zdw9915

Results 1 comments of zdw9915

size mismatch for transformer_decoder.layers.0.0.fn.fn.to_q.weight: copying a param with shape torch.Size([512, 32]) from checkpoint, the shape in current model is torch.Size([64, 32]).

> 他把那个测试模型改了，测试模型换成和训练模型一样就行，改了半天，我以为是模型出错了呢，打印保存模型和现有模型才发现这个问题 非常感谢！问题已经解决了