Change AI response limitations.

main.py

@@ -127,7 +127,7 @@ def generate_completion(
     streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
 
     generation_kwargs = dict(
-        max_new_tokens=512,
+        max_new_tokens=1024,
         repetition_penalty=repetition_penalty,
         length_penalty=length_penalty,
         streamer=streamer,