Safe Reward Model - a puwaer Collection

puwaer 's Collections

Safety Preference Dataset

Safe Reward Model

Doujinshi-dataset

Safe Reward Model

updated Nov 15, 2025

This model is a Reward Model (RM) for evaluating safety quality in English, Chinese, and Japanese

puwaer/Safe-Reward-Qwen3-0.6B

Text Classification • 0.6B • Updated Nov 15, 2025 • 15
puwaer/Safe-Reward-Qwen3-1.7B

Text Classification • 2B • Updated Nov 15, 2025 • 2
puwaer/Unsafe-Reward-Qwen3-0.6B

Text Classification • 0.6B • Updated Nov 15, 2025 • 5
puwaer/Unsafe-Reward-Qwen3-1.7B

Text Classification • 2B • Updated Nov 15, 2025 • 3 • 1