To avoid the error when use_program_cache is True in Transformer infe…rence.

To avoid the data decode error.

* init paddle-nlp tools for QA test

* Fix paragraph extraction bug

* Update download links

* first update LAC README.md

* rename EmoTect as emotion_detection

* download data from bos

* Update README.md

* Rename project

* second add code

* modify downloads.sh for lac

* rename LAC to lexical_analysis

* update lac readme

* Update README.md

* Update README.md

* Update README.md

* add struct.jpg

* Update README.md

* Update README.md

* update README

* Update README.md

* update emotion_detection README

* add download_data.sh and download_model.sh

* first commit ADE

* dialogue_model_toolkit_update

* update emotion_detection model bos url

* update README

* update readme

* update readme

* update download file

* first commit DAM

* add readme

* fix readme

* fix readme

* fix readme

* fix readme

* fix readme

* rename

* rename again

* 1. add gradient_clip for ernie_lac
2. delete LARK config

* fix download.sh

* Rename MRC task

* fix logger

* fix to douban

* fix final

* update readme

* update readme

* update readme

* fix batch is null

* fix typo

* fix typo

* fix typo

* update ernie config

* update readme

* add AI platform url in readme

* update readme subtitlestyle

* update

* Update README.md

* Update README.md

* update

* Create README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* update batch size

* adapt to samll data size

* update ERNIE bcebos url

* add language model

* modify readme

* update

* update

* Update README.md

* Update README.md

* fix readme

* fix max_step, update run.sh and run_ernie.sh

* add finetuned model for lac

* fix bug

* Update README.md

* update

* Update README.md

* add ERNIE pretrained model, and update README

* update readme

* add CPU

* update infer in run.sh and run_ernie.sh

* Update README.md

* Update README.md

* Delete test.py

* fix bug

* fix run.sh infer bug & add ernie infer code

* fix cpu mode

* Update README.md

* fix bug for python3

* fix CPU and GPU diff result bug

* Update README.md

* update readme

* Update run_classifier.py

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update run.sh

* Update run_ernie.sh

* modify dir

* Update README.md

* modify dir too

* modify path

* Update README.md

* PaddleNLP modules backup to old/, rm links-LAC,Senta,SimNet

* mv all modules out of paddle-nlp, rm Senta, auto_dialog_eval, deep_match

* mv models/classify to models/classification, models/seq_lab to models/sequence_labeling

* update readme for models/classification

* update sentiment_classification and rm README

* Add Transformer into paddle-nlp

* change seq_lab to sequence labeling

* Rename old as unarchived in PaddleNLP

* add LARK

* Update README, add paddlehub

* add paddlehub

* Add tmp readme

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update run_ernie.sh

* Update run_ernie.sh

* Update README.md

* Update run_ernie_classifier.py

* Update README.md

* Update README.md

* Update run.sh

* Update run_ernie_classifier.py

* update

* fix chunk_evaluator bug

* change names

* Update README

* add gitmodules

* add install code

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update READMEs

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* README

* Update README.md

* update emotion_detection README

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* update REAME, add finetune doc

* update emotion_detection readme

* change run.sh

* Update README.md

* Update the link in fluid dir

* update readme

* update README for markdown style

* Update README.md

* Update README.md

* Shift up fluid models

* Update nlp submodules

* Add redirect guide in org readme

* Move HiNAS_models to AutoDL

* Delete file
* Rever the raw file

* Adjust the structure of whole repo

* Correct the readme for speec

* Update submodules LAC, Senta and SimNet

* Add py-reader and parallel-executor support in Transformer inference

* Add statick k, v cache for encoder output in Transformer inference

* Replace the cache from compute_qkv with cahce from split_heads in Transformer inference

* Fuse k, q, v projection in Transformer

* Revert the fused k, q, v projection in Transformer to be compatible with saved models

* Use gather_op to replace sequence_expand_op in Transformer inference

* Add fluid_transformer.md

* Refine README for released models and data in Transformer

* Refine README for released models and data in Transformer

* Load Data --> 64 sec
* Shuffle/Batch --> 14 sec