I am using the “google/electra-base-discriminator” model like below,
model = ElectraForPreTraining.from_pretrained(“google/electra-base-discriminator”)
tokenizer = ElectraTokenizerFast.from_pretrained(“google/electra-base-discriminator”)
but facing the below error:
Unable to load weights from pytorch checkpoint file for 'C:\Users\Prajapati.Kishor/.cache\huggingface\hub\models–google–electra-base-discriminator\snaps
hots\1b48ef100dac4676d84125a8a7b7ab7c51e00386\pytorch_model.bin’ at 'C:\Users\Prajapati.Kishor/.cache\huggingface\hub\models–google–electra-base-discriminator\sn
apshots\1b48ef100dac4676d84125a8a7b7ab7c51e00386\pytorch_model.bin’. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.
I also tried by using from_tf=True, like below:
model = ElectraForPreTraining.from_pretrained(“google/electra-base-discriminator”,from_tf=True)
tokenizer = ElectraTokenizerFast.from_pretrained(“google/electra-base-discriminator”,from_tf=True)
but I am facing the below issue:
File “h5py\h5f.pyx”, line 106, in h5py.h5f.open
OSError: Unable to open file (truncated file: eof = 45749007, sblock->base_addr = 0, stored_eof = 438200172)