Update README.md

README.md

@@ -797,9 +797,9 @@ 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)