70 lines
2.0 KiB
Markdown
70 lines
2.0 KiB
Markdown
---
|
|
base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
|
|
datasets: knoveleng/open-rs
|
|
library_name: transformers
|
|
model_name: DAPO-8B
|
|
tags:
|
|
- generated_from_trainer
|
|
- open-r1
|
|
- dapo
|
|
- trl
|
|
licence: license
|
|
---
|
|
|
|
# Model Card for DAPO-8B
|
|
|
|
This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) on the [knoveleng/open-rs](https://huggingface.co/datasets/knoveleng/open-rs) 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="kangdawei/DAPO-8B", 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 DAPO, a method introduced in [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://huggingface.co/papers/2503.14476).
|
|
|
|
### Framework versions
|
|
|
|
- TRL: 0.16.0.dev0
|
|
- Transformers: 4.57.1
|
|
- Pytorch: 2.5.1
|
|
- Datasets: 3.2.0
|
|
- Tokenizers: 0.22.1
|
|
|
|
## Citations
|
|
|
|
Cite DAPO as:
|
|
|
|
```bibtex
|
|
@article{yu2025dapo,
|
|
title = {{DAPO: An Open-Source LLM Reinforcement Learning System at Scale}},
|
|
author = {Qiying Yu and Zheng Zhang and others},
|
|
year = 2025,
|
|
eprint = {arXiv:2503.14476},
|
|
}
|
|
|
|
```
|
|
|
|
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}}
|
|
}
|
|
``` |