Update app.py

app.py

@@ -36,15 +36,15 @@ def generate(
     max_new_tokens: int = 1024,
     temperature: float = 0.6,
     top_p: float = 0.9,
-    top_k: int = 50,
-    repetition_penalty: float = 1.2,
 ) -> Iterator[str]:
     
     conversation = []
     if system_prompt:
         conversation.append({"role": "system", "content": system_prompt})
+        
     for user, assistant in chat_history:
         conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
+        
     conversation.append({"role": "user", "content": message})
 
     input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
@@ -60,10 +60,7 @@ def generate(
         max_new_tokens=max_new_tokens,
         do_sample=True,
         top_p=top_p,
-        top_k=top_k,
         temperature=temperature,
-        num_beams=1,
-        repetition_penalty=repetition_penalty,
     )
     t = Thread(target=model.generate, kwargs=generate_kwargs)
     t.start()
@@ -114,9 +111,9 @@ def respond(
 chat_interface = gr.ChatInterface(
     fn=generate,
     additional_inputs=[
-        gr.Textbox(value="Ets un chatbot amigable.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Textbox(value="Ets un chatbot amigable. Responeu preguntes i ajudeu els usuaris", label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=1024, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.6, step=0.1, label="Temperature"),
         gr.Slider(
             minimum=0.1,
             maximum=1.0,
@@ -125,12 +122,17 @@ chat_interface = gr.ChatInterface(
             label="Top-p (nucleus sampling)",
         ),
     ],
+    examples=[
+        ["A quina velocitat poden volar els cocodrils?"],
+        ["Explica pas a pas com resoldre l'equació següent: 2x + 10 = 0"],
+        ["Pot Donald Trump sopar amb Juli Cèsar?"],
+    ],
 )
 
-with gr.Blocks() as demo:
+with gr.Blocks(css="style.css") as demo:
     gr.Markdown(DESCRIPTION)
     chat_interface.render()
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.queue(max_size=20).launch()