minor fix on config.json

README.md

@@ -1,7 +1,9 @@
 ---
 language: ja
 thumbnail: https://github.com/rinnakk/japanese-pretrained-models/blob/master/rinna.png
+license: apache-2.0
 tags:
+- feature-extraction
 - ja
 - japanese
 - clip
@@ -12,16 +14,22 @@ tags:
 
 ![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/)
+This is a Japanese [CLIP (Contrastive Language-Image Pre-Training)](https://arxiv.org/abs/2103.00020) model trained by [rinna Co., Ltd.](https://corp.rinna.co.jp/).
+
+Please see [japanese-clip](https://github.com/rinnakk/japanese-clip) for the other available models.
+
 
 # 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
@@ -53,3 +61,13 @@ with torch.no_grad():
 print("Label probs:", text_probs)  # prints: [[1.0, 0.0, 0.0]]
 ```
 
+# Model architecture
+The model was trained  a ViT-B/16 Transformer architecture as an image encoder and uses a 12-layer BERT as a text encoder. The image encoder was initialized from the [AugReg `vit-base-patch16-224` model](https://github.com/google-research/vision_transformer).
+
+# Training
+The model was trained on [CC12M](https://github.com/google-research-datasets/conceptual-12m) translated the captions to Japanese.
+
+
+# License
+
+[The Apache 2.0 license](https://www.apache.org/licenses/LICENSE-2.0)