Update pipeline tag and add link to Github
#3
by
nielsr
HF staff
- opened
This PR updates the pipeline tag to image-to-text to better reflect the model's capabilities. The model can be used for image-text retrieval and as a vision encoder for VLMs, in addition to zero-shot image classification.
I also link to the Big Vision Github repository, where the model was developed.
nielsr
changed pull request status to
closed