MLC-LLM uses multimodal LLM

#1

The instructions on MLC-LLM are all unimodal models, can I use a multimodal image text model based on llama2 for prebuilt? And use it on ipad or android.

#2

this is something work in progress, you can follow tracking issue here https://github.com/mlc-ai/mlc-llm/issues/679

1 Like