Update README.md

README.md

@@ -41,7 +41,7 @@ GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/gger
 * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/orca_mini_3B-GGML)
 * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/psmathur/orca_mini_3b)
 
-## Prompt template: Alpaca with system message
+## Prompt template:
 
 ```
 ### System:
@@ -50,7 +50,7 @@ You are an AI assistant that follows instruction extremely well. Help as much as
 ### User:
 prompt
 
-### Response
+### Response:
 ```
 or
 ```
@@ -60,10 +60,10 @@ You are an AI assistant that follows instruction extremely well. Help as much as
 ### User:
 prompt
 
-### Input
+### Input:
 input
 
-### Response
+### Response:
 ```
 
 <!-- compatibility_ggml start -->