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

app = Flask(__name__)

model_name = "vilm/vinallama-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")

@app.route("/generate", methods=["POST"])
def generate():
    data = request.get_json()
    prompt = data.get("prompt", "")
    inputs = tokenizer(prompt, return_tensors="pt", truncation=True, max_length=1024)
    outputs = model.generate(inputs.input_ids, max_length=512, pad_token_id=tokenizer.eos_token_id)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return jsonify({"response": response})

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