Update app.py

app.py

@@ -5,10 +5,10 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 # Set seed for reproducibility
 torch.random.manual_seed(0)
 
-# Load the model and tokenizer
+# Load the model and tokenizer (using CPU)
 model = AutoModelForCausalLM.from_pretrained(
     "microsoft/Phi-3.5-mini-instruct",
-    device_map="cpu",
+    device_map="cpu",  # Use CPU
     torch_dtype="auto",
     trust_remote_code=True,
 )
@@ -19,6 +19,7 @@ pipe = pipeline(
     "text-generation",
     model=model,
     tokenizer=tokenizer,
+    device=-1  # CPU
 )
 
 # System message (invisible to the user)
@@ -49,26 +50,30 @@ with gr.Blocks() as demo:
     
     with gr.Row():
         with gr.Column():
-            chatbox = gr.Chatbot()
-            input_box = gr.Textbox(label="Your Message")
+            chatbox = gr.Chatbot(label="Conversation")
+            input_box = gr.Textbox(label="Your Message", placeholder="Type your message here...")
             submit_btn = gr.Button("Submit")
     
     conversation_state = gr.State([])  # Maintain conversation history
 
+    # Function to update the conversation
     def update_conversation(user_input, history):
         if user_input.strip():
             history.append({"user_input": user_input})
             updated_history = chatbot_response(history)
-            return updated_history, ""
-        return history, ""
+            # Format conversation history for the Chatbot component
+            formatted_conversation = [
+                (msg["user_input"], msg.get("assistant_reply", ""))
+                for msg in updated_history
+            ]
+            return formatted_conversation, updated_history, ""
+        return [], history, ""
 
     submit_btn.click(
         update_conversation,
         inputs=[input_box, conversation_state],
-        outputs=[conversation_state, input_box],
+        outputs=[chatbox, conversation_state, input_box],
     )
-    
-    chatbox.update(chatbot_response(conversation_state))
 
 # Launch the interface
 demo.launch()