Closed NineMeowICT closed 1 month ago
@NineMeowICT the weights are probably bfloat16 because model was cast to lower precision LayerNormFp32 was not handled correctly (or disabled), there is code in open_clip to do cast to bfloat16/float16 correctly https://github.com/mlfoundations/open_clip/blob/fc5a37b72d705f760ebbc7915b84729816ed471f/src/open_clip/factory.py#L269-L291
This looks like a usage bug and note an OpenCLIP bug
@rwightman Okay, I will check my code again. Thank you.
I think it's quite strange, since to() function should convert the input correctly.