168
IDEFICS2 Playground
π¨
Idefics2 πΆ
Idefics2-8B is a foundation vision-language model. In this collection, you will find the models, datasets and demo related to its creation.
-
-
HuggingFaceM4/idefics2-8b
Image-Text-to-Text β’ Updated β’ 19.7k β’ β’ 602 -
HuggingFaceM4/idefics2-8b-chatty
Image-Text-to-Text β’ Updated β’ 2.13k β’ β’ 94 -
HuggingFaceM4/idefics2-8b-base
Image-Text-to-Text β’ Updated β’ 1.07k β’ 28 -
HuggingFaceM4/the_cauldron
Viewer β’ Updated β’ 1.88M β’ 578k β’ 379 -
HuggingFaceM4/OBELICS
Viewer β’ Updated β’ 276M β’ 54.6k β’ 152 -
145
Idefics 8b
πGenerate text from images and prompts
-
What matters when building vision-language models?
Paper β’ 2405.02246 β’ Published β’ 102 -
HuggingFaceM4/idefics2-8b-AWQ
Image-Text-to-Text β’ Updated β’ 77 β’ 26 -
HuggingFaceM4/idefics2-8b-chatty-AWQ
Image-Text-to-Text β’ Updated β’ 19 β’ 5 -
HuggingFaceM4/idefics2-8b-base-AWQ
Image-Text-to-Text β’ Updated β’ 16 β’ 5