"""Smoke generate for local ForgePlex-M2-9M Hub package."""

from pathlib import Path

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = Path(__file__).resolve().parent

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    trust_remote_code=True,
    dtype=torch.float32,
    device_map="auto",
)

prompt = "Once upon a time"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.inference_mode():
    out = model.generate(**inputs, max_new_tokens=64, do_sample=False)
print(tokenizer.decode(out[0], skip_special_tokens=True))