from fugashi import Tagger 

from transformers import (
    pipeline,
    XLNetLMHeadModel,
    XLNetTokenizer
)

class XLNet():
    def __init__(self):
        self.m = Tagger('-Owakati') 
        self.gen_model = XLNetLMHeadModel.from_pretrained("hajime9652/xlnet-japanese")
        self.gen_tokenizer = XLNetTokenizer.from_pretrained("hajime9652/xlnet-japanese")
         
    def generate(self, prompt="福岡のご飯は美味しい。コンパクトで暮らしやすい街。"):
        prompt = self.m.parse(prompt)
        inputs = self.gen_tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
        prompt_length = len(self.gen_tokenizer.decode(inputs[0], skip_special_tokens=True, clean_up_tokenization_spaces=True))
        outputs = self.gen_model.generate(inputs, max_length=200, do_sample=True, top_p=0.95, top_k=60)
        generated = prompt + self.gen_tokenizer.decode(outputs[0])[prompt_length:]
        return generated

Limitations and bias

This model's training use the Japanese Business News.

Important matter

The company that created and published this model is called Stockmark. This repository is for use by HuggingFace and not for infringement. See this documents https://qiita.com/mkt3/items/4d0ae36f3f212aee8002 published by https://github.com/mkt3