c-my/transformers
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
2,817 Commits 171 Branches 49 Tags
6b2200fc881222c19bd5c4bcc9ac735760272c4e
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Lysandre a436574bfd Release: v2.3.0 2019-12-20 16:22:20 -05:00
Lysandre cb6d54bfda Numpy compatibility for sentence piece 
convert to int earlier
 2019-12-20 15:06:28 -05:00
Lysandre 65c75fc587 Clean special tokens test 2019-12-20 11:34:16 -05:00
Lysandre fb393ad994 Added test for all special tokens 2019-12-20 11:29:58 -05:00
Lysandre 33adab2b91 Fix albert example 2019-12-19 12:40:43 -05:00
Lysandre a1f1dce0ae Correct max position for SQUAD and TFDS 2019-12-19 12:25:55 -05:00
Lysandre 8efc6dd544 fix #2214 2019-12-18 10:47:59 -05:00
Lysandre 5e289f69bc regex 2019.12.17 install fails with Python 2 2019-12-17 15:54:05 -05:00
Lysandre 2cff4bd8f3 Fix segmentation fault 2019-12-17 15:54:05 -05:00
Lysandre 18a879f475 fix #2180 2019-12-16 16:44:29 -05:00
Lysandre d803409215 Fix run squad evaluate during training 2019-12-16 16:31:38 -05:00
Lysandre 7bd11dda6f Release: v2.2.2 2019-12-13 16:45:30 -05:00
LysandreJik c3248cf122 Tests for all tokenizers 2019-12-13 16:41:44 -05:00
Lysandre d461472948 return for SQuAD [BLACKED] 2019-12-13 15:31:52 -05:00
Lysandre f24a228a93 Speed up tokenization process 2019-12-13 14:50:35 -05:00
Lysandre c8ed1c82c8 [SQUAD] Load checkpoint when evaluating without training 2019-12-13 12:13:48 -05:00
LysandreJik 7296f1010b Cleanup squad and add allow train_file and predict_file usage 2019-12-12 13:01:04 -05:00
LysandreJik 3fd71c4431 Update example scripts 2019-12-12 12:08:54 -05:00
LysandreJik fe92755b99 Fix special tokens mask in encode 2019-12-12 11:37:19 -05:00
LysandreJik 3d57c51111 Fix encode plus 2019-12-11 15:10:17 -05:00
LysandreJik 4c12860f7a Remove misleading documentation 2019-12-11 09:22:37 -05:00
LysandreJik b72f9d340e Correct index in script 2019-12-10 18:33:17 -05:00
LysandreJik ec6fb25c21 Patch documentation 2019-12-10 15:49:20 -05:00
LysandreJik 418589244d Uniforming the ignored indices 2019-12-10 15:26:19 -05:00
LysandreJik 6a73382706 Complete warning + cleanup 2019-12-10 14:33:24 -05:00
Lysandre dc4e9e5cb3 DataParallel for SQuAD + fix XLM 2019-12-10 19:21:20 +00:00
LysandreJik 2a4ef098d6 Add ALBERT and XLM to SQuAD script 2019-12-09 10:46:47 -05:00
LysandreJik e9217da5ff Cleanup 
Improve global visibility on the run_squad script, remove unused files and fixes related to XLNet.
 2019-12-05 16:01:51 -05:00
LysandreJik 9ecd83dace Patch evaluation for impossible values + cleanup 2019-12-05 14:44:57 -05:00
LysandreJik ce158a076f Return dataset (pytorch) 2019-12-04 17:55:52 -05:00
LysandreJik 7a03519975 Documentation 2019-12-04 17:24:35 -05:00
LysandreJik 33508ae310 Remove only_first 2019-12-04 16:26:45 -05:00
LysandreJik f7e4a7cdfa Cleanup 2019-12-04 16:24:15 -05:00
LysandreJik a7ca6d738b Padding side is tokenizer-dependant 2019-12-04 15:43:34 -05:00
LysandreJik cca75e7884 Kill the demon spawn 2019-12-04 15:42:29 -05:00
LysandreJik bf119c0568 TFDS dataset can now be evaluated 2019-12-04 11:34:59 -05:00
LysandreJik 9ddc3f1a12 Naming update + XLNet/XLM evaluation 2019-12-04 10:37:00 -05:00
LysandreJik de276de1c1 Working evaluation 2019-12-03 17:15:51 -05:00
LysandreJik c835bc85c2 Compute predictions 2019-12-03 15:28:16 -05:00
LysandreJik 285b1241e3 Added SquadResult 2019-12-03 15:00:49 -05:00
LysandreJik 8101924a68 Patch: v2.2.1 2019-12-03 11:20:26 -05:00
LysandreJik fbaf05bd92 Remove annoying tokenization message 2019-12-02 18:23:00 -05:00
Lysandre e85855f2c4 Fix ALBERT exports with pretraining + sp classifier; Fix naming for ALBERT TF models 2019-12-02 18:00:19 -05:00
Lysandre b3d834ae11 Reorganize ALBERT conversion script 2019-12-02 15:01:52 -05:00
Lysandre 1e9ac5a7cf New -> normal 2019-11-28 17:43:47 -05:00
Lysandre 0b84b9fd8a Add processors to __init__ 2019-11-28 17:38:52 -05:00
Lysandre f671997ef7 Interface with TFDS 2019-11-28 17:17:20 -05:00
Lysandre bd41e8292a Cleanup & Evaluation now works 2019-11-28 16:03:56 -05:00
Lysandre 45d767297a Updated v2.2.0 doc 2019-11-27 10:12:20 -05:00
Lysandre 361620954a Remove TFBertForPreTraining from ALBERT doc 2019-11-27 10:11:37 -05:00
Lysandre cc7968227e Updated v2.2.0 doc 2019-11-26 15:52:25 -05:00
Lysandre ce02550d50 Fix pretrained models table 2019-11-26 15:47:02 -05:00
Lysandre cf26a0c85e Fix pretrained models table 2019-11-26 15:40:03 -05:00
Lysandre 44b82c777f Updated v2.2.0 doc 2019-11-26 15:15:11 -05:00
Lysandre ee4647bd5c CamemBERT & ALBERT doc 2019-11-26 15:10:51 -05:00
Lysandre 7c6000e412 Updated v2.2.0 doc 2019-11-26 14:55:29 -05:00
Lysandre 668aac45d2 Pretrained models 2019-11-26 14:52:42 -05:00
Lysandre ae98d45991 Release: v2.2.0 2019-11-26 14:12:44 -05:00
Lysandre f2f329408d Fix input embeddings 2019-11-26 13:08:12 -05:00
LysandreJik c536c2a480 ALBERT Input Embeds 2019-11-26 13:08:12 -05:00
LysandreJik f873b55e43 Warning for ALBERT-v2 models 2019-11-26 13:08:12 -05:00
Lysandreandwassname c9cb7f8a0f Torch 1.1.0 compatibility + FP16 O1 + TF checkpoints 
Co-authored-by: wassname
 2019-11-26 13:08:12 -05:00
Lysandre b18509c208 Tests for ALBERT in TF2 + fixes 2019-11-26 13:08:12 -05:00
Lysandre 7bddbf5961 TFAlbertForSequenceClassification 2019-11-26 13:08:12 -05:00
Lysandre f6f382532b ALBERT in TF2 2019-11-26 13:08:12 -05:00
Lysandre d9daad98c7 Re-ordering of group_idx/layer_idx + Python 2 tests 2019-11-26 13:08:12 -05:00
Lysandre 9d5c49546f Tests for AlbertForQuestionAnswering AlbertForSequenceClassification 2019-11-26 13:08:12 -05:00
Lysandre 16263f9685 Headmasking 2019-11-26 13:08:12 -05:00
Lysandre abb23a78ba Head pruning for ALBERT 2019-11-26 13:08:12 -05:00
Lysandre 4374eaea78 ALBERT for SQuAD 2019-11-26 13:08:12 -05:00
Lysandre 70d99980de ALBERT-V2 2019-11-26 13:08:12 -05:00
Lysandre c110c41fdb Run GLUE and remove LAMB 2019-11-26 13:08:12 -05:00
Lysandre 6637a77f80 AlbertForSequenceClassification 2019-11-26 13:08:12 -05:00
Lysandre 0d07a23c04 LAMB implementation 2019-11-26 13:08:12 -05:00
Lysandre c987545592 Converting script 2019-11-26 13:08:12 -05:00
Lysandre 4f3a54bfc8 ALBERT can load pre-trained models. Doesn't inherit from BERT anymore. 2019-11-26 13:08:12 -05:00
Lysandre c4403006b8 External MLM head 2019-11-26 13:08:12 -05:00
Lysandre b21402fc86 Python 2 tests + licence 2019-11-26 13:08:12 -05:00
Lysandre c14a22272f ALBERT passes all tests 2019-11-26 13:08:12 -05:00
Lysandre 870320a24e Early tests 2019-11-26 13:08:12 -05:00
Lysandre 25a31953e8 Output Attentions + output hidden states 2019-11-26 13:08:12 -05:00
Lysandre ce9eade29c Initializer range using BertPreTrainedModel 2019-11-26 13:08:12 -05:00
Lysandre 5680a11063 Activation function managed from the config file 2019-11-26 13:08:12 -05:00
Lysandre 1e5b31c388 Several fixes and improvements 2019-11-26 13:08:12 -05:00
Lysandre ee20201d33 Tokenization tests + fixes + init 2019-11-26 13:08:12 -05:00
Lysandre e3ea5d1d8d Docstrings 2019-11-26 13:08:12 -05:00
Lysandre fedac786d4 Tokenization + small fixes 2019-11-26 13:08:12 -05:00
Lysandre 67b422662c Documentation + improved AlbertForMaskedLM 2019-11-26 13:08:12 -05:00
Lysandre 1b92564330 Reorganize and cleanup 2019-11-26 13:08:12 -05:00
Lysandre 12290c0d5c Handles multi layer and multi groups 2019-11-26 13:08:12 -05:00
Lysandre 139affaa8d Albert layer/layer groups 2019-11-26 13:08:12 -05:00
Lysandre 91ccbae788 Accepts multiple sizes 2019-11-26 13:08:12 -05:00
Lysandre c0c2088333 ALBERT model 2019-11-26 13:08:12 -05:00
Lysandre 0669c1fcd1 SQuAD v2 BERT + XLNet 2019-11-25 19:22:21 -05:00
Lysandre 7485caefb0 fix #1894 2019-11-25 09:33:39 -05:00
Lysandre e0e55bc550 Manage training example & refactor the refactor 2019-11-22 16:27:45 -05:00
Lysandre c3ba645237 Works for XLNet 2019-11-22 16:27:37 -05:00
LysandreJik a5a8a6175f Works for BERT 2019-11-22 16:27:31 -05:00
LysandreJik a7dafe2f41 Padding strategy (left and right) rather than boolean flag 2019-11-22 16:27:25 -05:00
LysandreJik 9f374c8252 encode and encode_plus handle attention masks and padding 2019-11-22 16:27:15 -05:00