app.py

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

# Title of the app
st.title("LLaMA 2 Chatbot")

# Load the LLaMA model and tokenizer from Hugging Face
@st.cache_resource
def load_model_and_tokenizer():
    # Load the model and tokenizer
    tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-hf")
    model = LlamaForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf")
    return tokenizer, model

# Function to generate text based on a prompt
def generate_text(prompt, tokenizer, model):
    inputs = tokenizer(prompt, return_tensors="pt")
    # Generate text
    with torch.no_grad():
        generate_ids = model.generate(inputs.input_ids, max_length=50)
    return tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]

# Input field for user prompt
user_input = st.text_input("Enter your prompt:", "Hey, are you conscious? Can you talk to me?")

# Load model and tokenizer
tokenizer, model = load_model_and_tokenizer()

# Generate response when user enters a prompt
if st.button("Generate Response"):
    with st.spinner("Generating response..."):
        response = generate_text(user_input, tokenizer, model)
    st.write(f"Response: {response}")