Matthew Honnibal 3e78e82a83 Experimental character-based pretraining (#5700) ... * Use cosine loss in Cloze multitask * Fix char_embed for gpu * Call resume_training for base model in train CLI * Fix bilstm_depth default in pretrain command * Implement character-based pretraining objective * Use chars loss in ClozeMultitask * Add method to decode predicted characters * Fix number characters * Rescale gradients for mlm * Fix char embed+vectors in ml * Fix pipes * Fix pretrain args * Move get_characters_loss * Fix import * Fix import * Mention characters loss option in pretrain * Remove broken 'self attention' option in pretrain * Revert "Remove broken 'self attention' option in pretrain" This reverts commit 56b820f6af. * Document 'characters' objective of pretrain		2020-07-05 15:48:39 +02:00
..
converters	Fix for Issue 4665 - conllu2json (#4953)	2020-02-03 13:01:48 +01:00
__init__.py	Move UD scripts to bin	2019-03-20 01:19:34 +01:00
_schemas.py	Store JSON schemas in Python and tidy up (#3235)	2019-02-07 19:44:31 +11:00
convert.py	Auto-format [ci skip]	2019-10-24 16:21:08 +02:00
debug_data.py	Tidy up and auto-format	2020-05-21 14:14:01 +02:00
download.py	Use latest wasabi	2019-11-04 02:38:45 +01:00
evaluate.py	Tidy up and avoid absolute spacy imports in core	2020-05-21 20:05:03 +02:00
info.py	Use latest wasabi	2019-11-04 02:38:45 +01:00
init_model.py	Tidy up and auto-format	2020-05-21 14:14:01 +02:00
link.py	Use latest wasabi	2019-11-04 02:38:45 +01:00
package.py	Use latest wasabi	2019-11-04 02:38:45 +01:00
pretrain.py	Experimental character-based pretraining (#5700)	2020-07-05 15:48:39 +02:00
profile.py	Restore tqdm imports (#4804)	2019-12-16 13:12:19 +01:00
train.py	Experimental character-based pretraining (#5700)	2020-07-05 15:48:39 +02:00
validate.py	Use latest wasabi	2019-11-04 02:38:45 +01:00