Qwen3-0.6B-RM-hs2

<a href="https://aiplans.org" target="_blank" style="margin: 2px;"> <img alt="AIPlans" src="./logos/AI-Plans.svg" style="display: inline-block; vertical-align: middle;"/> </a>

Model Card for qwen3-0.6b-RM-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 reward model and was trained using prompts with a chosen response >=3 only. It took about 1h 20mins 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}}
}