R-I-S-E/RISE-Judge-Qwen2.5-7B
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:Feb 12, 2025Architecture:Transformer0.0K Cold

RISE-Judge-Qwen2.5-7B is a 7.6 billion parameter generative judge model developed by R-I-S-E, built upon the Qwen2.5-7B-Base architecture with a 32768 token context length. It is specifically fine-tuned using a two-stage SFT Warm-Up and DPO Enhancement framework on preference data, making it highly effective at evaluating and judging the quality of LLM responses. This model excels in judging abilities, achieving state-of-the-art performance on the Reward-Bench benchmark, particularly in reasoning and safety, and is designed to generate preference pairs for DPO training of other internal models.

Loading preview...