Update code example in readme to use `device` variable instead of hard coded `cuda`

The code example uses device for model creation but then uses a hard coded cuda for inputs. Updated to use device for inputs as well.

README.md

@@ -40,7 +40,7 @@ model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
 messages = [{"role": "user", "content": "List the steps to bake a chocolate cake from scratch."}]
 input_text=tokenizer.apply_chat_template(messages, tokenize=False)
 print(input_text)
-inputs = tokenizer.encode(input_text, return_tensors="pt").to("cuda")
+inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
 outputs = model.generate(inputs, max_new_tokens=100, temperature=0.6, top_p=0.92, do_sample=True)
 print(tokenizer.decode(outputs[0]))
 ```