base_model, library_name, model_name, tags, licence, datasets, license, language, pipeline_tag

base_model	library_name	model_name	tags	licence	datasets	license	language	pipeline_tag
Qwen/Qwen3-0.6B-Base	transformers	qwen3-0.6b-SFT-hs2	generated_from_trainer sft trl	license	Jennny/helpsteer2-helpfulness-preference nvidia/HelpSteer2	mit	en	text-generation

Model Card for qwen3-0.6b-SFT-hs2

This model is a fine-tuned version of Qwen/Qwen3-0.6B-Base. It has been trained using TRL. Intended Use: Research on model diffing, preference fine-tuning, and evaluation of lightweight LLM behavior changes. It was developed for use in the Model Diffing project of AI-Plans.

Training procedure

This model is a SFT model and was trained with the chosen responses only(with score >=3), of the dataset used. It took about 1hr 10 mins for training with an A100(40 GB).

Framework versions

• TRL: 0.25.1
• Transformers: 4.57.3
• Pytorch: 2.9.0+cu126
• Datasets: 4.4.1
• Tokenizers: 0.22.1

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}}
}