Downloads · 30 days
51
1% of all-time downloads
rice-vit-large-patch14-560
DeepGlint-AI/rice-vit-large-patch14-560
rice-vit-large-patch14-560 is a image feature extraction model from DeepGlint-AI. Use it for the image feature extraction task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
[[Github]](https://github.com/deepglint/MVT) [[Paper]](https://arxiv.org/abs/2507.20025)
All-time downloads
5.9K
Public
Parameters
303M
1.2 GB on disk
Likes
11
Public
Repo makeup
Click a slice to open those files.
.safetensors1.2 GB · 100%
At a glance
- Task
- Image Feature Extraction
- License
- mit
- Model type
- mlcd
- Access
- Public
- Created
- May 16, 2025
- Updated
- Jul 29, 2025
- SHA
- 25594cb5
Model card
From the Hugging Face model README
RICE-ViT-L Model Card
Installation
pip install torch transformers
git clone https://github.com/deepglint/unicom
cd unicom/mlcd
Usage
from vit_rope2d_hf import MLCDVisionModel
from transformers import CLIPImageProcessor
from PIL import Image
import requests
import torch
# Load model and processor
model = MLCDVisionModel.from_pretrained("DeepGlint-AI/rice-vit-large-patch14-560")
processor = CLIPImageProcessor.from_pretrained("DeepGlint-AI/rice-vit-large-patch14-560")
# Process single image
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
inputs = processor(images=image, return_tensors="pt")
# Get visual features
with torch.no_grad():
outputs = model(**inputs)
features = outputs.last_hidden_state
print(f"Extracted features shape: {features.shape}")
- Task
- Image Feature Extraction
- Type
- mlcd
- License
- mit
- Created
- May 16, 2025
- Updated
- Jul 29, 2025