Llm Jp Clip Vit Base Patch16

🚀 llm-jp-clip-vit-base-patch16

A Japanese CLIP model trained on a Japanese translation of the English subset of ReLAION-5B, enabling zero-shot image classification.

🚀 Quick Start

This model is a Japanese CLIP model trained with OpenCLIP on relaion2B-en-research-safe-japanese-translation. It can be used for zero-shot image classification tasks.

✨ Features

• Japanese CLIP: Specifically trained for Japanese language tasks.
• Zero-shot Image Classification: Capable of classifying images without prior training on specific classes.
• Trained on Large-scale Data: Utilizes a large Japanese translation dataset for training.

📦 Installation

$ pip install open_clip_torch

💻 Usage Examples

Basic Usage

import open_clip

model, preprocess = open_clip.create_model_from_pretrained('hf-hub:llm-jp/llm-jp-clip-vit-base-patch16')
tokenizer = open_clip.get_tokenizer('hf-hub:llm-jp/llm-jp-clip-vit-base-patch16')

import torch
from PIL import Image
import requests

url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)
image = preprocess(image).unsqueeze(0)
text = tokenizer(["猫", "犬", "鳥"])

with torch.no_grad(), torch.cuda.amp.autocast():
    image_features = model.encode_image(image)
    text_features = model.encode_text(text)
    image_features /= image_features.norm(dim=-1, keepdim=True)
    text_features /= text_features.norm(dim=-1, keepdim=True)

    text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)

print("Label probs:", text_probs)
# Label probs: tensor([[9.9425e-01, 5.2273e-03, 5.2600e-04]])

Reference

• Using OpenCLIP at Hugging Face, HuggingFace Docs
• OpenCLIP repository

📚 Documentation

Model Details

A Japanese CLIP model trained with OpenCLIP on relaion2B-en-research-safe-japanese-translation, a Japanese translation of the English subset of ReLAION-5B (https://huggingface.co/datasets/laion/relaion2B-en-research-safe), translated by gemma-2-9b-it.

The total number of parameters of this model is 248M.

Training Details

Model Architecture

Training Data

This model is trained on relaion2B-en-research-safe-japanese-translation. Due to a 70% success rate in image downloads, the dataset size was 1.45 billion samples, and we processed it over 9 epochs (13 billion samples in total).

Evaluation

Evaluation Code: https://github.com/llm-jp/clip-eval

Table: Performance of each model in zero-shot image classification and image-text retrieval tasks. Bold indicates first place, and underline indicates second place.

📄 License

The Apache License, Version 2.0

Please refer to the Gemma Terms of Use, as the training data was translated using gemma-2-9b-it. We utilizes Gemma solely for translation purposes. According to the definition of "Model Derivatives" in Section 1.1(e), our model does not fall under the category of a "model in order to cause that model to perform similarly to Gemma." Therefore, we have concluded that it is not necessary to inherit the Gemma license.

📚 Citation

@inproceedings{sugiura-etal-2025-developing,
    title = "Developing {J}apanese {CLIP} Models Leveraging an Open-weight {LLM} for Large-scale Dataset Translation",
    author = "Sugiura, Issa  and
      Kurita, Shuhei  and
      Oda, Yusuke  and
      Kawahara, Daisuke  and
      Okazaki, Naoaki",
    editor = "Ebrahimi, Abteen  and
      Haider, Samar  and
      Liu, Emmy  and
      Haider, Sammar  and
      Leonor Pacheco, Maria  and
      Wein, Shira",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
    month = apr,
    year = "2025",
    address = "Albuquerque, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.naacl-srw.15/",
    pages = "162--170",
    ISBN = "979-8-89176-192-6",
    abstract = "CLIP is a foundational model that bridges images and text, widely adopted as a key component in numerous vision-language models.However, the lack of large-scale open Japanese image-text pairs poses a significant barrier to the development of Japanese vision-language models.In this study, we constructed a Japanese image-text pair dataset with 1.5 billion examples using machine translation with open-weight LLMs and pre-trained Japanese CLIP models on the dataset.The performance of the pre-trained models was evaluated across seven benchmark datasets, achieving competitive average scores compared to models of similar size without the need for extensive data curation. However, the results also revealed relatively low performance on tasks specific to Japanese culture, highlighting the limitations of translation-based approaches in capturing cultural nuances. Our dataset, models, and code are publicly available."
}