I installed fastai with anaconda and found the following bug in the package code.
In fastai/text/learner.py
def load_encoder(self, name:str, device:torch.device=None):
"Load the encoder `name` from the model directory."
encoder = get_model(self.model)[0]
if device is None: device = self.data.device
if hasattr(encoder, 'module'): encoder = encoder.module
encoder.load_state_dict(torch.load(self.path/self.model_dir/f'{name}.pth'))
encoder.load_state_dict(torch.load(self.path/self.model_dir/f'{name}.pth', map_location=device))
self.freeze()
Line 69 needs to be erased. The same line of code is repeated with and without specifying the device. This code would break if actually used on a CPU.