Update app.py

app.py

@@ -15,7 +15,7 @@ def format_prompt(message, history):
   return prompt
 
 def generate(
-    prompt, history, temperature=0.9, max_length=2000, top_p=0.95, repetition_penalty=1.0,
+    prompt, history, temperature=0.9, max_new_tokens=1000, top_p=0.95, repetition_penalty=1.0,
 ):
     temperature = float(temperature)
     if temperature < 1e-2:
@@ -24,7 +24,7 @@ def generate(
 
     generate_kwargs = dict(
         temperature=temperature,
-        max_length=max_length,
+        max_new_tokens=max_new_tokens,
         top_p=top_p,
         repetition_penalty=repetition_penalty,
         do_sample=True,
@@ -53,13 +53,13 @@ additional_inputs=[
         info="Higher values produce more diverse outputs",
     ),
     gr.Slider(
-        label="Maximum Length",
-        value=2000,
+        label="Max new tokens",
+        value=1000,
         minimum=0,
         maximum=1048,
         step=64,
         interactive=True,
-        info="The maximum numbers of total tokens",
+        info="The maximum numbers of new tokens",
     ),
     gr.Slider(
         label="Top-p (nucleus sampling)",