L
lmms-finetune
zjysteven/lmms-finetune
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.
★373stars
Python
Apache-2.0
Updated: 1mo ago
📋 Project at a Glance
Tap to expand
What's this?Models project leveraging finetuning and foundation-models, built with Python, open-source
Who made it?Maintained by zjysteven team, 373⭐ on GitHub, #1998 out of 3201 in Models
Why does it exist?As the Models landscape evolved, the zjysteven team identified the need for better finetuning solutions. lmms-finetune was created to simplify foundation-models workflows.
What can it do?Key use cases: instruction-tuning, large-language-model, large-multimodal-models
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/zjysteven/lmms-finetune
🔗 github.com/zjysteven/lmms-finetune
Topics
finetuningfoundation-modelsinstruction-tuninglarge-language-modellarge-multimodal-modelsllavallava-nextmultimodalmultimodal-large-language-modelsqwen-vlvision-languagevisual-instruction-tuning