Update README.md

README.md

@@ -39,11 +39,23 @@ Many thanks to William Beauchamp from [Chai](https://chai-research.com/) for pro
 * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Redmond-Puffin-13B-GGML)
 * [Original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/NousResearch/Redmond-Puffin-13B)
 
-## Prompt template: Human-Gpt
+## Prompt template: Human-Response
 
 ```
-### human:
-### gpt:
+### human: {prompt}
+
+### response:
+```
+Optional reccomended pre-prompt / system prompt:
+
+```
+### human: Interact in conversation to the best of your ability, please be concise, logical, intelligent and coherent.
+
+### response: Sure! sounds good.
+
+### human: {prompt}
+
+### response:
 ```
 
 ## Provided files
@@ -131,9 +143,13 @@ model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
 """
 
 prompt = "Tell me about AI"
-prompt_template=f'''### human:
-### gpt:
-'''
+prompt_template=f'''### human: Interact in conversation to the best of your ability, please be concise, logical, intelligent and coherent.
+
+### response: Sure! sounds good.
+
+### human: {prompt}
+
+### response:'''
 
 print("\n\n*** Generate:")