Chinese Ancient BERT Model

Model description

The model's architecture is the BERT-large. We trained this model in 4 P100 about 7 days. (batch size = 6, steps = 1M)

How to use

You can use the model directly with a pipeline for text generation:

>>> from transformers import pipeline
>>> unmasker = pipeline('fill-mask', model='zhuimengshaonian/bert-ancient-base')
>>> unmasker("海阔凭鱼跃，天高[MASK]鸟飞。")