Update README.md

README.md

@@ -38,7 +38,9 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 
 model = GPTQModel.from_quantized(model_name)
 
-inputs = tokenizer.apply_chat_template(prompt, tokenize=False, add_generation_prompt=True)
-outputs = model.generate(prompts=inputs, temperature=0.95, max_length=128)
-print(outputs[0].outputs[0].text)
+input_tensor = tokenizer.apply_chat_template(prompt, add_generation_prompt=True, return_tensors="pt")
+outputs = model.generate(input_ids=input_tensor.to(model.device), max_new_tokens=100)
+result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=True)
+
+print(result)
 ```