Edit model card

clip-vit-large-patch14-ko

Korean CLIP model trained by Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation

Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation로 학습된 한국어 CLIP 모델입니다.

훈련 코드: https://github.com/Bing-su/KoCLIP_training_code

사용된 데이터: AIHUB에 있는 모든 한국어-영어 병렬 데이터

How to Use

1.

import requests
import torch
from PIL import Image
from transformers import AutoModel, AutoProcessor

repo = "Bingsu/clip-vit-large-patch14-ko"
model = AutoModel.from_pretrained(repo)
processor = AutoProcessor.from_pretrained(repo)

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
inputs = processor(text=["고양이 두 마리", "개 두 마리"], images=image, return_tensors="pt", padding=True)
with torch.inference_mode():
    outputs = model(**inputs)
logits_per_image = outputs.logits_per_image
probs = logits_per_image.softmax(dim=1)
>>> probs
tensor([[0.9974, 0.0026]])

2.

from transformers import pipeline

repo = "Bingsu/clip-vit-large-patch14-ko"
pipe = pipeline("zero-shot-image-classification", model=repo)

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
result = pipe(images=url, candidate_labels=["고양이 한 마리", "고양이 두 마리", "분홍색 소파에 드러누운 고양이 친구들"], hypothesis_template="{}")
>>> result
[{'score': 0.9907576441764832, 'label': '분홍색 소파에 드러누운 고양이 친구들'},
 {'score': 0.009206341579556465, 'label': '고양이 두 마리'},
 {'score': 3.606083555496298e-05, 'label': '고양이 한 마리'}]
Downloads last month
199
Safetensors
Model size
428M params
Tensor type
F32
·
I64
·
Hosted inference API
This model can be loaded on the Inference API on-demand.