Update README.md

README.md

@@ -7,16 +7,17 @@ It is simply a base model in which the embeddings and tokenizer were patched wit
 
 
 
-I used this repo to identify missing Cantonese characters
-https://github.com/ayaka14732/bert-tokenizer-cantonese
+I used this [repo](https://github.com/ayaka14732/bert-tokenizer-cantonese) to identify missing Cantonese characters
 
-My forked and modified version: https://github.com/jedcheng/bert-tokenizer-cantonese
+[My forked and modified version](https://github.com/jedcheng/bert-tokenizer-cantonese)
 
-After identifying the missing characters, the huggingface library provides very high level API to modify the tokenizer and embeddings. 
+After identifying the missing characters, the Huggingface library provides very high level API to modify the tokenizer and embeddings. 
 
 ```
-Download your model from the Huggingface library 
+Download a tokenizer and a model from the Huggingface library. Then: 
 
 tokenizer.add_tokens("your new tokens")
 model.resize_token_embeddings(len(tokenizer))
+
+tokenizer.push_to_hub("your model name")
 ```