Downloads · 30 days
18
9% of all-time downloads
cat2vec-v2
aeth0r/cat2vec-v2
cat2vec-v2 is a image feature extraction model from aeth0r. Use it for the image feature extraction task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as gpl-3.0.
The cat2vec model is a search model for cats.
All-time downloads
197
Public
Parameters
22.1M
88.2 MB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors88.2 MB · 100%
At a glance
- Task
- Image Feature Extraction
- Library
- transformers
- License
- gpl-3.0
- Model type
- dinov2
- Access
- Public
- Created
- Oct 27, 2025
- Updated
- Oct 27, 2025
- SHA
- 5808501f
Base models
Model card
From the Hugging Face model README
cat2vec
The cat2vec model is a search model for cats.
It was trained using the Labeled Cats In The Wild dataset and a triplet loss.
Usage
from transformers import AutoImageProcessor, ResNetModel
import torch
from datasets import load_dataset
dataset = load_dataset("huggingface/cats-image")
image = dataset["test"]["image"][:2]
processor = AutoImageProcessor.from_pretrained("facebook/dinov2-small")
model = ResNetModel.from_pretrained("aeth0r/cat2vec-v2")
inputs = processor(image, return_tensors="pt")
with torch.no_grad():
features = model(**inputs)
print(features)
- Task
- Image Feature Extraction
- Library
- transformers
- Type
- dinov2
- License
- gpl-3.0
- Created
- Oct 27, 2025
- Updated
- Oct 27, 2025