app.py

import streamlit as st
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Set page config
st.set_page_config(
    page_title="Phi2 GPro Chat",
    page_icon="🚀",
    layout="wide"
)

# Initialize session state for chat history if it doesn't exist
if "messages" not in st.session_state:
    st.session_state.messages = []

@st.cache_resource
def load_model():
    from peft import PeftModel, PeftConfig
    
    # Load base model and tokenizer
    tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-2")
    base_model = AutoModelForCausalLM.from_pretrained(
        "microsoft/phi-2",
        torch_dtype=torch.float16,
        device_map="auto",
        low_cpu_mem_usage=True
    )
    
    # Load and apply adapter weights
    model = PeftModel.from_pretrained(base_model, "sft-model")
    return model, tokenizer

def generate_response(prompt, model, tokenizer, max_length=512):
    inputs = tokenizer(prompt, return_tensors="pt", truncation=True, max_length=max_length)
    inputs = {k: v.to(model.device) for k, v in inputs.items()}
    
    with torch.no_grad():
        outputs = model.generate(
            **inputs,
            max_new_tokens=512,
            do_sample=True,
            temperature=0.7,
            top_p=0.9,
            pad_token_id=tokenizer.eos_token_id
        )
    
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    # Remove the input prompt from the response
    response = response[len(tokenizer.decode(inputs['input_ids'][0], skip_special_tokens=True)):].strip()
    return response

# Main app
st.title("Phi2 GPro Chat 🚀")

# Load model
try:
    model, tokenizer = load_model()
    st.success("Model loaded successfully! Ready to chat.")
except Exception as e:
    st.error(f"Error loading model: {str(e)}")
    st.stop()

# Display chat messages
for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.write(message["content"])

# Chat input
if prompt := st.chat_input("What would you like to discuss?"):
    # Add user message to chat history
    st.session_state.messages.append({"role": "user", "content": prompt})
    with st.chat_message("user"):
        st.write(prompt)

    # Generate response
    with st.chat_message("assistant"):
        with st.spinner("Thinking..."):
            # Prepare conversation history
            conversation = ""
            for msg in st.session_state.messages:
                if msg["role"] == "user":
                    conversation += f"User: {msg['content']}\n"
                else:
                    conversation += f"Assistant: {msg['content']}\n"
            
            response = generate_response(conversation, model, tokenizer)
            st.write(response)
            st.session_state.messages.append({"role": "assistant", "content": response})

# Add a sidebar with information
with st.sidebar:
    st.title("About")
    st.markdown("""
    This is a chatbot powered by the Phi2 GPro model. 
    Feel free to ask questions and engage in conversation!
    
    **Features:**
    - Contextual responses
    - Memory of conversation
    - Fast inference
    """)