search

jshilong / GPT4RoI

GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest
Other
506 stars 25 forks source link

Finetuning stage 2 from a checkpoint #24

Open anex004 opened 1 year ago

anex004 commented 1 year ago

Hi @jshilong, thanks again for releasing the code and the models! I am trying to finetune the model from stage 2. Could you please share a stage 2 checkpoint. I am getting a 'ValueError: Can't find a valid checkpoint at ./exp/stage2/checkpoint-0' when trying to start from the current weight directory as the starting point.

Appreciate your help!

jshilong commented 1 year ago

@anex004 Please refer to https://github.com/jshilong/GPT4RoI/issues/15 I will add a load_from parameter in the next version

anex004 commented 1 year ago

Hi @jshilong, thanks for the prompt response! I was following that structure and your instructions. I guess I need a 'load_from parameter' to start from the existing weights. Otherwise, I need to start from stage 1 and then move to stage 2, is that right?