flypythoncom/GPT2-Chinese
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Zeyao Du
2019-12-09 15:57:56 +08:00
committed by GitHub
parent d8b648b25d
commit 825f9b0d94
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -5,6 +5,10 @@
- Chinese version of GPT2 training code, using BERT tokenizer or BPE tokenizer. It is based on the extremely awesome repository from HuggingFace team [Transformers](https://github.com/huggingface/transformers). Can write poems, news, novels, or train general language models. Support char level, word level and BPE level. Support large training corpus.
- 中文的GPT2训练代码，使用BERT的Tokenizer或Sentencepiece的BPE model（感谢[kangzhonghua](https://github.com/kangzhonghua)的贡献，实现BPE模式需要略微修改train.py的代码）。可以写诗，新闻，小说，或是训练通用语言模型。支持字为单位或是分词模式或是BPE模式（需要略微修改train.py的代码）。支持大语料训练。
## NEWS 12.9.2019
- 新项目[GPT2-chitchat](https://github.com/yangjianxin1/GPT2-chitchat)已发布，部分基于本项目代码。包含训练GPT2对话模型的代码与与训练模型，以及生成样例，欢迎大家参观。
## NEWS 12.7.2019
- 新项目[Decoders-Chinese-TF2.0](https://github.com/Morizeyao/Decoders-Chinese-TF2.0)同样支持GPT2的中文训练，在使用上更加简单，不易产生各种问题。目前还在测试阶段，欢迎大家提出意见。