base_model, library_name, model_name, tags, licence

base_model	library_name	model_name	tags	licence
Qwen/Qwen3-1.7B-Base	transformers	Qwen3-1.7B-Base_dsum_3_6_rel_1e2_1p0_0p0_1p0_grpo_42_rule	generated_from_trainer grpo trl	license

Model Card for Qwen3-1.7B-Base_dsum_3_6_rel_1e2_1p0_0p0_1p0_grpo_42_rule

This model is a fine-tuned version of Qwen/Qwen3-1.7B-Base. 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="Kazuki1450/Qwen3-1.7B-Base_dsum_3_6_rel_1e2_1p0_0p0_1p0_grpo_42_rule", 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 GRPO, a method introduced in DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Framework versions

• TRL: 0.29.0
• Transformers: 4.57.6
• Pytorch: 2.9.0
• Datasets: 4.8.2
• Tokenizers: 0.22.2

Citations

Cite GRPO 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}
}