Open TimYao18 opened 1 year ago
Its about the transformer. https://github.com/huggingface/transformers/issues/1083
Sorry but I use this issue for questioning:
I found .mlmodelc and diffusers format both need these files but .mlpackage didn't.
It is possible that those files are stored inside the text encoder piece of the .mlpackage.
Hi all,
I want to know why the vocab.json and merges.txt are the same ones from the converting process? If we use a different CLIP model or Text Encoder model, shouldn't it be different?