Initial GPTQ model commit

README.md

@@ -44,10 +44,10 @@ Multiple GPTQ parameter permutations are provided; see Provided Files below for
 * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/OpenOrcaxOpenChat-Preview2-13B-GGML)
 * [Open-Orca's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Open-Orca/OpenOrcaxOpenChat-Preview2-13B)
 
-## Prompt template: TBC
+## Prompt template: OpenChat Llama2 V1
 
 ```
-Info on prompt template will be added shortly.
+User: {prompt}<|end_of_turn|>Assistant:
 ```
 
 ## Provided files
@@ -141,7 +141,7 @@ model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
 """
 
 prompt = "Tell me about AI"
-prompt_template=f'''Info on prompt template will be added shortly.
+prompt_template=f'''User: {prompt}<|end_of_turn|>Assistant:
 '''
 
 print("\n\n*** Generate:")