Commit Graph
170 Commits
Author SHA1 Message Date
thomwolf 0227b4a940 fix #827 2019-07-23 14:06:43 +02:00
Anish Moorthy 490ebbdcf7 Fix PretrainedModel.from_pretrained not passing cache_dir forward 2019-07-22 18:03:08 -04:00
Anish Moorthy b8009cb0da Make PreTrainedModel.from_pretrained pass unused arguments to model 2019-07-22 18:03:08 -04:00
Yiqing-Zhou bef0c629ca fix
Remove '\n' before adding token into vocab
2019-07-22 22:30:49 +08:00
Yiqing-Zhou 897d0841be read().splitlines() -> readlines()
splitlines() does not work as what we expect here for bert-base-chinese because there is a '\u2028' (unicode line seperator) token in vocab file. Value of '\u2028'.splitlines() is ['', ''].
Perhaps we should use readlines() instead.
2019-07-22 20:49:09 +08:00
Wei-Sheng Chin c4e9615691 Fix a path so that test can run on Windows 2019-07-17 09:08:40 -07:00
Minho Ryu cd8980e1f4 import sys twice 2019-07-17 18:12:01 +09:00
thomwolf 5fe0b378d8 adding missing docstring fix #793 2019-07-16 21:35:53 +02:00
thomwolf ed7549bb1a release version 1.0 2019-07-16 16:10:58 +02:00
thomwolf 4acaa65068 model in evaluation mode by default after from_pretrained 2019-07-16 15:41:57 +02:00
thomwolf f289e6cfe4 fix docstrings 2019-07-16 15:31:21 +02:00
thomwolf 9726b229cf model name typo 2019-07-16 15:17:45 +02:00
thomwolf 1849aa7d39 update readme and pretrained model weight files 2019-07-16 15:11:29 +02:00
thomwolf f31154cb9d Merge branch 'xlnet' 2019-07-16 11:51:13 +02:00
thomwolf 1b35d05d4b update conversion scripts and __main__ 2019-07-16 09:41:55 +02:00
thomwolf 352e3ff998 added migration guide to readme 2019-07-16 09:03:49 +02:00
thomwolf 3b8b0e01bb update readme 2019-07-16 00:12:55 +02:00
thomwolf e691fc0963 update QA models tests + run_generation 2019-07-15 17:45:24 +02:00
thomwolf 15d8b1266c update tokenizer - update squad example for xlnet 2019-07-15 17:30:42 +02:00
thomwolf 3b469cb422 updating squad for compatibility with XLNet 2019-07-15 15:28:37 +02:00
thomwolf 8ca767f13c clean up optimization 2019-07-15 13:49:07 +02:00
thomwolf 74a24f0fe9 clean up file_utils 2019-07-15 13:49:01 +02:00
thomwolf ab49fafc04 update tokenization docstrings for #328 2019-07-15 12:51:23 +02:00
thomwolf a9ab15174c fix #328 2019-07-15 12:42:12 +02:00
thomwolf f7cd7392fd fixed tests 2019-07-15 12:32:19 +02:00
thomwolf e28d8bde0d doc on base classes 2019-07-15 12:08:06 +02:00
thomwolf 44c985facd update doc for XLM and XLNet 2019-07-15 11:36:50 +02:00
thomwolf 0201d86015 added doc for transformer-xl 2019-07-15 10:11:09 +02:00
thomwolf 4cb489457f added doc for openai GPT 2019-07-15 09:58:01 +02:00
thomwolf 62b8eb43c1 fix add_start_docstrings on python 2 (removed) 2019-07-15 09:49:02 +02:00
thomwolf 5bc3d0cc5b added gpt2 doc 2019-07-15 09:40:05 +02:00
thomwolf 183fedfed5 fix doc on python2 2019-07-15 09:00:09 +02:00
thomwolf 2397f958f9 updating examples and doc 2019-07-14 23:20:10 +02:00
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