ClipCaptionModel errors

[LiXinghui-666]

Hi, @Colin97 when running the following code of caption.py in PATH (openshape-demo-support/openshape/demo)

tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
prefix_length = 10
model = ClipCaptionModel(prefix_length)
# print(model.gpt_embedding_size)
model.load_state_dict(torch.load(hf_hub_download('OpenShape/clipcap-cc', 'conceptual_weights.pt', token=True), map_location='cpu'))

report error

RuntimeError: Error(s) in loading state_dict for ClipCaptionModel:
        Unexpected key(s) in state_dict: "gpt.transformer.h.0.attn.bias", "gpt.transformer.h.0.attn.masked_bias", "gpt.transformer.h.1.attn.bias", 
"gpt.transformer.h.1.attn.masked_bias", "gpt.transformer.h.2.attn.bias", "gpt.transformer.h.2.attn.masked_bias", "gpt.transformer.h.3.attn.bias", 
"gpt.transformer.h.3.attn.masked_bias", "gpt.transformer.h.4.attn.bias", "gpt.transformer.h.4.attn.masked_bias", "gpt.transformer.h.5.attn.bias", 
"gpt.transformer.h.5.attn.masked_bias", "gpt.transformer.h.6.attn.bias", "gpt.transformer.h.6.attn.masked_bias", "gpt.transformer.h.7.attn.bias", 
"gpt.transformer.h.7.attn.masked_bias", "gpt.transformer.h.8.attn.bias", "gpt.transformer.h.8.attn.masked_bias", "gpt.transformer.h.9.attn.bias", 
"gpt.transformer.h.9.attn.masked_bias", "gpt.transformer.h.10.attn.bias", "gpt.transformer.h.10.attn.masked_bias", "gpt.transformer.h.11.attn.bias", 
"gpt.transformer.h.11.attn.masked_bias".

what is wrong?

[Colin97]

It seems that the package "transformers" has recently been updated. Using the old version 4.29.2 can resolve the problem.

[LiXinghui-666]

It seems that the package "transformers" has recently been updated. Using the old version 4.29.2 can resolve the problem.

This works for me. Thanks!

[Kaisor-Yuan]

I followed your suggestion, but it remained false. Is there any other method?

It seems that the package "transformers" has recently been updated. Using the old version 4.29.2 can resolve the problem.