Visual Question Answering
English

DinoV2-SigLIP-Phi3(LoRA) VLM

  • 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-train (Align) Dataset - LLaVA-CC3M-Pretrain-595K
  • Fine-tune (Instruction) Dataset - LLAVA-v1.5-Instruct + LRV-Instruct

Scripts to build and train the models are available at NMS05/DinoV2-SigLIP-Phi3-LoRA-VLM.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Datasets used to train nms05/Dinov2-SigLIP-Phi3-LoRA