Update app.py

app.py

@@ -11,7 +11,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStream
 
 DESCRIPTION = "# Claire Chat"
 
-MAX_MAX_NEW_TOKENS = 2048
+MAX_MAX_NEW_TOKENS = 256
 DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
@@ -25,10 +25,10 @@ def generate(
     message: str,
     chat_history: list[tuple[str, str]],
     system_prompt: str = "",
-    max_new_tokens: int = 1024,
+    max_new_tokens: int = 256,
     temperature: float = 0.7,
     top_p: float = 0.95,
-    top_k: int = 50,
+    top_k: int = 10,
     repetition_penalty: float = 1.0,
 ) -> Iterator[str]:
     conversation = []