alibaba-pai

/

Qwen2-7B-Instruct-Exp

like 0

The model file model-00001-of-00004.safetensors seems to be corrupted.

I can not load this model with vllm. And then when I attempted to open the 'model-00001-of-00004.safetensors' model file manually, I encountered the same error. However, the remaining model files can be loaded correctly.

ERROR:

>>> from safetensors import safe_open
>>> a = safe_open("/cpfs01/llm/shared/ckpts/Qwen2-7B-Instruct-Exp/model-00001-of-00004.safetensors", framework="pt")
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
safetensors_rust.SafetensorError: Error while deserializing header: MetadataIncompleteBuffer

I cross-verified the SHA256 of my local file against the original repository's version and found them identical.

>>> sha256sum /cpfs01/llm/shared/ckpts/Qwen2-7B-Instruct-Exp/model-00001-of-00004.safetensors                                                                                                                                                                                                                                    
12394788ad91d483edcc58dfa02c0b1b087ffb71fb9d7b0b1b5f1a6db609b337 /cpfs01/llm/shared/ckpts/Qwen2-7B-Instruct-Exp/model-00001-of-00004.safetensors

Hoping for the corrected version of the model file!