Update app.py

app.py

@@ -15,7 +15,7 @@ def format_prompt(message, history):
   return prompt
 
 def generate(
-    prompt, history, system_prompt, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
+    prompt, history, system_prompt, temperature=0.9, max_new_tokens=4096, top_p=0.95, repetition_penalty=1.0,
 ):
     temperature = float(temperature)
     if temperature < 1e-2:
@@ -24,6 +24,7 @@ def generate(
 
     generate_kwargs = dict(
         temperature=temperature,
+        min_new_tokens=min_new_tokens,
         max_new_tokens=max_new_tokens,
         top_p=top_p,
         repetition_penalty=repetition_penalty,
@@ -56,11 +57,20 @@ additional_inputs=[
         interactive=True,
         info="Higher values produce more diverse outputs",
     ),
+    gr.Slider(
+        label="Min new tokens",
+        value=0,
+        minimum=0,
+        maximum=32000,
+        step=64,
+        interactive=True,
+        info="The minimum numbers of new tokens",
+    ),
     gr.Slider(
         label="Max new tokens",
         value=256,
         minimum=0,
-        maximum=30000,
+        maximum=32000,
         step=64,
         interactive=True,
         info="The maximum numbers of new tokens",