README.md

---
base_model: EssentialAI/rnj-1-instruct
datasets: AI-MO/NuminaMath-TIR
library_name: transformers
model_name: EssentialAI-rnj-1-instruct-trl-grpo
tags:
- generated_from_trainer
- trackio:https://sshahriyar-EssentialAI-rnj-1-instruct-trl-grpo.hf.space?project=huggingface&runs=sshahriyar-1774227545&sidebar=collapsed
- grpo
- trl
- trackio
licence: license
---

# Model Card for EssentialAI-rnj-1-instruct-trl-grpo

This model is a fine-tuned version of [EssentialAI/rnj-1-instruct](https://huggingface.co/EssentialAI/rnj-1-instruct) on the [AI-MO/NuminaMath-TIR](https://huggingface.co/datasets/AI-MO/NuminaMath-TIR) 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="sshahriyar/EssentialAI-rnj-1-instruct-trl-grpo", 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/gradio-app/trackio/refs/heads/main/trackio/assets/badge.png" alt="Visualize in Trackio" title="Visualize in Trackio" width="150" height="24"/>](https://sshahriyar-EssentialAI-rnj-1-instruct-trl-grpo.hf.space?project=huggingface&runs=sshahriyar-1774227545&sidebar=collapsed)


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: 0.29.1
- Transformers: 5.0.0
- Pytorch: 2.10.0+cu128
- Datasets: 4.0.0
- Tokenizers: 0.22.2

## 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
@software{vonwerra2020trl,
  title   = {{TRL: Transformers Reinforcement Learning}},
  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
  license = {Apache-2.0},
  url     = {https://github.com/huggingface/trl},
  year    = {2020}
}
```