kohjingyu / fromage

🧀 Code and models for the ICML 2023 paper "Grounding Language Models to Images for Multimodal Inputs and Outputs".

Home Page:https://jykoh.com/fromage

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Unexpected key(s) in state_dict

mlarrarte opened this issue · comments

Hey!
I'm trying to load the checkpoint provided to test the model a little bit but I got the following error:

Unexpected key(s) in state_dict: "model.logit_scale", "model.text_hidden_fcs.0.0.bias", "model.text_hidden_fcs.0.0.weight", "model.visual_embeddings.bias", "model.visual_embeddings.weight", "model.visual_fc.bias", "model.visual_fc.weight", "ret_input_embeddings.weight".

I know that in issue #29 a solution was provided but I don't know which script I need to modify.

Can you help me please?