metadata
inference: false
Model Card
Bunny is a family of lightweight multimodal models.
Bunny-pretrain-phi-1.5-siglip is the pretrained weights for bunny-phi-1.5-siglip-lora, which leverages Phi-1.5 as the language model backbone and SigLIP as the vision encoder. It is pretrained on LAION-2M.
More details about this model can be found in GitHub.