Commit Graph

37 Commits

Author SHA1 Message Date
thomwolf
7d4b200e40 good quality generation example for GPT, GPT-2, Transfo-XL, XLNet 2019-07-13 15:25:03 +02:00
thomwolf
699bc7e86e fix gpt-2 unk token test 2019-07-12 11:46:57 +02:00
thomwolf
7442956361 save config file 2019-07-12 11:26:16 +02:00
Thomas Wolf
c57e9d946f
Merge branch 'xlnet' into embeddings 2019-07-12 11:10:14 +02:00
thomwolf
2918b7d2a0 updating tests 2019-07-12 10:57:58 +02:00
LysandreJik
3fbceed8d2 Fix layer reference loss + previous attempted fix 2019-07-11 22:29:55 -04:00
LysandreJik
6c2ee16c04 Test suite testing the tie_weights function as well as the resize_token_embeddings function.
Patched an issue relating to the tied weights I had introduced with the TorchScript addition.
Byte order mark management in TSV glue reading.
2019-07-11 22:09:16 -04:00
LysandreJik
e3fb4310d6 From pretrained correct initialization. Unknown token handling for gpt2. 2019-07-11 18:44:29 -04:00
thomwolf
bd404735a7 embeddings resizing + tie_weights 2019-07-12 00:02:49 +02:00
LysandreJik
50e62a4cb4 fix gpt/gpt-2 from pretrained 2019-07-11 16:50:21 -04:00
thomwolf
273617b86d update config - fix gpt/gpt-2 from pretrained 2019-07-11 22:45:03 +02:00
thomwolf
c6bf1a400d fix test examples et model pretrained 2019-07-11 22:29:08 +02:00
thomwolf
92a782b108 fix run_glue test 2019-07-11 22:20:10 +02:00
thomwolf
ccb6947dc1 optimization tests 2019-07-11 17:39:47 +02:00
Thomas Wolf
b87eb82b4f
Merge branch 'xlnet' into doc-sphinx 2019-07-11 15:46:27 +02:00
thomwolf
b21d84b027 update examples 2019-07-11 15:37:34 +02:00
thomwolf
ec07cf5a66 rewamp optimization 2019-07-11 14:48:22 +02:00
thomwolf
4fef5919a5 updating examples 2019-07-11 12:03:08 +02:00
LysandreJik
7fdbc47822 Added the two CLM XLM pretrained checkpoints.
Fixed file extensions for config/vocab/merges of XLM models.
2019-07-10 19:37:24 -04:00
LysandreJik
dee3e45b93 Fixed XLM weights conversion script. Added 5 new checkpoints for XLM. 2019-07-10 19:04:21 -04:00
LysandreJik
5288913bdd All TODOs to be checked by Thom have been added. 2019-07-10 15:16:40 -04:00
LysandreJik
f773faa258 Fixed all links. Removed TPU. Changed CLI to Converting TF models. Many minor formatting adjustments. Added "TODO Lysandre filled" where necessary. 2019-07-10 14:45:56 -04:00
thomwolf
50b7e52a7f WIP examples 2019-07-10 15:33:34 +02:00
LysandreJik
83fb311ef7 Patched warnings + Refactored XLNet's Docstrings 2019-07-09 16:38:30 -04:00
LysandreJik
8fe2c9d98e Refactored Docstrings of BERT, GPT2, GPT, TransfoXL, XLM and XLNet. 2019-07-09 15:55:31 -04:00
thomwolf
ed6c8d37f4 fix merge 2019-07-09 17:14:52 +02:00
thomwolf
e468192e2f Merge branch 'pytorch-transformers' into xlnet 2019-07-09 17:05:37 +02:00
thomwolf
d743f2f34e updating test 2019-07-09 15:58:58 +02:00
thomwolf
d0efbd3cd1 update sequencesummary module 2019-07-09 15:46:43 +02:00
thomwolf
d5481cbe1b adding tests to examples - updating summary module - coverage update 2019-07-09 15:29:42 +02:00
thomwolf
c079d7ddff fix python 2 tests 2019-07-09 10:40:59 +02:00
thomwolf
b19786985d unified tokenizer api and serialization + tests 2019-07-09 10:25:18 +02:00
thomwolf
1113f97f33 clean up glue example 2019-07-05 16:31:13 +02:00
thomwolf
162ba383b0 fix model loading 2019-07-05 15:57:14 +02:00
thomwolf
6dacc79d39 fix python2 tests 2019-07-05 15:11:59 +02:00
thomwolf
36bca545ff tokenization abstract class - tests for examples 2019-07-05 15:02:59 +02:00
thomwolf
0bab55d5d5 [BIG] name change 2019-07-05 11:55:36 +02:00