OpenGVLab / LLaMA-Adapter

Hi, great work!

Currently, I am using the LORA-BIAS-7B-v21 under llama_adapter_v2_multimodal7b, however, it shows that:

LLaMA_Adapter/llama_adapter_v2_multimodal7b/llama/utils.py", line 69, in _download
    raise RuntimeError("Model has been downloaded but the SHA256 checksum does not not match")
RuntimeError: Model has been downloaded but the SHA256 checksum does not not match

Thanks for your report! Now we have fixed it. You can also comment the following lines to make it work.

LLaMA-Adapter/llama_adapter_v2_multimodal7b/llama/utils.py

Lines 68 to 69 in a50befe

    
           if hashlib.sha256(open(download_target, "rb").read()).hexdigest() != expected_sha256: 
        
               raise RuntimeError("Model has been downloaded but the SHA256 checksum does not not match")

	if hashlib.sha256(open(download_target, "rb").read()).hexdigest() != expected_sha256:
	raise RuntimeError("Model has been downloaded but the SHA256 checksum does not not match")

SHA256 checksum does not not match for LORA-BIAS-7B-v21