Update README.md

README.md

@@ -66,7 +66,7 @@ max_model_len, tp_size = 4096, 1
 model_name = "th-nuernberg/DeepHermes-3-Mistral-24B-Preview-FP8-Dynamic"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 llm = LLM(model=model_name, tensor_parallel_size=tp_size, max_model_len=max_model_len, trust_remote_code=True)
-sampling_params = SamplingParams(temperature=0.3, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
+sampling_params = SamplingParams(temperature=0.15, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
 
 messages_list = [
     [{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],