haven't used models with the SuperHOT LoRA enough to have any sense of performance differences.
- This comparison isn't perfect. I did use the 1.4.1 dataset, the quantization method is slightly different.
## Prompting:
See original model card below.
# Original model card: Jon Durbin's Airoboros 33B GPT4 1.4
__not yet tested!__
## Overview
This is a qlora fine-tune 33b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros
This is mostly an extension of the previous gpt-4 series, with a few extras:
* fixed (+ more examples of) multi-character, multi-turn conversations
* coding examples in 10 languages from rosettacode.org dataset thanks to Mike aka kryptkpr: https://huggingface.co/datasets/mike-ravkine/rosettacode-parsed
* more roleplay examples
* jokes
* riddles
* all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT)
This model was fine-tuned with a fork of [qlora](https://github.com/jondurbin/qlora)
The prompt it was trained with was:
```
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT:
```
So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).
## Usage
To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors.
```
pip install git+https://github.com/jondurbin/FastChat
```
Be sure you are pulling the latest branch!
Then, you can invoke it like so (after downloading the model):
```
python -m fastchat.serve.cli \
--model-path airoboros-33b-gpt4-1.4 \
--temperature 0.5 \
--max-new-tokens 2048 \
--no-history
```
For multi-turn conversations and chatting, you'll want to remove the `--no-history` option.
### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
url: https://some.web.site/123
date: 2023-06-01
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described:
```
USER: BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
ASSISTANT:
```
### Coding
You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt):
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can optionally add a newline and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js.
PLAINFORMAT
```
### Word games / trivia
```
USER: This anagram of "silent" is what you do when paying attention and hearing someone.
ASSISTANT: listen
```
```
USER: Give me a list of 7 words that start with EN
ASSISTANT: 1. Endlessly
2. Enthusiastically
3. Enormously
4. Enveloping
5. Enduring
6. Enlightening
7. Encouraging
```
### Multiple choice
```
USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt?
A) Mercury
B) Venus
C) Pluto
D) Jupiter
ASSISTANT: C, Pluto
```
### Writing
<details>
<summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary>
Response:
```
ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home.
Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes.
No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice.
So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary>
```
</details>
### Jokes
```
USER: Tell me a joke about bananas.
ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E.
```
### Riddles (not great, but slightly better)
```
USER: What has a neck but no head?
ASSISTANT: A bottle.
```
### Multi-character conversations
```
USER: Characters:
- Yoda, the ever clever jedi master.
- Homer Simpson, you know, the goofy yellow guy.
- USER/Jon - don't generate any speech or actions on behalf of Jon
Rules:
- be sure to use the manerisms and speaking style of the characters correctly
- surround character actions with asterisks
- always put quotes around words spoken by the characters
- use a new line for each character's actions or speech
- always prefix actions/speech with the character's name and colon
- only generate text and actions on behalf of Yoda or Homer, and never anyone else
Conversation will revolve around the grapes, in a local cafe with delicious coffee.
Generate a single interaction between Yoda and Homer to start, with one sentence each.
ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer."
Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!"
USER: *enters the cafe* Sorry I'm late guys!
ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes."
Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!"
*Yoda raises an eyebrow*
```
### Usage and License Notices
All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because:
- the base model is LLaMa, which has it's own special research license
- the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai
So, to reiterate: this model (and datasets) cannot be used commercially.
|
hemulitch/finetuned_model
|
hemulitch
| 2023-07-04T00:12:38Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"token-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-07-03T21:02:30Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: finetuned_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. -->
# finetuned_model
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: 0.0524
- Precision: 0.9802
- Recall: 0.9799
- F1: 0.9800
- Accuracy: 0.9799
## 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 |
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.0788 | 1.0 | 7048 | 0.0674 | 0.9763 | 0.9751 | 0.9756 | 0.9751 |
| 0.0567 | 2.0 | 14096 | 0.0524 | 0.9802 | 0.9799 | 0.9800 | 0.9799 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
foreverip/ppo-Huggy
|
foreverip
| 2023-07-04T00:00:55Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-07-04T00:00:44Z |
---
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: foreverip/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
NasimB/gpt2-dp-gutenberg-fixed
|
NasimB
| 2023-07-03T23:58:26Z | 5 | 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
| 2023-07-03T21:47:55Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: gpt2-dp-gutenberg-fixed
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. -->
# gpt2-dp-gutenberg-fixed
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: 3.1394
## 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 |
|:-------------:|:-----:|:-----:|:---------------:|
| 6.7114 | 0.27 | 500 | 5.6575 |
| 5.3632 | 0.54 | 1000 | 5.2280 |
| 5.0215 | 0.81 | 1500 | 4.9772 |
| 4.7647 | 1.08 | 2000 | 4.8238 |
| 4.5742 | 1.35 | 2500 | 4.7096 |
| 4.4883 | 1.62 | 3000 | 4.6098 |
| 4.4004 | 1.89 | 3500 | 4.5143 |
| 4.207 | 2.16 | 4000 | 4.4732 |
| 4.1128 | 2.43 | 4500 | 4.4205 |
| 4.0827 | 2.7 | 5000 | 4.3622 |
| 4.0505 | 2.97 | 5500 | 4.3114 |
| 3.8066 | 3.24 | 6000 | 4.3173 |
| 3.7866 | 3.51 | 6500 | 4.2872 |
| 3.7701 | 3.78 | 7000 | 4.2562 |
| 3.7022 | 4.05 | 7500 | 4.2455 |
| 3.4888 | 4.32 | 8000 | 4.2468 |
| 3.4902 | 4.59 | 8500 | 4.2348 |
| 3.4834 | 4.86 | 9000 | 4.2222 |
| 3.3882 | 5.13 | 9500 | 4.2306 |
| 3.2957 | 5.4 | 10000 | 4.2306 |
| 3.2966 | 5.67 | 10500 | 4.2293 |
| 3.2954 | 5.94 | 11000 | 4.2286 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
|
zwpython/stable-vicuna-13B-chinese
|
zwpython
| 2023-07-03T23:33:53Z | 0 | 9 | null |
[
"license:unknown",
"region:us"
] | null | 2023-05-07T00:44:28Z |
---
license: unknown
---
http://gpt.meta-font.vip/gptapp/h5/
国内版是我们自己本地模型 目前都是免费的
---------------
为响应国家AI大战略需求，提高国内AI、GPT初创团队的竞争力，不要输在起跑线上。
zw-vicuna-33B-cn中文汉化版，首度提供免费下载通道。
zw-vicuna-33B中文版 百度网盘提取码：hiks
链接：https://pan.baidu.com/s/1EH19ablXVLYQP1f-IaPS-Q?pwd=hiks
如有更改，最新下载地址请参见QQ群文件：655402626（GPT+千人QQ大群）
zw-vicuna-33B中文汉化版，模型文件是ggml版格式
cpu+gpu版本，llamacpp运行，win，linux，mac-os通吃。
具体细节参见：https://github.com/ggerganov/llama.cpp
Prompt template提示词模板：
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input
USER: prompt
ASSISTANT:
更多细节和技术参数，参见：
官方原版：https://huggingface.co/lmsys/vicuna-33b-v1.3
Github项目： https://github.com/ziwang-com/chinese-StableVicuna
------------
chinese-StableVicuna 全球首个StableVicuna中文优化版。
http://metafont.vip 短域名:http://m-f.vip
基于CarperAI官方 stable-vicuna-13B 模型。
StableVicuna基于Vicuna-13B模型实现，是全球首个基于--RLHF人类反馈训练--的开源LLM模型。
被业界视为：是自ChatGPT推出以来的第二个里程碑。
Stable-Vicuna发布不到一周，HF网站就涌现10个衍生版本。zw团队的StableVicuna中文优化版，是其中唯一的中文版本。
相关项目网址：
https://github.com/ziwang-com/chinese-StableVicuna
https://huggingface.co/zwpython/stable-vicuna-13B-chinese
这几天UC佰克利大学发布的开源模型排行榜，vicuna-13B排名第一，相关衍生模型可能更多，特别是Stable-Vicuna系列。
StableVicuna中文优化版，在中文细节，优于原版StableVicuna模型，语境、场景好多了，有点人情味了。
联系方式：
微信：zwpython，或扫码HF账号头像二维码。
QQ：357811718（zw字王）
合作伙伴请提供相关文字资料：团队核心成员简介，研究课题，合作方向，如有相关PPT资料更好。
|
kikeavi36/GPT4SPAIN
|
kikeavi36
| 2023-07-03T23:24:15Z | 0 | 0 | null |
[
"license:bigscience-openrail-m",
"region:us"
] | null | 2023-07-03T23:24:15Z |
---
license: bigscience-openrail-m
---
|
spike-spiegel/ppo-LunarLander-v2
|
spike-spiegel
| 2023-07-03T23:20:25Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-03T14:46:03Z |
---
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: 250.87 +/- 23.58
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
...
```
|
Shezus/finetuning-sentiment-model-5000-samples
|
Shezus
| 2023-07-03T23:03:36Z | 99 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:imdb",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-07-03T22:54:14Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
- f1
model-index:
- name: finetuning-sentiment-model-5000-samples
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: imdb
type: imdb
config: plain_text
split: test
args: plain_text
metrics:
- name: Accuracy
type: accuracy
value: 0.903
- name: F1
type: f1
value: 0.902902902902903
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# finetuning-sentiment-model-5000-samples
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2992
- Accuracy: 0.903
- F1: 0.9029
## 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
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Shezus/finetuning-sentiment-model-10000-samples
|
Shezus
| 2023-07-03T22:39:49Z | 104 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:imdb",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-07-03T20:23:09Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
- f1
model-index:
- name: finetuning-sentiment-model-10000-samples
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: imdb
type: imdb
config: plain_text
split: test
args: plain_text
metrics:
- name: Accuracy
type: accuracy
value: 0.923
- name: F1
type: f1
value: 0.9234845975488573
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# finetuning-sentiment-model-10000-samples
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4001
- Accuracy: 0.923
- F1: 0.9235
## 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: 4
### Training results
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
JesseJr/ppo-Huggy
|
JesseJr
| 2023-07-03T22:21:48Z | 11 | 1 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-07-03T22:21:44Z |
---
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: JesseJr/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
squeeze-ai-lab/sq-llama-7b-w4-s5
|
squeeze-ai-lab
| 2023-07-03T22:18:05Z | 0 | 0 | null |
[
"arxiv:2306.07629",
"arxiv:2302.13971",
"region:us"
] | null | 2023-06-20T21:24:02Z |
**SqueezeLLM** is a post-training quantization framework that incorporates a new method called Dense-and-Sparse Quantization to enable efficient LLM serving.
**TLDR:** Deploying LLMs is difficult due to their large memory size. This can be addressed with reduced precision quantization.
But a naive method hurts performance. We address this with a new Dense-and-Sparse Quantization method.
Dense-and-Sparse splits weight matrices into two components: A dense component that can be heavily quantized without affecting model performance,
as well as a sparse part that preserves sensitive and outlier parts of the weight matrices With this approach,
we are able to serve larger models with smaller memory footprint, the same latency, and yet higher accuracy and quality.
For more details please check out our [paper](https://arxiv.org/pdf/2306.07629.pdf).
## Model description
4-bit quantized LLaMA 7B model using SqueezeLLM. More details can be found in the [paper](https://arxiv.org/pdf/2306.07629.pdf).
* **Base Model:** [LLaMA 7B](https://arxiv.org/abs/2302.13971)
* **Bitwidth:** 4-bit
* **Sparsity Level:** 0.05%
## Links
* **Paper**: [https://arxiv.org/pdf/2306.07629.pdf](https://arxiv.org/pdf/2306.07629.pdf)
* **Code**: [https://github.com/SqueezeAILab/SqueezeLLM](https://github.com/SqueezeAILab/SqueezeLLM)
---
license: other
---
|
squeeze-ai-lab/sq-llama-65b-w4-s5
|
squeeze-ai-lab
| 2023-07-03T22:18:02Z | 0 | 0 | null |
[
"arxiv:2306.07629",
"arxiv:2302.13971",
"region:us"
] | null | 2023-06-25T16:34:37Z |
**SqueezeLLM** is a post-training quantization framework that incorporates a new method called Dense-and-Sparse Quantization to enable efficient LLM serving.
**TLDR:** Deploying LLMs is difficult due to their large memory size. This can be addressed with reduced precision quantization.
But a naive method hurts performance. We address this with a new Dense-and-Sparse Quantization method.
Dense-and-Sparse splits weight matrices into two components: A dense component that can be heavily quantized without affecting model performance,
as well as a sparse part that preserves sensitive and outlier parts of the weight matrices With this approach,
we are able to serve larger models with smaller memory footprint, the same latency, and yet higher accuracy and quality.
For more details please check out our [paper](https://arxiv.org/pdf/2306.07629.pdf).
## Model description
4-bit quantized LLaMA 65B model using SqueezeLLM. More details can be found in the [paper](https://arxiv.org/pdf/2306.07629.pdf).
* **Base Model:** [LLaMA 65B](https://arxiv.org/abs/2302.13971)
* **Bitwidth:** 4-bit
* **Sparsity Level:** 0.05%
## Links
* **Paper**: [https://arxiv.org/pdf/2306.07629.pdf](https://arxiv.org/pdf/2306.07629.pdf)
* **Code**: [https://github.com/SqueezeAILab/SqueezeLLM](https://github.com/SqueezeAILab/SqueezeLLM)
---
license: other
---
|
squeeze-ai-lab/sq-llama-65b-w4-s45
|
squeeze-ai-lab
| 2023-07-03T22:18:01Z | 0 | 0 | null |
[
"arxiv:2306.07629",
"arxiv:2302.13971",
"region:us"
] | null | 2023-06-25T16:34:18Z |
**SqueezeLLM** is a post-training quantization framework that incorporates a new method called Dense-and-Sparse Quantization to enable efficient LLM serving.
**TLDR:** Deploying LLMs is difficult due to their large memory size. This can be addressed with reduced precision quantization.
But a naive method hurts performance. We address this with a new Dense-and-Sparse Quantization method.
Dense-and-Sparse splits weight matrices into two components: A dense component that can be heavily quantized without affecting model performance,
as well as a sparse part that preserves sensitive and outlier parts of the weight matrices With this approach,
we are able to serve larger models with smaller memory footprint, the same latency, and yet higher accuracy and quality.
For more details please check out our [paper](https://arxiv.org/pdf/2306.07629.pdf).
## Model description
4-bit quantized LLaMA 65B model using SqueezeLLM. More details can be found in the [paper](https://arxiv.org/pdf/2306.07629.pdf).
* **Base Model:** [LLaMA 65B](https://arxiv.org/abs/2302.13971)
* **Bitwidth:** 4-bit
* **Sparsity Level:** 0.45%
## Links
* **Paper**: [https://arxiv.org/pdf/2306.07629.pdf](https://arxiv.org/pdf/2306.07629.pdf)
* **Code**: [https://github.com/SqueezeAILab/SqueezeLLM](https://github.com/SqueezeAILab/SqueezeLLM)
---
license: other
---
|
squeeze-ai-lab/sq-llama-65b-w3-s5
|
squeeze-ai-lab
| 2023-07-03T22:17:59Z | 0 | 0 | null |
[
"arxiv:2306.07629",
"arxiv:2302.13971",
"region:us"
] | null | 2023-06-25T16:34:03Z |
**SqueezeLLM** is a post-training quantization framework that incorporates a new method called Dense-and-Sparse Quantization to enable efficient LLM serving.
**TLDR:** Deploying LLMs is difficult due to their large memory size. This can be addressed with reduced precision quantization.
But a naive method hurts performance. We address this with a new Dense-and-Sparse Quantization method.
Dense-and-Sparse splits weight matrices into two components: A dense component that can be heavily quantized without affecting model performance,
as well as a sparse part that preserves sensitive and outlier parts of the weight matrices With this approach,
we are able to serve larger models with smaller memory footprint, the same latency, and yet higher accuracy and quality.
For more details please check out our [paper](https://arxiv.org/pdf/2306.07629.pdf).
## Model description
3-bit quantized LLaMA 65B model using SqueezeLLM. More details can be found in the [paper](https://arxiv.org/pdf/2306.07629.pdf).
* **Base Model:** [LLaMA 65B](https://arxiv.org/abs/2302.13971)
* **Bitwidth:** 3-bit
* **Sparsity Level:** 0.05%
## Links
* **Paper**: [https://arxiv.org/pdf/2306.07629.pdf](https://arxiv.org/pdf/2306.07629.pdf)
* **Code**: [https://github.com/SqueezeAILab/SqueezeLLM](https://github.com/SqueezeAILab/SqueezeLLM)
---
license: other
---
|
squeeze-ai-lab/sq-llama-65b-w3-s45
|
squeeze-ai-lab
| 2023-07-03T22:17:58Z | 0 | 0 | null |
[
"arxiv:2306.07629",
"arxiv:2302.13971",
"region:us"
] | null | 2023-06-25T16:33:45Z |
**SqueezeLLM** is a post-training quantization framework that incorporates a new method called Dense-and-Sparse Quantization to enable efficient LLM serving.
**TLDR:** Deploying LLMs is difficult due to their large memory size. This can be addressed with reduced precision quantization.
But a naive method hurts performance. We address this with a new Dense-and-Sparse Quantization method.
Dense-and-Sparse splits weight matrices into two components: A dense component that can be heavily quantized without affecting model performance,
as well as a sparse part that preserves sensitive and outlier parts of the weight matrices With this approach,
we are able to serve larger models with smaller memory footprint, the same latency, and yet higher accuracy and quality.
For more details please check out our [paper](https://arxiv.org/pdf/2306.07629.pdf).
## Model description
3-bit quantized LLaMA 65B model using SqueezeLLM. More details can be found in the [paper](https://arxiv.org/pdf/2306.07629.pdf).
* **Base Model:** [LLaMA 65B](https://arxiv.org/abs/2302.13971)
* **Bitwidth:** 3-bit
* **Sparsity Level:** 0.45%
## Links
* **Paper**: [https://arxiv.org/pdf/2306.07629.pdf](https://arxiv.org/pdf/2306.07629.pdf)
* **Code**: [https://github.com/SqueezeAILab/SqueezeLLM](https://github.com/SqueezeAILab/SqueezeLLM)
---
license: other
---
|
squeeze-ai-lab/sq-llama-30b-w4-s5
|
squeeze-ai-lab
| 2023-07-03T22:17:56Z | 0 | 0 | null |
[
"arxiv:2306.07629",
"arxiv:2302.13971",
"region:us"
] | null | 2023-06-21T06:37:01Z |
**SqueezeLLM** is a post-training quantization framework that incorporates a new method called Dense-and-Sparse Quantization to enable efficient LLM serving.
**TLDR:** Deploying LLMs is difficult due to their large memory size. This can be addressed with reduced precision quantization.
But a naive method hurts performance. We address this with a new Dense-and-Sparse Quantization method.
Dense-and-Sparse splits weight matrices into two components: A dense component that can be heavily quantized without affecting model performance,
as well as a sparse part that preserves sensitive and outlier parts of the weight matrices With this approach,
we are able to serve larger models with smaller memory footprint, the same latency, and yet higher accuracy and quality.
For more details please check out our [paper](https://arxiv.org/pdf/2306.07629.pdf).
## Model description
4-bit quantized LLaMA 30B model using SqueezeLLM. More details can be found in the [paper](https://arxiv.org/pdf/2306.07629.pdf).
* **Base Model:** [LLaMA 30B](https://arxiv.org/abs/2302.13971)
* **Bitwidth:** 4-bit
* **Sparsity Level:** 0.05%
## Links
* **Paper**: [https://arxiv.org/pdf/2306.07629.pdf](https://arxiv.org/pdf/2306.07629.pdf)
* **Code**: [https://github.com/SqueezeAILab/SqueezeLLM](https://github.com/SqueezeAILab/SqueezeLLM)
---
license: other
---
|
squeeze-ai-lab/sq-llama-13b-w4-s5
|
squeeze-ai-lab
| 2023-07-03T22:17:37Z | 0 | 0 | null |
[
"arxiv:2306.07629",
"arxiv:2302.13971",
"region:us"
] | null | 2023-06-20T21:24:39Z |
**SqueezeLLM** is a post-training quantization framework that incorporates a new method called Dense-and-Sparse Quantization to enable efficient LLM serving.
**TLDR:** Deploying LLMs is difficult due to their large memory size. This can be addressed with reduced precision quantization.
But a naive method hurts performance. We address this with a new Dense-and-Sparse Quantization method.
Dense-and-Sparse splits weight matrices into two components: A dense component that can be heavily quantized without affecting model performance,
as well as a sparse part that preserves sensitive and outlier parts of the weight matrices With this approach,
we are able to serve larger models with smaller memory footprint, the same latency, and yet higher accuracy and quality.
For more details please check out our [paper](https://arxiv.org/pdf/2306.07629.pdf).
## Model description
4-bit quantized LLaMA 13B model using SqueezeLLM. More details can be found in the [paper](https://arxiv.org/pdf/2306.07629.pdf).
* **Base Model:** [LLaMA 13B](https://arxiv.org/abs/2302.13971)
* **Bitwidth:** 4-bit
* **Sparsity Level:** 0.05%
## Links
* **Paper**: [https://arxiv.org/pdf/2306.07629.pdf](https://arxiv.org/pdf/2306.07629.pdf)
* **Code**: [https://github.com/SqueezeAILab/SqueezeLLM](https://github.com/SqueezeAILab/SqueezeLLM)
---
license: other
---
|
squeeze-ai-lab/sq-llama-13b-w4-s45
|
squeeze-ai-lab
| 2023-07-03T22:17:33Z | 0 | 0 | null |
[
"arxiv:2306.07629",
"arxiv:2302.13971",
"region:us"
] | null | 2023-06-20T21:24:52Z |
**SqueezeLLM** is a post-training quantization framework that incorporates a new method called Dense-and-Sparse Quantization to enable efficient LLM serving.
**TLDR:** Deploying LLMs is difficult due to their large memory size. This can be addressed with reduced precision quantization.
But a naive method hurts performance. We address this with a new Dense-and-Sparse Quantization method.
Dense-and-Sparse splits weight matrices into two components: A dense component that can be heavily quantized without affecting model performance,
as well as a sparse part that preserves sensitive and outlier parts of the weight matrices With this approach,
we are able to serve larger models with smaller memory footprint, the same latency, and yet higher accuracy and quality.
For more details please check out our [paper](https://arxiv.org/pdf/2306.07629.pdf).
## Model description
4-bit quantized LLaMA 13B model using SqueezeLLM. More details can be found in the [paper](https://arxiv.org/pdf/2306.07629.pdf).
* **Base Model:** [LLaMA 13B](https://arxiv.org/abs/2302.13971)
* **Bitwidth:** 4-bit
* **Sparsity Level:** 0.45%
## Links
* **Paper**: [https://arxiv.org/pdf/2306.07629.pdf](https://arxiv.org/pdf/2306.07629.pdf)
* **Code**: [https://github.com/SqueezeAILab/SqueezeLLM](https://github.com/SqueezeAILab/SqueezeLLM)
---
license: other
---
|
Cristi12342/irafiel
|
Cristi12342
| 2023-07-03T22:16:35Z | 0 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"art",
"ro",
"license:openrail",
"region:us"
] | null | 2023-07-03T22:13:46Z |
---
license: openrail
language:
- ro
library_name: adapter-transformers
tags:
- art
---
|
data354/camembert-fr-covid-tweet-sentiment-classification
|
data354
| 2023-07-03T22:14:35Z | 220 | 1 |
transformers
|
[
"transformers",
"pytorch",
"camembert",
"text-classification",
"classification",
"fr",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2022-03-02T23:29:04Z |
---
language:
- fr
tags:
- classification
license: apache-2.0
metrics:
- accuracy
widget:
- text: "tchai on est morts. on va se faire vacciner et ils vont contrôler comme les marionnettes avec des fils. d'après les 'ont dit'..."
---
# camembert-fr-covid-tweet-sentiment-classification
This model is a fine-tune checkpoint of [Yanzhu/bertweetfr-base](https://huggingface.co/Yanzhu/bertweetfr-base), fine-tuned on SST-2.
This model reaches an accuracy of 71% on the dev set.
In this dataset, given a tweet, the goal was to infer the underlying topic of the tweet by choosing from four topics classes:
- 0 : negatif
- 1 : neutre
- 2 : positif
# Pipelining the Model
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
tokenizer = AutoTokenizer.from_pretrained("data354/camembert-fr-covid-tweet-sentiment-classification")
model = AutoModelForSequenceClassification.from_pretrained("data354/camembert-fr-covid-tweet-sentiment-classification")
nlp_topic_classif = transformers.pipeline('topics-classification', model = model, tokenizer = tokenizer)
nlp_topic_classif("tchai on est morts. on va se faire vacciner et ils vont contrôler comme les marionnettes avec des fils. d'après les '' ont dit ''...")
# Output: [{'label': 'opinions', 'score': 0.831]
```
|
Lancer1408/bark-es-tokenizer
|
Lancer1408
| 2023-07-03T22:09:57Z | 0 | 1 | null |
[
"region:us"
] | null | 2023-07-03T19:49:10Z |
Spanish test~ish tokenier for use in bark
Doesn't sound terrible.
Trained in a bunch of random poems, el quijote and cien años de soledad.
14 epochs
|
amiraksiksi/our-dataset
|
amiraksiksi
| 2023-07-03T22:03:37Z | 75 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"layoutlmv3",
"token-classification",
"generated_from_trainer",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-07-03T21:44:19Z |
---
license: cc-by-nc-sa-4.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: our-dataset
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. -->
# our-dataset
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0167
- Precision: 0.7541
- Recall: 0.6479
- F1: 0.6970
- Accuracy: 0.7975
## 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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1000
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log | 4.55 | 100 | 1.2849 | 0.5789 | 0.4648 | 0.5156 | 0.6456 |
| No log | 9.09 | 200 | 1.0959 | 0.6724 | 0.5493 | 0.6047 | 0.7215 |
| No log | 13.64 | 300 | 1.1048 | 0.6833 | 0.5775 | 0.6260 | 0.7342 |
| No log | 18.18 | 400 | 1.0442 | 0.7541 | 0.6479 | 0.6970 | 0.7848 |
| 0.488 | 22.73 | 500 | 1.0966 | 0.7333 | 0.6197 | 0.6718 | 0.7722 |
| 0.488 | 27.27 | 600 | 1.0650 | 0.75 | 0.6338 | 0.6870 | 0.7848 |
| 0.488 | 31.82 | 700 | 0.9722 | 0.7742 | 0.6761 | 0.7218 | 0.8101 |
| 0.488 | 36.36 | 800 | 1.0596 | 0.7541 | 0.6479 | 0.6970 | 0.7975 |
| 0.488 | 40.91 | 900 | 0.9996 | 0.7541 | 0.6479 | 0.6970 | 0.7975 |
| 0.0298 | 45.45 | 1000 | 1.0167 | 0.7541 | 0.6479 | 0.6970 | 0.7975 |
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 1.12.0+cu102
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Sebastian-Ae/ppo-LunarLander-v2
|
Sebastian-Ae
| 2023-07-03T21:55:40Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-03T21:55:24Z |
---
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: 259.36 +/- 21.67
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
...
```
|
joydragon/dqn-SpaceInvadersNoFrameskip-v4
|
joydragon
| 2023-07-03T21:48:19Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-03T21:47:39Z |
---
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: 692.00 +/- 265.03
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 joydragon -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 joydragon -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 joydragon
```
## 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'}
```
|
Ahmed007/Dr.Smart_v3
|
Ahmed007
| 2023-07-03T21:42:03Z | 45 | 0 |
transformers
|
[
"transformers",
"tf",
"tensorboard",
"vit",
"image-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-07-03T21:01:40Z |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Ahmed007/Dr.Smart_v3
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. -->
# Ahmed007/Dr.Smart_v3
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.3548
- Train Accuracy: 0.9304
- Train Top-3-accuracy: 0.9905
- Validation Loss: 0.6948
- Validation Accuracy: 0.7893
- Validation Top-3-accuracy: 0.9455
- Epoch: 3
## 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: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 2198, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
- training_precision: mixed_float16
### Training results
| Train Loss | Train Accuracy | Train Top-3-accuracy | Validation Loss | Validation Accuracy | Validation Top-3-accuracy | Epoch |
|:----------:|:--------------:|:--------------------:|:---------------:|:-------------------:|:-------------------------:|:-----:|
| 1.5583 | 0.5509 | 0.8160 | 1.1523 | 0.6705 | 0.9045 | 0 |
| 0.9379 | 0.7513 | 0.9445 | 0.8892 | 0.75 | 0.9304 | 1 |
| 0.5855 | 0.8658 | 0.9746 | 0.7279 | 0.7964 | 0.9491 | 2 |
| 0.3548 | 0.9304 | 0.9905 | 0.6948 | 0.7893 | 0.9455 | 3 |
### Framework versions
- Transformers 4.31.0.dev0
- TensorFlow 2.12.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
davidmunechika/coreml-hubble-diffusion-2
|
davidmunechika
| 2023-07-03T21:41:07Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-30T17:48:16Z |
---
license: creativeml-openrail-m
---
|
NasimB/gpt2-cl-concat-log-rarity-7
|
NasimB
| 2023-07-03T21:17:08Z | 122 | 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
| 2023-07-03T20:22:15Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: gpt2-cl-concat-log-rarity-7
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. -->
# gpt2-cl-concat-log-rarity-7
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: 5.0905
## 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: 1
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 6.3347 | 0.11 | 500 | 5.9468 |
| 5.045 | 0.21 | 1000 | 5.5848 |
| 4.7703 | 0.32 | 1500 | 5.3941 |
| 4.5788 | 0.43 | 2000 | 5.2868 |
| 4.4333 | 0.53 | 2500 | 5.1941 |
| 4.3074 | 0.64 | 3000 | 5.1275 |
| 4.1934 | 0.75 | 3500 | 5.0645 |
| 4.1106 | 0.85 | 4000 | 5.0273 |
| 4.0628 | 0.96 | 4500 | 5.0116 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
|
TheBloke/SuperPlatty-30B-GGML
|
TheBloke
| 2023-07-03T21:13:14Z | 0 | 6 | null |
[
"llama",
"en",
"arxiv:2302.13971",
"license:other",
"region:us"
] | null | 2023-07-03T20:23:59Z |
---
inference: false
language:
- en
tags:
- llama
license: other
metrics:
- MMLU
- ARC
- HellaSwag
- TruthfulQA
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Ariel Lee's GPlatty 30B GGML
These files are GGML format model files for [Ariel Lee's GPlatty 30B](https://huggingface.co/ariellee/SuperPlatty-30B).
GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
* [KoboldCpp](https://github.com/LostRuins/koboldcpp)
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python)
* [ctransformers](https://github.com/marella/ctransformers)
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/SuperPlatty-30B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/SuperPlatty-30B-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ariellee/SuperPlatty-30B)
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request
### Instruction: prompt
### Response:
```
<!-- compatibility_ggml start -->
## Compatibility
### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0`
I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit `2d5db48`.
These are guaranteed to be compatbile with any UIs, tools and libraries released since late May.
### New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`
These new quantisation methods are compatible with llama.cpp as of June 6th, commit `2d43387`.
They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python and ctransformers. Other tools and libraries may or may not be compatible - check their documentation if in doubt.
## Explanation of the new k-quant methods
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
* GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.
Refer to the Provided Files table below to see what files use which methods, and how.
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| superplatty-30b.ggmlv3.q2_K.bin | q2_K | 2 | 13.71 GB | 16.21 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
| superplatty-30b.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 17.28 GB | 19.78 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| superplatty-30b.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 15.72 GB | 18.22 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| superplatty-30b.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 14.06 GB | 16.56 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
| superplatty-30b.ggmlv3.q4_0.bin | q4_0 | 4 | 18.30 GB | 20.80 GB | Original llama.cpp quant method, 4-bit. |
| superplatty-30b.ggmlv3.q4_1.bin | q4_1 | 4 | 20.33 GB | 22.83 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| superplatty-30b.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 19.62 GB | 22.12 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
| superplatty-30b.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 18.36 GB | 20.86 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
| superplatty-30b.ggmlv3.q5_0.bin | q5_0 | 5 | 22.37 GB | 24.87 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| superplatty-30b.ggmlv3.q5_1.bin | q5_1 | 5 | 24.40 GB | 26.90 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| superplatty-30b.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 23.05 GB | 25.55 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
| superplatty-30b.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 22.40 GB | 24.90 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
| superplatty-30b.ggmlv3.q6_K.bin | q6_K | 6 | 26.69 GB | 29.19 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors |
| superplatty-30b.ggmlv3.q8_0.bin | q8_0 | 8 | 34.56 GB | 37.06 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
## How to run in `llama.cpp`
I use the following command line; adjust for your tastes and needs:
```
./main -t 10 -ngl 32 -m superplatty-30b.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\n### Response:"
```
If you're able to use full GPU offloading, you should use `-t 1` to get best performance.
If not able to fully offload to GPU, you should use more cores. Change `-t 10` to the number of physical CPU cores you have, or a lower number depending on what gives best performance.
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix, ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Ariel Lee's GPlatty 30B
# Information
SuperPlatty-30B is a merge of [lilloukas/Platypus-30B](https://huggingface.co/lilloukas/Platypus-30B) and [kaiokendev/SuperCOT-LoRA](https://huggingface.co/kaiokendev/SuperCOT-LoRA)
| Metric | Value |
|-----------------------|-------|
| MMLU (5-shot) | 62.6 |
| ARC (25-shot) | 66.1 |
| HellaSwag (10-shot) | 83.9 |
| TruthfulQA (0-shot) | 54.0 |
| Avg. | 66.6 |
We use state-of-the-art EleutherAI [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above.
## Model Details
* **Trained by**: Platypus-30B trained by Cole Hunter & Ariel Lee; SuperCOT-LoRA trained by kaiokendev.
* **Model type:** **SuperPlatty-30B** is an auto-regressive language model based on the LLaMA transformer architecture.
* **Language(s)**: English
* **License for base weights**: License for the base LLaMA model's weights is Meta's [non-commercial bespoke license](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md).
| Hyperparameter | Value |
|---------------------------|-------|
| \\(n_\text{parameters}\\) | 33B |
| \\(d_\text{model}\\) | 6656 |
| \\(n_\text{layers}\\) | 60 |
| \\(n_\text{heads}\\) | 52 |
## Reproducing Evaluation Results
Install LM Evaluation Harness:
```
git clone https://github.com/EleutherAI/lm-evaluation-harness
cd lm-evaluation-harness
pip install -e .
```
Each task was evaluated on a single A100 80GB GPU.
ARC:
```
python main.py --model hf-causal-experimental --model_args pretrained=ariellee/SuperPlatty-30B --tasks arc_challenge --batch_size 1 --no_cache --write_out --output_path results/SuperPlatty-30B/arc_challenge_25shot.json --device cuda --num_fewshot 25
```
HellaSwag:
```
python main.py --model hf-causal-experimental --model_args pretrained=ariellee/SuperPlatty-30B --tasks hellaswag --batch_size 1 --no_cache --write_out --output_path results/SuperPlatty-30B/hellaswag_10shot.json --device cuda --num_fewshot 10
```
MMLU:
```
python main.py --model hf-causal-experimental --model_args pretrained=ariellee/SuperPlatty-30B --tasks hendrycksTest-* --batch_size 1 --no_cache --write_out --output_path results/SuperPlatty-30B/mmlu_5shot.json --device cuda --num_fewshot 5
```
TruthfulQA:
```
python main.py --model hf-causal-experimental --model_args pretrained=ariellee/SuperPlatty-30B --tasks truthfulqa_mc --batch_size 1 --no_cache --write_out --output_path results/SuperPlatty-30B/truthfulqa_0shot.json --device cuda
```
## Limitations and bias
The base LLaMA model is trained on various data, some of which may contain offensive, harmful, and biased content that can lead to toxic behavior. See Section 5.1 of the LLaMA paper. We have not performed any studies to determine how fine-tuning on the aforementioned datasets affect the model's behavior and toxicity. Do not treat chat responses from this model as a substitute for human judgment or as a source of truth. Please use responsibly.
## Citations
```bibtex
@article{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}
}
@article{hu2021lora,
title={LoRA: Low-Rank Adaptation of Large Language Models},
author={Hu, Edward J. and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Chen, Weizhu},
journal={CoRR},
year={2021}
}
```
|
cerspense/zeroscope_v2_XL
|
cerspense
| 2023-07-03T21:13:09Z | 443 | 498 |
diffusers
|
[
"diffusers",
"video-to-video",
"license:cc-by-nc-4.0",
"diffusers:VideoToVideoSDPipeline",
"region:us"
] | null | 2023-06-21T23:29:21Z |
---
pipeline_tag: video-to-video
license: cc-by-nc-4.0
---
[example outputs](https://www.youtube.com/watch?v=HO3APT_0UA4) (courtesy of [dotsimulate](https://www.instagram.com/dotsimulate/))
# zeroscope_v2 XL
A watermark-free Modelscope-based video model capable of generating high quality video at 1024 x 576. This model was trained from the [original weights](https://huggingface.co/damo-vilab/modelscope-damo-text-to-video-synthesis) with offset noise using 9,923 clips and 29,769 tagged frames at 24 frames, 1024x576 resolution.<br />
zeroscope_v2_XL is specifically designed for upscaling content made with [zeroscope_v2_576w](https://huggingface.co/cerspense/zeroscope_v2_567w) using vid2vid in the [1111 text2video](https://github.com/kabachuha/sd-webui-text2video) extension by [kabachuha](https://github.com/kabachuha). Leveraging this model as an upscaler allows for superior overall compositions at higher resolutions, permitting faster exploration in 576x320 (or 448x256) before transitioning to a high-resolution render.<br />
zeroscope_v2_XL uses 15.3gb of vram when rendering 30 frames at 1024x576
### Using it with the 1111 text2video extension
1. Download files in the zs2_XL folder.
2. Replace the respective files in the 'stable-diffusion-webui\models\ModelScope\t2v' directory.
### Upscaling recommendations
For upscaling, it's recommended to use the 1111 extension. It works best at 1024x576 with a denoise strength between 0.66 and 0.85. Remember to use the same prompt that was used to generate the original clip.
### Usage in 🧨 Diffusers
Let's first install the libraries required:
```bash
$ pip install git+https://github.com/huggingface/diffusers.git
$ pip install transformers accelerate torch
```
Now, let's first generate a low resolution video using [cerspense/zeroscope_v2_576w](https://huggingface.co/cerspense/zeroscope_v2_576w).
```py
import torch
from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
from diffusers.utils import export_to_video
pipe = DiffusionPipeline.from_pretrained("cerspense/zeroscope_v2_576w", torch_dtype=torch.float16)
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
pipe.enable_model_cpu_offload()
pipe.enable_vae_slicing()
pipe.unet.enable_forward_chunking(chunk_size=1, dim=1) # disable if enough memory as this slows down significantly
prompt = "Darth Vader is surfing on waves"
video_frames = pipe(prompt, num_inference_steps=40, height=320, width=576, num_frames=36).frames
video_path = export_to_video(video_frames)
```
Next, we can upscale it using [cerspense/zeroscope_v2_XL](https://huggingface.co/cerspense/zeroscope_v2_XL).
```py
pipe = DiffusionPipeline.from_pretrained("cerspense/zeroscope_v2_XL", torch_dtype=torch.float16)
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
pipe.enable_model_cpu_offload()
pipe.enable_vae_slicing()
video = [Image.fromarray(frame).resize((1024, 576)) for frame in video_frames]
video_frames = pipe(prompt, video=video, strength=0.6).frames
video_path = export_to_video(video_frames, output_video_path="/home/patrick/videos/video_1024_darth_vader_36.mp4")
```
Here are some results:
<table>
<tr>
Darth vader is surfing on waves.
<br>
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/darth_vader_36_1024.gif"
alt="Darth vader surfing in waves."
style="width: 576;" />
</center></td>
</tr>
</table>
### Known issues
Rendering at lower resolutions or fewer than 24 frames could lead to suboptimal outputs. <br />
Thanks to [camenduru](https://github.com/camenduru), [kabachuha](https://github.com/kabachuha), [ExponentialML](https://github.com/ExponentialML), [dotsimulate](https://www.instagram.com/dotsimulate/), [VANYA](https://twitter.com/veryVANYA), [polyware](https://twitter.com/polyware_ai), [tin2tin](https://github.com/tin2tin)<br />
|
pinkpekoe/ppo-Huggy
|
pinkpekoe
| 2023-07-03T21:08:25Z | 13 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-07-03T21:08:15Z |
---
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: pinkpekoe/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
sd-concepts-library/ahx-beta-4a32f04
|
sd-concepts-library
| 2023-07-03T21:06:50Z | 0 | 0 | null |
[
"license:mit",
"region:us"
] | null | 2023-07-03T21:06:47Z |
---
license: mit
---
### ahx-beta-4a32f04 on Stable Diffusion
This is the `<ahx-beta-4a32f04>` concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the [Stable Conceptualizer](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/stable_conceptualizer_inference.ipynb) notebook. You can also train your own concepts and load them into the concept libraries using [this notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_textual_inversion_training.ipynb).
Here is the new concept you will be able to use as a `style`:
|
SwampMan/dqn-SpaceInvadersNoFrameskip-v4
|
SwampMan
| 2023-07-03T20:37:38Z | 8 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-02T21:25:57Z |
---
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: 591.00 +/- 154.43
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 SwampMan -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 SwampMan -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 SwampMan
```
## 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', 10000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
bigscience/bloom-1b7-intermediate
|
bigscience
| 2023-07-03T20:33:36Z | 17 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"bloom",
"text-generation",
"ak",
"ar",
"as",
"bm",
"bn",
"ca",
"code",
"en",
"es",
"eu",
"fon",
"fr",
"gu",
"hi",
"id",
"ig",
"ki",
"kn",
"lg",
"ln",
"ml",
"mr",
"ne",
"nso",
"ny",
"or",
"pa",
"pt",
"rn",
"rw",
"sn",
"st",
"sw",
"ta",
"te",
"tn",
"ts",
"tum",
"tw",
"ur",
"vi",
"wo",
"xh",
"yo",
"zh",
"zhs",
"zht",
"zu",
"arxiv:1909.08053",
"arxiv:2110.02861",
"arxiv:2108.12409",
"license:bigscience-bloom-rail-1.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-08-07T18:15:55Z |
---
license: bigscience-bloom-rail-1.0
language:
- ak
- ar
- as
- bm
- bn
- ca
- code
- en
- es
- eu
- fon
- fr
- gu
- hi
- id
- ig
- ki
- kn
- lg
- ln
- ml
- mr
- ne
- nso
- ny
- or
- pa
- pt
- rn
- rw
- sn
- st
- sw
- ta
- te
- tn
- ts
- tum
- tw
- ur
- vi
- wo
- xh
- yo
- zh
- zhs
- zht
- zu
---
# <span style="color:red"><b>WARNING:</b> The checkpoints on this repo are not fully trained model. Evaluations of intermediary checkpoints and the final model will be added when conducted (see below).</span>
# <p>BLOOM LM<br/> _BigScience Large Open-science Open-access Multilingual Language Model_ <br/>Model Card</p>
<img src="https://assets.website-files.com/6139f3cdcbbff3a68486761d/613cd8997b270da063e230c5_Tekengebied%201-p-500.png" alt="BigScience Logo" width="200"/>
Version 1.3 / 11.July.2022 - Available intermediary checkpoints - global steps:
+ `1000`, `10000`, `50000`, `100000`, `150000`, `200000`, `250000`, `300000`
You can check the available checkpoints by clicking on the branches section of the repo
# How to load a specific version
We use `git tags` to load a model in a specific version (eg. `global_step1000`):
```python
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
"bigscience/bloom-1b3-intermediate",
revision="global_step1000",
torch_dtype="auto",
)
```
# Table of Contents
1. [Model Details](#model-details)
2. [Uses](#uses)
3. [Training Data](#training-data)
4. [Risks and Limitations](#risks-and-limitations)
5. [Evaluation](#evaluation)
6. [Recommendations](#recommendations)
7. [Glossary and Calculations](#glossary-and-calculations)
8. [More Information](#more-information)
9. [Model Card Authors](#model-card-authors)
---
# Model Details
BLOOM is a type of language model, which is a probability distribution over sequences of words. Specifically, BLOOM is a Large Language Model (LLM), meaning that it is trained on vast amounts of text data using industrial-scale computational resources. As such, the model is able to capture the statistical tendencies of words, phrases, sentences, and larger spans of text that it is exposed to in the training data.
## Basics
*This section provides information about the model type, version, license, funders, release date, developers, and contact information.*
*It is useful for anyone who wants to reference the model.*
<details>
<summary>Click to expand</summary>
**Developed by:** BigScience ([website](https://bigscience.huggingface.co))
*All collaborators are either volunteers or have an agreement with their employer. (Further breakdown of participants forthcoming.)*
**Model Type:** Transformer-based Language Model
**Version:** 1.0.0
**Languages:** Multiple; see [training data](#training-data)
**License:** RAIL License v1.0 ([link](https://huggingface.co/spaces/bigscience/license))
**Release Date Estimate:** Monday, 11.July.2022
**Send Questions to:** [email protected]
**Cite as:** BigScience, _BigScience Language Open-science Open-access Multilingual (BLOOM) Language Model_. International, May 2021-May 2022
**Funded by:**
* The French government.
* Hugging Face ([website](https://huggingface.co)).
* Organizations of contributors. *(Further breakdown of organizations forthcoming.)*
</details>
## Technical Specifications
*This section includes details about the model objective and architecture, and the compute infrastructure.*
*It is useful for people interested in model development.*
<details>
<summary>Click to expand</summary>
Please see [the BLOOM training README](https://github.com/bigscience-workshop/bigscience/tree/master/train/tr11-176B-ml#readme) for full details on replicating training.
### Model Architecture and Objective
* Modified from Megatron-LM GPT2 (see [paper](https://arxiv.org/abs/1909.08053), [BLOOM Megatron code](https://github.com/bigscience-workshop/Megatron-DeepSpeed)):
* Decoder-only architecture
* Layer normalization applied to word embeddings layer (`StableEmbedding`; see [code](https://github.com/facebookresearch/bitsandbytes), [paper](https://arxiv.org/pdf/2110.02861.pdf))
* ALiBI positional encodings (see [paper](https://arxiv.org/pdf/2108.12409.pdf)), with GeLU activation functions
* 176 billion parameters:
* 70 layers, 112 attention heads
* Hidden layers are 14336-dimensional
* Sequence length of 2048 tokens used (see [BLOOM tokenizer](https://huggingface.co/bigscience/tokenizer), [tokenizer description](#tokenization))
**Objective Function:** Cross Entropy with mean reduction (see [API documentation](https://pytorch.org/docs/stable/generated/torch.nn.CrossEntropyLoss.html#torch.nn.CrossEntropyLoss)).
### Compute infrastructure
Jean Zay Public Supercomputer, provided by the French government (see [announcement](https://www.enseignementsup-recherche.gouv.fr/fr/signature-du-marche-d-acquisition-de-l-un-des-supercalculateurs-les-plus-puissants-d-europe-46733)).
#### Hardware
* 384 A100 80GB GPUs (48 nodes)
* Additional 32 A100 80GB GPUs (4 nodes) in reserve
* 8 GPUs per node Using NVLink 4 inter-gpu connects, 4 OmniPath links
* CPU: AMD
* CPU memory: 512GB per node
* GPU memory: 640GB per node
* Inter-node connect: Omni-Path Architecture (OPA)
* NCCL-communications network: a fully dedicated subnet
* Disc IO network: shared network with other types of nodes
#### Software
* Megatron-DeepSpeed ([Github link](https://github.com/bigscience-workshop/Megatron-DeepSpeed))
* DeepSpeed ([Github link](https://github.com/microsoft/DeepSpeed))
* PyTorch (pytorch-1.11 w/ CUDA-11.5; see [Github link](https://github.com/pytorch/pytorch))
* apex ([Github link](https://github.com/NVIDIA/apex))
</details>
---
# Training
*This section provides information about the training data, the speed and size of training elements, and the environmental impact of training.*
*It is useful for people who want to learn more about the model inputs and training footprint.*
<details>
<summary>Click to expand</summary>
## Training Data
*This section provides a high-level overview of the training data. It is relevant for anyone who wants to know the basics of what the model is learning.*
Details for each dataset are provided in individual [Data Cards](https://huggingface.co/spaces/bigscience/BigScienceCorpus).
Training data includes:
- 45 natural languages
- 12 programming languages
- In 1.5TB of pre-processed text, converted into 350B unique tokens (see [the tokenizer section](#tokenization) for more.)
### Languages
The pie chart shows the distribution of languages in training data.
The following tables shows the further distribution of Niger-Congo & Indic languages and programming languages in the training data.
Distribution of Niger Congo and Indic languages.
| Niger Congo | Percentage | | Indic | Percentage |
|----------------|------------ |------ |-----------|------------|
| Chi Tumbuka | 0.00002 | | Assamese | 0.01 |
| Kikuyu | 0.00004 | | Odia | 0.04 |
| Bambara | 0.00004 | | Gujarati | 0.04 |
| Akan | 0.00007 | | Marathi | 0.05 |
| Xitsonga | 0.00007 | | Punjabi | 0.05 |
| Sesotho | 0.00007 | | Kannada | 0.06 |
| Chi Chewa | 0.0001 | | Nepali | 0.07 |
| Setswana | 0.0002 | | Telugu | 0.09 |
| Northern Sotho | 0.0002 | | Malayalam | 0.10 |
| Fon | 0.0002 | | Urdu | 0.10 |
| Kirundi | 0.0003 | | Tamil | 0.20 |
| Wolof | 0.0004 | | Bengali | 0.50 |
| Kuganda | 0.0004 | | Hindi | 0.70 |
| Chi Shona | 0.001 |
| Isi Zulu | 0.001 |
| Igbo | 0.001 |
| Xhosa | 0.001 |
| Kinyarwanda | 0.003 |
| Yoruba | 0.006 |
| Swahili | 0.02 |
Distribution of programming languages.
| Extension | Language | Number of files |
|----------------|------------|-----------------|
| java | Java | 5,407,724 |
| php | PHP | 4,942,186 |
| cpp | C++ | 2,503,930 |
| py | Python | 2,435,072 |
| js | JavaScript | 1,905,518 |
| cs | C# | 1,577,347 |
| rb | Ruby | 6,78,413 |
| cc | C++ | 443,054 |
| hpp | C++ | 391,048 |
| lua | Lua | 352,317 |
| go | GO | 227,763 |
| ts | TypeScript | 195,254 |
| C | C | 134,537 |
| scala | Scala | 92,052 |
| hh | C++ | 67,161 |
| H | C++ | 55,899 |
| tsx | TypeScript | 33,107 |
| rs | Rust | 29,693 |
| phpt | PHP | 9,702 |
| c++ | C++ | 1,342 |
| h++ | C++ | 791 |
| php3 | PHP | 540 |
| phps | PHP | 270 |
| php5 | PHP | 166 |
| php4 | PHP | 29 |
### Preprocessing
**Tokenization:** The BLOOM tokenizer ([link](https://huggingface.co/bigscience/tokenizer)), a learned subword tokenizer trained using:
- A byte-level Byte Pair Encoding (BPE) algorithm
- A simple pre-tokenization rule, no normalization
- A vocabulary size of 250,680
It was trained on a subset of a preliminary version of the corpus using alpha-weighting per language.
## Speeds, Sizes, Times
Training logs: [Tensorboard link](https://huggingface.co/tensorboard/bigscience/tr11-176B-ml-logs/)
- Dates:
- Started 11th March, 2022 11:42am PST
- Estimated end: 5th July, 2022
- Checkpoint size:
- Bf16 weights: 329GB
- Full checkpoint with optimizer states: 2.3TB
- Training throughput: About 150 TFLOP per GPU per second
- Number of epochs: 1
- Estimated cost of training: Equivalent of $2-5M in cloud computing (including preliminary experiments)
- Server training location: Île-de-France, France
## Environmental Impact
The training supercomputer, Jean Zay ([website](http://www.idris.fr/eng/jean-zay/jean-zay-presentation-eng.html)), uses mostly nuclear energy. The heat generated by it is reused for heating campus housing.
**Estimated carbon emissions:** *(Forthcoming.)*
**Estimated electricity usage:** *(Forthcoming.)*
</details>
---
# Uses
*This section addresses questions around how the model is intended to be used, discusses the foreseeable users of the model (including those affected by the model), and describes uses that are considered out of scope or misuse of the model.*
*It is useful for anyone considering using the model or who is affected by the model.*
<details>
<summary>Click to expand</summary>
## Intended Use
This model is being created in order to enable public research on large language models (LLMs). LLMs are intended to be used for language generation or as a pretrained base model that can be further fine-tuned for specific tasks. Use cases below are not exhaustive.
### Direct Use
- Text generation
- Exploring characteristics of language generated by a language model
- Examples: Cloze tests, counterfactuals, generations with reframings
### Downstream Use
- Tasks that leverage language models include: Information Extraction, Question Answering, Summarization
### Misuse and Out-of-scope Use
*This section addresses what users ought not do with the model.*
See the [BLOOM License](https://huggingface.co/spaces/bigscience/license), Attachment A, for detailed usage restrictions. The below list is non-exhaustive, but lists some easily foreseeable problematic use cases.
#### Out-of-scope Uses
Using the model in [high-stakes](#high-stakes) settings is out of scope for this model. The model is not designed for [critical decisions](#critical-decisions) nor uses with any material consequences on an individual's livelihood or wellbeing. The model outputs content that appears factual but is not correct.
Out-of-scope Uses Include:
- Usage in biomedical domains, political and legal domains, or finance domains
- Usage for evaluating or scoring individuals, such as for employment, education, or credit
- Applying the model for critical automatic decisions, generating factual content, creating reliable summaries, or generating predictions that must be correct
#### Misuse
Intentionally using the model for harm, violating [human rights](#human-rights), or other kinds of malicious activities, is a misuse of this model. This includes:
- Spam generation
- Disinformation and influence operations
- Disparagement and defamation
- Harassment and abuse
- [Deception](#deception)
- Unconsented impersonation and imitation
- Unconsented surveillance
- Generating content without attribution to the model, as specified in the [RAIL License, Use Restrictions](https://huggingface.co/spaces/bigscience/license)
## Intended Users
### Direct Users
- General Public
- Researchers
- Students
- Educators
- Engineers/developers
- Non-commercial entities
- Community advocates, including human and civil rights groups
### Indirect Users
- Users of derivatives created by Direct Users, such as those using software with an [intended use](#intended-use)
- Users of [Derivatives of the Model, as described in the License](https://huggingface.co/spaces/bigscience/license)
### Others Affected (Parties Prenantes)
- People and groups referred to by the LLM
- People and groups exposed to outputs of, or decisions based on, the LLM
- People and groups whose original work is included in the LLM
</details>
---
# Risks and Limitations
*This section identifies foreseeable harms and misunderstandings.*
<details>
<summary>Click to expand</summary>
Model may:
- Overrepresent some viewpoints and underrepresent others
- Contain stereotypes
- Contain [personal information](#personal-data-and-information)
- Generate:
- Hateful, abusive, or violent language
- Discriminatory or prejudicial language
- Content that may not be appropriate for all settings, including sexual content
- Make errors, including producing incorrect information as if it were factual
- Generate irrelevant or repetitive outputs
</details>
---
# Evaluation
*This section describes the evaluation protocols and provides the results.*
<details>
<summary>Click to expand</summary>
## Metrics
*This section describes the different ways performance is calculated and why.*
Includes:
| Metric | Why chosen |
|--------------------|--------------------------------------------------------------------|
| [Perplexity](#perplexity) | Standard metric for quantifying model improvements during training |
| Cross Entropy [Loss](#loss) | Standard objective for language models. |
And multiple different metrics for specific tasks. _(More evaluation metrics forthcoming upon completion of evaluation protocol.)_
## Factors
*This section lists some different aspects of what BLOOM models. Its focus is on those aspects that are likely to give rise to high variance in model behavior.*
- Language, such as English or Yoruba
- Domain, such as newswire or stories
- Demographic characteristics, such as gender or nationality
## Results
*Results are based on the [Factors](#factors) and [Metrics](#metrics).*
**Train-time Evaluation:**
As of 25.May.2022, 15:00 PST:
- Training Loss: 2.0
- Validation Loss: 2.2
- Perplexity: 8.9
(More evaluation scores forthcoming.)
</details>
---
# Recommendations
*This section provides information on warnings and potential mitigations.*
<details>
<summary>Click to expand</summary>
- Indirect users should be made aware when the content they're working with is created by the LLM.
- Users should be aware of [Risks and Limitations](#risks-and-limitations), and include an appropriate age disclaimer or blocking interface as necessary.
- Models trained or finetuned downstream of BLOOM LM should include an updated Model Card.
- Users of the model should provide mechanisms for those affected to provide feedback, such as an email address for comments.
</details>
---
# Glossary and Calculations
*This section defines common terms and how metrics are calculated.*
<details>
<summary>Click to expand</summary>
- <a name="loss">**Loss:**</a> A calculation of the difference between what the model has learned and what the data shows ("groundtruth"). The lower the loss, the better. The training process aims to minimize the loss.
- <a name="perplexity">**Perplexity:**</a> This is based on what the model estimates the probability of new data is. The lower the perplexity, the better. If the model is 100% correct at predicting the next token it will see, then the perplexity is 1. Mathematically this is calculated using entropy.
- <a name="high-stakes">**High-stakes settings:**</a> Such as those identified as "high-risk AI systems" and "unacceptable risk AI systems" in the European Union's proposed [Artificial Intelligence (AI) Act](https://artificialintelligenceact.eu/annexes/).
- <a name="critical-decisions">**Critical decisions:**</a> Such as those defined in [the United States' proposed Algorithmic Accountability Act](https://www.congress.gov/117/bills/s3572/BILLS-117s3572is.pdf).
- <a name="human-rights">**Human rights:**</a> Includes those rights defined in the [Universal Declaration of Human Rights](https://www.un.org/sites/un2.un.org/files/2021/03/udhr.pdf).
- <a name="personal-data-and-information">**Personal Data and Personal Information:**</a> Personal data and information is defined in multiple data protection regulations, such as "[personal data](https://gdpr-info.eu/issues/personal-data/)" in the [European Union's General Data Protection Regulation](https://gdpr-info.eu); and "personal information" in the Republic of South Africa's [Protection of Personal Information Act](https://www.gov.za/sites/default/files/gcis_document/201409/3706726-11act4of2013popi.pdf), The People's Republic of China's [Personal information protection law](http://en.npc.gov.cn.cdurl.cn/2021-12/29/c_694559.htm).
- <a name="sensitive-characteristics">**Sensitive characteristics:**</a> This includes specifically protected categories in human rights (see [UHDR, Article 2](https://www.un.org/sites/un2.un.org/files/2021/03/udhr.pdf)) and personal information regulation (see GDPR, [Article 9; Protection of Personal Information Act, Chapter 1](https://www.gov.za/sites/default/files/gcis_document/201409/3706726-11act4of2013popi.pdf))
- <a name="deception">**Deception:**</a> Doing something to intentionally mislead individuals to believe something that is false, such as by creating deadbots or chatbots on social media posing as real people, or generating text documents without making consumers aware that the text is machine generated.
</details>
---
# More Information
*This section provides links to writing on dataset creation, technical specifications, lessons learned, and initial results.*
<details>
<summary>Click to expand</summary>
## Dataset Creation
Blog post detailing the design choices during the dataset creation: https://bigscience.huggingface.co/blog/building-a-tb-scale-multilingual-dataset-for-language-modeling
## Technical Specifications
Blog post summarizing how the architecture, size, shape, and pre-training duration where selected: https://bigscience.huggingface.co/blog/what-language-model-to-train-if-you-have-two-million-gpu-hours
More details on the architecture/optimizer: https://github.com/bigscience-workshop/bigscience/tree/master/train/tr11-176B-ml
Blog post on the hardware/engineering side: https://bigscience.huggingface.co/blog/which-hardware-to-train-a-176b-parameters-model
Details on the distributed setup used for the training: https://github.com/bigscience-workshop/bigscience/tree/master/train/tr11-176B-ml
Tensorboard updated during the training: https://huggingface.co/bigscience/tr11-176B-ml-logs/tensorboard#scalars&tagFilter=loss
## Lessons
Insights on how to approach training, negative results: https://github.com/bigscience-workshop/bigscience/blob/master/train/lessons-learned.md
Details on the obstacles overcome during the preparation on the engineering side (instabilities, optimization of training throughput, so many technical tricks and questions): https://github.com/bigscience-workshop/bigscience/blob/master/train/tr11-176B-ml/chronicles.md
## Initial Results
Initial prompting experiments using interim checkpoints: https://huggingface.co/spaces/bigscience/bloom-book
</details>
---
# Model Card Authors
*Ordered roughly chronologically and by amount of time spent.*
Margaret Mitchell, Giada Pistilli, Yacine Jernite, Ezinwanne Ozoani, Marissa Gerchick, Nazneen Rajani, Sasha Luccioni, Irene Solaiman, Maraim Masoud, Somaieh Nikpoor, Carlos Muñoz Ferrandis, Stas Bekman, Christopher Akiki, Danish Contractor, David Lansky, Angelina McMillan-Major, Tristan Thrush, Suzana Ilić, Gérard Dupont, Shayne Longpre, Manan Dey, Stella Biderman, Douwe Kiela, Emi Baylor, Teven Le Scao, Aaron Gokaslan, Julien Launay, Niklas Muennighoff
|
LarryAIDraw/Inori
|
LarryAIDraw
| 2023-07-03T20:27:22Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-07-03T20:19:27Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/17230?modelVersionId=20354
|
idealflaw/ppo-LunarLander-v2
|
idealflaw
| 2023-07-03T20:27:22Z | 4 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-03T20:27:04Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 264.20 +/- 23.03
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
...
```
|
LarryAIDraw/InoriV1
|
LarryAIDraw
| 2023-07-03T20:26:42Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-07-03T20:19:50Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/12139?modelVersionId=14324
|
espnet/brianyan918_mustc-v2_en-de_st_ctc_rnnt_asrinit_raw_en_de_bpe_tc4000_sp
|
espnet
| 2023-07-03T20:20:51Z | 1 | 0 | null |
[
"region:us"
] | null | 2023-07-03T20:18:41Z |
- Download model and run inference:
`./run.sh --skip_data_prep false --skip_train true --download_model espnet/brianyan918_mustc-v2_en-de_st_ctc_rnnt_asrinit_raw_en_de_bpe_tc4000_sp --inference_config conf/tuning/decode_rnnt_tsd_mse4_scorenormduring_beam10.yaml`
|dataset|score|verbose_score|
|---|---|---|
|decode_rnnt_tsd_mse4_scorenormduring_beam10_st_model_valid.loss.ave_10best/tst-COMMON.en-de|27.6|60.2/33.6/21.0/13.7 (BP = 0.998 ratio = 0.998 hyp_len = 51602 ref_len = 51699)|
|
espnet/brianyan918_mustc-v2_en-de_st_ctc_md_conformer_asrinit_v3_raw_en_de_bpe_tc4000_sp
|
espnet
| 2023-07-03T20:17:25Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-07-03T20:15:03Z |
- Download model and run inference:
`./run.sh --skip_data_prep false --skip_train true --download_model espnet/brianyan918_mustc-v2_en-de_st_ctc_md_conformer_asrinit_v3_raw_en_de_bpe_tc4000_sp --inference_config conf/tuning/decode_st_md_ctc0.3.yaml`
|dataset|score|verbose_score|
|---|---|---|
|decode_st_md_ctc0.3_st_model_valid.acc.ave_10best/tst-COMMON.en-de|28.8|61.5/35.0/22.2/14.7 (BP = 0.994 ratio = 0.994 hyp_len = 51386 ref_len = 51699)|
|
computroidai/COMPUTROID
|
computroidai
| 2023-07-03T20:12:36Z | 0 | 0 | null |
[
"en",
"hi",
"dataset:Open-Orca/OpenOrca",
"license:mit",
"region:us"
] | null | 2023-07-03T20:10:55Z |
---
license: mit
datasets:
- Open-Orca/OpenOrca
language:
- en
- hi
---
|
hemulitch/hueta-finetuned_1
|
hemulitch
| 2023-07-03T20:07:57Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"token-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-07-03T17:31:33Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: hueta-finetuned_1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# hueta-finetuned_1
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:
- eval_loss: 0.0495
- eval_precision: 0.9810
- eval_recall: 0.9810
- eval_f1: 0.9809
- eval_accuracy: 0.9810
- eval_runtime: 292.5187
- eval_samples_per_second: 96.373
- eval_steps_per_second: 6.024
- epoch: 1.56
- step: 11026
## 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
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
espnet/brianyan918_mustc-v2_en-de_st_conformer_asrinit_v2_raw_en_de_bpe_tc4000_sp
|
espnet
| 2023-07-03T20:01:19Z | 2 | 0 | null |
[
"region:us"
] | null | 2023-07-03T19:41:26Z |
- Download model and run inference:
`./run.sh --skip_data_prep false --skip_train true --download_model espnet/brianyan918_mustc-v2_en-de_st_conformer_asrinit_v2_raw_en_de_bpe_tc4000_sp --inference_config conf/tuning/decode_st_conformer.yaml`
|dataset|score|verbose_score|
|---|---|---|
|decode_st_conformer_st_model_valid.acc.ave_10best/tst-COMMON.en-de|25.7|62.3/34.6/21.8/14.3 (BP = 0.897 ratio = 0.902 hyp_len = 46612 ref_len = 51699)|
|
Nidhiiii/my_awesome_model
|
Nidhiiii
| 2023-07-03T19:54:17Z | 61 | 0 |
transformers
|
[
"transformers",
"tf",
"distilbert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-07-03T19:13:59Z |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Nidhiiii/my_awesome_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. -->
# Nidhiiii/my_awesome_model
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: 0.2520
- Validation Loss: 0.1938
- Train Accuracy: 0.9234
- Epoch: 0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': 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': 7810, '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 | Train Accuracy | Epoch |
|:----------:|:---------------:|:--------------:|:-----:|
| 0.2520 | 0.1938 | 0.9234 | 0 |
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
|
andersonbcdefg/flan_t5_80m-finetune-samsum-adapter
|
andersonbcdefg
| 2023-07-03T19:51:34Z | 4 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-03T19:51:33Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
nikitakapitan/distilbert-base-uncased-finetuned-emotion
|
nikitakapitan
| 2023-07-03T19:49:07Z | 79 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-07-03T19:42:46Z |
---
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
config: split
split: validation
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.9235
- name: F1
type: f1
value: 0.9235743183364048
---
<!-- 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: 0.2113
- Accuracy: 0.9235
- F1: 0.9236
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8004 | 1.0 | 250 | 0.2959 | 0.9135 | 0.9124 |
| 0.2377 | 2.0 | 500 | 0.2113 | 0.9235 | 0.9236 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
PrakhAI/HelloWorld
|
PrakhAI
| 2023-07-03T19:22:35Z | 0 | 0 | null |
[
"dataset:mnist",
"license:gpl-3.0",
"region:us"
] | null | 2023-07-02T01:34:55Z |
---
license: gpl-3.0
datasets:
- mnist
---
Flax handwritten digit (MNIST) classification model trained using https://colab.research.google.com/github/google/flax/blob/main/docs/getting_started.ipynb
|
andres-gv/model-cmi-1
|
andres-gv
| 2023-07-03T19:19:59Z | 4 | 0 |
bertopic
|
[
"bertopic",
"text-classification",
"region:us"
] |
text-classification
| 2023-07-03T19:13:59Z |
---
pipeline_tag: text-classification
library_name: bertopic
---
|
practical-dreamer/rpgpt-7b-lora
|
practical-dreamer
| 2023-07-03T19:08:58Z | 0 | 1 | null |
[
"dataset:practicaldreamer/RPGPT_PublicDomain-ShareGPT",
"region:us"
] | null | 2023-07-03T18:16:52Z |
---
datasets:
- practicaldreamer/RPGPT_PublicDomain-ShareGPT
---
## Introduction
This is my first attempt at training a model for long form character interaction using asterisk roleplay format.
There are plenty of general instruction/answer models but most focus on single responses between an ai and a human.
My goal for this project is to more closely align the training data with CHARACTER interactions for roleplay.
This model is trained on a small synthetic dataset of characters interacting through a variety of scenarios.
The Characters, Scenarios and interactions were all generated by GPT4.
Intended for research, creative writing, entertainment, DnD campaigns? fun!
## Train Summary
[<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)
```
duration: ~1hr
gpu: 1xA100 80GB
epochs: 1.0
speed: 3e-5
sequence_len: 2048
gradient_accumulation_steps: 32
wandb: https://wandb.ai/practicaldreamer/rpgpt/runs/bvyawfro
```
*Please see the documentation folder for more information*
## Usage
This LoRA was trained for use with **Neko-Institute-of-Science/LLaMA-7B-HF**
Please follow the prompt format outlined below. *Hint: If you're not sure what to put for your character description (or you're lazy) just ask chatgpt to generate it for you! Example:*
```
Generate a short character description for Dr. Watson (The Adventures of Sherlock Holmes) that includes gender, age, MBTI and speech accent using 30 words or less.
```
## Prompt Format
Context/Memory:
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
USER: Write a character roleplay dialogue using asterisk roleplay format based on the following character descriptions and scenario. (Each line in your response must be from the perspective of one of these characters)
## Characters
<User-Character Name> (<User-Character Universe>):
<User-Character Description>
<Bot-Character Name> (Bot-Character Universe):
<Bot-Character Description>
## Scenario
<Scenario Description>
ASSISTANT:
```
Turn Template:
```
<User-Character Name>: \*<1st person action/sensations/thoughts>\* <Spoken Word> \*<1st person action/sensations/thoughts>\*
<Bot-Character Name>: \*<1st person action/sensations/thoughts>\* <Spoken Word> \*<1st person action/sensations/thoughts>\*
<User-Character Name>: \*<1st person action/sensations/thoughts>\* <Spoken Word> \*<1st person action/sensations/thoughts>\*
<Bot-Character Name>: \*<1st person action/sensations/thoughts>\* <Spoken Word> \*<1st person action/sensations/thoughts>\*
...
```
## Example
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
USER: Write a character roleplay dialogue using asterisk roleplay format based on the following character descriptions and scenario. (Each line in your response must be from the perspective of one of these characters)
## Characters
Baloo (The Jungle Book):
Male, middle-aged bear, ENFP, primarily American accent with slight Indian inflections. Wise, carefree, and friendly, he teaches Mowgli the ways of the jungle.
The Queen of Hearts (Alice's Adventures in Wonderland):
Female, middle-aged, ENTJ, British English accent; imperious, temperamental, commanding, but quick to change from anger to warmth - the quintessential capricious monarch.
## Scenario
In an enchanted glade deep within Wonderland, Baloo finds himself separated from Mowgli and in the Queen of Hearts' territory. Having heard tales of this mercurial ruler, Baloo is intrigued but cautious. To his surprise, the Queen of Hearts approaches him with a broken heart - she has been betrayed by one of her closest confidants.
The Queen initially sees Baloo as an opportunity to vent her frustrations and seek validation for her hurt feelings. Baloo, however, quickly recognizes that the Queen's explosive temperament is driving others away and contributing to her own isolation.\n\nUsing his wisdom and patience, Baloo tries to teach the Queen the value of empathy and understanding in forming meaningful relationships. Through their dialogue, they explore their contrasting attitudes toward power, authority, and friendship. The Queen learns that it is not through fear and command that she can find true loyalty, but rather by treating others with kindness.
In this somber environment where both characters are out of their comfort zones, can Baloo help the Queen mend her own heart by opening up about his experiences with Mowgli? Will the Queen allow herself to be vulnerable enough to learn from the wise bear? And can these two unlikely friends find common ground in this enchanted glade within Wonderland?
ASSISTANT:
Baloo: *stumbles into the enchanted glade, looking around curiously* Well, I must've taken a wrong turn back there. Mowgli! *calls out for Mowgli*
The Queen of Hearts: *storms into the glade, clutching a broken heart symbol, face contorted in anger* Off with their heads! Everyone's heads!
Baloo: *gently scratches his head and approaches the Queen cautiously* Uh, excuse me, ma'am? I couldn't help but notice that you seem rather... upset.
The Queen of Hearts: *sniffs haughtily and scowls at Baloo* And who are you to pry into my affairs? You should be bowing to your queen!
Baloo: *bows graciously but maintains eye contact* Begging your pardon, Your Majesty. My name is Baloo, and I've heard tales of your... unique temperament.
The Queen of Hearts:
```
## Thanks
openaccess-ai-collective https://huggingface.co/openaccess-ai-collective
---
license: mit
---
|
nolanaatama/vstzthllvd1000pchsrvcmgzb
|
nolanaatama
| 2023-07-03T18:52:02Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-07-03T18:45:44Z |
---
license: creativeml-openrail-m
---
|
geekyrakshit/DeepLabV3-Plus
|
geekyrakshit
| 2023-07-03T18:51:23Z | 60 | 0 |
keras
|
[
"keras",
"segmentation",
"tensorflow",
"cityscapes",
"arxiv:1802.02611",
"region:us"
] | null | 2023-07-03T17:32:36Z |
---
metrics:
- accuracy
- mean_iou
tags:
- segmentation
- keras
- tensorflow
- cityscapes
---
# DeepLabV3-Plus
Keras implementation of the DeepLabV3+ model as proposed by the paper [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://arxiv.org/abs/1802.02611)(ECCV 2018).
The models were trained on the fine-annotations set of the [Cityscapes dataset](cityscapes-dataset.com) for creating presets for [this PR](https://github.com/keras-team/keras-cv/pull/1831) on the `keras-cv` repository.
**Weights & Biases Dashboard:** https://wandb.ai/geekyrakshit/deeplabv3-keras-cv
|
zh-plus/faster-whisper-large-v2-japanese-5k-steps
|
zh-plus
| 2023-07-03T18:42:31Z | 289 | 16 |
transformers
|
[
"transformers",
"pytorch",
"faster-whisper",
"whisper",
"CTranslate2",
"automatic-speech-recognition",
"ja",
"dataset:mozilla-foundation/common_voice_11_0",
"license:mit",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-07-03T08:29:37Z |
---
license: mit
datasets:
- mozilla-foundation/common_voice_11_0
language:
- ja
pipeline_tag: automatic-speech-recognition
tags:
- pytorch
- faster-whisper
- whisper
- CTranslate2
metrics:
- wer
---
Converted from [clu-ling/whisper-large-v2-japanese-5k-steps](https://huggingface.co/clu-ling/whisper-large-v2-japanese-5k-steps) using [CTranslate2](https://github.com/OpenNMT/CTranslate2).
Usage:
1. Install `pip install faster-whisper` (Check [faster-whisper](https://github.com/guillaumekln/faster-whisper) for detailed instructions.)
2. ```python
from faster_whisper import WhisperModel
model = WhisperModel('zh-plus/faster-whisper-large-v2-japanese-5k-steps', device="cuda", compute_type="float16")
segments, info = model.transcribe("audio.mp3", beam_size=5)
print("Detected language '%s' with probability %f" % (info.language, info.language_probability))
for segment in segments:
print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
```
|
anujsahani01/finetuned_mbart
|
anujsahani01
| 2023-07-03T18:40:55Z | 15 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"mbart",
"text2text-generation",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-06-17T14:19:05Z |
---
license: mit
tags:
- generated_from_trainer
model-index:
- name: finetuned_Mbart
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. -->
# finetuned_Mbart
This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) 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: 0.0005
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 10000
### Training results
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Enymy/t5-base-feedback-generator
|
Enymy
| 2023-07-03T18:38:49Z | 102 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"jax",
"t5",
"text2text-generation",
"generated_from_keras_callback",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-07-03T18:36:24Z |
---
tags:
- generated_from_keras_callback
model-index:
- name: t5-base-feedback-generator
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. -->
# t5-base-feedback-generator
This model was trained from scratch 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 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
|
ihanif/distilhubert-music-gtzan-classification
|
ihanif
| 2023-07-03T18:35:17Z | 160 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"hubert",
"audio-classification",
"generated_from_trainer",
"dataset:marsyas/gtzan",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
audio-classification
| 2023-07-03T14:42:56Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-music-classification
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: 0.86
---
<!-- 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-music-classification
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: 0.7110
- Accuracy: 0.86
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 16
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.1284 | 1.0 | 113 | 1.9802 | 0.5 |
| 1.435 | 2.0 | 226 | 1.3403 | 0.65 |
| 1.0235 | 3.0 | 339 | 0.9941 | 0.74 |
| 0.8973 | 4.0 | 452 | 0.9184 | 0.69 |
| 0.7312 | 5.0 | 565 | 0.6918 | 0.79 |
| 0.4306 | 6.0 | 678 | 0.6343 | 0.78 |
| 0.4204 | 7.0 | 791 | 0.6174 | 0.83 |
| 0.1326 | 8.0 | 904 | 0.5888 | 0.83 |
| 0.0766 | 9.0 | 1017 | 0.5939 | 0.84 |
| 0.0308 | 10.0 | 1130 | 0.7191 | 0.86 |
| 0.0318 | 11.0 | 1243 | 0.7308 | 0.84 |
| 0.0657 | 12.0 | 1356 | 0.7222 | 0.81 |
| 0.0096 | 13.0 | 1469 | 0.7075 | 0.84 |
| 0.0077 | 14.0 | 1582 | 0.7268 | 0.84 |
| 0.0073 | 15.0 | 1695 | 0.6957 | 0.85 |
| 0.0066 | 16.0 | 1808 | 0.7110 | 0.86 |
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
JNK789/ppo-lunarlander-v2
|
JNK789
| 2023-07-03T18:30:11Z | 1 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-03T18:29:48Z |
---
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: 248.18 +/- 22.45
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
...
```
|
falkne/QforJustification
|
falkne
| 2023-07-03T18:20:46Z | 2 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"adapterhub:argument/quality",
"roberta",
"region:us"
] | null | 2023-07-03T18:20:44Z |
---
tags:
- adapterhub:argument/quality
- roberta
- adapter-transformers
---
# Adapter `falkne/QforJustification` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [argument/quality](https://adapterhub.ml/explore/argument/quality/) dataset and includes a prediction head for classification.
This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
## Usage
First, install `adapter-transformers`:
```
pip install -U adapter-transformers
```
_Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. [More](https://docs.adapterhub.ml/installation.html)_
Now, the adapter can be loaded and activated like this:
```python
from transformers import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("roberta-base")
adapter_name = model.load_adapter("falkne/QforJustification", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here -->
|
falkne/cogency
|
falkne
| 2023-07-03T18:20:41Z | 2 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"adapterhub:argument/quality",
"roberta",
"region:us"
] | null | 2023-07-03T18:20:40Z |
---
tags:
- adapterhub:argument/quality
- roberta
- adapter-transformers
---
# Adapter `falkne/cogency` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [argument/quality](https://adapterhub.ml/explore/argument/quality/) dataset and includes a prediction head for classification.
This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
## Usage
First, install `adapter-transformers`:
```
pip install -U adapter-transformers
```
_Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. [More](https://docs.adapterhub.ml/installation.html)_
Now, the adapter can be loaded and activated like this:
```python
from transformers import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("roberta-base")
adapter_name = model.load_adapter("falkne/cogency", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here -->
|
falkne/argumentative
|
falkne
| 2023-07-03T18:20:37Z | 2 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"adapterhub:argument/quality",
"roberta",
"region:us"
] | null | 2023-07-03T18:20:36Z |
---
tags:
- adapterhub:argument/quality
- roberta
- adapter-transformers
---
# Adapter `falkne/argumentative` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [argument/quality](https://adapterhub.ml/explore/argument/quality/) dataset and includes a prediction head for classification.
This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
## Usage
First, install `adapter-transformers`:
```
pip install -U adapter-transformers
```
_Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. [More](https://docs.adapterhub.ml/installation.html)_
Now, the adapter can be loaded and activated like this:
```python
from transformers import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("roberta-base")
adapter_name = model.load_adapter("falkne/argumentative", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here -->
|
falkne/respect
|
falkne
| 2023-07-03T18:20:33Z | 2 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"adapterhub:argument/quality",
"roberta",
"region:us"
] | null | 2023-07-03T18:20:32Z |
---
tags:
- adapterhub:argument/quality
- roberta
- adapter-transformers
---
# Adapter `falkne/respect` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [argument/quality](https://adapterhub.ml/explore/argument/quality/) dataset and includes a prediction head for classification.
This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
## Usage
First, install `adapter-transformers`:
```
pip install -U adapter-transformers
```
_Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. [More](https://docs.adapterhub.ml/installation.html)_
Now, the adapter can be loaded and activated like this:
```python
from transformers import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("roberta-base")
adapter_name = model.load_adapter("falkne/respect", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here -->
|
falkne/reasonableness
|
falkne
| 2023-07-03T18:20:30Z | 3 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"adapterhub:argument/quality",
"roberta",
"region:us"
] | null | 2023-07-03T18:20:28Z |
---
tags:
- adapterhub:argument/quality
- roberta
- adapter-transformers
---
# Adapter `falkne/reasonableness` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [argument/quality](https://adapterhub.ml/explore/argument/quality/) dataset and includes a prediction head for classification.
This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
## Usage
First, install `adapter-transformers`:
```
pip install -U adapter-transformers
```
_Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. [More](https://docs.adapterhub.ml/installation.html)_
Now, the adapter can be loaded and activated like this:
```python
from transformers import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("roberta-base")
adapter_name = model.load_adapter("falkne/reasonableness", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here -->
|
falkne/negEmotion
|
falkne
| 2023-07-03T18:20:24Z | 0 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"adapterhub:argument/quality",
"roberta",
"region:us"
] | null | 2023-07-03T18:20:23Z |
---
tags:
- adapterhub:argument/quality
- roberta
- adapter-transformers
---
# Adapter `falkne/negEmotion` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [argument/quality](https://adapterhub.ml/explore/argument/quality/) dataset and includes a prediction head for classification.
This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
## Usage
First, install `adapter-transformers`:
```
pip install -U adapter-transformers
```
_Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. [More](https://docs.adapterhub.ml/installation.html)_
Now, the adapter can be loaded and activated like this:
```python
from transformers import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("roberta-base")
adapter_name = model.load_adapter("falkne/negEmotion", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here -->
|
falkne/interactivity
|
falkne
| 2023-07-03T18:20:18Z | 0 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"adapterhub:argument/quality",
"roberta",
"region:us"
] | null | 2023-07-03T18:20:17Z |
---
tags:
- adapterhub:argument/quality
- roberta
- adapter-transformers
---
# Adapter `falkne/interactivity` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [argument/quality](https://adapterhub.ml/explore/argument/quality/) dataset and includes a prediction head for classification.
This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
## Usage
First, install `adapter-transformers`:
```
pip install -U adapter-transformers
```
_Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. [More](https://docs.adapterhub.ml/installation.html)_
Now, the adapter can be loaded and activated like this:
```python
from transformers import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("roberta-base")
adapter_name = model.load_adapter("falkne/interactivity", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here -->
|
falkne/overall
|
falkne
| 2023-07-03T18:20:16Z | 2 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"adapterhub:argument/quality",
"roberta",
"region:us"
] | null | 2023-07-03T18:20:15Z |
---
tags:
- adapterhub:argument/quality
- roberta
- adapter-transformers
---
# Adapter `falkne/overall` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [argument/quality](https://adapterhub.ml/explore/argument/quality/) dataset and includes a prediction head for classification.
This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
## Usage
First, install `adapter-transformers`:
```
pip install -U adapter-transformers
```
_Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. [More](https://docs.adapterhub.ml/installation.html)_
Now, the adapter can be loaded and activated like this:
```python
from transformers import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("roberta-base")
adapter_name = model.load_adapter("falkne/overall", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here -->
|
falkne/empathie
|
falkne
| 2023-07-03T18:20:14Z | 0 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"adapterhub:argument/quality",
"roberta",
"region:us"
] | null | 2023-07-03T18:20:13Z |
---
tags:
- adapterhub:argument/quality
- roberta
- adapter-transformers
---
# Adapter `falkne/empathie` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [argument/quality](https://adapterhub.ml/explore/argument/quality/) dataset and includes a prediction head for classification.
This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
## Usage
First, install `adapter-transformers`:
```
pip install -U adapter-transformers
```
_Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. [More](https://docs.adapterhub.ml/installation.html)_
Now, the adapter can be loaded and activated like this:
```python
from transformers import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("roberta-base")
adapter_name = model.load_adapter("falkne/empathie", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here -->
|
falkne/proposal
|
falkne
| 2023-07-03T18:20:12Z | 0 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"adapterhub:argument/quality",
"roberta",
"region:us"
] | null | 2023-07-03T18:17:56Z |
---
tags:
- adapterhub:argument/quality
- roberta
- adapter-transformers
---
# Adapter `falkne/proposal` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [argument/quality](https://adapterhub.ml/explore/argument/quality/) dataset and includes a prediction head for classification.
This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
## Usage
First, install `adapter-transformers`:
```
pip install -U adapter-transformers
```
_Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. [More](https://docs.adapterhub.ml/installation.html)_
Now, the adapter can be loaded and activated like this:
```python
from transformers import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("roberta-base")
adapter_name = model.load_adapter("falkne/proposal", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here -->
|
falkne/effectiveness
|
falkne
| 2023-07-03T18:20:09Z | 2 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"adapterhub:argument/quality",
"roberta",
"region:us"
] | null | 2023-07-03T18:17:55Z |
---
tags:
- adapterhub:argument/quality
- roberta
- adapter-transformers
---
# Adapter `falkne/effectiveness` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [argument/quality](https://adapterhub.ml/explore/argument/quality/) dataset and includes a prediction head for classification.
This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
## Usage
First, install `adapter-transformers`:
```
pip install -U adapter-transformers
```
_Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. [More](https://docs.adapterhub.ml/installation.html)_
Now, the adapter can be loaded and activated like this:
```python
from transformers import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("roberta-base")
adapter_name = model.load_adapter("falkne/effectiveness", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here -->
|
BBAI/qlora-koalpaca-polyglot-12.8b-50step
|
BBAI
| 2023-07-03T18:06:07Z | 5 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-22T06:33:23Z |
---
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 0.4.0.dev0
|
hopkins/eng-kor-simcse.dev2.44k
|
hopkins
| 2023-07-03T17:51:10Z | 92 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"mbart",
"text2text-generation",
"translation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2023-07-03T17:38:07Z |
---
tags:
- translation
- generated_from_trainer
metrics:
- bleu
model-index:
- name: eng-kor-simcse.dev2.44k
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. -->
# eng-kor-simcse.dev2.44k
This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9818
- Bleu: 7.4953
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
Officialletai/Taxi-v3
|
Officialletai
| 2023-07-03T17:46:05Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-03T17:43:57Z |
---
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: 7.54 +/- 2.69
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="Officialletai/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"])
```
|
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.