68 lines
2.0 KiB
Markdown
68 lines
2.0 KiB
Markdown
---
|
|
base_model: HuggingFaceTB/SmolLM3-3B
|
|
library_name: transformers
|
|
model_name: SmolLM3-3B-GRPO-think
|
|
tags:
|
|
- generated_from_trainer
|
|
- trl
|
|
- grpo
|
|
licence: license
|
|
---
|
|
|
|
# Model Card for SmolLM3-3B-GRPO-think
|
|
|
|
This model is a fine-tuned version of [HuggingFaceTB/SmolLM3-3B](https://huggingface.co/HuggingFaceTB/SmolLM3-3B).
|
|
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="burtenshaw/SmolLM3-3B-GRPO-think", device="cuda")
|
|
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
|
print(output["generated_text"])
|
|
```
|
|
|
|
## Training procedure
|
|
|
|
|
|
|
|
|
|
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
|
|
|
|
### Framework versions
|
|
|
|
- TRL: 0.24.0.dev0
|
|
- Transformers: 4.56.2
|
|
- Pytorch: 2.7.1
|
|
- Datasets: 4.1.1
|
|
- Tokenizers: 0.22.1
|
|
|
|
## Citations
|
|
|
|
Cite GRPO as:
|
|
|
|
```bibtex
|
|
@article{shao2024deepseekmath,
|
|
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
|
|
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
|
|
year = 2024,
|
|
eprint = {arXiv:2402.03300},
|
|
}
|
|
|
|
```
|
|
|
|
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}}
|
|
}
|
|
``` |