Update pipeline tag to image-text-to-text and add transformers metadata
#1
by nielsr HF Staff - opened
Hi! I'm Niels from the Hugging Face community team.
I noticed that this model is a multimodal web agent (based on Qwen3.5-VL architecture) capable of processing visual information to navigate websites. I've updated the pipeline_tag to image-text-to-text so it appears in the correct category on the Hub.
I also added library_name: transformers to the metadata, as the repository contains the necessary configuration files for compatibility. Finally, I've added a citation section to the model card to make it easier for researchers to cite your work.
xhluca changed pull request status to merged
thanks!