Qwen1.5-MOE-aux-free-sft-math7k-1e-3-gamma-1epoch/README.md

base_model, datasets, library_name, model_name, tags, licence

base_model	datasets	library_name	model_name	tags	licence
Qwen/Qwen1.5-MoE-A2.7B	HectorHe/math7k	transformers	Qwen1.5-MOE-aux-free-sft-math7k-1e-3-gamma-1epoch	generated_from_trainer open-r1 trl sft	license

Model Card for Qwen1.5-MOE-aux-free-sft-math7k-1e-3-gamma-1epoch

This model is a fine-tuned version of Qwen/Qwen1.5-MoE-A2.7B on the HectorHe/math7k 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="xd2010/Qwen1.5-MOE-aux-free-sft-math7k-1e-3-gamma-1epoch", 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: 0.16.0.dev0
• Transformers: 4.51.0
• Pytorch: 2.6.0
• Datasets: 4.8.3
• Tokenizers: 0.21.4

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