Deploy Opensource Multimodal Large Language Models

LLaVA

Project Page Paper Demo Data Model

running the server

python -m llava.serve.model_worker –host 0.0.0.0 –controller http://localhost:10000 –port 40000 –worker http://localhost:40000 –model-path /mnt/g/Developing/Research/NLP-LLM/LLaVA/.checkpoints/LLaVA-Lightning-7B-v1-1 –multi-modal

Reference

• Previous
  Deploy LLM on any device
• Next
  Faiss-GPU