Task
Zero Shot Image Classification
N
visheratin/nllb-clip-large-oc
Zero Shot Image Classification·visheratin· 25.8K· 2
open_clip
cc-by-nc-4.0
Zero Shot Image Classification
dataset:visheratin/laion-coco-nllbarxiv:2309.01859license:cc-by-nc-4.0region:us
NLLB-CLIP is a model that combines a text encoder from the NLLB model and an image encoder from the LAION CLIP. This allows us to extend the model capabilities to 201 languages of the Flores-200. NLLB-CLIP sets state-of-the-art on the Crossmodal-3600 dataset by performing very well on low-resource languages. You can find more details about the model in the paper.
# pull & run locally
pip install mlforge-sdk && mlforge pull visheratin/nllb-clip-large-oc
pip install mlforge-sdk && mlforge pull visheratin/nllb-clip-large-oc
Model details
Provider
visheratin
Framework
open_clip
Size
5.2 GB
License
cc-by-nc-4.0
Downloads
25.8K
Likes
2
Paper
arXiv:2309.01859
Updated
2023-10-24
About visheratin/nllb-clip-large-oc
NLLB-CLIP is a model that combines a text encoder from the NLLB model and an image encoder from the LAION CLIP. This allows us to extend the model capabilities to 201 languages of the Flores-200. NLLB-CLIP sets state-of-the-art on the Crossmodal-3600 dataset by performing very well on low-resource languages. You can find more details about the model in the paper.