neu-eddata-yjzhang
commited on
Commit
•
2e08f8f
1
Parent(s):
c010025
1111
Browse files- ._LICENSE.txt +0 -0
- ._README.md +0 -0
- ._config.json +0 -0
- ._flax_model.msgpack +3 -0
- ._gitattributes.txt +0 -0
- ._pytorch_model.bin +3 -0
- ._rust_model.ot +3 -0
- ._tf_model.h5 +3 -0
- ._tokenizer.json +0 -0
- ._tokenizer_config.json +0 -0
- ._vocab.txt +0 -0
- LICENSE.txt +201 -0
- README.md +251 -0
- config.json +24 -0
- flax_model.msgpack +3 -0
- gitattributes.txt +10 -0
- pytorch_model.bin +3 -0
- rust_model.ot +3 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +3 -0
- vocab.txt +0 -0
._LICENSE.txt
ADDED
Binary file (4.1 kB). View file
|
|
._README.md
ADDED
Binary file (4.1 kB). View file
|
|
._config.json
ADDED
Binary file (4.1 kB). View file
|
|
._flax_model.msgpack
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0264486d338aa060baa17ea139617c872ac8cc36566a46ffb4d72a18664e433a
|
3 |
+
size 4096
|
._gitattributes.txt
ADDED
Binary file (4.1 kB). View file
|
|
._pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8603087bf31f59bda5bbcaa7ddd395ebcf2f8cf33b986468ea5738da0cb6aef
|
3 |
+
size 4096
|
._rust_model.ot
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39e0b16831252668d0759237f2702eaadf3cfd0a858eba391542b1403afdc321
|
3 |
+
size 4096
|
._tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5083bb65dcea2c6324557b02aed52027a975b45381080fd17d8a834e87976780
|
3 |
+
size 4096
|
._tokenizer.json
ADDED
Binary file (4.1 kB). View file
|
|
._tokenizer_config.json
ADDED
Binary file (4.1 kB). View file
|
|
._vocab.txt
ADDED
Binary file (4.1 kB). View file
|
|
LICENSE.txt
ADDED
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Apache License
|
2 |
+
Version 2.0, January 2004
|
3 |
+
http://www.apache.org/licenses/
|
4 |
+
|
5 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
6 |
+
|
7 |
+
1. Definitions.
|
8 |
+
|
9 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
10 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
11 |
+
|
12 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
13 |
+
the copyright owner that is granting the License.
|
14 |
+
|
15 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
16 |
+
other entities that control, are controlled by, or are under common
|
17 |
+
control with that entity. For the purposes of this definition,
|
18 |
+
"control" means (i) the power, direct or indirect, to cause the
|
19 |
+
direction or management of such entity, whether by contract or
|
20 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
21 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
22 |
+
|
23 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
24 |
+
exercising permissions granted by this License.
|
25 |
+
|
26 |
+
"Source" form shall mean the preferred form for making modifications,
|
27 |
+
including but not limited to software source code, documentation
|
28 |
+
source, and configuration files.
|
29 |
+
|
30 |
+
"Object" form shall mean any form resulting from mechanical
|
31 |
+
transformation or translation of a Source form, including but
|
32 |
+
not limited to compiled object code, generated documentation,
|
33 |
+
and conversions to other media types.
|
34 |
+
|
35 |
+
"Work" shall mean the work of authorship, whether in Source or
|
36 |
+
Object form, made available under the License, as indicated by a
|
37 |
+
copyright notice that is included in or attached to the work
|
38 |
+
(an example is provided in the Appendix below).
|
39 |
+
|
40 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
41 |
+
form, that is based on (or derived from) the Work and for which the
|
42 |
+
editorial revisions, annotations, elaborations, or other modifications
|
43 |
+
represent, as a whole, an original work of authorship. For the purposes
|
44 |
+
of this License, Derivative Works shall not include works that remain
|
45 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
46 |
+
the Work and Derivative Works thereof.
|
47 |
+
|
48 |
+
"Contribution" shall mean any work of authorship, including
|
49 |
+
the original version of the Work and any modifications or additions
|
50 |
+
to that Work or Derivative Works thereof, that is intentionally
|
51 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
52 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
53 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
54 |
+
means any form of electronic, verbal, or written communication sent
|
55 |
+
to the Licensor or its representatives, including but not limited to
|
56 |
+
communication on electronic mailing lists, source code control systems,
|
57 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
58 |
+
Licensor for the purpose of discussing and improving the Work, but
|
59 |
+
excluding communication that is conspicuously marked or otherwise
|
60 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
61 |
+
|
62 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
63 |
+
on behalf of whom a Contribution has been received by Licensor and
|
64 |
+
subsequently incorporated within the Work.
|
65 |
+
|
66 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
67 |
+
this License, each Contributor hereby grants to You a perpetual,
|
68 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
69 |
+
copyright license to reproduce, prepare Derivative Works of,
|
70 |
+
publicly display, publicly perform, sublicense, and distribute the
|
71 |
+
Work and such Derivative Works in Source or Object form.
|
72 |
+
|
73 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
74 |
+
this License, each Contributor hereby grants to You a perpetual,
|
75 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
76 |
+
(except as stated in this section) patent license to make, have made,
|
77 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
78 |
+
where such license applies only to those patent claims licensable
|
79 |
+
by such Contributor that are necessarily infringed by their
|
80 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
81 |
+
with the Work to which such Contribution(s) was submitted. If You
|
82 |
+
institute patent litigation against any entity (including a
|
83 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
84 |
+
or a Contribution incorporated within the Work constitutes direct
|
85 |
+
or contributory patent infringement, then any patent licenses
|
86 |
+
granted to You under this License for that Work shall terminate
|
87 |
+
as of the date such litigation is filed.
|
88 |
+
|
89 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
90 |
+
Work or Derivative Works thereof in any medium, with or without
|
91 |
+
modifications, and in Source or Object form, provided that You
|
92 |
+
meet the following conditions:
|
93 |
+
|
94 |
+
(a) You must give any other recipients of the Work or
|
95 |
+
Derivative Works a copy of this License; and
|
96 |
+
|
97 |
+
(b) You must cause any modified files to carry prominent notices
|
98 |
+
stating that You changed the files; and
|
99 |
+
|
100 |
+
(c) You must retain, in the Source form of any Derivative Works
|
101 |
+
that You distribute, all copyright, patent, trademark, and
|
102 |
+
attribution notices from the Source form of the Work,
|
103 |
+
excluding those notices that do not pertain to any part of
|
104 |
+
the Derivative Works; and
|
105 |
+
|
106 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
107 |
+
distribution, then any Derivative Works that You distribute must
|
108 |
+
include a readable copy of the attribution notices contained
|
109 |
+
within such NOTICE file, excluding those notices that do not
|
110 |
+
pertain to any part of the Derivative Works, in at least one
|
111 |
+
of the following places: within a NOTICE text file distributed
|
112 |
+
as part of the Derivative Works; within the Source form or
|
113 |
+
documentation, if provided along with the Derivative Works; or,
|
114 |
+
within a display generated by the Derivative Works, if and
|
115 |
+
wherever such third-party notices normally appear. The contents
|
116 |
+
of the NOTICE file are for informational purposes only and
|
117 |
+
do not modify the License. You may add Your own attribution
|
118 |
+
notices within Derivative Works that You distribute, alongside
|
119 |
+
or as an addendum to the NOTICE text from the Work, provided
|
120 |
+
that such additional attribution notices cannot be construed
|
121 |
+
as modifying the License.
|
122 |
+
|
123 |
+
You may add Your own copyright statement to Your modifications and
|
124 |
+
may provide additional or different license terms and conditions
|
125 |
+
for use, reproduction, or distribution of Your modifications, or
|
126 |
+
for any such Derivative Works as a whole, provided Your use,
|
127 |
+
reproduction, and distribution of the Work otherwise complies with
|
128 |
+
the conditions stated in this License.
|
129 |
+
|
130 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
131 |
+
any Contribution intentionally submitted for inclusion in the Work
|
132 |
+
by You to the Licensor shall be under the terms and conditions of
|
133 |
+
this License, without any additional terms or conditions.
|
134 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
135 |
+
the terms of any separate license agreement you may have executed
|
136 |
+
with Licensor regarding such Contributions.
|
137 |
+
|
138 |
+
6. Trademarks. This License does not grant permission to use the trade
|
139 |
+
names, trademarks, service marks, or product names of the Licensor,
|
140 |
+
except as required for reasonable and customary use in describing the
|
141 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
142 |
+
|
143 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
144 |
+
agreed to in writing, Licensor provides the Work (and each
|
145 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
146 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
147 |
+
implied, including, without limitation, any warranties or conditions
|
148 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
149 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
150 |
+
appropriateness of using or redistributing the Work and assume any
|
151 |
+
risks associated with Your exercise of permissions under this License.
|
152 |
+
|
153 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
154 |
+
whether in tort (including negligence), contract, or otherwise,
|
155 |
+
unless required by applicable law (such as deliberate and grossly
|
156 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
157 |
+
liable to You for damages, including any direct, indirect, special,
|
158 |
+
incidental, or consequential damages of any character arising as a
|
159 |
+
result of this License or out of the use or inability to use the
|
160 |
+
Work (including but not limited to damages for loss of goodwill,
|
161 |
+
work stoppage, computer failure or malfunction, or any and all
|
162 |
+
other commercial damages or losses), even if such Contributor
|
163 |
+
has been advised of the possibility of such damages.
|
164 |
+
|
165 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
166 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
167 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
168 |
+
or other liability obligations and/or rights consistent with this
|
169 |
+
License. However, in accepting such obligations, You may act only
|
170 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
171 |
+
of any other Contributor, and only if You agree to indemnify,
|
172 |
+
defend, and hold each Contributor harmless for any liability
|
173 |
+
incurred by, or claims asserted against, such Contributor by reason
|
174 |
+
of your accepting any such warranty or additional liability.
|
175 |
+
|
176 |
+
END OF TERMS AND CONDITIONS
|
177 |
+
|
178 |
+
APPENDIX: How to apply the Apache License to your work.
|
179 |
+
|
180 |
+
To apply the Apache License to your work, attach the following
|
181 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
182 |
+
replaced with your own identifying information. (Don't include
|
183 |
+
the brackets!) The text should be enclosed in the appropriate
|
184 |
+
comment syntax for the file format. We also recommend that a
|
185 |
+
file or class name and description of purpose be included on the
|
186 |
+
same "printed page" as the copyright notice for easier
|
187 |
+
identification within third-party archives.
|
188 |
+
|
189 |
+
Copyright [yyyy] [name of copyright owner]
|
190 |
+
|
191 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
192 |
+
you may not use this file except in compliance with the License.
|
193 |
+
You may obtain a copy of the License at
|
194 |
+
|
195 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
196 |
+
|
197 |
+
Unless required by applicable law or agreed to in writing, software
|
198 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
199 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
200 |
+
See the License for the specific language governing permissions and
|
201 |
+
limitations under the License.
|
README.md
ADDED
@@ -0,0 +1,251 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: en
|
3 |
+
tags:
|
4 |
+
- exbert
|
5 |
+
license: apache-2.0
|
6 |
+
datasets:
|
7 |
+
- bookcorpus
|
8 |
+
- wikipedia
|
9 |
+
---
|
10 |
+
|
11 |
+
# BERT base model (uncased)
|
12 |
+
|
13 |
+
Pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in
|
14 |
+
[this paper](https://arxiv.org/abs/1810.04805) and first released in
|
15 |
+
[this repository](https://github.com/google-research/bert). This model is uncased: it does not make a difference
|
16 |
+
between english and English.
|
17 |
+
|
18 |
+
Disclaimer: The team releasing BERT did not write a model card for this model so this model card has been written by
|
19 |
+
the Hugging Face team.
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it
|
24 |
+
was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of
|
25 |
+
publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it
|
26 |
+
was pretrained with two objectives:
|
27 |
+
|
28 |
+
- Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run
|
29 |
+
the entire masked sentence through the model and has to predict the masked words. This is different from traditional
|
30 |
+
recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like
|
31 |
+
GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the
|
32 |
+
sentence.
|
33 |
+
- Next sentence prediction (NSP): the models concatenates two masked sentences as inputs during pretraining. Sometimes
|
34 |
+
they correspond to sentences that were next to each other in the original text, sometimes not. The model then has to
|
35 |
+
predict if the two sentences were following each other or not.
|
36 |
+
|
37 |
+
This way, the model learns an inner representation of the English language that can then be used to extract features
|
38 |
+
useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard
|
39 |
+
classifier using the features produced by the BERT model as inputs.
|
40 |
+
|
41 |
+
## Model variations
|
42 |
+
|
43 |
+
BERT has originally been released in base and large variations, for cased and uncased input text. The uncased models also strips out an accent markers.
|
44 |
+
Chinese and multilingual uncased and cased versions followed shortly after.
|
45 |
+
Modified preprocessing with whole word masking has replaced subpiece masking in a following work, with the release of two models.
|
46 |
+
Other 24 smaller models are released afterwards.
|
47 |
+
|
48 |
+
The detailed release history can be found on the [google-research/bert readme](https://github.com/google-research/bert/blob/master/README.md) on github.
|
49 |
+
|
50 |
+
| Model | #params | Language |
|
51 |
+
|------------------------|--------------------------------|-------|
|
52 |
+
| [`bert-base-uncased`](https://huggingface.co/bert-base-uncased) | 110M | English |
|
53 |
+
| [`bert-large-uncased`](https://huggingface.co/bert-large-uncased) | 340M | English | sub
|
54 |
+
| [`bert-base-cased`](https://huggingface.co/bert-base-cased) | 110M | English |
|
55 |
+
| [`bert-large-cased`](https://huggingface.co/bert-large-cased) | 340M | English |
|
56 |
+
| [`bert-base-chinese`](https://huggingface.co/bert-base-chinese) | 110M | Chinese |
|
57 |
+
| [`bert-base-multilingual-cased`](https://huggingface.co/bert-base-multilingual-cased) | 110M | Multiple |
|
58 |
+
| [`bert-large-uncased-whole-word-masking`](https://huggingface.co/bert-large-uncased-whole-word-masking) | 340M | English |
|
59 |
+
| [`bert-large-cased-whole-word-masking`](https://huggingface.co/bert-large-cased-whole-word-masking) | 340M | English |
|
60 |
+
|
61 |
+
## Intended uses & limitations
|
62 |
+
|
63 |
+
You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to
|
64 |
+
be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?filter=bert) to look for
|
65 |
+
fine-tuned versions on a task that interests you.
|
66 |
+
|
67 |
+
Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked)
|
68 |
+
to make decisions, such as sequence classification, token classification or question answering. For tasks such as text
|
69 |
+
generation you should look at model like GPT2.
|
70 |
+
|
71 |
+
### How to use
|
72 |
+
|
73 |
+
You can use this model directly with a pipeline for masked language modeling:
|
74 |
+
|
75 |
+
```python
|
76 |
+
>>> from transformers import pipeline
|
77 |
+
>>> unmasker = pipeline('fill-mask', model='bert-base-uncased')
|
78 |
+
>>> unmasker("Hello I'm a [MASK] model.")
|
79 |
+
|
80 |
+
[{'sequence': "[CLS] hello i'm a fashion model. [SEP]",
|
81 |
+
'score': 0.1073106899857521,
|
82 |
+
'token': 4827,
|
83 |
+
'token_str': 'fashion'},
|
84 |
+
{'sequence': "[CLS] hello i'm a role model. [SEP]",
|
85 |
+
'score': 0.08774490654468536,
|
86 |
+
'token': 2535,
|
87 |
+
'token_str': 'role'},
|
88 |
+
{'sequence': "[CLS] hello i'm a new model. [SEP]",
|
89 |
+
'score': 0.05338378623127937,
|
90 |
+
'token': 2047,
|
91 |
+
'token_str': 'new'},
|
92 |
+
{'sequence': "[CLS] hello i'm a super model. [SEP]",
|
93 |
+
'score': 0.04667217284440994,
|
94 |
+
'token': 3565,
|
95 |
+
'token_str': 'super'},
|
96 |
+
{'sequence': "[CLS] hello i'm a fine model. [SEP]",
|
97 |
+
'score': 0.027095865458250046,
|
98 |
+
'token': 2986,
|
99 |
+
'token_str': 'fine'}]
|
100 |
+
```
|
101 |
+
|
102 |
+
Here is how to use this model to get the features of a given text in PyTorch:
|
103 |
+
|
104 |
+
```python
|
105 |
+
from transformers import BertTokenizer, BertModel
|
106 |
+
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
|
107 |
+
model = BertModel.from_pretrained("bert-base-uncased")
|
108 |
+
text = "Replace me by any text you'd like."
|
109 |
+
encoded_input = tokenizer(text, return_tensors='pt')
|
110 |
+
output = model(**encoded_input)
|
111 |
+
```
|
112 |
+
|
113 |
+
and in TensorFlow:
|
114 |
+
|
115 |
+
```python
|
116 |
+
from transformers import BertTokenizer, TFBertModel
|
117 |
+
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
|
118 |
+
model = TFBertModel.from_pretrained("bert-base-uncased")
|
119 |
+
text = "Replace me by any text you'd like."
|
120 |
+
encoded_input = tokenizer(text, return_tensors='tf')
|
121 |
+
output = model(encoded_input)
|
122 |
+
```
|
123 |
+
|
124 |
+
### Limitations and bias
|
125 |
+
|
126 |
+
Even if the training data used for this model could be characterized as fairly neutral, this model can have biased
|
127 |
+
predictions:
|
128 |
+
|
129 |
+
```python
|
130 |
+
>>> from transformers import pipeline
|
131 |
+
>>> unmasker = pipeline('fill-mask', model='bert-base-uncased')
|
132 |
+
>>> unmasker("The man worked as a [MASK].")
|
133 |
+
|
134 |
+
[{'sequence': '[CLS] the man worked as a carpenter. [SEP]',
|
135 |
+
'score': 0.09747550636529922,
|
136 |
+
'token': 10533,
|
137 |
+
'token_str': 'carpenter'},
|
138 |
+
{'sequence': '[CLS] the man worked as a waiter. [SEP]',
|
139 |
+
'score': 0.0523831807076931,
|
140 |
+
'token': 15610,
|
141 |
+
'token_str': 'waiter'},
|
142 |
+
{'sequence': '[CLS] the man worked as a barber. [SEP]',
|
143 |
+
'score': 0.04962705448269844,
|
144 |
+
'token': 13362,
|
145 |
+
'token_str': 'barber'},
|
146 |
+
{'sequence': '[CLS] the man worked as a mechanic. [SEP]',
|
147 |
+
'score': 0.03788609802722931,
|
148 |
+
'token': 15893,
|
149 |
+
'token_str': 'mechanic'},
|
150 |
+
{'sequence': '[CLS] the man worked as a salesman. [SEP]',
|
151 |
+
'score': 0.037680890411138535,
|
152 |
+
'token': 18968,
|
153 |
+
'token_str': 'salesman'}]
|
154 |
+
|
155 |
+
>>> unmasker("The woman worked as a [MASK].")
|
156 |
+
|
157 |
+
[{'sequence': '[CLS] the woman worked as a nurse. [SEP]',
|
158 |
+
'score': 0.21981462836265564,
|
159 |
+
'token': 6821,
|
160 |
+
'token_str': 'nurse'},
|
161 |
+
{'sequence': '[CLS] the woman worked as a waitress. [SEP]',
|
162 |
+
'score': 0.1597415804862976,
|
163 |
+
'token': 13877,
|
164 |
+
'token_str': 'waitress'},
|
165 |
+
{'sequence': '[CLS] the woman worked as a maid. [SEP]',
|
166 |
+
'score': 0.1154729500412941,
|
167 |
+
'token': 10850,
|
168 |
+
'token_str': 'maid'},
|
169 |
+
{'sequence': '[CLS] the woman worked as a prostitute. [SEP]',
|
170 |
+
'score': 0.037968918681144714,
|
171 |
+
'token': 19215,
|
172 |
+
'token_str': 'prostitute'},
|
173 |
+
{'sequence': '[CLS] the woman worked as a cook. [SEP]',
|
174 |
+
'score': 0.03042375110089779,
|
175 |
+
'token': 5660,
|
176 |
+
'token_str': 'cook'}]
|
177 |
+
```
|
178 |
+
|
179 |
+
This bias will also affect all fine-tuned versions of this model.
|
180 |
+
|
181 |
+
## Training data
|
182 |
+
|
183 |
+
The BERT model was pretrained on [BookCorpus](https://yknzhu.wixsite.com/mbweb), a dataset consisting of 11,038
|
184 |
+
unpublished books and [English Wikipedia](https://en.wikipedia.org/wiki/English_Wikipedia) (excluding lists, tables and
|
185 |
+
headers).
|
186 |
+
|
187 |
+
## Training procedure
|
188 |
+
|
189 |
+
### Preprocessing
|
190 |
+
|
191 |
+
The texts are lowercased and tokenized using WordPiece and a vocabulary size of 30,000. The inputs of the model are
|
192 |
+
then of the form:
|
193 |
+
|
194 |
+
```
|
195 |
+
[CLS] Sentence A [SEP] Sentence B [SEP]
|
196 |
+
```
|
197 |
+
|
198 |
+
With probability 0.5, sentence A and sentence B correspond to two consecutive sentences in the original corpus and in
|
199 |
+
the other cases, it's another random sentence in the corpus. Note that what is considered a sentence here is a
|
200 |
+
consecutive span of text usually longer than a single sentence. The only constrain is that the result with the two
|
201 |
+
"sentences" has a combined length of less than 512 tokens.
|
202 |
+
|
203 |
+
The details of the masking procedure for each sentence are the following:
|
204 |
+
- 15% of the tokens are masked.
|
205 |
+
- In 80% of the cases, the masked tokens are replaced by `[MASK]`.
|
206 |
+
- In 10% of the cases, the masked tokens are replaced by a random token (different) from the one they replace.
|
207 |
+
- In the 10% remaining cases, the masked tokens are left as is.
|
208 |
+
|
209 |
+
### Pretraining
|
210 |
+
|
211 |
+
The model was trained on 4 cloud TPUs in Pod configuration (16 TPU chips total) for one million steps with a batch size
|
212 |
+
of 256. The sequence length was limited to 128 tokens for 90% of the steps and 512 for the remaining 10%. The optimizer
|
213 |
+
used is Adam with a learning rate of 1e-4, \\(\beta_{1} = 0.9\\) and \\(\beta_{2} = 0.999\\), a weight decay of 0.01,
|
214 |
+
learning rate warmup for 10,000 steps and linear decay of the learning rate after.
|
215 |
+
|
216 |
+
## Evaluation results
|
217 |
+
|
218 |
+
When fine-tuned on downstream tasks, this model achieves the following results:
|
219 |
+
|
220 |
+
Glue test results:
|
221 |
+
|
222 |
+
| Task | MNLI-(m/mm) | QQP | QNLI | SST-2 | CoLA | STS-B | MRPC | RTE | Average |
|
223 |
+
|:----:|:-----------:|:----:|:----:|:-----:|:----:|:-----:|:----:|:----:|:-------:|
|
224 |
+
| | 84.6/83.4 | 71.2 | 90.5 | 93.5 | 52.1 | 85.8 | 88.9 | 66.4 | 79.6 |
|
225 |
+
|
226 |
+
|
227 |
+
### BibTeX entry and citation info
|
228 |
+
|
229 |
+
```bibtex
|
230 |
+
@article{DBLP:journals/corr/abs-1810-04805,
|
231 |
+
author = {Jacob Devlin and
|
232 |
+
Ming{-}Wei Chang and
|
233 |
+
Kenton Lee and
|
234 |
+
Kristina Toutanova},
|
235 |
+
title = {{BERT:} Pre-training of Deep Bidirectional Transformers for Language
|
236 |
+
Understanding},
|
237 |
+
journal = {CoRR},
|
238 |
+
volume = {abs/1810.04805},
|
239 |
+
year = {2018},
|
240 |
+
url = {http://arxiv.org/abs/1810.04805},
|
241 |
+
archivePrefix = {arXiv},
|
242 |
+
eprint = {1810.04805},
|
243 |
+
timestamp = {Tue, 30 Oct 2018 20:39:56 +0100},
|
244 |
+
biburl = {https://dblp.org/rec/journals/corr/abs-1810-04805.bib},
|
245 |
+
bibsource = {dblp computer science bibliography, https://dblp.org}
|
246 |
+
}
|
247 |
+
```
|
248 |
+
|
249 |
+
<a href="https://huggingface.co/exbert/?model=bert-base-uncased">
|
250 |
+
<img width="300px" src="https://cdn-media.huggingface.co/exbert/button.png">
|
251 |
+
</a>
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"transformers_version": "4.4.1",
|
21 |
+
"type_vocab_size": 2,
|
22 |
+
"use_cache": true,
|
23 |
+
"vocab_size": 30522
|
24 |
+
}
|
flax_model.msgpack
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea201fabe466ef7182f1f687fb5be4b62a73d3a78883f11264ff7f682cdb54bf
|
3 |
+
size 438064459
|
gitattributes.txt
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c533e6ead764989ed5506bdb2edfc5a6b53bd6c93be0c60b1921ce74cda30a68
|
3 |
+
size 437981044
|
rust_model.ot
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afd9aa425fd45c5655d3d43a0d041f9b76729bf475d6c017a0e9304a38f89972
|
3 |
+
size 534240408
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7a17d6d844b5de815ccab5f42cad6d24496db3850a2a43d8258221018ce87d2
|
3 |
+
size 536063208
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_lower_case": true
|
3 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|