pdate general distill in ppminilm (PaddlePaddle#1520)

Merge pull request PaddlePaddle#1483 from PaddlePaddle/update-faster-…

…tokenizer-map

Support ppminilm in FasterTokenizer

Add use_faster to faster_gpt sample. (PaddlePaddle#1443)

Merge pull request PaddlePaddle#1201 from wawltor/check_release_2.1

update the code for the download_file and document

add sharding for gpt3 (PaddlePaddle#1064)

* add sharding for gpt-3

* del debug

* add sharding save model

* update model save

* fix seed func

* set control in tensor parallel

Co-authored-by: Zhong Hui <[email protected]>

Refine api docs and readme and fix baseline bug (PaddlePaddle#912)

* fix unified transformer dtype problem

* fix win dtype bug

* Fix plato-2 and plato-mini dtype bug

* Fix plato-2 tokenization

* Refine some doc

* Add general k support for topk sampling

* fix seed

* minor fix

* Fix unitransformer readme

* topk kernel optimization

* add unimo model and fix generate api

* add 3 datasets for unimo-text

* fix tokenizer bug

* paddlenlp+lightseq sample

* Refine api docs and readme and fix baseline bug

* add shell srcipt

* remove lightseq samples

* minor fix

* minor fix

Co-authored-by: Jiaqi Liu <[email protected]>
Co-authored-by: liu zhengxi <[email protected]>

update ernie text cls ci (PaddlePaddle#823)

* add ernie text cls ci

* mv ernie_text_cls_params.txt to ernie_text_cls directory

update doc of wordtag

Simplify transformer.rst code block

Simplify transformer.rst code block