Zero-Shot Image Classification
Transformers
Safetensors
siglip
vision
Inference Endpoints

question about 'model_type' in config.json

#5
by XA-hyy - opened

why param "model_type" in config.json is siglip,siglip_text_model and siglip_vision_model, not siglip2, siglip2_text_model and siglip2_vision_model?I noticed existed model class 'Siglip2Model',but still use 'SiglipModel'

Hey @XA-hyy , Siglip2Model is only for -naflex checkpoints. Other checkpoints are compatible with Siglip (v1)

Sign up or log in to comment