Promote Sign in Sign up

Multimodal model

Florence-2-VQAJP2

Listed for image text to text. Explore the model card for usage and requirements.

aipib Multimodal Open weights mit
Open model card ↗
Type
Multimodal
Weights
Open
Downloads
216k
Likes
1
Pipeline
image text to text
License
mit

Model hub

aipib/Florence-2-VQAJP2

Repo
aipib/Florence-2-VQAJP2
Library
transformers
Access
Public
Technical tags and languages
transformers safetensors florence2 image-text-to-text custom_code dataset:Kendamarron/japanese-photo-instruction base_model:microsoft/Florence-2-base-ft base_model:finetune:microsoft/Florence-2-base-ft endpoints_compatible
Open on Hugging Face