Downloads · 30 days
8
7% of all-time downloads
DFN5B-CLIP-ViT-H-14-378-SAFETENSORS
exdysa/DFN5B-CLIP-ViT-H-14-378-SAFETENSORS
DFN5B-CLIP-ViT-H-14-378-SAFETENSORS is a zero-shot image classification model from exdysa. Use it for the zero-shot image classification task on the model card, and read the license before you ship it in a product. The card lists the license as apple-amlr.
[!IMPORTANT] Original Model Link : https://huggingface.co/apple/DFN5B-CLIP-ViT-H-14-378
All-time downloads
114
Public
Parameters
987M
15.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.9 GB · 100%
Parameter types
How the weights are stored.
F32987M · 100%
Base models
Datasets
Model card
From the Hugging Face model README
[!IMPORTANT] Original Model Link : https://huggingface.co/apple/DFN5B-CLIP-ViT-H-14-378
name: DFN5B-CLIP-ViT-H-14-378-SAFETENSORS
base_model: laion/CLIP-ViT-H-14-laion2B-s32B-b79K
license: apple-amlr
pipeline_tag: zero-shot-image-classification
tags:
- clip
- Apple
- OpenAI
size:
- 3946981876
- 3.95 GB
tasks:
- contrastive image-text
- vision
language: en
papers:
- https://arxiv.org/abs/2309.17425
datasets:
- CommonPool-12.8B
license_link: LICENS
DFN5B-CLIP-ViT-H-14-378-SAFETENSORS
CLIP ViT-H/14 trained on DFN-5B Data Filtering Network filtered from a 43B uncurated pool from CommonPool-12.8B + 30B public images.
- Task
- Zero-Shot Image Classification
- Type
- clip
- License
- apple-amlr
- Languages
- en
- Created
- Aug 10, 2025
- Updated
- Aug 10, 2025