fix: the maximum number of tokens

app.py

@@ -31,7 +31,7 @@ def format_prompt(message, history, system_prompt):
     prompt += f"System: {system_prompt}\n"
   for user_prompt, bot_response in history:
     prompt += f"User: {user_prompt}\n"
-    prompt += f"Falcon: {bot_response}\n" # Response already contains "Falcon: "
+    prompt += f"PersianGPT: {bot_response}\n" # Response already contains "PersianGPT: "
   prompt += f"""User: {message}
 Falcon:"""
   return prompt
@@ -39,7 +39,7 @@ Falcon:"""
 seed = 42
 
 def generate(
-    prompt, history, system_prompt="<|endoftext|>", temperature=0.9, max_new_tokens=250, top_p=0.95, repetition_penalty=1.0,
+    prompt, history, system_prompt="<|endoftext|>", temperature=0.9, max_new_tokens=100, top_p=0.95, repetition_penalty=1.0,
 ):
     temperature = float(temperature)
     if temperature < 1e-2:
@@ -86,9 +86,9 @@ additional_inputs=[
     ),
     gr.Slider(
         label="Max new tokens",
-        value=256,
+        value=100,
         minimum=0,
-        maximum=8192,
+        maximum=250,
         step=64,
         interactive=True,
         info="The maximum numbers of new tokens",