Coobiw/MPP-LLaVA

Personal Project: MPP-Qwen14B & MPP-Qwen-Next(Multimodal Pipeline Parallel based on Qwen-LM). Support [video/image/multi-image] {sft/conversations}. Don't let the poverty limit your imagination! Train your own 8B/14B LLaVA-training-like MLLM on RTX3090/4090 24GB.

Jupyter NotebookStars 536Forks 28Watchers 536Open issues 8
Details
仓库信息
OwnerCoobiw
Homepage
Last pushed2025-03-10
Last updated2025-12-14
Issues fetched at

Stats

Community at a glance

Loading...

Loading

--

Loading

--

Loading

--

Loading

--