LLaVA-MoD
by shufangxun
Pythonpushed almost 2 years ago
Making LLaVA Tiny via MoE-Knowledge Distillation
AI summary
MMLM Distiller
This project provides a novel framework for training small-scale Multimodal Language Models by distilling knowledge from larger models using a sparse Mixture of Experts architecture.
- stars
- 69
- forks
- 4
- watching
- 9