app.py

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

app = Flask(__name__)

tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-2")
model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2")
@app.route('/chat', methods=['POST'])
def chat():
    data = request.get_json()
    prompt = data.get("prompt", "")

    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=100)
    reply = tokenizer.decode(outputs[0], skip_special_tokens=True)

    return jsonify({"response": reply})


if __name__ == "__main__":
    app.run(host="0.0.0.0", port=7860)