load_example.py

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


REPO_ID = "bmax16634/sologpt-v3-150m-base"


def main():
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    tokenizer = AutoTokenizer.from_pretrained(REPO_ID, trust_remote_code=True)
    model = AutoModelForCausalLM.from_pretrained(REPO_ID, trust_remote_code=True).to(device)
    model.eval()

    prompt = "The future of artificial intelligence is"
    inputs = tokenizer(prompt, return_tensors="pt").to(device)

    with torch.no_grad():
        output_ids = model.generate(
            **inputs,
            max_new_tokens=80,
            do_sample=True,
            temperature=0.8,
            top_k=40,
            use_cache=False,
            remove_invalid_values=True,
            renormalize_logits=True,
            pad_token_id=tokenizer.eos_token_id,
        )

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


if __name__ == "__main__":
    main()