model_name = "Kohsaku/gemma-2-9b-finetune-2"

max_seq_length = 1024

dtype = None
load_in_4bit = True

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = model_name,
    max_seq_length = max_seq_length,
    dtype = dtype,
    load_in_4bit = load_in_4bit,
    token = HF_TOKEN,
)
FastLanguageModel.for_inference(model)

text = "自然言語処理とは何か"
tokenized_input = tokenizer.encode(text, add_special_tokens=True , return_tensors="pt").to(model.device)

with torch.no_grad():
    output = model.generate(
        tokenized_input,
        max_new_tokens = 1024,
        use_cache = True,
        do_sample=False,
        repetition_penalty=1.2
    )[0]
print(tokenizer.decode(output))