GitLab

* change do_samples back

* None better default as boolean

* adapt do_sample to True in test example

* make style

* Remove unused kwargs
* dont call forward in tests

* improved documentation

`generate` code that produces 99% identical summarizations to fairseq on CNN test data, with caching.

* Fix tests on GPU (torch)

* Fix bart slow tests
Co-authored-by: Sam Shleifer <sshleifer@gmail.com>

* Results same as fairseq
* Wrote a ton of tests
* Struggled with api signatures
* added some docs