albertvillanova's picture
End of training
3c1ae09 verified
---
base_model: trl-internal-testing/tiny-Qwen2ForCausalLM-2.5
library_name: transformers
model_name: test_training_with_generation_1
tags:
- generated_from_trainer
- grpo
- trl
licence: license
---
# Model Card for test_training_with_generation_1
This model is a fine-tuned version of [trl-internal-testing/tiny-Qwen2ForCausalLM-2.5](https://huggingface.co/trl-internal-testing/tiny-Qwen2ForCausalLM-2.5).
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="albertvillanova/test_training_with_generation_1", 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: 0.25.0.dev0
- Transformers: 4.57.3
- Pytorch: 2.8.0
- Datasets: 4.0.0
- 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}}
}
```