app.py

import os
import requests
from transformers import pipeline
from flask import Flask, render_template, request, jsonify

app = Flask(__name__)

# Define model URL and local path
MODEL_URL = "https://huggingface.co/unsloth/Qwen3-4B-128K-GGUF/resolve/main/Qwen3-4B-128K-UD-IQ1_M.gguf"
MODEL_PATH = "Qwen3-4B-128K-UD-IQ1_M.gguf"

# Function to download the model
def download_model():
    if not os.path.exists(MODEL_PATH):
        print("Downloading the model...")
        response = requests.get(MODEL_URL, stream=True)
        with open(MODEL_PATH, 'wb') as model_file:
            for chunk in response.iter_content(chunk_size=128):
                model_file.write(chunk)
        print("Model downloaded successfully.")

# Load the model with Hugging Face Transformers pipeline
def load_model():
    download_model()
    model = pipeline("text-generation", model=MODEL_PATH)
    return model

# Global model object
model = load_model()

@app.route('/')
def index():
    return render_template('index.html')

@app.route('/generate', methods=['POST'])
def generate():
    user_input = request.form['message']
    response = model(user_input, max_length=100)
    return jsonify({"response": response[0]['generated_text']})

if __name__ == '__main__':
    app.run(debug=True)