[Usage] Not able to fine tune the LLaVA model with llava-v1.5-7b. about llava HOT 5 OPEN

same issue . have you found any potential solutions ?

from llava.

model_name_or_path can not be iuhaotian/llava-v1.5-7b, should be llama2 or vicuna.

from llava.

hi

I have solved the issue by changing the names in arguments aling with that I have also made some changes in LLaVA.py file.

now code is working on both pretrain and fine tunning.

Thanks

from llava.

in arguments aling

Hi, can you please show the changes you have made

from llava.

in arguments aling

Hi, can you please show the changes you have made
well, if you try to us llava-v1.5-7b, you can just remove --pretrain_mm_mlp_adapter
it already contains the adapter weights

from llava.