llava-next

[CVPR'25 highlight] RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness

An open-source implementation for training LLaVA-NeXT.

A minimal codebase for finetuning large multimodal models, supporting llava-1.5/1.6, llava-interleave, llava-next-video, llava-onevision, llama-3.2-vision, qwen-vl, qwen2-vl, phi3-v etc.

Matryoshka Multimodal Models