Update README.md

README.md

@@ -75,25 +75,27 @@ This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/
 
 ```python
 from vllm import LLM, SamplingParams
-from transformers import AutoTokenizer
+from transformers import AutoProcessor
 
-model_id = "RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16"
+model_id = "RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-FP8-dynamic"
 number_gpus = 1
 
 sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)
+processor = AutoProcessor.from_pretrained(model_id)
 
-tokenizer = AutoTokenizer.from_pretrained(model_id)
+messages = [{"role": "user", "content": "Give me a short introduction to large language model."}]
 
-prompt = "Give me a short introduction to large language model."
+prompts = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
 
 llm = LLM(model=model_id, tensor_parallel_size=number_gpus)
 
-outputs = llm.generate(prompt, sampling_params)
+outputs = llm.generate(prompts, sampling_params)
 
 generated_text = outputs[0].outputs[0].text
 print(generated_text)
 ```
 
+
 vLLM aslo supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.
 
 ## Creation