metadata

base_model: open-r1/Qwen2.5-Math-7B-RoPE-300k
datasets: open-r1/Mixture-of-Thoughts
library_name: transformers
model_name: OpenR1-Distill-7B
tags:
  - generated_from_trainer
  - open-r1
  - trl
  - sft
licence: license

Model Card for OpenR1-Distill-7B

This model is a fine-tuned version of open-r1/Qwen2.5-Math-7B-RoPE-300k on the open-r1/Mixture-of-Thoughts 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="edbeeching/OpenR1-Distill-7B", 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 SFT.

Framework versions

TRL: 0.18.0.dev0
Transformers: 4.52.0.dev0
Pytorch: 2.6.0
Datasets: 3.5.0
Tokenizers: 0.21.1

Citations

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 Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}