add inference.py

inference.py

@@ -10,7 +10,7 @@ model = AutoModelForCausalLM.from_pretrained(
     device_map="auto",
     dtype=torch.bfloat16
 )
-enizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
 messages = [{"role": "user", "content": "I've been having headaches lately, especially worse in the afternoon. What should I do?"}]
 text = tokenizer.apply_chat_template(
     messages,