说明文档

这是一个在转换为日文平假名并反转的数据集上进行预训练的语言模型。由于它以字符级别对平假名进行分词，因此适用于强调音节数量的任务，如回文或川柳（一种日本诗歌形式）。

This is a language model pre-trained on a dataset converted into Japaneses-Hiragana and reversed. Since it tokenizes Hiragana at the character level, it is suitable for tasks that emphasize the number of sounds, such as palindromes or senryu (a form of Japanese poetry).

hukuda222/hiragana-reverse-gpt2-xsmall

作者 hukuda222

↓ 1 ♥ 0

创建时间: 2025-01-19 08:35:00+00:00

更新时间: 2025-01-19 16:32:50+00:00

在 Hugging Face 上查看

文件 (9)

.gitattributes

README.md

config.json

generation_config.json

model.safetensors

onnx/config.json

onnx/generation_config.json

onnx/model.onnx ONNX

tokenizer_config.json