app.py

import streamlit as st
from streamlit_chat import message as st_message
from transformers import AutoModelForCausalLM, AutoTokenizer

@st.cache_resource 
def get_models():
    model_name = "PY007/TinyLlama-1.1B-Chat-v0.3"
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModelForCausalLM.from_pretrained(model_name)
    return tokenizer, model


if "history" not in st.session_state:
    st.session_state.history = []

st.title("Hello Tiny Llama Chatbot")


def generate_answer():
    tokenizer, model = get_models()
    user_message = st.session_state.input_text
    inputs = tokenizer(st.session_state.input_text, return_tensors="pt")
    result = model.generate(**inputs)
    message_bot = tokenizer.decode(
        result[0], skip_special_tokens=True
    )  # .replace("<s>", "").replace("</s>", "")

    st.session_state.history.append({"message": user_message, "is_user": True})
    st.session_state.history.append({"message": message_bot, "is_user": False})


st.text_input("Talk to the bot", key="input_text", on_change=generate_answer)

for i, chat in enumerate(st.session_state.history):
    st_message(**chat, key=str(i)) #unpacking