Update README.md

README.md

@@ -134,15 +134,15 @@ tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 
 model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
         model_basename=model_basename,
+        max_memory={0: '60GiB', 1: '79GiB'} # max_memory is for 2 x 80GB GPUs; adjust if your config is different!
         use_safetensors=True,
         trust_remote_code=False,
-        device="cuda:0",
         use_triton=use_triton,
         quantize_config=None)
 
-prompt = "Translate this to French: AI is the future of computing"
-prompt_template=f'''{prompt}
-Translation:
+prompt = "Write a story about llamas"
+prompt_template=f'''<human>: {prompt}
+<bot>:
 '''
 
 print("\n\n*** Generate:")