app.py

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

# Load the model and tokenizer
@st.cache(allow_output_mutation=True)
def load_model():
    model = AutoModelForCausalLM.from_pretrained("AdaptLLM/finance-chat")
    tokenizer = AutoTokenizer.from_pretrained("AdaptLLM/finance-chat", use_fast=False)
    return model, tokenizer

model, tokenizer = load_model()

# Streamlit interface
st.title("Finance Chatbot")

# User input
user_input = st.text_area("Enter your query:")

if st.button("Submit"):
    if user_input:
        # Prepare the prompt
        prompt = f"<s>[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n<</SYS>>\n\n{user_input} [/INST]"

        # Tokenize and generate response
        inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).input_ids.to(model.device)
        outputs = model.generate(input_ids=inputs, max_length=4096)[0]

        answer_start = int(inputs.shape[-1])
        pred = tokenizer.decode(outputs[answer_start:], skip_special_tokens=True)

        # Display the output
        st.write("### Assistant Output:")
        st.write(pred)
    else:
        st.write("Please enter a query.")