README.md

metadata

license: apache-2.0
datasets:
  - HaoyeZhang/RLAIF-V-Dataset
language:
  - en

Model Card for RLAIF-V

GitHub ]

RLAIF-V is a novel framework that aligns MLLMs in a fully open-source paradigm for super GPT-4V trustworthiness. RLAIF-V maximally exploits the open-source feedback from two key perspectives, including high-quality feedback data and online feedback learning algorithm.

Model Details

Model Description

• Trained from model: llava-v1.5-7B
• Trained on data: RLAIF-V-Dataset