Update README.md

README.md

@@ -22,7 +22,7 @@ The model is tuned after 4 iterations of online alignment. In each iteration, we
 
 - Step 3: Apply CUT to fine-tune the target model with the above instruction-response-judgment triplets.
 
-We use [LLaMA2-chat-13b](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) as the base LLM. In each iteration, we sample 1000 instructions from [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca).
+Specifically, we use [LLaMA2-chat-13b](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) as the base LLM. In each iteration, we sample 1000 instructions from [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca).
 To avoid over-fitting, we ensure that the sampled data are different in each iteration.
 We then ask GPT4 for the judgment annotation.
 
@@ -40,7 +40,7 @@ Below is an instruction that describes a task. Write a response that appropriate
 
 ### 3. How to use
 
-#### 1. Huggingface
+#### 3.1. Huggingface
 
 ```python
 import torch
@@ -63,7 +63,7 @@ text = tokenizer.batch_decode(outputs)[0]
 print(text)
 ```
 
-#### 2. FastChat
+#### 3.2. FastChat
 
 [Fastchat](https://github.com/lm-sys/FastChat) provides a simple setup for those interested in trying our aligned model. After downloading the [CUT model](https://huggingface.co/xww033/cut-13b) through HuggingFace, clone the Fastchat repository: