from flask import Flask, request, render_template
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

app = Flask(__name__)

# Load fine-tuned model and tokenizer
model_path = "./finetuned_weights"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path)
device = torch.device("cpu")
model.to(device)

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

@app.route('/generate', methods=['POST'])
def generate():
    user_input = request.form['prompt'].strip()
    prompt = f"<|USER|> {user_input} <|ASSISTANT|> "
    inputs = tokenizer(prompt, return_tensors="pt").to(device)
    outputs = model.generate(**inputs, max_length=100, num_return_sequences=1, pad_token_id=tokenizer.eos_token_id)
    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
    response = generated_text.split("<|ASSISTANT|> ")[-1] if "<|ASSISTANT|> " in generated_text else generated_text
    return response

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