app.py

from flask import Flask, request, jsonify
from transformers import AutoModelForCausalLM, AutoTokenizer

app = Flask(__name__)

# Load model and tokenizer
model_name = "meta-llama/LLaMA-2-7b"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

@app.route('/predict', methods=['POST'])
def predict():
    data = request.json
    inputs = tokenizer(data['text'], return_tensors='pt')
    outputs = model.generate(**inputs)
    response_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return jsonify({'response': response_text})

if __name__ == '__main__':
    app.run(host='0.0.0.0', port=5000)