Update README.md

README.md

@@ -75,7 +75,7 @@ llm = Llama.from_pretrained(
 chat_history = [
     {"role": "system", "content": """
 You are a helpful assistant named Llama, made by Meta AI.
-Always use your <|reasoning|> <|end_reasoning|> tokens, without any text formatting, plain text only.
+Always use your <|reasoning|> and <|end_reasoning|> tokens, without any text formatting, plain text only.
     """}
 ]
 
@@ -93,7 +93,7 @@ while True:
     # Call the chat completion API in streaming mode with the updated conversation.
     output_stream = llm.create_chat_completion(
         messages=chat_history,
-        temperature=0.7,
+        temperature=0.4,
         top_p=0.95,
         max_tokens=4096,
         stream=True