Update app.py

app.py

@@ -51,7 +51,7 @@ def generate(
         conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
     conversation.append({"role": "user", "content": message})
 
-    chat = tokenizer.apply_chat_template(conversation, tokenize=False)
+    chat = tokenizer.apply_chat_template([{"role": "user", "content": message}], tokenize=False)
     inputs = tokenizer(chat, return_tensors="pt", add_special_tokens=False).to("cuda")
     if len(inputs) > MAX_INPUT_TOKEN_LENGTH:
         inputs = inputs[-MAX_INPUT_TOKEN_LENGTH:]
@@ -94,21 +94,21 @@ chat_interface = gr.ChatInterface(
             minimum=0.1,
             maximum=4.0,
             step=0.1,
-            value=0.6,
+            value=0.1,
         ),
         gr.Slider(
             label="Top-p (nucleus sampling)",
             minimum=0.05,
             maximum=1.0,
             step=0.05,
-            value=0.9,
+            value=0.05,
         ),
         gr.Slider(
             label="Top-k",
             minimum=1,
             maximum=1000,
             step=1,
-            value=50,
+            value=1000,
         ),
         gr.Slider(
             label="Repetition penalty",