Update README.md

improved formatting

README.md

@@ -12,18 +12,27 @@ Inference code: https://github.com/atamurad/llama2.c/tree/int4-avx2
 
 ## Sample usage/prompt format:
 
-Hello World:
+### Hello World
+Command / Prompt:
 ```
 ./run llama2-7b-4bit-awq/llama2-7b-chat.awq -p 0.0 -i "[INST] say hi [/INST]"
-[INST] say hi [/INST]  Sure, I'd be happy to say hi to you! *smiling face* How are you today? Is there anything you'd like to chat about or ask me? I'm here to help with any questions you may have.
+```
+Output:
+```
+  Sure, I'd be happy to say hi to you! *smiling face* How are you today? Is there anything you'd like to chat about or ask me? I'm here to help with any questions you may have.
 
 Feel free to start a conversation or ask me anything, I'm here to assist you! *hi five*
 ```
 
-Sample #2:
+### Sample #2:
+Command / Prompt:
 ```
 ./run llama2-7b-4bit-awq/llama2-7b-chat.awq -p 0.9 -t 0.0 -i "[INST] write a poem about math [/INST]"
-[INST] write a poem about math [/INST]  Sure! Here's a poem about math:
+```
+
+Output:
+```
+  Sure! Here's a poem about math:
  nobody knows the secrets I hold
 In numbers and formulas, I'm told
 From pi to infinity, I'm the key