There is a problem bewteen the pre-training model and PLBartForSequenceClassification architecture?
#3
by
hrshy0629
- opened
RuntimeError: Error(s) in loading state_dict for PLBartForSequenceClassification:
size mismatch for classification_head.out_proj.weight: copying a param with shape torch.Size([2, 768]) from checkpoint, the shape in current model is torch.Size([1, 768]).
size mismatch for classification_head.out_proj.bias: copying a param with shape torch.Size([2]) from checkpoint, the shape in current model is torch.Size([1]).