Update app.py

app.py

@@ -1,78 +1,21 @@
 import gradio as gr
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-# Set seed for reproducibility
-torch.random.manual_seed(0)
-
-# Load the model and tokenizer (using Accelerate)
-model = AutoModelForCausalLM.from_pretrained(
-    "microsoft/Phi-3.5-mini-instruct",
-    device_map="auto",  # Managed by Accelerate
-    torch_dtype="auto",
-    trust_remote_code=True,
-)
-tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3.5-mini-instruct")
-
-# Define the pipeline (no device argument)
-pipe = pipeline(
-    "text-generation",
-    model=model,
-    tokenizer=tokenizer,
-)
-
-# System message (invisible to the user)
-SYSTEM_MESSAGE = {"role": "system", "content": "You are a helpful AI assistant."}
-
-# Function to process the user input and generate output
-def chatbot_response(conversation_history):
-    # Build message sequence
-    messages = [SYSTEM_MESSAGE] + [
-        {"role": "user", "content": message["user_input"]} for message in conversation_history
-    ]
-    # Pass messages to the model
-    generation_args = {
-        "max_new_tokens": 500,
-        "return_full_text": False,
-        "temperature": 0.0,
-        "do_sample": False,
-    }
-    output = pipe(messages, **generation_args)
-    assistant_reply = output[0]["generated_text"]
-    # Append assistant's response to history
-    conversation_history[-1]["assistant_reply"] = assistant_reply
-    return conversation_history
-
-# Define Gradio interface
-with gr.Blocks() as demo:
-    gr.Markdown("# AI Chatbot with System Message")
+def custom_model_input(input_text):
+    # First prompt to be used before anything else
+    system_prompt = "you are xylaria 1.4 senoa, developed by sk md saad amin"
     
-    with gr.Row():
-        with gr.Column():
-            chatbox = gr.Chatbot(label="Conversation")
-            input_box = gr.Textbox(label="Your Message", placeholder="Type your message here...")
-            submit_btn = gr.Button("Submit")
+    # Combine system prompt with user input
+    prompt = f"{system_prompt} User's input: {input_text}"
     
-    conversation_state = gr.State([])  # Maintain conversation history
+    # Call your model with the combined prompt
+    response = your_model_function(prompt)  # Replace this with actual model call
+    return response
 
-    # 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)
-            # 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, ""
+# Create the interface
+interface = gr.Interface(fn=custom_model_input, inputs=gr.Textbox(), outputs=gr.Textbox())
 
-    submit_btn.click(
-        update_conversation,
-        inputs=[input_box, conversation_state],
-        outputs=[chatbox, conversation_state, input_box],
-    )
+# Load the model
+interface.load("models/Qwen/QwQ-32B-Preview")
 
-# Launch the interface
-demo.launch()
+# Start the interface
+interface.launch()