Update README.md

README.md

@@ -85,6 +85,10 @@ model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
         use_triton=use_triton,
         quantize_config=None)
 
+prompt = "Tell me about AI"
+prompt_template=f'''### Instruction: {prompt}
+### Response:'''
+
 print("\n\n*** Generate:")
 
 input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
@@ -96,10 +100,6 @@ print(tokenizer.decode(output[0]))
 # Prevent printing spurious transformers error when using pipeline with AutoGPTQ
 logging.set_verbosity(logging.CRITICAL)
 
-prompt = "Tell me about AI"
-prompt_template=f'''### Human: {prompt}
-### Assistant:'''
-
 print("*** Pipeline:")
 pipe = pipeline(
     "text-generation",