Holden-Lin / gpt2_chinese

forked from https://github.com/imcaspar/gpt2-ml

GPT2 for Multiple Languages

中文说明 | English

• Simplifed GPT2 train scripts（based on Grover, supporting TPUs）
• Ported bert tokenizer, multilingual corpus compatible
• 1.5B GPT2 pretrained Chinese model ( ~15G corpus, 10w steps )
• Batteries-included Colab demo #
• 1.5B GPT2 pretrained Chinese model ( ~30G corpus, 22w steps )

Pretrained Model

1.5B GPT2 pretrained Chinese model ( ~30G corpus, 22w steps ) [Google Drive] SHA256: e698cc97a7f5f706f84f58bb469d614e51d3c0ce5f9ab9bf77e01e3fcb41d482

1.5B GPT2 pretrained Chinese model ( ~15G corpus, 10w steps ) [Google Drive] SHA256: 4a6e5124df8db7ac2bdd902e6191b807a6983a7f5d09fb10ce011f9a073b183e

Corpus from THUCNews and nlp_chinese_corpus

Using Cloud TPU Pod v3-256 to train 22w steps

Google Colab

With just 2 clicks (not including Colab auth process), the 1.5B pretrained Chinese model demo is ready to go:

[Colab Notebook]

Train

Disclaimer

The contents in this repository are for academic research purpose, and we do not provide any conclusive remarks.

Citation

@misc{GPT2-ML,
  author = {Zhibo Zhang},
  title = {GPT2-ML: GPT-2 for Multiple Languages},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/imcaspar/gpt2-ml}},
}

Reference

https://github.com/google-research/bert

https://github.com/rowanz/grover

Research supported with Cloud TPUs from Google's TensorFlow Research Cloud (TFRC)