utils.py

from model import model, tokenizer
import torch
import json

def generate(prompt: str, max_new_tokens: int = 100) -> str:
    inputs = tokenizer.encode(prompt, return_tensors="pt").to(model.device)
    with torch.no_grad():
        outputs = model.generate(
            inputs,
            max_new_tokens=max_new_tokens,
            temperature=0.2,
            do_sample=False,
            pad_token_id=tokenizer.eos_token_id
        )
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    # Entferne Prompt aus Antwort
    if response.startswith(prompt):
        response = response[len(prompt):].strip()
    return response