Downloads · 30 days
17
13% of all-time downloads
DFN-public-SAFETENSORS
exdysa/DFN-public-SAFETENSORS
DFN-public-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/DFN-public
All-time downloads
130
Public
Parameters
151M
1.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors605 MB · 99%
Parameter types
How the weights are stored.
F32151M · 100%
Base models
Datasets
Model card
From the Hugging Face model README
[!IMPORTANT] Original Model Link : https://huggingface.co/apple/DFN-public
name: DFN-public-SAFETENSORS
base_model: openai/clip-vit-base-patch32
license: apple-amlr
pipeline_tag: zero-shot-image-classification
tags:
- clip
- Apple
- OpenAI
size:
- 605159932
- 605MB
tasks:
- contrastive image-text
- vision
language: en
papers:
- https://arxiv.org/abs/2309.17425
datasets:
- Conceptual Captions 12M
- Conceptual Captions 3M
- Shutterstock 15M.
license_link: LICENSE
DFN-public-SAFETENSORS
A Drop-in replacement for OpenCLIP trained on Data Filtering Network from CC12M, CC3M, and SS15M
- Task
- Zero-Shot Image Classification
- Type
- clip
- License
- apple-amlr
- Languages
- en
- Created
- Jul 7, 2025
- Updated
- Aug 10, 2025