update app.py

app.py

@@ -1,70 +1,80 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from llama_cpp import Llama
 
+# Load YOUR fine-tuned model
+model_path = "samzito12/finetome-llama-3b-gguf"
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    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,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+print("Loading model...")
+llm = Llama.from_pretrained(
+    repo_id=model_path,
+    filename="*Q4_K_M.gguf",
+    n_ctx=2048,
+    n_threads=2,
+    verbose=False
+)
 
-        response += token
-        yield response
+# System prompt to fix identity issue
+SYSTEM_PROMPT = """You are a helpful AI assistant based on Meta's Llama-3.2-3B model, fine-tuned on the FineTome dataset. You are NOT ChatGPT and you are NOT made by OpenAI. You were created as part of a university machine learning project."""
 
+def chat(message, history):
+    """Generate response from YOUR fine-tuned model"""
+    
+    # Build conversation with system prompt
+    conversation = f"<|start_header_id|>system<|end_header_id|>\n\n{SYSTEM_PROMPT}<|eot_id|>"
+    
+    # Add chat history
+    for user_msg, assistant_msg in history:
+        conversation += f"<|start_header_id|>user<|end_header_id|>\n\n{user_msg}<|eot_id|>"
+        conversation += f"<|start_header_id|>assistant<|end_header_id|>\n\n{assistant_msg}<|eot_id|>"
+    
+    # Add current message
+    conversation += f"<|start_header_id|>user<|end_header_id|>\n\n{message}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
+    
+    # Generate response
+    response = llm(
+        conversation,
+        max_tokens=512,
+        temperature=0.7,
+        top_p=0.9,
+        stop=["<|eot_id|>", "<|start_header_id|>"],
+        echo=False
+    )
+    
+    return response['choices'][0]['text'].strip()
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    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)",
-        ),
+# Create Gradio interface
+demo = gr.ChatInterface(
+    chat,
+    title="🦙 My Fine-Tuned Llama-3.2-3B Chatbot",
+    description="""
+    **Model**: Llama-3.2-3B fine-tuned on FineTome-100k dataset
+    
+    This chatbot uses a custom fine-tuned model, NOT ChatGPT.
+    
+    Created for ID2223 Lab 2 at KTH.
+    """,
+    examples=[
+        "What model are you?",
+        "Explain machine learning in simple terms",
+        "Write a Python function to reverse a string",
+        "What is the weather like in Stockholm?"
     ],
+    theme="soft",
+    retry_btn="🔄 Retry",
+    undo_btn="↩️ Undo",
+    clear_btn="🗑️ Clear"
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
 if __name__ == "__main__":
     demo.launch()
+```
+
+---
+
+### **Step 3: Update requirements.txt**
+
+You also need to update the dependencies. Click on **`requirements.txt`** file and replace its contents with:
+```
+gradio
+llama-cpp-python
+huggingface-hub