v0.4: Add encoding cache and lazy-train mechanism (#50)

Better support for knowledge distillation tasks.
Enable label loading for large size of data.
Add auto test for pull request.

v0.3 release

Support Sequence Labelling.
Support Knowledge distillation task.

Support Chinese Language

v0.2

add language supported for README (#33)

v0.1 release

add installation and quick start in readme.md