MMR-DAPO

Model Card for MMR-DAPO

This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B on the knoveleng/open-rs dataset. It has been trained using TRL.

Quick start

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/MMR-DAPO", 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.

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:

@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:

@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}}
}