Update app.py

app.py

@@ -4,9 +4,11 @@ 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
 """
-client = InferenceClient("Futuresony/future_ai_12_10_2024.gguf")
 
+# 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]],
@@ -14,72 +16,73 @@ def respond(
     max_tokens,
     temperature,
     top_p,
-    top_k=50,  # Added top_k for fine control over generation
-    repetition_penalty=1.2,  # Added to penalize repetitive patterns
 ):
+    # Prepare the system message and chat history
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
-        if val[0]:
+        if val[0]:  # User's message
             messages.append({"role": "user", "content": val[0]})
-        if val[1]:
+        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 = ""
 
-    # Streaming response with additional settings
+    # Use `stream=True` to receive token-by-token responses
     for message in client.chat_completion(
-        messages,
+        messages=messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
-        top_k=top_k,  # Added top_k
-        repetition_penalty=repetition_penalty,  # Added repetition_penalty
-        use_cache=True,  # Enables caching for efficiency
+        use_cache=True,  # Enable caching for efficiency
     ):
+        # Append the content of the generated token
         token = message.choices[0].delta.content
-
         response += token
-        yield response
+        yield response  # Stream the response incrementally to the interface
 
 
 """
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+Customize the ChatInterface using Gradio. For details, check Gradio's documentation:
+https://www.gradio.app/docs/chatinterface
 """
 demo = gr.ChatInterface(
-    respond,
+    fn=respond,  # Function to handle the chat
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", 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)",
-        ),
+        gr.Textbox(
+            value="You are a friendly and helpful assistant.",
+            label="System message",
+        ),  # Default system message
         gr.Slider(
-            minimum=10,
-            maximum=100,
-            value=50,
+            minimum=1,
+            maximum=2048,
+            value=512,
             step=1,
-            label="Top-k (sampling control)",  # New input for top-k
-        ),
+            label="Max new tokens",
+        ),  # Slider to control max token limit
         gr.Slider(
-            minimum=1.0,
+            minimum=0.1,
             maximum=2.0,
-            value=1.2,
+            value=0.7,
             step=0.1,
-            label="Repetition Penalty",  # New input for repetition_penalty
-        ),
+            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()
-