Update README.md

README.md

@@ -37,14 +37,14 @@ model = AutoModelForCausalLM.from_pretrained(
     MODEL,
     torch_dtype=torch.float16,
     low_cpu_mem_usage=True,
-).to(device=7, non_blocking=True)
+).to(device=f"cuda", non_blocking=True)
 model.eval()
 
 pipe = pipeline(
     'text-generation', 
     model=model,
     tokenizer=MODEL,
-    device=7
+    device=0
 )
 pipe.model.config.pad_token_id = pipe.model.config.eos_token_id