Delete app.py

app.py

@@ -1,88 +0,0 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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
-"""
-
-# Load the inference client
-client = InferenceClient("Futuresony/future_ai_12_10_2024.gguf")
-
-# Function to handle the chat interaction
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    # Prepare the system message and chat history
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:  # User's message
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:  # Assistant's response
-            messages.append({"role": "assistant", "content": val[1]})
-
-    # Add the new user message
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    # Use `stream=True` to receive token-by-token responses
-    for message in client.chat_completion(
-        messages=messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-        use_cache=True,  # Enable caching for efficiency
-    ):
-        # Append the content of the generated token
-        token = message.choices[0].delta.content
-        response += token
-        yield response  # Stream the response incrementally to the interface
-
-
-"""
-Customize the ChatInterface using Gradio. For details, check Gradio's documentation:
-https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    fn=respond,  # Function to handle the chat
-    additional_inputs=[
-        gr.Textbox(
-            value="You are a friendly and helpful assistant.",
-            label="System message",
-        ),  # Default system message
-        gr.Slider(
-            minimum=1,
-            maximum=2048,
-            value=512,
-            step=1,
-            label="Max new tokens",
-        ),  # Slider to control max token limit
-        gr.Slider(
-            minimum=0.1,
-            maximum=2.0,
-            value=0.7,
-            step=0.1,
-            label="Temperature",
-        ),  # Slider to adjust temperature
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.9,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),  # Slider to adjust top-p
-    ],
-    title="AI Chatbot Interface",
-    description="Interact with the AI model using this chat interface. Adjust generation parameters for better control.",
-)
-
-# Launch the Gradio interface
-if __name__ == "__main__":
-    demo.launch()