Idefics2-8B is a foundation vision-language model. In this collection, you will find the models, datasets and demo related to its creation.
HuggingFaceM4
Enterprise
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.
Collections
4
WebSight is a dataset of 823,000 HTML/CSS codes representing synthetically generated English websites, each accompanied by a corresponding screenshot.
-
HuggingFaceM4/WebSight
Viewer • Updated • 2.75M • 7.08k • 353 -
HuggingFaceM4/VLM_WebSight_finetuned
Text Generation • Updated • 4.27k • 188 -
896
Screenshot to HTML
⚡Convert screenshots to HTML code
-
Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset
Paper • 2403.09029 • Published • 56
Idefics2-8B is a foundation vision-language model. In this collection, you will find the models, datasets and demo related to its creation.
WebSight is a dataset of 823,000 HTML/CSS codes representing synthetically generated English websites, each accompanied by a corresponding screenshot.
-
HuggingFaceM4/WebSight
Viewer • Updated • 2.75M • 7.08k • 353 -
HuggingFaceM4/VLM_WebSight_finetuned
Text Generation • Updated • 4.27k • 188 -
896
Screenshot to HTML
⚡Convert screenshots to HTML code
-
Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset
Paper • 2403.09029 • Published • 56
spaces
13
pinned
Runtime error
376
IDEFICS Playground
🐨
Running
102
Idefics3
📊
Generate text based on an image and prompt
Running
on
Zero
15
Florence 2
📉
Generate answers from images and questions
Running
on
Zero
896
Screenshot to HTML
⚡
Convert screenshots to HTML code
Runtime error
167
IDEFICS2 Playground
🐨
Running
145
Idefics 8b
🐠
Generate text from images and prompts
models
34
HuggingFaceM4/Idefics3-8B-Llama3
Image-Text-to-Text
•
Updated
•
44.2k
•
286
HuggingFaceM4/Florence-2-DocVQA
Image-Text-to-Text
•
Updated
•
3.36k
•
60
HuggingFaceM4/idefics2-8b
Image-Text-to-Text
•
Updated
•
551k
•
608
HuggingFaceM4/idefics2-8b-base
Image-Text-to-Text
•
Updated
•
959
•
28
HuggingFaceM4/idefics2-8b-chatty
Image-Text-to-Text
•
Updated
•
361
•
94
HuggingFaceM4/siglip-so400m-14-364-flash-attn2-navit
Zero-Shot Image Classification
•
Updated
•
22
•
1
HuggingFaceM4/siglip-so400m-14-700-flash-attn2-navit
Zero-Shot Image Classification
•
Updated
•
17
•
2
HuggingFaceM4/siglip-so400m-14-384-flash-attn2-navit
Zero-Shot Image Classification
•
Updated
•
19
•
1
HuggingFaceM4/idefics2-8b-chatty-AWQ
Image-Text-to-Text
•
Updated
•
9
•
5
HuggingFaceM4/idefics2-8b-AWQ
Image-Text-to-Text
•
Updated
•
101
•
26
datasets
78
HuggingFaceM4/Caltech-101
Updated
•
296
•
3
HuggingFaceM4/Docmatix
Viewer
•
Updated
•
2.55M
•
12.8k
•
278
HuggingFaceM4/the_cauldron
Viewer
•
Updated
•
1.88M
•
96.9k
•
449
HuggingFaceM4/FairFace
Viewer
•
Updated
•
195k
•
1.41k
•
14
HuggingFaceM4/MMBench
Viewer
•
Updated
•
11k
•
194
•
3
HuggingFaceM4/WebSight
Viewer
•
Updated
•
2.75M
•
7.08k
•
353
HuggingFaceM4/debug_MMMU_mcq_to_remove
Viewer
•
Updated
•
10.9k
•
82
HuggingFaceM4/debug_MMMU_open_ended_to_remove
Viewer
•
Updated
•
689
•
53
HuggingFaceM4/debug_MathVista_mcq_to_remove
Viewer
•
Updated
•
3.39k
•
33
HuggingFaceM4/debug_MathVista_open_ended_to_remove
Viewer
•
Updated
•
2.75k
•
34