Update app.py

app.py

@@ -71,42 +71,6 @@ def generate(
         yield "".join(outputs)
 
 
-"""
-client = InferenceClient("catallama/CataLlama-v0.1-Instruct-DPO")
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-"""
-
 
 chat_interface = gr.ChatInterface(
     fn=generate,
@@ -117,7 +81,7 @@ chat_interface = gr.ChatInterface(
         gr.Slider(
             minimum=0.1,
             maximum=1.0,
-            value=0.95,
+            value=0.90,
             step=0.05,
             label="Top-p (nucleus sampling)",
         ),