Missing `tokenizer.model`

by abetlen - opened Aug 21

Aug 21

Hi there, thank you for the amazing work on this model release. I was just curious because looking at the file manifest it seems to be missing the sentencepiece tokenizer model found in the other models in this 3.5 release. Is this vision-instruct model using the same one as mini-instruct?

haipingwu

Microsoft org Aug 21

hi @abetlen , thanks for your interest. tokenizer.model is not needed for loading and using the model as tokenizer configs are provided.

abetlen changed discussion status to closed Aug 22

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment