Update README.md

README.md

@@ -15,6 +15,8 @@ Github: https://github.com/Neutralzz/BiLLa
 The weight of `word embedding` is the sum of the weights of the trained model and the original LLaMA, 
 so as to ensure that developers with LLaMA original model accessibility can convert the model released by this hub into a usable one.
 
+## Usage
+
 First, you can revert the model weights by [this script](https://github.com/Neutralzz/BiLLa/blob/main/embedding_convert.py):
 ```shell
 python3 embedding_convert.py \
@@ -44,8 +46,11 @@ outputs = tokenizer.decode(output_ids, skip_special_tokens=True).strip()
 print(outputs)
 ```
 
-Different from [BiLLa-7B-LLM](https://huggingface.co/Neutralzz/BiLLa-7B-LLM), the model input of `BiLLa-7B-SFT` should be formatted as follows (note that a space is following the `Assistant:`):
+### Input Format
+Different from [BiLLa-7B-LLM](https://huggingface.co/Neutralzz/BiLLa-7B-LLM), the model input of `BiLLa-7B-SFT` should be formatted as follows:
 ```
 Human: [Your question]
 Assistant: 
 ```
+Note that <b>a space</b> is following the `Assistant:`
+