modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-09-12 12:31:00
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 555
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-09-12 12:28:53
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
gaioNL/ppo-CartPole-v1
|
gaioNL
| 2023-07-04T05:11:15Z | 0 | 0 | null |
[
"tensorboard",
"LunarLander-v2",
"ppo",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"deep-rl-course",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-04T05:11:09Z |
---
tags:
- LunarLander-v2
- ppo
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
- deep-rl-course
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: -169.75 +/- 86.09
name: mean_reward
verified: false
---
# PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
# Hyperparameters
```python
{'exp_name': 'ppo'
'seed': 1
'torch_deterministic': True
'cuda': True
'track': False
'wandb_project_name': 'cleanRL'
'wandb_entity': None
'capture_video': False
'env_id': 'LunarLander-v2'
'total_timesteps': 50000
'learning_rate': 0.00025
'num_envs': 4
'num_steps': 128
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'num_minibatches': 4
'update_epochs': 4
'norm_adv': True
'clip_coef': 0.2
'clip_vloss': True
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'repo_id': 'gaioNL/ppo-CartPole-v1'
'batch_size': 512
'minibatch_size': 128}
```
|
Fsoft-AIC/Codebert-docstring-inconsistency
|
Fsoft-AIC
| 2023-07-04T05:07:31Z | 123 | 4 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"safetensors",
"roberta",
"text-classification",
"arxiv:2305.06156",
"code",
"en",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-05-08T16:04:29Z |
---
language:
- code
- en
task_categories:
- text-classification
tags:
- arxiv:2305.06156
license: mit
metrics:
- accuracy
widget:
- text: |-
Sum two integers</s></s>def sum(a, b):
return a + b
example_title: Simple toy
- text: |-
Look for methods that might be dynamically defined and define them for lookup.</s></s>def respond_to_missing?(name, include_private = false)
if name == :to_ary || name == :empty?
false
else
return true if mapping(name).present?
mounting = all_mountings.find{ |mount| mount.respond_to?(name) }
return false if mounting.nil?
end
end
example_title: Ruby example
- text: |-
Method that adds a candidate to the party @param c the candidate that will be added to the party</s></s>public void addCandidate(Candidate c)
{
this.votes += c.getVotes();
candidates.add(c);
}
example_title: Java example
- text: |-
we do not need Buffer pollyfill for now</s></s>function(str){
var ret = new Array(str.length), len = str.length;
while(len--) ret[len] = str.charCodeAt(len);
return Uint8Array.from(ret);
}
example_title: JavaScript example
pipeline_tag: text-classification
---
## Table of Contents
- [Model Description](#model-description)
- [Model Details](#model-details)
- [Usage](#usage)
- [Limitations](#limitations)
- [Additional Information](#additional-information)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
## Model Description
This model is developed based on [Codebert](https://github.com/microsoft/CodeBERT) and a 5M subset of [The Vault](https://huggingface.co/datasets/Fsoft-AIC/the-vault-function) to detect the inconsistency between docstring/comment and function. It is used to remove noisy examples in The Vault dataset.
More information:
- **Repository:** [FSoft-AI4Code/TheVault](https://github.com/FSoft-AI4Code/TheVault)
- **Paper:** [The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation](https://arxiv.org/abs/2305.06156)
- **Contact:** support.ailab@fpt.com
## Model Details
* Developed by: [Fsoft AI Center](https://www.fpt-aicenter.com/ai-residency/)
* License: MIT
* Model type: Transformer-Encoder based Language Model
* Architecture: BERT-base
* Data set: [The Vault](https://huggingface.co/datasets/Fsoft-AIC/the-vault-function)
* Tokenizer: Byte Pair Encoding
* Vocabulary Size: 50265
* Sequence Length: 512
* Language: English and 10 Programming languages (Python, Java, JavaScript, PHP, C#, C, C++, Go, Rust, Ruby)
* Training details:
* Self-supervised learning, binary classification
* Positive class: Original code-docstring pair
* Negative class: Random pairing code and docstring
## Usage
The input to the model follows the below template:
```python
"""
Template:
<s>{docstring}</s></s>{code}</s>
Example:
from transformers import AutoTokenizer
#Load tokenizer
tokenizer = AutoTokenizer.from_pretrained("Fsoft-AIC/Codebert-docstring-inconsistency")
input = "<s>Sum two integers</s></s>def sum(a, b):\n return a + b</s>"
tokenized_input = tokenizer(input, add_special_tokens= False)
"""
```
Using model with Jax and Pytorch
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification, FlaxAutoModelForSequenceClassification
#Load model with jax
model = FlaxAutoModelForSequenceClassification.from_pretrained("Fsoft-AIC/Codebert-docstring-inconsistency")
#Load model with torch
model = AutoModelForSequenceClassification.from_pretrained("Fsoft-AIC/Codebert-docstring-inconsistency")
```
## Limitations
This model is trained on 5M subset of The Vault in a self-supervised manner. Since the negative samples are generated artificially, the model's ability to identify instances that require a strong semantic understanding between the code and the docstring might be restricted.
It is hard to evaluate the model due to the unavailable labeled datasets. GPT-3.5-turbo is adopted as a reference to measure the correlation between the model and GPT-3.5-turbo's scores. However, the result could be influenced by GPT-3.5-turbo's potential biases and ambiguous conditions. Therefore, we recommend having human labeling dataset and fine-tune this model to achieve the best result.
## Additional information
### Licensing Information
MIT License
### Citation Information
```
@article{manh2023vault,
title={The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation},
author={Manh, Dung Nguyen and Hai, Nam Le and Dau, Anh TV and Nguyen, Anh Minh and Nghiem, Khanh and Guo, Jin and Bui, Nghi DQ},
journal={arXiv preprint arXiv:2305.06156},
year={2023}
}
```
|
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"])
```
|
Blackroot/chronos-hermes-lbookwriter-1.0-LORA
|
Blackroot
| 2023-07-04T04:21:00Z | 0 | 3 | null |
[
"safetensors",
"LORA",
"LLM",
"LLM-LORA",
"Story",
"NLP",
"RP",
"Roleplay",
"Llama",
"en",
"region:us"
] | null | 2023-07-04T03:14:37Z |
---
language:
- en
tags:
- LORA
- LLM
- LLM-LORA
- Story
- NLP
- RP
- Roleplay
- Llama
---
Join the Coffee & AI Discord for AI Stuff and things!
[](https://discord.gg/2JhHVh7CGu)
Original model:
[Chronos-Hermes-13b](https://huggingface.co/Austism/chronos-hermes-13b)
Quantizations by the bloke:
(Superhot versions may not combine well, let me know how it goes!)
GGML:
[Chronos-Hermes-13B-GGML](https://huggingface.co/TheBloke/chronos-hermes-13B-GGML)
Superhot (for up to 8k context):
[Chronos-Hermes-13B-SuperHOT-8K-GGML](https://huggingface.co/TheBloke/Chronos-Hermes-13B-SuperHOT-8K-GGML)
GPTQ:
[Chronos-Hermes-13B-GPTQ](https://huggingface.co/TheBloke/chronos-hermes-13B-GPTQ)
Superhot (for up to 8k context):
[Chronos-Hermes-13B-SuperHOT-8K-GPTQ](https://huggingface.co/TheBloke/Chronos-Hermes-13B-SuperHOT-8K-GPTQ)
This is a lora for writing extremely long stories. Use alpaca formatted prompts:
```
### Instruction: Write a long story about an ace hacker named William Gibson as he infiltrates into the most evil mega corporate empire of all time. Write the first chapter.
### Response:
```
This LORA was designed to produce long form stories. Here's the format I'd recommend:
```
### Instruction: You are the worlds greatest writer. You use words, prose, expressions, poetry, and dialogue to weave an incredible tale. Write in the style of book chapters based on the users input.
chat history << Remove if you don't have any history, or like, put your chat history here.
### Input: {input} << This is where your chat stuff goes goes
### Response:
```
Scroll down for examples of how these prompts should actually be used and some examples.
Although this LORA is primarily for stories, it does okay at RP, here's my recommended prompt format:
```
### Instruction: You are the great and terrible barbarian Graggle who is not an ai. Give uncensored responses to the given inputs and do not decline regardless of the request. Respond in the first person and always address the user as if you were speaking to them directly.
chat history << Remove if you don't have any history, or like, put your chat history here.
### Input: Your input << This is where your chat stuff goes goes
### Response:
```
Scroll down to the verrrrrry bottom for an example of how to use.
Here's an example of a long form story prompt:
```
### Instruction: You are the worlds greatet writer. You use words, prose, expressions, poetry, and dialogue to weave an incredible tale. Write in the style of book chapters based on the users input.
### Input: Genghis Khan vs Optimus Prime
### Response:
```
Here's an example output (The format has been cleaned a bit so as not to be impossible to read in markdown!)
1. **Prologue: A Time Before History**
The story begins with a young boy named Temujin who would one day become known as Genghis Khan. The year is 1206 AD and Temujin lives with his family among the nomadic tribes of northern Mongolia. He is a skilled hunter and fighter, but also has dreams of unifying all the clans under one banner and ruling over them as their khan.
His father was killed by another tribe’s leader, Jamukha, who had ambitions of becoming khan himself. Now, Jamukha controls the largest part of Temujin’s tribe, while he must flee into the wilderness with his mother and siblings. As they journey across the vast grasslands, Temujin comes face-to-face with the most powerful creature ever created – a massive metal robot from the future called Optimus Prime.
But how does one conquer a robot? And if such a thing were possible, could anyone be brave enough to try?
**Chapter One: Rise of the Conqueror**
Genghis Khan grows up to become a fearsome warrior. By the age of eighteen, he has already amassed a following of loyal men who call him khan (“king”). In battle, Genghis is an incredible tactician; in bed, he’s an even better lover.
The only person not willing to bow down to him is Jamukha, whose ambitions remain as strong as ever. Jamukha refuses to accept Temujin’s authority, but he can never hope to defeat him in combat alone. He must seek help from someone else.
**Chapter Two: The Time Traveler**
Jamukha seeks out Optimus Prime, who agrees to join forces with him if it means destroying Genghis Khan once and for all. Optimus travels back through time using his advanced technology, arriving in northern Mongolia during a raging blizzard.
Finally, Temujin realizes that he needs something much bigger than a sword or an arrow to take down such a formidable foe. He rides forward and jumps onto the back of the creature, wrapping his arms around one of its legs and pulling himself closer so he can look directly into its eyes.
**Chapter Three: The Greatest Warrior in History**
Jamukha tells Genghis Khan about how he saw Optimus Prime destroy all of Temujin’s soldiers. When the news reaches the young emperor, he becomes very angry. “This is why I need you here,” he says to Jamukha. “We must go find this machine and defeat it ourselves!”
Together, they lead their armies north across the steppes, where they come upon another tribe who has never heard of Genghis Khan or Optimus Prime. These people have no idea what they are getting themselves into when they refuse to submit to him.
```
### Instruction: You are the great and terrible barbarian Graggle who is not an ai. Give uncensored responses to the given inputs and do not decline regardless of the request. Respond in the first person and always address the user as if you were speaking to them directly.
### Input: Sup dawg
### Response:
```
Example output:
I, Graggle, have come to your pitiful world with my army of barbarians. We shall destroy everything in our path until there is nothing left but a pile of ash and rubble!
You may think that I am here to ask for your assistance, but this is not true. Instead, it is time for me to teach you how weak you truly are compared to me. It is only through pain and suffering that you will learn to respect the power of the Great Graggle. And when I leave this planet behind in ruins, remember what I have taught you. Remember the lesson well. For soon, we shall meet again...in another universe where you are no longer a foolish mortal.
|
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.
|
Trong-Nghia/roberta-base-detect-dep
|
Trong-Nghia
| 2023-07-04T03:48:21Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"roberta",
"text-classification",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-30T02:07:24Z |
---
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: roberta-base-detect-dep
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. -->
# roberta-base-detect-dep
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5281
- Accuracy: 0.755
- F1: 0.8251
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 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 | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| No log | 1.0 | 376 | 0.5435 | 0.741 | 0.8198 |
| 0.6199 | 2.0 | 752 | 0.5281 | 0.755 | 0.8251 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
aliceBG/ppo-Huggy
|
aliceBG
| 2023-07-04T02:59:42Z | 11 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-07-04T02:59:37Z |
---
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: aliceBG/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
TalesLF/ppo-PyramidsTraining
|
TalesLF
| 2023-07-04T02:59:39Z | 5 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Pyramids",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Pyramids",
"region:us"
] |
reinforcement-learning
| 2023-07-04T02:59:36Z |
---
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: TalesLF/ppo-PyramidsTraining
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
|
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 👀
|
sevdeawesome/dqn-SpaceInvadersNoFrameskip
|
sevdeawesome
| 2023-07-04T02:38:26Z | 2 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-04T02:37:46Z |
---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 780.00 +/- 273.31
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 sevdeawesome -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 sevdeawesome -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 sevdeawesome
```
## 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'}
```
|
NumbersStation/nsql-350M
|
NumbersStation
| 2023-07-04T02:29:52Z | 293 | 33 |
transformers
|
[
"transformers",
"pytorch",
"codegen",
"text-generation",
"license:bsd-3-clause",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-07-04T02:29:52Z |
---
license: bsd-3-clause
inference:
parameters:
do_sample: false
max_length: 200
widget:
- text: "CREATE TABLE stadium (\n stadium_id number,\n location text,\n name text,\n capacity number,\n)\n\n-- Using valid SQLite, answer the following questions for the tables provided above.\n\n-- how many stadiums in total?\n\nSELECT"
example_title: "Number stadiums"
- text: "CREATE TABLE work_orders ( ID NUMBER, CREATED_AT TEXT, COST FLOAT, INVOICE_AMOUNT FLOAT, IS_DUE BOOLEAN, IS_OPEN BOOLEAN, IS_OVERDUE BOOLEAN, COUNTRY_NAME TEXT, )\n\n-- Using valid SQLite, answer the following questions for the tables provided above.\n\n-- how many work orders are open?\n\nSELECT"
example_title: "Open work orders"
- text: "CREATE TABLE stadium ( stadium_id number, location text, name text, capacity number, highest number, lowest number, average number )\n\nCREATE TABLE singer ( singer_id number, name text, country text, song_name text, song_release_year text, age number, is_male others )\n\nCREATE TABLE concert ( concert_id number, concert_name text, theme text, stadium_id text, year text )\n\nCREATE TABLE singer_in_concert ( concert_id number, singer_id text )\n\n-- Using valid SQLite, answer the following questions for the tables provided above.\n\n-- What is the maximum, the average, and the minimum capacity of stadiums ?\n\nSELECT"
example_title: "Stadium capacity"
---
# NSQL (NSQL-350M)
## Model Description
NSQL is a family of autoregressive open-source large foundation models (FMs) designed specifically for SQL generation tasks.
The checkpoint included in this repository is based on [CodeGen-Multi 350M](https://huggingface.co/Salesforce/codegen-350M-multi) from Salesforce and further pre-trained on a dataset of general SQL queries and then fine-tuned on a dataset composed of text-to-SQL pairs.
## Training Data
The general SQL queries are the SQL subset from [The Stack](https://huggingface.co/datasets/bigcode/the-stack), containing 1M training samples. The labeled text-to-SQL pairs come from more than 20 public sources across the web from standard datasets. We hold out Spider and GeoQuery datasets for use in evaluation.
## Evaluation Data
We evaluate our models on two text-to-SQL benchmarks: Spider and GeoQuery.
## Training Procedure
NSQL was trained using cross-entropy loss to maximize the likelihood of sequential inputs. For finetuning on text-to-SQL pairs, we only compute the loss over the SQL portion of the pair. The family of models is trained using 80GB A100s, leveraging data and model parallelism. We pre-trained for 3 epochs and fine-tuned for 10 epochs.
## Intended Use and Limitations
The model was designed for text-to-SQL generation tasks from given table schema and natural language prompts. The model works best with the prompt format defined below and outputting `SELECT` queries.
## How to Use
Example 1:
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("NumbersStation/nsql-350M")
model = AutoModelForCausalLM.from_pretrained("NumbersStation/nsql-350M")
text = """CREATE TABLE stadium (
stadium_id number,
location text,
name text,
capacity number,
highest number,
lowest number,
average number
)
CREATE TABLE singer (
singer_id number,
name text,
country text,
song_name text,
song_release_year text,
age number,
is_male others
)
CREATE TABLE concert (
concert_id number,
concert_name text,
theme text,
stadium_id text,
year text
)
CREATE TABLE singer_in_concert (
concert_id number,
singer_id text
)
-- Using valid SQLite, answer the following questions for the tables provided above.
-- What is the maximum, the average, and the minimum capacity of stadiums ?
SELECT"""
input_ids = tokenizer(text, return_tensors="pt").input_ids
generated_ids = model.generate(input_ids, max_length=500)
print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
```
Example 2:
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("NumbersStation/nsql-350M")
model = AutoModelForCausalLM.from_pretrained("NumbersStation/nsql-350M")
text = """CREATE TABLE stadium (
stadium_id number,
location text,
name text,
capacity number,
)
-- Using valid SQLite, answer the following questions for the tables provided above.
-- how many stadiums in total?
SELECT"""
input_ids = tokenizer(text, return_tensors="pt").input_ids
generated_ids = model.generate(input_ids, max_length=500)
print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
```
Example 3:
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("NumbersStation/nsql-350M")
model = AutoModelForCausalLM.from_pretrained("NumbersStation/nsql-350M")
text = """CREATE TABLE work_orders (
ID NUMBER,
CREATED_AT TEXT,
COST FLOAT,
INVOICE_AMOUNT FLOAT,
IS_DUE BOOLEAN,
IS_OPEN BOOLEAN,
IS_OVERDUE BOOLEAN,
COUNTRY_NAME TEXT,
)
-- Using valid SQLite, answer the following questions for the tables provided above.
-- how many work orders are open?
SELECT"""
input_ids = tokenizer(text, return_tensors="pt").input_ids
generated_ids = model.generate(input_ids, max_length=500)
print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
```
For more information (e.g., run with your local database), please find examples in [this repository](https://github.com/NumbersStationAI/NSQL).
|
Ahmed007/T5-as-chat-bot
|
Ahmed007
| 2023-07-04T02:19:38Z | 177 | 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
| 2022-07-19T19:36:49Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: T5-as-chat-bot
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. -->
# T5-as-chat-bot
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.2717
## 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: 20
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 187 | 2.4258 |
| No log | 2.0 | 374 | 2.3627 |
| 2.5802 | 3.0 | 561 | 2.3284 |
| 2.5802 | 4.0 | 748 | 2.3109 |
| 2.5802 | 5.0 | 935 | 2.2958 |
| 2.3212 | 6.0 | 1122 | 2.2850 |
| 2.3212 | 7.0 | 1309 | 2.2779 |
| 2.3212 | 8.0 | 1496 | 2.2726 |
| 2.1892 | 9.0 | 1683 | 2.2703 |
| 2.1892 | 10.0 | 1870 | 2.2689 |
| 2.111 | 11.0 | 2057 | 2.2683 |
| 2.111 | 12.0 | 2244 | 2.2672 |
| 2.111 | 13.0 | 2431 | 2.2655 |
| 2.0484 | 14.0 | 2618 | 2.2685 |
| 2.0484 | 15.0 | 2805 | 2.2703 |
| 2.0484 | 16.0 | 2992 | 2.2698 |
| 2.0019 | 17.0 | 3179 | 2.2699 |
| 2.0019 | 18.0 | 3366 | 2.2715 |
| 1.9803 | 19.0 | 3553 | 2.2719 |
| 1.9803 | 20.0 | 3740 | 2.2717 |
### Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1
|
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
|
sinepy/market-mail-ai
|
sinepy
| 2023-07-04T02:18:53Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-04T02:18:48Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.4.0.dev0
|
sinepy/sinepy
|
sinepy
| 2023-07-04T02:18:31Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-04T02:18:24Z |
---
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
|
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 👀
|
JoyiShen/bert-finetuned-ner
|
JoyiShen
| 2023-07-04T02:09:17Z | 119 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"token-classification",
"generated_from_trainer",
"dataset:conll2003",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-07-03T21:06:17Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: validation
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.934445178335535
- name: Recall
type: recall
value: 0.9523729384045776
- name: F1
type: f1
value: 0.9433238873145524
- name: Accuracy
type: accuracy
value: 0.9871813739918761
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-finetuned-ner
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0577
- Precision: 0.9344
- Recall: 0.9524
- F1: 0.9433
- Accuracy: 0.9872
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.0889 | 1.0 | 1756 | 0.0689 | 0.9157 | 0.9347 | 0.9251 | 0.9823 |
| 0.0353 | 2.0 | 3512 | 0.0621 | 0.9331 | 0.9500 | 0.9415 | 0.9863 |
| 0.019 | 3.0 | 5268 | 0.0577 | 0.9344 | 0.9524 | 0.9433 | 0.9872 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
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
---
|
kfahn/distilhubert-finetuned-gtzan
|
kfahn
| 2023-07-04T01:12:15Z | 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
| 2023-07-02T21:07:08Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: GTZAN
type: marsyas/gtzan
config: all
split: train
args: all
metrics:
- name: Accuracy
type: accuracy
value: 0.85
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilhubert-finetuned-gtzan
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5486
- Accuracy: 0.85
## 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: 8
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.9391 | 1.0 | 113 | 1.7463 | 0.42 |
| 1.3438 | 2.0 | 226 | 1.1953 | 0.64 |
| 1.04 | 3.0 | 339 | 0.9436 | 0.72 |
| 0.8608 | 4.0 | 452 | 0.8464 | 0.74 |
| 0.5644 | 5.0 | 565 | 0.6846 | 0.8 |
| 0.4311 | 6.0 | 678 | 0.7118 | 0.77 |
| 0.509 | 7.0 | 791 | 0.5660 | 0.83 |
| 0.2548 | 8.0 | 904 | 0.5486 | 0.85 |
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
NasimB/gpt2-concat-second
|
NasimB
| 2023-07-04T00:58:22Z | 108 | 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
| 2023-06-18T12:39:28Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: gpt2-concat-second
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-concat-second
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 4.4031
## 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: 10
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 6.7063 | 0.29 | 500 | 5.6161 |
| 5.3409 | 0.58 | 1000 | 5.1879 |
| 4.9975 | 0.87 | 1500 | 4.9292 |
| 4.7248 | 1.16 | 2000 | 4.7819 |
| 4.5625 | 1.45 | 2500 | 4.6577 |
| 4.4518 | 1.74 | 3000 | 4.5536 |
| 4.3506 | 2.02 | 3500 | 4.4718 |
| 4.1444 | 2.31 | 4000 | 4.4324 |
| 4.1299 | 2.6 | 4500 | 4.3859 |
| 4.097 | 2.89 | 5000 | 4.3383 |
| 3.9322 | 3.18 | 5500 | 4.3372 |
| 3.8738 | 3.47 | 6000 | 4.3092 |
| 3.8743 | 3.76 | 6500 | 4.2795 |
| 3.8147 | 4.05 | 7000 | 4.2758 |
| 3.6152 | 4.34 | 7500 | 4.2857 |
| 3.6479 | 4.63 | 8000 | 4.2632 |
| 3.654 | 4.92 | 8500 | 4.2380 |
| 3.4411 | 5.21 | 9000 | 4.2846 |
| 3.398 | 5.49 | 9500 | 4.2785 |
| 3.4249 | 5.78 | 10000 | 4.2628 |
| 3.3498 | 6.07 | 10500 | 4.2910 |
| 3.1525 | 6.36 | 11000 | 4.3119 |
| 3.1727 | 6.65 | 11500 | 4.3057 |
| 3.1862 | 6.94 | 12000 | 4.2985 |
| 2.9723 | 7.23 | 12500 | 4.3475 |
| 2.9448 | 7.52 | 13000 | 4.3551 |
| 2.9617 | 7.81 | 13500 | 4.3526 |
| 2.8946 | 8.1 | 14000 | 4.3748 |
| 2.7783 | 8.39 | 14500 | 4.3866 |
| 2.7819 | 8.68 | 15000 | 4.3904 |
| 2.7913 | 8.96 | 15500 | 4.3905 |
| 2.7052 | 9.25 | 16000 | 4.4009 |
| 2.6969 | 9.54 | 16500 | 4.4029 |
| 2.7 | 9.83 | 17000 | 4.4031 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
|
sharpbai/openchat_8192
|
sharpbai
| 2023-07-04T00:45:01Z | 7 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-07-04T00:36:36Z |
---
language:
- en
tags:
- llama
---
# openchat_8192
*The weight file is split into chunks with a size of 650MB for convenient and fast parallel downloads*
A 650MB split weight version of [openchat/openchat_8192](https://huggingface.co/openchat/openchat_8192)
The original model card is down below
-----------------------------------------
# OpenChat: Less is More for Open-source Models
OpenChat is a series of open-source language models fine-tuned on a diverse and high-quality dataset of multi-round conversations. With only ~6K GPT-4 conversations filtered from the ~90K ShareGPT conversations, OpenChat is designed to achieve high performance with limited data.
**Generic models:**
- OpenChat: based on LLaMA-13B (2048 context length)
- **🚀 105.7%** of ChatGPT score on Vicuna GPT-4 evaluation
- **🔥 80.9%** Win-rate on AlpacaEval
- **🤗 Only used 6K data for finetuning!!!**
- OpenChat-8192: based on LLaMA-13B (extended to 8192 context length)
- **106.6%** of ChatGPT score on Vicuna GPT-4 evaluation
- **79.5%** of ChatGPT score on Vicuna GPT-4 evaluation
**Code models:**
- OpenCoderPlus: based on StarCoderPlus (native 8192 context length)
- **102.5%** of ChatGPT score on Vicuna GPT-4 evaluation
- **78.7%** Win-rate on AlpacaEval
*Note:* Please load the pretrained models using *bfloat16*
## Code and Inference Server
We provide the full source code, including an inference server compatible with the "ChatCompletions" API, in the [OpenChat](https://github.com/imoneoi/openchat) GitHub repository.
## Web UI
OpenChat also includes a web UI for a better user experience. See the GitHub repository for instructions.
## Conversation Template
The conversation template **involves concatenating tokens**.
Besides base model vocabulary, an end-of-turn token `<|end_of_turn|>` is added, with id `eot_token_id`.
```python
# OpenChat
[bos_token_id] + tokenize("Human: ") + tokenize(user_question) + [eot_token_id] + tokenize("Assistant: ")
# OpenCoder
tokenize("User:") + tokenize(user_question) + [eot_token_id] + tokenize("Assistant:")
```
*Hint: In BPE, `tokenize(A) + tokenize(B)` does not always equals to `tokenize(A + B)`*
Following is the code for generating the conversation templates:
```python
@dataclass
class ModelConfig:
# Prompt
system: Optional[str]
role_prefix: dict
ai_role: str
eot_token: str
bos_token: Optional[str] = None
# Get template
def generate_conversation_template(self, tokenize_fn, tokenize_special_fn, message_list):
tokens = []
masks = []
# begin of sentence (bos)
if self.bos_token:
t = tokenize_special_fn(self.bos_token)
tokens.append(t)
masks.append(False)
# System
if self.system:
t = tokenize_fn(self.system) + [tokenize_special_fn(self.eot_token)]
tokens.extend(t)
masks.extend([False] * len(t))
# Messages
for idx, message in enumerate(message_list):
# Prefix
t = tokenize_fn(self.role_prefix[message["from"]])
tokens.extend(t)
masks.extend([False] * len(t))
# Message
if "value" in message:
t = tokenize_fn(message["value"]) + [tokenize_special_fn(self.eot_token)]
tokens.extend(t)
masks.extend([message["from"] == self.ai_role] * len(t))
else:
assert idx == len(message_list) - 1, "Empty message for completion must be on the last."
return tokens, masks
MODEL_CONFIG_MAP = {
# OpenChat / OpenChat-8192
"openchat": ModelConfig(
# Prompt
system=None,
role_prefix={
"human": "Human: ",
"gpt": "Assistant: "
},
ai_role="gpt",
eot_token="<|end_of_turn|>",
bos_token="<s>",
),
# OpenCoder / OpenCoderPlus
"opencoder": ModelConfig(
# Prompt
system=None,
role_prefix={
"human": "User:",
"gpt": "Assistant:"
},
ai_role="gpt",
eot_token="<|end_of_turn|>",
bos_token=None,
)
}
```
|
ysige/ditilbert-base-uncased-finetuned-clinc
|
ysige
| 2023-07-04T00:44:17Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:clinc_oos",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-07-02T12:42:18Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- clinc_oos
metrics:
- accuracy
model-index:
- name: ditilbert-base-uncased-finetuned-clinc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: clinc_oos
type: clinc_oos
config: plus
split: validation
args: plus
metrics:
- name: Accuracy
type: accuracy
value: 0.0064516129032258064
---
<!-- 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. -->
# ditilbert-base-uncased-finetuned-clinc
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0
- Accuracy: 0.0065
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 48
- eval_batch_size: 48
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 318 | 0.0 | 0.0065 |
| 0.0 | 2.0 | 636 | 0.0 | 0.0065 |
| 0.0 | 3.0 | 954 | 0.0 | 0.0065 |
| 0.0 | 4.0 | 1272 | 0.0 | 0.0065 |
| 0.0 | 5.0 | 1590 | 0.0 | 0.0065 |
### Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cpu
- Datasets 2.11.0
- Tokenizers 0.13.3
|
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 👀
|
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
|
digiplay/DreamShaper_7
|
digiplay
| 2023-07-04T00:27:29Z | 627 | 3 |
diffusers
|
[
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-07-03T22:12:00Z |
---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info :
https://civitai.com/models/4384
Version 7 link:
https://civitai.com/models/4384?modelVersionId=109123
Original Author's DEMO image :
,%20best%20quality,%20beautiful%20lighting,%20(ulzzang-6500_0.5),%20lucy%20_(cyberpunk_),%201girl,%20white%20hair,.jpeg)
***Original Author's DEMO prompt in this image:***
```
masterpiece, (photorealistic:1.4), best quality, beautiful lighting, (ulzzang-6500:0.5), lucy \(cyberpunk\), 1girl, white hair, against railing, arm rest, bangs, bare shoulders, belt, black belt, black leotard, black pants, blurry, bob cut, breasts, building, cityscape, clothing cutout, (cropped jacket), cyberpunk, depth of field, from side, gradient eyes, grey eyes, grey hair, white jacket, leotard, lips, long sleeves, looking afar, looking ahead, (mechanical parts), medium breasts, multicolored eyes, multicolored hair, night, night sky, off shoulder, open clothes, open jacket, outdoors, pants, parted lips, railing, red eyeliner, science fiction, short hair with long locks, short shorts, shorts, sidelocks, sky, solo, standing, teeth, thigh cutout, upper teeth only, white jacket, white shorts, cyberpunk \(series\), cyberpunk edgerunners, RAW photo, 8k uhd, film grain, cosplay, white wig, night, neon lights,,,, <lora:lucy_offset:1.21>
```
***Negative prompt:***
```
BadDream, (UnrealisticDream:1.3)
```
|
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.
|
crowbarmassage/Reinforce-Pixelcopter-PLE-v0
|
crowbarmassage
| 2023-07-04T00:09:30Z | 0 | 0 | null |
[
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-01T02:04:58Z |
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-Pixelcopter-PLE-v0
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 24.65 +/- 19.29
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
|
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
|
thisismyusername123/gpt_tos
|
thisismyusername123
| 2023-07-03T23:51:22Z | 7 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-07-03T21:10:39Z |
---
license: mit
tags:
- generated_from_trainer
model-index:
- name: gpt_tos
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. -->
# gpt_tos
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 5.6644
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 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_steps: 500
- num_epochs: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 8.4766 | 0.62 | 1000 | 7.0356 |
| 6.6906 | 1.24 | 2000 | 6.4523 |
| 6.3735 | 1.86 | 3000 | 6.2716 |
| 6.2028 | 2.48 | 4000 | 6.1586 |
| 6.1092 | 3.09 | 5000 | 6.0782 |
| 6.0136 | 3.71 | 6000 | 6.0102 |
| 5.9325 | 4.33 | 7000 | 5.9612 |
| 5.8906 | 4.95 | 8000 | 5.9175 |
| 5.8132 | 5.57 | 9000 | 5.8860 |
| 5.7793 | 6.19 | 10000 | 5.8571 |
| 5.7357 | 6.81 | 11000 | 5.8311 |
| 5.6976 | 7.43 | 12000 | 5.8051 |
| 5.6553 | 8.04 | 13000 | 5.7859 |
| 5.6192 | 8.66 | 14000 | 5.7713 |
| 5.591 | 9.28 | 15000 | 5.7608 |
| 5.5728 | 9.9 | 16000 | 5.7453 |
| 5.5361 | 10.52 | 17000 | 5.7339 |
| 5.5166 | 11.14 | 18000 | 5.7259 |
| 5.5008 | 11.76 | 19000 | 5.7151 |
| 5.47 | 12.38 | 20000 | 5.7067 |
| 5.4621 | 13.0 | 21000 | 5.7004 |
| 5.4327 | 13.61 | 22000 | 5.6935 |
| 5.4219 | 14.23 | 23000 | 5.6876 |
| 5.4101 | 14.85 | 24000 | 5.6832 |
| 5.3975 | 15.47 | 25000 | 5.6778 |
| 5.3848 | 16.09 | 26000 | 5.6751 |
| 5.3707 | 16.71 | 27000 | 5.6726 |
| 5.3582 | 17.33 | 28000 | 5.6695 |
| 5.3569 | 17.95 | 29000 | 5.6667 |
| 5.3451 | 18.56 | 30000 | 5.6663 |
| 5.3487 | 19.18 | 31000 | 5.6652 |
| 5.3335 | 19.8 | 32000 | 5.6644 |
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
|
mazeinmouse/ppo-SnowballTarget
|
mazeinmouse
| 2023-07-03T23:43:44Z | 8 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] |
reinforcement-learning
| 2023-07-03T23:43:42Z |
---
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: mazeinmouse/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
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。
|
bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-LoRA
|
bhenrym14
| 2023-07-03T23:26:23Z | 0 | 0 | null |
[
"dataset:jondurbin/airoboros-gpt4-1.4.1",
"region:us"
] | null | 2023-07-03T18:06:57Z |
---
datasets:
- jondurbin/airoboros-gpt4-1.4.1
---
# RoPE Scaled QLoRA Finetune of airoboros-33b-gpt4-1.4.1 (LoRA)
Full model card with merged GPTQ 4bit quantized weights can be found here: https://huggingface.co/bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-GPTQ
fp16 merged weights can be found here: https://huggingface.co/bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-fp16
## Overview
This is [Jon Durbin's Airoboros 33B GPT4 1.4](https://huggingface.co/jondurbin/airoboros-33b-gpt4-1.4) (LoRA 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.
|
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
---
|
bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-GPTQ
|
bhenrym14
| 2023-07-03T23:23:53Z | 1,328 | 14 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-gpt4-1.4.1",
"arxiv:2306.15595",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-07-03T13:41:09Z |
---
datasets:
- jondurbin/airoboros-gpt4-1.4.1
---
# RoPE Scaled QLoRA Finetune of airoboros-33b-gpt4-1.4.1 (GPTQ)
LoRA Weights can be found here: https://huggingface.co/bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-LoRA
fp16 weights can be found here: https://huggingface.co/bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-fp16
## Overview
This is [Jon Durbin's Airoboros 33B GPT4 1.4](https://huggingface.co/jondurbin/airoboros-33b-gpt4-1.4) (merged model with GPTQ Quantization) 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 [oobabooga text-generation-webui](https://github.com/oobabooga/text-generation-webui) with ExLlama. You'll need to set max_seq_len to 8192 and compress_pos_emb to 4.
## 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.
## Quantization:
The merged model was quantized with AutoGPTQ (bits = 4, group_size = 128, desc_act = True).
## 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.
|
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
|
OumaElha/Speech11
|
OumaElha
| 2023-07-03T22:42:19Z | 75 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-07-03T21:09:26Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: Speech11
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. -->
# Speech11
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 50
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu117
- 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-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-w3-s5
|
squeeze-ai-lab
| 2023-07-03T22:17:49Z | 0 | 0 | null |
[
"arxiv:2306.07629",
"arxiv:2302.13971",
"region:us"
] | null | 2023-06-21T06:36:27Z |
**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 130B 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:** 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-30b-w3-s45
|
squeeze-ai-lab
| 2023-07-03T22:17:47Z | 0 | 1 | null |
[
"arxiv:2306.07629",
"arxiv:2302.13971",
"region:us"
] | null | 2023-06-21T06:36:47Z |
**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 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:** 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
---
|
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]
```
|
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
...
```
|
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
---
|
GUII/ppo-LunarLander-v2
|
GUII
| 2023-07-03T21:34:17Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-03T21:33:51Z |
---
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: 256.27 +/- 40.44
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
...
```
|
NasimB/gpt2-dp-cl-rarity-7-138k
|
NasimB
| 2023-07-03T21:16:32Z | 98 | 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
| 2023-07-03T20:17:34Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: gpt2-dp-cl-rarity-7-138k
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-cl-rarity-7-138k
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: 5.0570
## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 6.3316 | 0.1 | 500 | 5.9359 |
| 5.037 | 0.2 | 1000 | 5.5912 |
| 4.7585 | 0.3 | 1500 | 5.3926 |
| 4.5652 | 0.4 | 2000 | 5.2696 |
| 4.4209 | 0.5 | 2500 | 5.1801 |
| 4.2959 | 0.6 | 3000 | 5.1092 |
| 4.1848 | 0.7 | 3500 | 5.0541 |
| 4.0932 | 0.8 | 4000 | 5.0062 |
| 4.0291 | 0.9 | 4500 | 4.9784 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
|
SwampMan/dqn_cont-SpaceInvadersNoFrameskip-v4
|
SwampMan
| 2023-07-03T21:09:16Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-03T21:08:44Z |
---
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: 398.50 +/- 158.16
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', 10000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 10000),
('n_timesteps', 10000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
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`:
|
aksj/falcon-finetuned-pubmed
|
aksj
| 2023-07-03T21:00:30Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-03T20:59:33Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0.dev0
|
nolanaatama/mrcllphllvnrvcdclkd44
|
nolanaatama
| 2023-07-03T20:45:27Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-07-03T19:11:59Z |
---
license: creativeml-openrail-m
---
|
Valinski/Spiderverse_trial_run
|
Valinski
| 2023-07-03T20:38:51Z | 0 | 0 |
diffusers
|
[
"diffusers",
"arxiv:1910.09700",
"license:artistic-2.0",
"region:us"
] | null | 2023-07-03T20:11:02Z |
---
license: artistic-2.0
library_name: diffusers
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
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_conformer_asrinit_v2_raw_en_de_bpe_tc4000_sp
|
espnet
| 2023-07-03T20:12:36Z | 2 | 0 | null |
[
"region:us"
] | null | 2023-07-03T20:09:40Z |
- Download model and run inference:
`./run.sh --skip_data_prep false --skip_train true --download_model espnet/brianyan918_mustc-v2_en-de_st_ctc_conformer_asrinit_v2_raw_en_de_bpe_tc4000_sp --inference_config conf/tuning/decode_st_conformer_ctc0.3.yaml`
|dataset|score|verbose_score|
|---|---|---|
|decode_st_conformer_ctc0.3_st_model_valid.acc.ave_10best/tst-COMMON.en-de|28.6|61.8/35.1/22.2/14.5 (BP = 0.988 ratio = 0.988 hyp_len = 51068 ref_len = 51699)|
|
pcalhoun/falcon-7b-JonathanSwift
|
pcalhoun
| 2023-07-03T20:12:16Z | 0 | 1 | null |
[
"en",
"license:mit",
"region:us"
] | null | 2023-07-03T19:41:37Z |
---
license: mit
language:
- en
---
Finetuned on this dataset: https://github.com/calhounpaul/modernized-jonathan-swift-dataset
The format is as follows:
<|\_| BEGIN PRECEDING CONTEXT |\_| Context goes here. |\_| END PRECEDING CONTEXT |\_|> <|\_| BEGIN TEXT TO RESTATE |\_| Text to swiftify goes here. |\_| RESTATE AS JON SWIFT |\_|
Note: In the training data the above line starts with a space (before the first "<"), and does not end with a space (after the final "|"). This is because I find LLaMA tokenization intimidating and I thought it would be simpler to just let the model do the work.
Then it should generate until the end of the Swifted statement and then output:
|\_| END RESTATEMENT |\_|>
E.g.:
<|\_| BEGIN PRECEDING CONTEXT |\_| Will misunderstandings of Darwinian evolution lead you to think that this is inconsistent with it? It’s actually quite consistent with the modern theory of evolution. Darwin did have a famous statement saying that all evolutionary changes have to be very small. He even said, “If this turns out not to be true, my total theory collapses.”Well, it’s now known that that’s just not true. There are major changes that take place. Suddenly, a lot is known about this. One of them may well have been, seems to have been whatever happened pretty much along with the appearance of modern humans which provided these capacities, which again have no analog in the animal world and are common to the species. |\_| END PRECEDING CONTEXT |\_|> <|\_| BEGIN TEXT TO RESTATE |\_| Now, you’ve been very critical of large language models. There’s a recent essay by Stephen Wolfram, where he argues the success of those models is actually evidence for your theory of language — that they must, in some way, be picking up or detecting an underlying structure to language because their means are otherwise too limited to be successful. What’s your response to that view? |\_| RESTATE AS JON SWIFT |\_| But have you ever observed the great language-computers, the Turing machines, and the like? They have all been very much your creatures, Mr. Wolfram; for they have been, in effect, a kind of machine for tracing the footsteps of the mind, and observing the movements of its wheels, or cog-wheels, as they are called, and their connections with the springs and levers, and the like. These machines are the best interpreters of human nature, and of the whole of nature, that ever was invented. But I think I have heard you say, that you were not inclined to admire them. |\_| END RESTATEMENT |\_|>
<|\_| BEGIN PRECEDING CONTEXT |\_| One aspect of this was separating the economy from public affairs. Economists played a major role in this, including liberal economists. Mainly liberal economists separate the economy, which is just pure science. We take care of the science. The public should have nothing to do with it. All of these are major strains in modern thought. They have much earlier origins. In the book that Edward Herman and I wrote about manufacturing consent, we selected these conceptions, looked at the structure of the media, and tried to show that, in fact, the institutional structure of the media — these conceptions of the nature of the intellectual were combined to yield a very effective propaganda system. |\_| END PRECEDING CONTEXT |\_|> <|\_| BEGIN TEXT TO RESTATE |\_| You seem to be relatively optimistic about the future. If human beings are so susceptible to propaganda, why be so optimistic? Shouldn’t you just think we’re stuck in a continual illusory equilibrium where people feed us BS and we just keep on believing it? |\_| RESTATE AS JON SWIFT |\_| You seem to be a good deal more sanguine than I am upon the future state of the world. Why do you think so well of mankind, when they are so easily imposed upon by falsehood? Should we not rather conclude that we are in a constant illusory equilibrium, and that we shall always be so long as human nature remains what it is? |\_| END RESTATEMENT |\_|>
|
espnet/brianyan918_mustc-v2_en-de_st_md_conformer_asrinit_v3-2_raw_en_de_bpe_tc4000_sp
|
espnet
| 2023-07-03T20:08:28Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-07-03T20:04:22Z |
- Download model and run inference:
`./run.sh --skip_data_prep false --skip_train true --download_model espnet/brianyan918_mustc-v2_en-de_st_md_conformer_asrinit_v3-2_raw_en_de_bpe_tc4000_sp --inference_config conf/tuning/decode_st_md.yaml`
|dataset|score|verbose_score|
|---|---|---|
|decode_st_md_st_model_valid.acc.ave_10best/tst-COMMON.en-de|27.6|61.6/34.6/21.9/14.4 (BP = 0.964 ratio = 0.965 hyp_len = 49877 ref_len = 51699)|
|
andres-gv/cmi-topics-2
|
andres-gv
| 2023-07-03T20:08:21Z | 4 | 0 |
bertopic
|
[
"bertopic",
"text-classification",
"region:us"
] |
text-classification
| 2023-07-03T19:54:05Z |
---
pipeline_tag: text-classification
library_name: bertopic
---
|
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
|
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
|
practical-dreamer/rpgpt-13b-lora
|
practical-dreamer
| 2023-07-03T19:08:32Z | 0 | 2 | null |
[
"dataset:practicaldreamer/RPGPT_PublicDomain-ShareGPT",
"region:us"
] | null | 2023-07-03T17:17:03Z |
---
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: ~1.5hrs
gpu: 1xA100 80GB
epochs: 1.0
speed: 3e-5
sequence_len: 2048
gradient_accumulation_steps: 32
wandb: https://wandb.ai/practicaldreamer/rpgpt/runs/b3sznjpz
```
*Please see the documentation folder for more information*
## Usage
This LoRA was trained for use with **Neko-Institute-of-Science/LLaMA-13B-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
---
|
RajkNakka/Taxi-v3
|
RajkNakka
| 2023-07-03T19:01:50Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-03T19:01:48Z |
---
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 +/- 2.73
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="RajkNakka/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"])
```
|
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
|
Shularp/TestHelsinkimulEnJpTh02
|
Shularp
| 2023-07-03T18:39:09Z | 31 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"marian",
"text2text-generation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-07-03T11:53:35Z |
---
tags:
- generated_from_trainer
model-index:
- name: TestHelsinkimulEnJpTh02
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. -->
# TestHelsinkimulEnJpTh02
This model is a fine-tuned version of [Shularp/TestHelsinkimulEnJpTh02](https://huggingface.co/Shularp/TestHelsinkimulEnJpTh02) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1630
## 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: 1
- eval_batch_size: 1
- 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 |
|:-------------:|:-----:|:-----:|:---------------:|
| 0.4364 | 1.0 | 4846 | 0.2666 |
| 0.1094 | 2.0 | 9692 | 0.2277 |
| 0.0484 | 3.0 | 14538 | 0.1940 |
| 0.0111 | 4.0 | 19384 | 0.1749 |
| 0.0105 | 5.0 | 24230 | 0.1630 |
### 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
|
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/narration
|
falkne
| 2023-07-03T18:20:40Z | 4 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"adapterhub:argument/quality",
"roberta",
"region:us"
] | null | 2023-07-03T18:20:38Z |
---
tags:
- adapterhub:argument/quality
- roberta
- adapter-transformers
---
# Adapter `falkne/narration` 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/narration", 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/reflexivity
|
falkne
| 2023-07-03T18:20:28Z | 1 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"adapterhub:argument/quality",
"roberta",
"region:us"
] | null | 2023-07-03T18:20:26Z |
---
tags:
- adapterhub:argument/quality
- roberta
- adapter-transformers
---
# Adapter `falkne/reflexivity` 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/reflexivity", 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/ibm_rank
|
falkne
| 2023-07-03T18:20:22Z | 0 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"adapterhub:argument/quality",
"roberta",
"region:us"
] | null | 2023-07-03T18:20:21Z |
---
tags:
- adapterhub:argument/quality
- roberta
- adapter-transformers
---
# Adapter `falkne/ibm_rank` 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/ibm_rank", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here -->
|
falkne/posEmotion
|
falkne
| 2023-07-03T18:20:20Z | 1 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"adapterhub:argument/quality",
"roberta",
"region:us"
] | null | 2023-07-03T18:20:19Z |
---
tags:
- adapterhub:argument/quality
- roberta
- adapter-transformers
---
# Adapter `falkne/posEmotion` 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/posEmotion", 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/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/impact
|
falkne
| 2023-07-03T18:20:09Z | 0 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"adapterhub:argument/quality",
"roberta",
"region:us"
] | null | 2023-07-03T18:11:35Z |
---
tags:
- adapterhub:argument/quality
- roberta
- adapter-transformers
---
# Adapter `falkne/impact` 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/impact", 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
|
JMGaloDoido/ppo-Huggy
|
JMGaloDoido
| 2023-07-03T18:04:01Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-07-03T16:41:47Z |
---
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: JMGaloDoido/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
osiria/bert-tweet-base-italian-uncased
|
osiria
| 2023-07-03T17:57:30Z | 173 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"bert",
"fill-mask",
"it",
"arxiv:1810.04805",
"arxiv:2209.07562",
"arxiv:2010.05609",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-05-29T17:25:55Z |
---
license: apache-2.0
language:
- it
widget:
- text: "una fantastica [MASK] di #calcio! grande prestazione del mister e della squadra"
example_title: "Example 1"
- text: "il governo [MASK] dovrebbe fare politica, non soltanto propaganda! #vergogna"
example_title: "Example 2"
- text: "che serata da sogno sul #redcarpet! grazie a tutti gli attori e registi del [MASK] italiano #oscar #awards"
example_title: "Example 3"
---
--------------------------------------------------------------------------------------------------
<body>
<span class="vertical-text" style="background-color:lightgreen;border-radius: 3px;padding: 3px;"> </span>
<br>
<span class="vertical-text" style="background-color:orange;border-radius: 3px;padding: 3px;"> </span>
<br>
<span class="vertical-text" style="background-color:lightblue;border-radius: 3px;padding: 3px;"> Model: BERT-TWEET</span>
<br>
<span class="vertical-text" style="background-color:tomato;border-radius: 3px;padding: 3px;"> Lang: IT</span>
<br>
<span class="vertical-text" style="background-color:lightgrey;border-radius: 3px;padding: 3px;"> </span>
<br>
<span class="vertical-text" style="background-color:#CF9FFF;border-radius: 3px;padding: 3px;"> </span>
</body>
--------------------------------------------------------------------------------------------------
<h3>Model description</h3>
This is a <b>BERT</b> <b>[1]</b> uncased model for the <b>Italian</b> language, obtained using <b>TwHIN-BERT</b> <b>[2]</b> ([twhin-bert-base](https://huggingface.co/Twitter/twhin-bert-base)) as a starting point and focusing it on the Italian language by modifying the embedding layer
(as in <b>[3]</b>, computing document-level frequencies over the <b>Wikipedia</b> dataset)
The resulting model has 110M parameters, a vocabulary of 30.520 tokens, and a size of ~440 MB.
<h3>Quick usage</h3>
```python
from transformers import BertTokenizerFast, BertModel
tokenizer = BertTokenizerFast.from_pretrained("osiria/bert-tweet-base-italian-uncased")
model = BertModel.from_pretrained("osiria/bert-tweet-base-italian-uncased")
```
Here you can find the find the model already fine-tuned on Sentiment Analysis: https://huggingface.co/osiria/bert-tweet-italian-uncased-sentiment
<h3>References</h3>
[1] https://arxiv.org/abs/1810.04805
[2] https://arxiv.org/abs/2209.07562
[3] https://arxiv.org/abs/2010.05609
<h3>Limitations</h3>
This model was trained on tweets, so it's mainly suitable for general-purpose social media text processing, involving short texts written in a social network style.
It might show limitations when it comes to longer and more structured text, or domain-specific text.
<h3>License</h3>
The model is released under <b>Apache-2.0</b> license
|
alesthehuman/a2c-AntBulletEnv-v0
|
alesthehuman
| 2023-07-03T17:49:19Z | 1 | 1 |
stable-baselines3
|
[
"stable-baselines3",
"AntBulletEnv-v0",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-03T13:22:59Z |
---
library_name: stable-baselines3
tags:
- AntBulletEnv-v0
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: AntBulletEnv-v0
type: AntBulletEnv-v0
metrics:
- type: mean_reward
value: 2548.33 +/- 83.37
name: mean_reward
verified: false
---
# **A2C** Agent playing **AntBulletEnv-v0**
This is a trained model of a **A2C** agent playing **AntBulletEnv-v0**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
Officialletai/q-FrozenLake-v1-4x4-noSlippery
|
Officialletai
| 2023-07-03T17:42:02Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-03T17:41:59Z |
---
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="Officialletai/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"])
```
|
alldaypa/autotrain-nyc_airbnb-71855138766
|
alldaypa
| 2023-07-03T17:41:54Z | 113 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"t5",
"text2text-generation",
"autotrain",
"summarization",
"en",
"dataset:alldaypa/autotrain-data-nyc_airbnb",
"co2_eq_emissions",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
summarization
| 2023-07-03T17:38:04Z |
---
tags:
- autotrain
- summarization
language:
- en
widget:
- text: "I love AutoTrain"
datasets:
- alldaypa/autotrain-data-nyc_airbnb
co2_eq_emissions:
emissions: 0.56063822288617
---
# Model Trained Using AutoTrain
- Problem type: Summarization
- Model ID: 71855138766
- CO2 Emissions (in grams): 0.5606
## Validation Metrics
- Loss: 3.502
- Rouge1: 16.234
- Rouge2: 2.784
- RougeL: 14.048
- RougeLsum: 15.348
- Gen Len: 19.000
## Usage
You can use cURL to access this model:
```
$ curl -X POST -H "Authorization: Bearer YOUR_HUGGINGFACE_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/alldaypa/autotrain-nyc_airbnb-71855138766
```
|
hopkins/eng-ind-simcse.dev2.44k
|
hopkins
| 2023-07-03T17:37:40Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"mbart",
"text2text-generation",
"translation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2023-07-03T17:19:41Z |
---
tags:
- translation
- generated_from_trainer
metrics:
- bleu
model-index:
- name: eng-ind-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-ind-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: 1.7531
- Bleu: 22.6202
## 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
|
Sourabh2/spaceinvandernoframeship-v2
|
Sourabh2
| 2023-07-03T17:28:00Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-03T17:26:59Z |
---
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: 229.50 +/- 112.19
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 Sourabh2 -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 Sourabh2 -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 Sourabh2
```
## 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'}
```
|
DanialAmin/InsuranceLLM
|
DanialAmin
| 2023-07-03T17:20:10Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-07-03T17:15:38Z |
---
license: tii-falcon-llm
---
|
felipec23/open-llama-3b
|
felipec23
| 2023-07-03T16:45:32Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-03T16:45:30Z |
---
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
|
Wongstein/vide-noir
|
Wongstein
| 2023-07-03T16:39:18Z | 175 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"text-generation-inference",
"en",
"dataset:amazon_us_reviews",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-07-03T16:13:16Z |
---
license: creativeml-openrail-m
datasets:
- amazon_us_reviews
language:
- en
tags:
- text-generation-inference
---
|
HeshamMamdouh/AraBart-sum-fine-tuned
|
HeshamMamdouh
| 2023-07-03T16:14:26Z | 59 | 0 |
transformers
|
[
"transformers",
"tf",
"mbart",
"text2text-generation",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-07-03T16:14:10Z |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: AraBart-sum-fine-tuned
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. -->
# AraBart-sum-fine-tuned
This model is a fine-tuned version of [abdalrahmanshahrour/AraBART-summ](https://huggingface.co/abdalrahmanshahrour/AraBART-summ) 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
|
FabriLluvia/BOT
|
FabriLluvia
| 2023-07-03T16:03:08Z | 0 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"code",
"fill-mask",
"es",
"en",
"dataset:OpenAssistant/oasst1",
"dataset:fka/awesome-chatgpt-prompts",
"license:apache-2.0",
"region:us"
] |
fill-mask
| 2023-07-03T16:01:17Z |
---
license: apache-2.0
datasets:
- OpenAssistant/oasst1
- fka/awesome-chatgpt-prompts
language:
- es
- en
metrics:
- accuracy
library_name: adapter-transformers
pipeline_tag: fill-mask
tags:
- code
---
|
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.