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.
Organization Card
About org cards
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 and version 2 Idefics2), datasets used for the training like OBELICS, WebSight or The Cauldron, and interactive tools to visualize the results.
models
32
HuggingFaceM4/Florence-2-DocVQA
Image-Text-to-Text
•
Updated
•
618
•
26
HuggingFaceM4/siglip-so400m-14-700-flash-attn2-navit
Zero-Shot Image Classification
•
Updated
•
4.73k
HuggingFaceM4/idefics2-8b-base
Image-Text-to-Text
•
Updated
•
7.43k
•
25
HuggingFaceM4/idefics2-8b
Image-Text-to-Text
•
Updated
•
261k
•
•
533
HuggingFaceM4/idefics2-8b-chatty
Image-Text-to-Text
•
Updated
•
16.9k
•
•
76
HuggingFaceM4/siglip-so400m-14-384-flash-attn2-navit
Zero-Shot Image Classification
•
Updated
•
22
HuggingFaceM4/idefics2-8b-chatty-AWQ
Image-Text-to-Text
•
Updated
•
1.24k
•
3
HuggingFaceM4/idefics2-8b-AWQ
Image-Text-to-Text
•
Updated
•
810
•
26
HuggingFaceM4/idefics2-8b-base-AWQ
Image-Text-to-Text
•
Updated
•
9
•
5
HuggingFaceM4/Meta-Llama-3-8B-tokenizer-pad-is-eos
Updated
datasets
76
HuggingFaceM4/the_cauldron
Viewer
•
Updated
•
1.88M
•
37.4k
•
260
HuggingFaceM4/FairFace
Viewer
•
Updated
•
195k
•
508
•
7
HuggingFaceM4/MMBench
Viewer
•
Updated
•
11k
•
20
•
1
HuggingFaceM4/WebSight
Viewer
•
Updated
•
2.75M
•
192
•
298
HuggingFaceM4/debug_MMMU_mcq_to_remove
Viewer
•
Updated
•
10.9k
•
4
HuggingFaceM4/debug_MMMU_open_ended_to_remove
Viewer
•
Updated
•
689
•
2
HuggingFaceM4/debug_MathVista_mcq_to_remove
Viewer
•
Updated
•
3.39k
•
3
HuggingFaceM4/debug_MathVista_open_ended_to_remove
Viewer
•
Updated
•
2.75k
•
1
HuggingFaceM4/ChartQA
Viewer
•
Updated
•
32.7k
•
392
•
10
HuggingFaceM4/SEED_Img_Modif
Viewer
•
Updated
•
14.2k
•
3