请问如果用自己的数据进行微调的话，怎么解决模块加载时，形状不匹配的问题？
Opened this issue · 0 comments
Wbxxx commented
RuntimeError: Error(s) in loading state_dict for Embedding:
size mismatch for weight: copying a param with shape torch.Size([18993, 256]) from checkpoint, the shape in current model is torch.Size([2559, 256]).