app.py

import streamlit as st
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("umar141/Gemma_1B_Baro_v2_vllm")
model = AutoModelForCausalLM.from_pretrained("umar141/Gemma_1B_Baro_v2_vllm")

# Streamlit page configuration
st.set_page_config(page_title="Gemma-based Chatbot", page_icon=":robot:")

# Introduction text
st.title("Gemma-based Chatbot")
st.write("This is a chatbot powered by a fine-tuned Gemma model.")

# User input
user_input = st.text_input("Ask me anything:")

# Generate response when the user inputs a query
if user_input:
    # Tokenize input and generate model response
    inputs = tokenizer.encode(user_input, return_tensors="pt")
    outputs = model.generate(inputs, max_length=150, num_return_sequences=1, pad_token_id=tokenizer.eos_token_id)
    
    # Decode the response
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    
    # Display the response
    st.write("AI Response:")
    st.write(response)