Add model

README.md

@@ -1,3 +1,55 @@
 ---
-license: mit
+language: ja
+thumbnail: https://github.com/rinnakk/japanese-pretrained-models/blob/master/rinna.png
+tags:
+- ja
+- japanese
+- clip
+- vision
 ---
+
+# rinna/japanese-clip-vit-b-16
+
+![rinna-icon](./rinna.png)
+
+This repository provides a Japanese [CLIP (Contrastive Language-Image Pre-Training)](https://arxiv.org/abs/2103.00020) model. The model was trained by [rinna Co., Ltd.](https://corp.rinna.co.jp/)
+
+# How to use the model
+
+
+1. Install package
+```shell
+$ pip install git+https://github.com/rinnakk/japanese-clip.git
+```
+2. Run
+```python
+import io
+import requests
+from PIL import Image
+import torch
+import japanese_clip as ja_clip
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+
+model, preprocess = ja_clip.load("rinna/japanese-clip-vit-b-16", cache_dir="/tmp/japanese_clip", device=device)
+tokenizer = ja_clip.load_tokenizer()
+
+img = Image.open(io.BytesIO(requests.get('https://images.pexels.com/photos/2253275/pexels-photo-2253275.jpeg?auto=compress&cs=tinysrgb&dpr=3&h=750&w=1260').content))
+image = preprocess(img).unsqueeze(0).to(device)
+encodings = ja_clip.tokenize(
+    texts=["犬", "猫", "象"],
+    max_seq_len=77,
+    device=device,
+    tokenizer=tokenizer, # this is optional. if you don't pass, load tokenizer each time
+)
+
+with torch.no_grad():
+    image_features = model.get_image_features(image)
+    text_features = model.get_text_features(**encodings)
+    
+    text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)
+
+print("Label probs:", text_probs)  # prints: [[1.0, 0.0, 0.0]]
+```
+

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd64ced7aa6d861b7a47fe5c96140b41abf81db484759485fd91e949278dc139
+size 786624867