Datasets used to train SmolDocling
HuggingFaceM4
Team
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
HuggingFaceM4 is the multimodal team at Hugging Face, working on vision-language models.
Within this organization on the Hugging Face hub, you can access the Idefics models (version 1 IDEFICS, version 2 Idefics2, version 3 Idefics3), datasets used for the training like OBELICS, WebSight, The Cauldron or Docmatix, and interactive tools to visualize the results.
Idefics2-8B is a foundation vision-language model. In this collection, you will find the models, datasets and demo related to its creation.
-
IDEFICS2 Playground
🐨170Chat with a visual AI that answers questions about images
-
HuggingFaceM4/idefics2-8b
Image-Text-to-Text • 8B • Updated • 5.73k • 629 -
HuggingFaceM4/idefics2-8b-chatty
Image-Text-to-Text • 8B • Updated • 732 • 95 -
HuggingFaceM4/idefics2-8b-base
Image-Text-to-Text • 8B • Updated • 248 • 28
Datasets used to train SmolDocling
Idefics2-8B is a foundation vision-language model. In this collection, you will find the models, datasets and demo related to its creation.
-
IDEFICS2 Playground
🐨170Chat with a visual AI that answers questions about images
-
HuggingFaceM4/idefics2-8b
Image-Text-to-Text • 8B • Updated • 5.73k • 629 -
HuggingFaceM4/idefics2-8b-chatty
Image-Text-to-Text • 8B • Updated • 732 • 95 -
HuggingFaceM4/idefics2-8b-base
Image-Text-to-Text • 8B • Updated • 248 • 28
spaces 28
pinned
Build error
Agents
Featured
376
IDEFICS Playground
🐨
Running
The Hugging Face Hack
🕵
Interrogate AI suspects to solve a mystery
Running
Voice Agents Demo
🚀
Running
11
Autoresearch for Data
🌿
We gave an agent our GPU cluster to improve our data mixture
Starting on A10G
Featured
257
faster-qwen3-tts
🎙
Generate natural speech from your text instantly
Running
Speech-to-Speech Community Activity
📈
GitHub activity and maintainer load for speech-to-speech.
models 34
HuggingFaceM4/Idefics3-8B-Llama3
Image-Text-to-Text • 8B • Updated • 38.4k • 307
HuggingFaceM4/Florence-2-DocVQA
Image-Text-to-Text • 0.8B • Updated • 3.44k • 65
HuggingFaceM4/idefics2-8b
Image-Text-to-Text • 8B • Updated • 5.73k • 629
HuggingFaceM4/idefics2-8b-base
Image-Text-to-Text • 8B • Updated • 248 • 28
HuggingFaceM4/idefics2-8b-chatty
Image-Text-to-Text • 8B • Updated • 732 • 95
HuggingFaceM4/siglip-so400m-14-364-flash-attn2-navit
Zero-Shot Image Classification • 0.9B • Updated • 18 • 1
HuggingFaceM4/siglip-so400m-14-700-flash-attn2-navit
Zero-Shot Image Classification • 0.9B • Updated • 21 • 2
HuggingFaceM4/siglip-so400m-14-384-flash-attn2-navit
Zero-Shot Image Classification • 0.9B • Updated • 15 • 1
HuggingFaceM4/idefics2-8b-chatty-AWQ
Image-Text-to-Text • 8B • Updated • 34 • 5
HuggingFaceM4/idefics2-8b-AWQ
Image-Text-to-Text • 8B • Updated • 83 • 26
datasets 82
HuggingFaceM4/FineVisionMax
Viewer • Updated • 24.2M • 268k • 47
HuggingFaceM4/FineVision
Viewer • Updated • 24.2M • 97k • 544
HuggingFaceM4/lmms-eval-embeddings
Updated • 840 • 2
HuggingFaceM4/DoclingMatix
Viewer • Updated • 1.27M • 3.21k • 58
HuggingFaceM4/Caltech-101
Updated • 1.27k • 5
HuggingFaceM4/Docmatix
Viewer • Updated • 2.55M • 25.5k • 319
HuggingFaceM4/the_cauldron
Viewer • Updated • 1.88M • 188k • 574
HuggingFaceM4/FairFace
Viewer • Updated • 195k • 6.29k • 40
HuggingFaceM4/MMBench
Viewer • Updated • 11k • 579 • 6
HuggingFaceM4/WebSight
Viewer • Updated • 2.75M • 15.2k • 412