plaguss's picture
plaguss HF staff
End of training
605fbc0 verified
---
base_model: Qwen/Qwen2.5-0.5B
datasets: plaguss/math_shepherd_token
library_name: transformers
model_name: Qwen2.5-0.5B-Math-Shepherd-PRM-token-0.1
tags:
- generated_from_trainer
- trl
- stepwise-reward-trainer
licence: license
---
# Model Card for Qwen2.5-0.5B-Math-Shepherd-PRM-token-0.1
This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) on the [plaguss/math_shepherd_token](https://huggingface.co/datasets/plaguss/math_shepherd_token) dataset.
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="plaguss/Qwen2.5-0.5B-Math-Shepherd-PRM-token-0.1", 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/plaguss/huggingface/runs/2or9lath)
This model was trained with Stepwise Reward.
### Framework versions
- TRL: 0.13.0.dev0
- Transformers: 4.46.0.dev0
- Pytorch: 2.4.1
- Datasets: 3.0.1
- Tokenizers: 0.20.1
## Citations
Cite Stepwise Reward as:
```bibtex
@article{uesato2022solving,
title = {Solving Math Word Problems With Process- and Outcome-Based Feedback},
author = {Uesato, Jonathan and Kushman, Nate and Kumar, Ramana and Song, Francis and Siegel, Noah and Wang, Lisa and Creswell, Antonia and Irving, Geoffrey and Higgins, Irina},
year = 2022,
journal = {arXiv preprint arXiv:2211.14275}
}
```
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 Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```