app.py

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

# Load the model and tokenizer
model_name = "Qwen/Qwen2.5-1.5B-Instruct"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Initialize chat history
if "messages" not in st.session_state:
    st.session_state.messages = [
        {"role": "system", "content": "You are a helpful assistant."}
    ]

# Display chat messages from history on app rerun
for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.markdown(message["content"])

# Accept user input
if prompt := st.chat_input("Ask me anything about data structures in LeetCode"):
    # Add user message to chat history
    st.session_state.messages.append({"role": "user", "content": prompt})
    # Display user message in chat message container
    with st.chat_message("user"):
        st.markdown(prompt)

    # Prepare the chat message for the model
    messages = st.session_state.messages[-10:]  # limit messages to last 10 for performance
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    # Generate response from the model
    generated_ids = model.generate(
        **model_inputs,
        max_new_tokens=512
    )
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    # Decode the response
    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

    # Add bot response to chat history
    st.session_state.messages.append({"role": "assistant", "content": response})

    # Display bot response in chat message container
    with st.chat_message("assistant"):
        st.markdown(response)