The error when conbine the LLaMA and Delta weights

[lalisa2020]

When I run the command: python -m fastchat.model.apply_delta --base {path_to_llama_weights} --target ./vicuna_ckpt/7b_v0/ --delta {path_to_delta_vicuna_weights}

I got this error: Unable to load weights from pytorch checkpoint file for './vicuna-7b/pytorch_model-00001-of-00002.bin' at './vicuna-7b/pytorch_model-00001-of-00002.bin'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.

[lalisa2020]

Because I can not run this command: pip install git+https://github.com/lm-sys/FastChat.git@v0.1.10

So I used this command: pip3 install fschat

Is this the cause of the problem?

[zhtstar]

Maybe it is caused by the versions of fschat and transformers you are using. This page introduces the corresponding relationship between model weights and the versions of fschat and transformers. I hope it can help you. https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md#how-to-apply-delta-weights-for-weights-v11-and-v0

Here are my settings, no errors reported: vicuna-7b-delta-v1.1 llama-7b-hf fschat version is 0.2.1 transformers version is 4.37.0.dev0

Also, if you cannot run pip install git+https://github.com/lm-sys/FastChat.git@v0.1.10, you can pip install fschat==0.1.10

[lalisa2020]

Maybe it is caused by the versions of fschat and transformers you are using. This page introduces the corresponding relationship between model weights and the versions of fschat and transformers. I hope it can help you. https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md#how-to-apply-delta-weights-for-weights-v11-and-v0

Here are my settings, no errors reported: vicuna-7b-delta-v1.1 llama-7b-hf fschat version is 0.2.1 transformers version is 4.37.0.dev0

Also, if you cannot run pip install git+https://github.com/lm-sys/FastChat.git@v0.1.10, you can pip install fschat==0.1.10

Thanks!!

[FantasticGNU]

@zhtstar Thank you for your answer! I will keep this issue Open for others to view.