from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("sudy-super/baku-13b-v2")
model = AutoModelForCausalLM.from_pretrained("sudy-super/baku-13b-v2", device_map="auto", torch_dtype=torch.bfloat16)
prompt = "大規模言語モデルとは、"
token_ids = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
with torch.no_grad():
    output_ids = model.generate(
        token_ids.to(model.device),
        max_new_tokens=100,
        do_sample=True,
        temperature=0.8,
        pad_token_id=tokenizer.pad_token_id,
        bos_token_id=tokenizer.bos_token_id,
        eos_token_id=tokenizer.eos_token_id
    )
result = tokenizer.decode(output_ids.tolist()[0])
print(result)