IDEA-CCNL/Fengshenbang-LM

fintune后加载推理报错,用法是标准的用法

o-github-o opened this issue · 1 comments

Some weights of BertModel were not initialized from the model checkpoint

return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
NotImplementedError: Cannot copy out of meta tensor; no data!

同样有这个问题,是怎么解决的吗