Modelpublic

rghosh8/nemotron-mini-4b-instruct-opencoder-educational-instruct-seed-42-G-8

sourceHugging Faceupdated 5mo agoView on Hugging Face

0likes9downloads

Model Card

Model Card for nemotron-mini-4b-instruct-opencoder-educational-instruct-seed-42-G-8

This model is a fine-tuned version of nvidia/Nemotron-Mini-4B-Instruct. It has been trained using 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="None", 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

—PEFT 0.18.1
—TRL: 1.1.0.dev0
—Transformers: 5.6.0.dev0
—Pytorch: 2.8.0
—Datasets: 4.8.4
—Tokenizers: 0.22.1

Citations

Cite GRPO as:

bibtex

@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:

bibtex

@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}
}