Task
Zero Shot Image Classification
V
UCSC-VLAA/ViT-L-14-CLIPA-datacomp1B
Zero Shot Image Classification·UCSC-VLAA· 656· 3
open_clip
apache-2.0
Zero Shot Image Classification
dataset:mlfoundations/datacomp_1barxiv:2306.15658arxiv:2305.07017license:apache-2.0region:us
Model Details - Model Type: Contrastive Image-Text, Zero-Shot Image Classification. - Original: https://github.com/UCSC-VLAA/CLIPA - Dataset: mlfoundations/datacomp1b - Papers: - CLIPA-v2: Scaling CLIP Training with 81.1% Zero-shot ImageNet Accuracy within a $10,000 Budget; An Extra $4,000 Unlocks 81.8% Accuracy: https://arxiv.org/abs/2306.15658 - An Inverse Scaling Law for CLIP Training: http
# pull & run locally
pip install mlforge-sdk && mlforge pull UCSC-VLAA/ViT-L-14-CLIPA-datacomp1B
pip install mlforge-sdk && mlforge pull UCSC-VLAA/ViT-L-14-CLIPA-datacomp1B
Model details
Provider
UCSC-VLAA
Framework
open_clip
Size
3.1 GB
License
apache-2.0
Downloads
656
Likes
3
Paper
arXiv:2306.15658
Updated
2023-10-17
About UCSC-VLAA/ViT-L-14-CLIPA-datacomp1B
Model Details - Model Type: Contrastive Image-Text, Zero-Shot Image Classification. - Original: https://github.com/UCSC-VLAA/CLIPA - Dataset: mlfoundations/datacomp1b - Papers: - CLIPA-v2: Scaling CLIP Training with 81.1% Zero-shot ImageNet Accuracy within a $10,000 Budget; An Extra $4,000 Unlocks 81.8% Accuracy: https://arxiv.org/abs/2306.15658 - An Inverse Scaling Law for CLIP Training: https://arxiv.org/abs/2305.07017