example.py

import torch
from pathlib import Path
from transformers import AutoTokenizer, AutoModelForCausalLM

MODEL = str(Path(__file__).resolve().parent)

tokenizer = AutoTokenizer.from_pretrained(MODEL, trust_remote_code=True)
dtype = torch.bfloat16 if torch.cuda.is_available() else torch.float32

kwargs = {
    "trust_remote_code": True,
    "dtype": dtype,
}
if torch.cuda.is_available():
    kwargs["device_map"] = "auto"

model = AutoModelForCausalLM.from_pretrained(MODEL, **kwargs)
model.eval()

prompt = "The most important reason the sky appears blue is"
inputs = tokenizer(prompt, return_tensors="pt")
inputs = {k: v.to(model.device) for k, v in inputs.items()}

with torch.inference_mode():
    out = model.generate(
        **inputs,
        max_new_tokens=32,
        do_sample=True,
        temperature=0.8,
        top_p=0.95,
        use_cache=False,
    )

print(tokenizer.decode(out[0], skip_special_tokens=True))