# streamlit_app.py

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

# Load the model and tokenizer
@st.cache_resource
def load_model():
    tokenizer = AutoTokenizer.from_pretrained("meta-math/MetaMath-Mistral-7B")
    model = AutoModelForCausalLM.from_pretrained("meta-math/MetaMath-Mistral-7B")
    return tokenizer, model

tokenizer, model = load_model()

# Streamlit app layout
st.title("MetaMath Mistral 7B Question-Answering")
st.write("Ask any question, and the model will generate an answer:")

# Input from user
question = st.text_input("Enter your question:")

if st.button("Generate Answer"):
    if question.strip():
        # Tokenize input
        inputs = tokenizer.encode(question, return_tensors="pt")

        # Generate response
        with torch.no_grad():
            outputs = model.generate(inputs, max_length=200, num_return_sequences=1)
        
        # Decode and display the output
        answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
        st.write("**Answer:**", answer)
    else:
        st.write("Please enter a question to get an answer.")