R-I-S-E/RISE-Judge-Qwen2.5-7B

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Feb 12, 2025Architecture:Transformer0.0K Featherless Exclusive 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...

RISE-Judge-Qwen2.5-7B Overview

RISE-Judge-Qwen2.5-7B is a 7.6 billion parameter generative judge model developed by R-I-S-E, built on the Qwen2.5-7B-Base architecture. It is designed to evaluate and judge the quality of responses from other large language models. The model utilizes a unique two-stage training framework: SFT Warm-Up and DPO Enhancement. The SFT stage involves generating step-by-step judgments using GPT-4o, while the DPO stage refines the model's judgment ability on challenging cases.

Key Capabilities

  • Advanced Judgment: Specifically trained to act as an "LLM-as-a-Judge," providing detailed evaluations of question-answer pairs.
  • High Performance on Reward-Bench: Achieves state-of-the-art results on the Reward-Bench benchmark, demonstrating strong capabilities across Chat, Chat-H, Safety, and Reasoning categories.
  • Preference Data Generation: Can generate high-quality preference pairs, which are valuable for DPO training of other internal models.
  • Robust Training Methodology: Employs a sophisticated two-stage training process with quality checks to minimize position bias and enhance judgment accuracy.

Good for

  • Automated LLM Evaluation: Ideal for developers needing an automated system to judge and compare the quality of different LLM outputs.
  • Reinforcement Learning from Human Feedback (RLHF) Data Generation: Useful for creating high-quality preference datasets to train or fine-tune other generative models.
  • Benchmarking and Model Development: Provides a strong baseline for evaluating and improving the judgment capabilities of new LLMs.
  • Applications requiring nuanced response assessment: Particularly strong in reasoning and safety judgments, making it suitable for critical evaluation tasks.

Finetunes
1 models