LysandreJik
bac332fec0
Updated the GLUE data processor. Corrections to RoBERTa and XLNet.
2019-09-19 10:55:06 +02:00
LysandreJik
c3df2136e1
Added binary masking tests
2019-09-19 10:55:06 +02:00
LysandreJik
e391d4735e
Tokenizers' encode function can output binary masks
2019-09-19 10:55:06 +02:00
erenup
46ffc28329
Merge branch 'master' into run_multiple_choice_merge
...
# Please enter a commit message to explain why this merge is necessary,
# especially if it merges an updated upstream into a topic branch.
#
# Lines starting with '#' will be ignored, and an empty message aborts
# the commit.
2019-09-18 21:43:46 +08:00
erenup
3cd6289758
Merge remote-tracking branch 'huggingface/master' into run_multiple_choice_merge
...
# Conflicts:
# examples/contrib/run_swag.py
2019-09-18 21:16:59 +08:00
Julien Chaumond
62760baf46
tiny fixes
2019-09-17 18:29:15 -04:00
thomwolf
45de034bf8
fix #1223
2019-09-17 10:25:06 +02:00
erenup
a9debaca3d
fixed init_weight
2019-09-16 19:55:24 +08:00
erenup
982f181aa7
Merge remote-tracking branch 'origin/master' into run_multiple_choice_add_doc
2019-09-16 19:12:00 +08:00
erenup
84b9d1c423
Merge remote-tracking branch 'huggingface/master'
...
# Conflicts:
# pytorch_transformers/__init__.py
2019-09-16 19:06:12 +08:00
erenup
4812a5a767
add doc string
2019-09-16 11:50:18 +08:00
Zili Wang
8bdee1cb73
fixed: hard coding for max and min number will out of range in fp16, which will cause nan.
2019-09-11 15:41:53 +08:00
mattolson93
f2cf6ce4a9
Fixing typo in gpt2 for doc site's class link
2019-09-10 09:12:01 -07:00
Thomas Wolf
2c177a87eb
Merge pull request #1228 from huggingface/head-masking-test
...
Trying to fix the head masking test
2019-09-10 11:55:27 +02:00
Thomas Wolf
3f05de6dde
Merge branch 'master' into reorder_arguments
2019-09-09 15:42:25 +03:00
thomwolf
3401980fc4
fix #1208
2019-09-09 10:22:12 +03:00
Thomas Wolf
5ac8b62265
Merge pull request #1205 from maru0kun/patch-2
...
Fix typo
2019-09-05 21:44:16 +02:00
thomwolf
5c6cac102b
adding test for common properties and cleaning up a bit base class
2019-09-05 21:31:29 +02:00
maru0kun
d737947725
Fix typo
2019-09-05 19:24:57 +09:00
thomwolf
85df4f7cca
also gathering file names in file_utils
2019-09-05 02:34:09 +02:00
thomwolf
121f88cae3
update conversion scripts
2019-09-05 02:17:50 +02:00
thomwolf
d77abd4d08
clean ups
2019-09-05 00:41:24 +02:00
thomwolf
2a667b1eb9
split configuration and modeling files
2019-09-05 00:27:11 +02:00
thomwolf
0be6a2a624
be sure we have uint8
2019-09-04 22:47:38 +02:00
thomwolf
7fba47b7d9
WIP reordering
2019-09-04 22:39:23 +02:00
thomwolf
e25cba78cf
WIP reodering arguments for torchscript and TF
2019-09-04 22:39:23 +02:00
thomwolf
38b79b5a63
Fixing this TransformerXL bool issue
2019-09-04 22:36:30 +02:00
thomwolf
89fd3450a6
Release: 1.2.0
2019-09-04 13:32:18 +02:00
Shijie Wu
a15562e170
Fix reference of import when called for the second time
2019-09-03 18:27:29 -07:00
Thomas Wolf
0287d264e9
Merge pull request #1162 from huggingface/xlnet-bias
...
XLNet bias fix on resize embeddings (cf #1124 )
2019-09-02 23:14:04 +02:00
LysandreJik
31d3373bc9
Appends space before special token
2019-09-01 21:07:00 -04:00
thomwolf
fede4ef45d
fixing #1133
2019-09-02 02:27:39 +02:00
Thomas Wolf
ff7368eb6b
Merge pull request #1077 from huggingface/pruning-save-and-load
...
Pruning changes so that deleted heads are kept on save/load
2019-09-01 09:42:15 +02:00
LysandreJik
6ae0bb5291
XLM 100 different URLs
2019-08-31 14:46:31 -04:00
LysandreJik
819b468f70
Fixed XLM model url
2019-08-31 14:40:51 -04:00
LysandreJik
58b59a0c31
Random seed is accessible anywhere within the common tests
2019-08-31 13:17:08 -04:00
LysandreJik
ea86bef545
Check for None
2019-08-31 00:56:22 -04:00
LysandreJik
e0f867a9ba
XLNet bias fix on resize embeddings (cf #1124 )
2019-08-31 00:50:59 -04:00
LysandreJik
11600edc6e
Rebase on master + DistilBERT head pruning patch
2019-08-31 00:37:41 -04:00
LysandreJik
b6992b7b47
Applied patch to OpenAI GPT, RoBERTa, TransfoL, XLM and XLNet
2019-08-31 00:33:50 -04:00
thomwolf
bdb4409ed8
updated pruning logic with sets - Bert and GPT-2
2019-08-31 00:33:50 -04:00
LysandreJik
0c8e823b03
Added patch to remaining models
2019-08-31 00:33:50 -04:00
LysandreJik
0cd283522a
Attempt to fix head index
2019-08-31 00:33:50 -04:00
LysandreJik
c85b5db61a
Conditional append/init + fixed warning
2019-08-31 00:33:50 -04:00
LysandreJik
5c2b94c82a
Changed string so that Circle CI accepts the warning
2019-08-31 00:33:50 -04:00
LysandreJik
87747518e9
Blocks deletion from already deleted heads. Necessary integration test.
...
Now raises a warning when a head to be deleted already has been deleted. An integration test verifying the total pipeline (-> from config -> save model -> load model -> additional head pruning) has been added.
2019-08-31 00:33:50 -04:00
LysandreJik
719cb3738d
Pruning for GPT and GPT-2
2019-08-31 00:33:50 -04:00
LysandreJik
fc1fbae45d
XLM can be pruned
2019-08-31 00:33:50 -04:00
Lysandre
42e00cf9e1
Pruning saved to configuration first try
2019-08-31 00:33:50 -04:00
LysandreJik
d7a4c3252e
Fixed filename
2019-08-31 00:08:56 -04:00
LysandreJik