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("01-ai/Yi-6B-Chat")
    model = AutoModelForCausalLM.from_pretrained("01-ai/Yi-6B-Chat")
    return tokenizer, model

tokenizer, model = load_model()

st.title("Chat with AI")

# User input
user_input = st.text_input("You: ", "Hello, how are you?")

if user_input:
    # Tokenize input and generate response
    inputs = tokenizer(user_input, return_tensors="pt")
    with torch.no_grad():
        outputs = model.generate(inputs.input_ids, max_length=50, num_return_sequences=1)
    
    # Decode and display the response
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    st.write(f"AI: {response}")