chr1ce

[Question] KeyError: 'LlavaConfig' of using cli

3

### Question ''' # python -m llava.serve.cli \ > --model-path checkpoints/llava-v1.5-7b-lora \ > --model-base checkpoints/vicuna-7b-v1.5 \ > --image-file "https://lmg.jj20.com/up/allimg/tp03/1Z921110450D60-0-lp.jpg" \ > --load-4bit [2023-12-25 13:22:09,390] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda...

mgm-34b-hd, should have a 'model_type' key in its config.json

2

 when I use cli of mini-gemini-34b-hd weight, it returns this

I'm confused that whether author released lora weight of LRV-v2??? I modified model_worker.py's lora_path, it returns that missing many key in state_dict. I tried another method to load in a...