Update app.py

app.py

@@ -86,102 +86,3 @@ def respond(
             # Potential cleanup if required by the library, often not needed explicitly
             pass
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    chatbot=gr.Chatbot(height=500), # Set chatbot height
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly psychotherapy AI capable of thinking.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=2.0, value=0.7, step=0.1, label="Temperature"), # Adjusted max temp based on common usage
-        gr.Slider(
-            minimum=0.05, # Min Top-P often > 0
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-P (nucleus sampling)",
-        ),
-        # Added Top-K slider
-        gr.Slider(
-            minimum=0, # 0 disables Top-K
-            maximum=100, # Common range, adjust if needed
-            value=0, # Default to disabled
-            step=1,
-            label="Top-K (0 = disabled)",
-        ),
-    ],
-     title="PsychoQwen Chat",
-     description=f"Chat with {MODEL_ID}. Adjust generation parameters below.",
-     retry_btn="Retry",
-     undo_btn="Undo",
-     clear_btn="Clear Chat",
-)
-
-
-if __name__ == "__main__":
-    demo.queue().launch(debug=True) # Add queue() for streaming
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("drwlf/PsychoQwen14b")
-
-
-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
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly psychotherapy AI capable of thinking.", 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.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()