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="flyingbugs/OpenR1-Qwen-7B-SFT", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

Visualize in Weights & Biases

This model was trained with SFT.

Evaluation Results

Model	MATH-500	AIME24	GPQA-diamond	MMLU (Generation)	BBH (Generation)	IFEVAL (Generation)	MMLU (Logits classification)
Qwen2.5-Math-7B-instruct	82.6	3.3	34.8	23.2	18.9		0.4173
Flyingbugs-OpenR1-Qwen-7B	88.8	43.3	37.8	23.1	18.9		0.3091

Framework versions

TRL: 0.16.0.dev0
Transformers: 4.49.0.dev0
Pytorch: 2.5.1
Datasets: 3.3.0
Tokenizers: 0.21.0

Citations

Cite TRL as:

bibtex

@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}}
}