Update README.md

README.md

@@ -37,6 +37,14 @@ Please note this is an experimental GPTQ model. Support for it is currently quit
 
 It is also expected to be **SLOW**. This is currently unavoidable, but is being looked at.
 
+## Prompt template
+
+```
+A helpful assistant who helps the user with any questions asked.
+User: prompt
+Assistant:
+```
+
 ## AutoGPTQ
 
 AutoGPTQ is required: `pip install auto-gptq`
@@ -113,8 +121,9 @@ model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
         quantize_config=None)
 
 prompt = "Tell me about AI"
-prompt_template=f'''### Human: {prompt}
-### Assistant:'''
+prompt_template=f'''A helpful assistant who helps the user with any questions asked.
+User: {prompt}
+Assistant:''
 
 print("\n\n*** Generate:")