Zero-Shot Image Classification
Transformers
Safetensors
siglip
vision

Fix model_max_length

#4
by fancyfeast - opened

Set model_max_length to 64.

Looks like model_max_length is erroneous, so this pull request sets it to 64, which I believe is the correct value given the text encoder's maximum input length.

This comment has been hidden
Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment