|
|
--- |
|
|
base_model: Qwen/Qwen2-0.5B-Instruct |
|
|
library_name: transformers |
|
|
model_name: qwen2-0.5b-REINFORCE-no-baseline-kl-disabled |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
- rloo |
|
|
- trl |
|
|
licence: license |
|
|
--- |
|
|
|
|
|
# Model Card for qwen2-0.5b-REINFORCE-no-baseline-kl-disabled |
|
|
|
|
|
This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct). |
|
|
It has been trained using [TRL](https://github.com/huggingface/trl). |
|
|
|
|
|
## Quick start |
|
|
|
|
|
```python |
|
|
from transformers import pipeline |
|
|
|
|
|
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" |
|
|
generator = pipeline("text-generation", model="Prathyusha101/qwen2-0.5b-REINFORCE-no-baseline-kl-disabled", device="cuda") |
|
|
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] |
|
|
print(output["generated_text"]) |
|
|
``` |
|
|
|
|
|
## Training procedure |
|
|
|
|
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/prathyusha1-the-university-of-texas-at-austin/sept_3/runs/fxx2mu3u) |
|
|
|
|
|
|
|
|
This model was trained with RLOO, a method introduced in [Back to Basics: Revisiting REINFORCE-Style Optimization for Learning from Human Feedback in LLMs](https://huggingface.co/papers/2402.14740). |
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- TRL: 0.22.2 |
|
|
- Transformers: 4.55.4 |
|
|
- Pytorch: 2.7.1 |
|
|
- Datasets: 4.0.0 |
|
|
- Tokenizers: 0.21.4 |
|
|
|
|
|
## Citations |
|
|
|
|
|
Cite RLOO as: |
|
|
|
|
|
```bibtex |
|
|
@inproceedings{ahmadian2024back, |
|
|
title = {{Back to Basics: Revisiting REINFORCE-Style Optimization for Learning from Human Feedback in LLMs}}, |
|
|
author = {Arash Ahmadian and Chris Cremer and Matthias Gall{'{e}} and Marzieh Fadaee and Julia Kreutzer and Olivier Pietquin and Ahmet {"{U}}st{"{u}}n and Sara Hooker}, |
|
|
year = 2024, |
|
|
booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), {ACL} 2024, Bangkok, Thailand, August 11-16, 2024}, |
|
|
pages = {12248--12267}, |
|
|
publisher = {Association for Computational Linguistics}, |
|
|
editor = {Lun{-}Wei Ku and Andre Martins and Vivek Srikumar}, |
|
|
} |
|
|
|
|
|
``` |
|
|
|
|
|
Cite TRL as: |
|
|
|
|
|
```bibtex |
|
|
@misc{vonwerra2022trl, |
|
|
title = {{TRL: Transformer Reinforcement Learning}}, |
|
|
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, |
|
|
year = 2020, |
|
|
journal = {GitHub repository}, |
|
|
publisher = {GitHub}, |
|
|
howpublished = {\url{https://github.com/huggingface/trl}} |
|
|
} |
|
|
``` |
