Update README.md

README.md

@@ -235,7 +235,7 @@ messages = [
 sampling_params = SamplingParams(max_tokens=128_000)
 
 # note that running this model on GPU requires over 300 GB of GPU RAM
-llm = LLM(model=model_name, tokenizer_mode="mistral", tensor_parallel_size=8, limit_mm_per_prompt={"image": 4})
+llm = LLM(model=model_name, tokenizer_mode="mistral", tensor_parallel_size=8, limit_mm_per_prompt={"image": 4}, max_model_len=32768)
 
 outputs = llm.chat(messages, sampling_params=sampling_params)