30B failed, pytorch_model-00039-of-00061.bin, If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.

project-baize / baize-chatbot

Let ChatGPT teach your own chatbot in hours with a single GPU!

https://arxiv.org/abs/2304.01196

GNU General Public License v3.0

3.15k stars 275 forks source link

30B failed, pytorch_model-00039-of-00061.bin, If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True. #31

Closed LIO-H-ZEN closed 1 year ago

LIO-H-ZEN commented 1 year ago

OSError: Unable to load weights from pytorch checkpoint file for 'model_cache/models--decapoda-research--llama-30b-hf/snapshots/f991780f9362b2fcaefad066cd235058844562b7/pytorch_model-00039-of-00061.bin'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.

The other shard is fine, any suggestion?

JetRunner commented 1 year ago

This seems to be a problem of the base model instead of Baize. Maybe one shard file is damaged. You can try to clear the cache and redownload the files.