Promote Sign in Sign up

Multimodal model

Idefics3-8B-Llama3

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

HuggingFaceM4 Multimodal Open weights apache-2.0
Open model card ↗
Type
Multimodal
Weights
Open
Downloads
128k
Likes
307
Pipeline
image text to text
License
apache-2.0

Model hub

HuggingFaceM4/Idefics3-8B-Llama3

Repo
HuggingFaceM4/Idefics3-8B-Llama3
Library
transformers
Access
Public
Technical tags and languages
en transformers safetensors idefics3 image-text-to-text multimodal vision conversational dataset:HuggingFaceM4/OBELICS dataset:HuggingFaceM4/the_cauldron dataset:HuggingFaceM4/Docmatix dataset:HuggingFaceM4/WebSight endpoints_compatible
Open on Hugging Face

Papers

3

More from HuggingFaceM4

2