---
datasets:
- liuhaotian/LLaVA-Instruct-150K
- liuhaotian/LLaVA-CC3M-Pretrain-595K
language:
- en
metrics:
- accuracy
pipeline_tag: visual-question-answering
---
# DinoV2-SigLIP-Phi3(LoRA) VLM

* **Vision Encoder** - DinoV2 + SigLIP @384px resolution. [Why 2 vision encoders?](https://arxiv.org/abs/2401.06209)
* **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](https://github.com/NMS05/DinoV2-SigLIP-Phi3-LoRA-VLM).