Update pipeline tag to image-to-text
#2
by
nielsr
HF staff
- opened
This PR updates the pipeline_tag metadata from zero-shot-image-classification to image-to-text. While zero-shot image classification is a key capability of SigLIP 2, image-to-text better reflects the model's broader functionality as a vision-language encoder capable of image-text retrieval and serving as a vision encoder for other tasks beyond zero-shot classification.
nielsr
changed pull request status to
closed