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.
显存够用的话,直接修改config文件里的
llm_model
项,改成14B的checkpoint路径就可以,我最近也会放一个在2张3090用流水线并行训练的14B版本