---
base_model: asas-ai/AceGPT-v2-8b-chat
datasets: open-r1/OpenR1-Math-220k
library_name: transformers
model_name: OpenR1-AceGPT-v2-8B-SFT
tags:
- generated_from_trainer
- open-r1
- trl
- sft
licence: license
---

# Model Card for OpenR1-AceGPT-v2-8B-SFT

This model is a fine-tuned version of [asas-ai/AceGPT-v2-8b-chat](https://huggingface.co/asas-ai/AceGPT-v2-8b-chat) on the [open-r1/OpenR1-Math-220k](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k) 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="khalidalt/OpenR1-AceGPT-v2-8B-SFT", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```


This model was trained with SFT.

### Framework versions

- TRL: 0.16.0.dev0
- Transformers: 4.49.0
- Pytorch: 2.5.1
- Datasets: 3.3.2
- Tokenizers: 0.21.0

## Citations

Cite open-r1 as:

```bibtex
@misc{open-r1,
	title        = {{Open R1: A fully open reproduction of DeepSeek-R1.}},
	year         = 2025,
	journal      = {GitHub repository},
	publisher    = {GitHub},
	howpublished = {\url{https://github.com/huggingface/open-r1}}
}
```


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}}
}
```