The model-type of Multi-Modal Full-Parameter Finetuning

[hekkang]

torchrun --nproc-per-node=2 demos/single_turn_mm.py
--llama_config /path/to/params.json --tokenizer_path /path/to/tokenizer.model
--pretrained_path /path/to/multimodel_llama

The prompts are as follows:
ValueError: Cannot determine llama_type

Then I don't know what type to choose, and there's no meta.json inside the model weight links