import torch
from transformers import AutoTokenizer
from auto_gptq import AutoGPTQForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rinna/youri-7b-gptq")
model = AutoGPTQForCausalLM.from_quantized("rinna/youri-7b-gptq", use_safetensors=True)

text = "西田幾多郎は、"
token_ids = tokenizer.encode(text, add_special_tokens=False, return_tensors="pt")

with torch.no_grad():
    output_ids = model.generate(
        input_ids=token_ids.to(model.device),
        max_new_tokens=200,
        min_new_tokens=200,
        do_sample=True,
        temperature=1.0,
        top_p=0.95,
        pad_token_id=tokenizer.pad_token_id,
        bos_token_id=tokenizer.bos_token_id,
        eos_token_id=tokenizer.eos_token_id
    )

output = tokenizer.decode(output_ids.tolist()[0])
print(output)

@misc{rinna-youri-7b-gptq,
    title = {rinna/youri-7b-gptq},
    author = {Wakatsuki, Toshiaki and Zhao, Tianyu and Sawada, Kei},
    url = {https://huggingface.co/rinna/youri-7b-gptq}
}

@inproceedings{sawada2024release,
    title = {Release of Pre-Trained Models for the {J}apanese Language},
    author = {Sawada, Kei and Zhao, Tianyu and Shing, Makoto and Mitsui, Kentaro and Kaga, Akio and Hono, Yukiya and Wakatsuki, Toshiaki and Mitsuda, Koh},
    booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
    month = {5},
    year = {2024},
    pages = {13898--13905},
    url = {https://aclanthology.org/2024.lrec-main.1213},
    note = {\url{https://arxiv.org/abs/2404.01657}}
}