Unable to load weights from pytorch checkpoint

#3
by hexu0212 - opened

Hello,

I recently cloned the model from your huggingface repo and wanted to test it. However, I could not load the model because of the following error:

OSError: Unable to load weights from pytorch checkpoint file for 'hf_models/gatortron-large/pytorch_model.bin' at 'hf_models/gatortron-large/pytorch_model.bin'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.
Output is truncated. View as a scrollable element or open in a text editor. Adjust cell output settings...

Here is the script I tried to run (same as the examples you provided on the model card):


import transformers
import torch

model_id = "/scratch/hexu/LLMs/hf_models/gatortron-large"

from transformers import AutoModel, AutoTokenizer, AutoConfig

tokenizer= AutoTokenizer.from_pretrained(model_id)
config=AutoConfig.from_pretrained(model_id)
mymodel=AutoModel.from_pretrained(model_id)

encoded_input=tokenizer("Bone scan: Negative for distant metastasis.", return_tensors="pt")
encoded_output = mymodel(**encoded_input)
print (encoded_output)

And here are the versions of the packages:
tensorflow 2.17.0
tokenizers 0.19.1
torch 2.2.2+cu118
transformers 4.43.0

Does anyone have any suggestions? Thanks in advance.

Sign up or log in to comment