Downloads · 30 days
6
4% of all-time downloads
DFN2B-CLIP-ViT-L-14-39B-SAFETENSORS
exdysa/DFN2B-CLIP-ViT-L-14-39B-SAFETENSORS
DFN2B-CLIP-ViT-L-14-39B-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/DFN2B-CLIP-ViT-L-14-39B
All-time downloads
142
Public
Parameters
428M
6.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.4 GB · 100%
Parameter types
How the weights are stored.
F32428M · 100%
Base models
Datasets
Model card
From the Hugging Face model README
[!IMPORTANT] Original Model Link : https://huggingface.co/apple/DFN2B-CLIP-ViT-L-14-39B
name: DFN2B-CLIP-ViT-L-14-39B-SAFETENSORS
base_model: openai/clip-vit-large-patch14
license: apple-amlr
pipeline_tag: zero-shot-image-classification
tags:
- clip
- Apple
- OpenAI
size:
- 1710540580
- 1.7 GB
tasks:
- contrastive image-text
- vision
language: en
papers:
- https://arxiv.org/abs/2309.17425
datasets:
- CommonPool-12.8B
license_link: LICENSE
DFN2B-CLIP-ViT-L-14-39B-SAFETENSORS
A Drop-in replacement for OpenCLIP trained on DFN-2b Data Filtering Network derived from 12.8 uncurated image-text pairs from CommonPool-12.8B
- Task
- Zero-Shot Image Classification
- Type
- clip
- License
- apple-amlr
- Languages
- en
- Created
- Jul 7, 2025
- Updated
- Aug 10, 2025