ai-forever / ru-clip

huggingface.co
Total runs: 0
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: December 24 2021

Introduction of ru-clip

Model Details of ru-clip

Model Card: ruCLIP

Disclaimer: The code for using model you can found here .

Model Details

The ruCLIP model was developed by researchers at SberDevices and Sber AI based on origin OpenAI paper.

Model Type

The model uses a ViT-B/32 Transformer architecture (initialized from OpenAI checkpoint and freezed while training) as an image encoder and uses ruGPT3Small as a text encoder. These encoders are trained to maximize the similarity of (image, text) pairs via a contrastive loss.

Documents

Our habr post .

Usage

Code for using model you can obtain in our repo .

from clip.evaluate.utils import (
    get_text_batch, get_image_batch, get_tokenizer,
    show_test_images, load_weights_only
)
import torch

# Load model and tokenizer
model, args = load_weights_only("ViT-B/32-small")
model = model.cuda().float().eval()
tokenizer = get_tokenizer()
# Load test images and prepare for model
images, texts = show_test_images(args)
input_ids, attention_mask = get_text_batch(["Это " + desc for desc in texts], tokenizer, args)
img_input = get_image_batch(images, args.img_transform, args)
# Call model
with torch.no_grad():
    logits_per_image, logits_per_text = model(
        img_input={"x": img_input},
        text_input={"x": input_ids, "attention_mask": attention_mask}
    )

Performance

We evaluate our model on CIFAR100 and CIFAR10 datasets.

zero-shot classification CIFAR100 top1 accuracy 0.4057; top5 accuracy 0.6975.

zero-shot classification CIFAR10 top1 accuracy 0.7803; top5 accuracy 0.9834.

Runs of ai-forever ru-clip on huggingface.co

0
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About ru-clip huggingface.co Model

ru-clip huggingface.co

ru-clip huggingface.co is an AI model on huggingface.co that provides ru-clip's model effect (), which can be used instantly with this ai-forever ru-clip model. huggingface.co supports a free trial of the ru-clip model, and also provides paid use of the ru-clip. Support call ru-clip model through api, including Node.js, Python, http.

ai-forever ru-clip online free

ru-clip huggingface.co is an online trial and call api platform, which integrates ru-clip's modeling effects, including api services, and provides a free online trial of ru-clip, you can try ru-clip online for free by clicking the link below.

ai-forever ru-clip online free url in huggingface.co:

https://huggingface.co/ai-forever/ru-clip

ru-clip install

ru-clip is an open source model from GitHub that offers a free installation service, and any user can find ru-clip on GitHub to install. At the same time, huggingface.co provides the effect of ru-clip install, users can directly use ru-clip installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

ru-clip install url in huggingface.co:

https://huggingface.co/ai-forever/ru-clip

Url of ru-clip

Provider of ru-clip huggingface.co

ai-forever
ORGANIZATIONS

Other API from ai-forever

huggingface.co

Total runs: 525.5K
Run Growth: 507.4K
Growth Rate: 96.56%
Updated: November 03 2023
huggingface.co

Total runs: 10.6K
Run Growth: 1.5K
Growth Rate: 13.75%
Updated: December 05 2023
huggingface.co

Total runs: 8.2K
Run Growth: 5.1K
Growth Rate: 59.45%
Updated: December 29 2024
huggingface.co

Total runs: 5.9K
Run Growth: 3.5K
Growth Rate: 60.26%
Updated: December 11 2023
huggingface.co

Total runs: 2.3K
Run Growth: -408
Growth Rate: -17.86%
Updated: December 05 2023
huggingface.co

Total runs: 1.3K
Run Growth: -6.3K
Growth Rate: -493.39%
Updated: December 05 2023
huggingface.co

Total runs: 315
Run Growth: 165
Growth Rate: 52.05%
Updated: January 26 2023
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated: June 08 2023
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated: September 21 2021