Matthew Honnibal 61e435610e 💫 Feature/improve pretraining (#2971) ... * Improve spacy pretrain script * Implement BERT-style 'masked language model' objective. Much better results. * Improve logging. * Add length cap for documents, to avoid memory errors. * Require thinc 7.0.0.dev1 * Require thinc 7.0.0.dev1 * Add argument for using pretrained vectors * Fix defaults * Fix syntax error * Improve spacy pretrain script * Implement BERT-style 'masked language model' objective. Much better results. * Improve logging. * Add length cap for documents, to avoid memory errors. * Require thinc 7.0.0.dev1 * Require thinc 7.0.0.dev1 * Add argument for using pretrained vectors * Fix defaults * Fix syntax error * Tweak pretraining script * Fix data limits in spacy.gold * Fix pretrain script		2018-11-28 18:04:58 +01:00
..
converters	Add converter for jsonl NER data	2018-08-14 14:04:32 +02:00
__init__.py	💫 Add experimental ULMFit/BERT/Elmo-like pretraining (#2931)	2018-11-15 22:17:16 +01:00
_messages.py	Add converter for jsonl NER data	2018-08-14 14:04:32 +02:00
conll17_ud_eval.py	Revert "Merge branch 'develop' of https://github.com/explosion/spaCy into develop"	2018-03-27 19:23:02 +02:00
convert.py	Add converter for jsonl NER data	2018-08-14 14:04:32 +02:00
download.py	Fix message formatting	2018-11-16 13:08:20 +01:00
evaluate.py	💫 New system for error messages and warnings (#2163)	2018-04-03 15:50:31 +02:00
info.py	Return data in cli.info and add silent option (resolves #2196)	2018-04-29 01:59:44 +02:00
init_model.py	Fix usage of deprecated freqs.txt in init-model	2018-08-14 13:19:15 +02:00
link.py	💫 New system for error messages and warnings (#2163)	2018-04-03 15:50:31 +02:00
package.py	Fix spacy requirement constraint in package template	2018-05-22 20:50:46 +02:00
pretrain.py	💫 Feature/improve pretraining (#2971)	2018-11-28 18:04:58 +01:00
profile.py	Don't pass CLI command name as dummy argument	2018-01-04 21:33:47 +01:00
train.py	Update hyper-parameters after NER random search (#2972)	2018-11-27 18:49:52 +01:00
ud_run_test.py	Don't modify Token in global scope	2018-05-09 00:43:00 +02:00
ud_train.py	Fix usage of PyTorch BiLSTM in ud_train	2018-09-13 22:54:59 +00:00
validate.py	💫 Improve model downloads: check for existing install, customise pip and use requests library again (#2346)	2018-05-20 20:26:56 +02:00
vocab.py	Don't pass CLI command name as dummy argument	2018-01-04 21:33:47 +01:00