RICE-ViT-L Model Card
[Github] [Paper]
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}")
