nms05

Dinov2-SigLIP-Phi3-LoRA

nms05/Dinov2-SigLIP-Phi3-LoRA

Dinov2-SigLIP-Phi3-LoRA is a visual question answering model from nms05. Use it for the visual question answering task on the model card, and read the license before you ship it in a product.

Vision Encoder - DinoV2 + SigLIP @384px resolution. Why 2 vision encoders? Connector - MLP (Dino and SigLIP features are concatenated and then projected to Phi3 representation space) Language Model - Phi3 + LoRA Pre-t…