Update README.md

README.md

@@ -28,7 +28,7 @@ You can use the raw model for text infilling. However, the model is mostly meant
 
 # How to use the model
 
-*NOTE:* Use `trust_remote_code=True` to initiate the tokenizer.
+*NOTE:* Since we are using a custom tokenizer, please use `trust_remote_code=True` to initialize the tokenizer.
 
 ## Simple use
 
@@ -127,5 +127,10 @@ The model uses a [sentencepiece](https://github.com/google/sentencepiece)-based
 # Licenses
 The pretrained models are distributed under the terms of the [MIT License](https://opensource.org/licenses/mit-license.php).
 
+*NOTE:*  Only tokenization_bart_japanese_news.py is Apache License, Version 2.0.
+
+# Contact
+If you have any questions, please contact us using [our contact form](https://stockmark.co.jp/contact).
+
 # Acknowledgement
 This comparison study supported with Cloud TPUs from Google’s TensorFlow Research Cloud (TFRC).