Update app.py

app.py

@@ -5,7 +5,7 @@ from huggingface_hub import InferenceClient
 
 # --- Configuration Constants ---
 # Define the maximum number of tokens the model should generate in a single response
-FIXED_MAX_TOKENS = 99999 # Note: This is a very high value, typical values are much lower (e.g., 512, 1024, 2048, 4096 for many models)
+FIXED_MAX_TOKENS = 1000 # Note: This is a very high value, typical values are much lower (e.g., 512, 1024, 2048, 4096 for many models)
 
 
 # --- Initialize the InferenceClient ---