README.md

---
base_model: Qwen/Qwen2.5-Math-7B-Instruct
datasets: trl-lib/math_shepherd
library_name: transformers
model_name: Qwen2.5-Math-7B-Instruct-PRM-Modified-math_shepherd
tags:
- generated_from_trainer
- trl
- prm
licence: license
---

# Model Card for Qwen2.5-Math-7B-Instruct-PRM-Modified-math_shepherd

This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct) on the [trl-lib/math_shepherd](https://huggingface.co/datasets/trl-lib/math_shepherd) 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="hzy/Qwen2.5-Math-7B-Instruct-PRM-Modified-math_shepherd", 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/hzy312/prm-modified/runs/7259093582.28342-2d8cbf99-871d-4b90-8210-d21d813eb3df) 


This model was trained with PRM.

### Framework versions

- TRL: 0.15.2
- Transformers: 4.49.0
- Pytorch: 2.4.0
- Datasets: 3.3.2
- Tokenizers: 0.21.0

## Citations

Cite PRM 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}}
}
```