Update README.md

README.md

@@ -14,7 +14,7 @@ widget:
 ---
 
 ### Model description
-This model was trained on ZH, JA, KO's Wikipedia (5 epochs).
+- This model was trained on **ZH, JA, KO**'s Wikipedia (5 epochs).
 
 ### How to use
 ```python
@@ -22,7 +22,8 @@ from transformers import AutoTokenizer, AutoModelForMaskedLM
 tokenizer = AutoTokenizer.from_pretrained("conan1024hao/cjkbert-small")
 model = AutoModelForMaskedLM.from_pretrained("conan1024hao/cjkbert-small")
 ```
-Before you fine-tune downstream tasks, you don't need any text segmentation. (Though you may obtain better results if you applied morphological analysis to the data before fine-tuning.)
+- Before you fine-tune downstream tasks, you don't need any text segmentation.
+- (Though you may obtain better results if you applied morphological analysis to the data before fine-tuning.)
 
 ### Morphological analysis tools
 - ZH: For Chinese, we use [LTP](https://github.com/HIT-SCIR/ltp).
@@ -30,7 +31,7 @@ Before you fine-tune downstream tasks, you don't need any text segmentation. (Th
 - KO: For Korean, we use [KoNLPy](https://github.com/konlpy/konlpy)(Kkma class).
 
 ### Tokenization
-We use character-based tokenization with whole-word-masking strategy.
+- We use character-based tokenization with **whole-word-masking** strategy.
 
 ### Model size
 - vocab_size: 15015