Model Card for terminus-pi-trl-qwen3-4b-rollout-22189657

This model is a fine-tuned version of Qwen/Qwen3-4B. 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="burtenshaw/terminus-pi-trl-qwen3-4b-rollout-22189657", 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 AsyncGRPO, a method introduced in DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Framework versions

• TRL: 1.6.0.dev0
• Transformers: 5.10.0.dev0
• Pytorch: 2.10.0
• Datasets: 4.8.5
• Tokenizers: 0.22.2

Citations

Cite AsyncGRPO as:

@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:

@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}
}

Base model