tokenizers 0.2.0-x86_64-linux

Sign up to get free protection for your applications and to get access to all the features.
data/LICENSE.txt ADDED
@@ -0,0 +1,202 @@
1
+
2
+ Apache License
3
+ Version 2.0, January 2004
4
+ http://www.apache.org/licenses/
5
+
6
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7
+
8
+ 1. Definitions.
9
+
10
+ "License" shall mean the terms and conditions for use, reproduction,
11
+ and distribution as defined by Sections 1 through 9 of this document.
12
+
13
+ "Licensor" shall mean the copyright owner or entity authorized by
14
+ the copyright owner that is granting the License.
15
+
16
+ "Legal Entity" shall mean the union of the acting entity and all
17
+ other entities that control, are controlled by, or are under common
18
+ control with that entity. For the purposes of this definition,
19
+ "control" means (i) the power, direct or indirect, to cause the
20
+ direction or management of such entity, whether by contract or
21
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
22
+ outstanding shares, or (iii) beneficial ownership of such entity.
23
+
24
+ "You" (or "Your") shall mean an individual or Legal Entity
25
+ exercising permissions granted by this License.
26
+
27
+ "Source" form shall mean the preferred form for making modifications,
28
+ including but not limited to software source code, documentation
29
+ source, and configuration files.
30
+
31
+ "Object" form shall mean any form resulting from mechanical
32
+ transformation or translation of a Source form, including but
33
+ not limited to compiled object code, generated documentation,
34
+ and conversions to other media types.
35
+
36
+ "Work" shall mean the work of authorship, whether in Source or
37
+ Object form, made available under the License, as indicated by a
38
+ copyright notice that is included in or attached to the work
39
+ (an example is provided in the Appendix below).
40
+
41
+ "Derivative Works" shall mean any work, whether in Source or Object
42
+ form, that is based on (or derived from) the Work and for which the
43
+ editorial revisions, annotations, elaborations, or other modifications
44
+ represent, as a whole, an original work of authorship. For the purposes
45
+ of this License, Derivative Works shall not include works that remain
46
+ separable from, or merely link (or bind by name) to the interfaces of,
47
+ the Work and Derivative Works thereof.
48
+
49
+ "Contribution" shall mean any work of authorship, including
50
+ the original version of the Work and any modifications or additions
51
+ to that Work or Derivative Works thereof, that is intentionally
52
+ submitted to Licensor for inclusion in the Work by the copyright owner
53
+ or by an individual or Legal Entity authorized to submit on behalf of
54
+ the copyright owner. For the purposes of this definition, "submitted"
55
+ means any form of electronic, verbal, or written communication sent
56
+ to the Licensor or its representatives, including but not limited to
57
+ communication on electronic mailing lists, source code control systems,
58
+ and issue tracking systems that are managed by, or on behalf of, the
59
+ Licensor for the purpose of discussing and improving the Work, but
60
+ excluding communication that is conspicuously marked or otherwise
61
+ designated in writing by the copyright owner as "Not a Contribution."
62
+
63
+ "Contributor" shall mean Licensor and any individual or Legal Entity
64
+ on behalf of whom a Contribution has been received by Licensor and
65
+ subsequently incorporated within the Work.
66
+
67
+ 2. Grant of Copyright License. Subject to the terms and conditions of
68
+ this License, each Contributor hereby grants to You a perpetual,
69
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70
+ copyright license to reproduce, prepare Derivative Works of,
71
+ publicly display, publicly perform, sublicense, and distribute the
72
+ Work and such Derivative Works in Source or Object form.
73
+
74
+ 3. Grant of Patent License. Subject to the terms and conditions of
75
+ this License, each Contributor hereby grants to You a perpetual,
76
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
+ (except as stated in this section) patent license to make, have made,
78
+ use, offer to sell, sell, import, and otherwise transfer the Work,
79
+ where such license applies only to those patent claims licensable
80
+ by such Contributor that are necessarily infringed by their
81
+ Contribution(s) alone or by combination of their Contribution(s)
82
+ with the Work to which such Contribution(s) was submitted. If You
83
+ institute patent litigation against any entity (including a
84
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
85
+ or a Contribution incorporated within the Work constitutes direct
86
+ or contributory patent infringement, then any patent licenses
87
+ granted to You under this License for that Work shall terminate
88
+ as of the date such litigation is filed.
89
+
90
+ 4. Redistribution. You may reproduce and distribute copies of the
91
+ Work or Derivative Works thereof in any medium, with or without
92
+ modifications, and in Source or Object form, provided that You
93
+ meet the following conditions:
94
+
95
+ (a) You must give any other recipients of the Work or
96
+ Derivative Works a copy of this License; and
97
+
98
+ (b) You must cause any modified files to carry prominent notices
99
+ stating that You changed the files; and
100
+
101
+ (c) You must retain, in the Source form of any Derivative Works
102
+ that You distribute, all copyright, patent, trademark, and
103
+ attribution notices from the Source form of the Work,
104
+ excluding those notices that do not pertain to any part of
105
+ the Derivative Works; and
106
+
107
+ (d) If the Work includes a "NOTICE" text file as part of its
108
+ distribution, then any Derivative Works that You distribute must
109
+ include a readable copy of the attribution notices contained
110
+ within such NOTICE file, excluding those notices that do not
111
+ pertain to any part of the Derivative Works, in at least one
112
+ of the following places: within a NOTICE text file distributed
113
+ as part of the Derivative Works; within the Source form or
114
+ documentation, if provided along with the Derivative Works; or,
115
+ within a display generated by the Derivative Works, if and
116
+ wherever such third-party notices normally appear. The contents
117
+ of the NOTICE file are for informational purposes only and
118
+ do not modify the License. You may add Your own attribution
119
+ notices within Derivative Works that You distribute, alongside
120
+ or as an addendum to the NOTICE text from the Work, provided
121
+ that such additional attribution notices cannot be construed
122
+ as modifying the License.
123
+
124
+ You may add Your own copyright statement to Your modifications and
125
+ may provide additional or different license terms and conditions
126
+ for use, reproduction, or distribution of Your modifications, or
127
+ for any such Derivative Works as a whole, provided Your use,
128
+ reproduction, and distribution of the Work otherwise complies with
129
+ the conditions stated in this License.
130
+
131
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
132
+ any Contribution intentionally submitted for inclusion in the Work
133
+ by You to the Licensor shall be under the terms and conditions of
134
+ this License, without any additional terms or conditions.
135
+ Notwithstanding the above, nothing herein shall supersede or modify
136
+ the terms of any separate license agreement you may have executed
137
+ with Licensor regarding such Contributions.
138
+
139
+ 6. Trademarks. This License does not grant permission to use the trade
140
+ names, trademarks, service marks, or product names of the Licensor,
141
+ except as required for reasonable and customary use in describing the
142
+ origin of the Work and reproducing the content of the NOTICE file.
143
+
144
+ 7. Disclaimer of Warranty. Unless required by applicable law or
145
+ agreed to in writing, Licensor provides the Work (and each
146
+ Contributor provides its Contributions) on an "AS IS" BASIS,
147
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148
+ implied, including, without limitation, any warranties or conditions
149
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150
+ PARTICULAR PURPOSE. You are solely responsible for determining the
151
+ appropriateness of using or redistributing the Work and assume any
152
+ risks associated with Your exercise of permissions under this License.
153
+
154
+ 8. Limitation of Liability. In no event and under no legal theory,
155
+ whether in tort (including negligence), contract, or otherwise,
156
+ unless required by applicable law (such as deliberate and grossly
157
+ negligent acts) or agreed to in writing, shall any Contributor be
158
+ liable to You for damages, including any direct, indirect, special,
159
+ incidental, or consequential damages of any character arising as a
160
+ result of this License or out of the use or inability to use the
161
+ Work (including but not limited to damages for loss of goodwill,
162
+ work stoppage, computer failure or malfunction, or any and all
163
+ other commercial damages or losses), even if such Contributor
164
+ has been advised of the possibility of such damages.
165
+
166
+ 9. Accepting Warranty or Additional Liability. While redistributing
167
+ the Work or Derivative Works thereof, You may choose to offer,
168
+ and charge a fee for, acceptance of support, warranty, indemnity,
169
+ or other liability obligations and/or rights consistent with this
170
+ License. However, in accepting such obligations, You may act only
171
+ on Your own behalf and on Your sole responsibility, not on behalf
172
+ of any other Contributor, and only if You agree to indemnify,
173
+ defend, and hold each Contributor harmless for any liability
174
+ incurred by, or claims asserted against, such Contributor by reason
175
+ of your accepting any such warranty or additional liability.
176
+
177
+ END OF TERMS AND CONDITIONS
178
+
179
+ APPENDIX: How to apply the Apache License to your work.
180
+
181
+ To apply the Apache License to your work, attach the following
182
+ boilerplate notice, with the fields enclosed by brackets "[]"
183
+ replaced with your own identifying information. (Don't include
184
+ the brackets!) The text should be enclosed in the appropriate
185
+ comment syntax for the file format. We also recommend that a
186
+ file or class name and description of purpose be included on the
187
+ same "printed page" as the copyright notice for easier
188
+ identification within third-party archives.
189
+
190
+ Copyright [yyyy] [name of copyright owner]
191
+
192
+ Licensed under the Apache License, Version 2.0 (the "License");
193
+ you may not use this file except in compliance with the License.
194
+ You may obtain a copy of the License at
195
+
196
+ http://www.apache.org/licenses/LICENSE-2.0
197
+
198
+ Unless required by applicable law or agreed to in writing, software
199
+ distributed under the License is distributed on an "AS IS" BASIS,
200
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
+ See the License for the specific language governing permissions and
202
+ limitations under the License.
data/README.md ADDED
@@ -0,0 +1,65 @@
1
+ # Tokenizers Ruby
2
+
3
+ :slightly_smiling_face: Fast state-of-the-art [tokenizers](https://github.com/huggingface/tokenizers) for Ruby
4
+
5
+ [![Build Status](https://github.com/ankane/tokenizers-ruby/workflows/build/badge.svg?branch=master)](https://github.com/ankane/tokenizers-ruby/actions)
6
+
7
+ ## Installation
8
+
9
+ Add this line to your application’s Gemfile:
10
+
11
+ ```ruby
12
+ gem "tokenizers"
13
+ ```
14
+
15
+ ## Getting Started
16
+
17
+ Load a pretrained tokenizer
18
+
19
+ ```ruby
20
+ tokenizer = Tokenizers.from_pretrained("bert-base-cased")
21
+ ```
22
+
23
+ Encode
24
+
25
+ ```ruby
26
+ encoded = tokenizer.encode("I can feel the magic, can you?")
27
+ encoded.ids
28
+ encoded.tokens
29
+ ```
30
+
31
+ Decode
32
+
33
+ ```ruby
34
+ tokenizer.decode(ids)
35
+ ```
36
+
37
+ Load a tokenizer from files
38
+
39
+ ```ruby
40
+ tokenizer = Tokenizers::CharBPETokenizer.new("vocab.json", "merges.txt")
41
+ ```
42
+
43
+ ## History
44
+
45
+ View the [changelog](https://github.com/ankane/tokenizers-ruby/blob/master/CHANGELOG.md)
46
+
47
+ ## Contributing
48
+
49
+ Everyone is encouraged to help improve this project. Here are a few ways you can help:
50
+
51
+ - [Report bugs](https://github.com/ankane/tokenizers-ruby/issues)
52
+ - Fix bugs and [submit pull requests](https://github.com/ankane/tokenizers-ruby/pulls)
53
+ - Write, clarify, or fix documentation
54
+ - Suggest or add new features
55
+
56
+ To get started with development:
57
+
58
+ ```sh
59
+ git clone https://github.com/ankane/tokenizers-ruby.git
60
+ cd tokenizers-ruby
61
+ bundle install
62
+ bundle exec rake compile
63
+ bundle exec rake download:files
64
+ bundle exec rake test
65
+ ```
Binary file
Binary file
Binary file
@@ -0,0 +1,19 @@
1
+ module Tokenizers
2
+ class CharBPETokenizer
3
+ def initialize(vocab, merges)
4
+ @tokenizer = Tokenizer.new(BPE.new(vocab, merges))
5
+ @tokenizer.add_special_tokens(["<unk>"])
6
+ @tokenizer.normalizer = BertNormalizer.new
7
+ @tokenizer.pre_tokenizer = BertPreTokenizer.new
8
+ @tokenizer.decoder = BPEDecoder.new
9
+ end
10
+
11
+ def encode(text)
12
+ @tokenizer.encode(text)
13
+ end
14
+
15
+ def decode(ids)
16
+ @tokenizer.decode(ids)
17
+ end
18
+ end
19
+ end
@@ -0,0 +1,3 @@
1
+ module Tokenizers
2
+ VERSION = "0.2.0"
3
+ end
data/lib/tokenizers.rb ADDED
@@ -0,0 +1,18 @@
1
+ # ext
2
+ begin
3
+ require "tokenizers/#{RUBY_VERSION.to_f}/tokenizers"
4
+ rescue LoadError
5
+ require "tokenizers/tokenizers"
6
+ end
7
+
8
+ # modules
9
+ require "tokenizers/char_bpe_tokenizer"
10
+ require "tokenizers/version"
11
+
12
+ module Tokenizers
13
+ class Error < StandardError; end
14
+
15
+ def self.from_pretrained(identifier, revision: "main", auth_token: nil)
16
+ _from_pretrained(identifier, revision, auth_token)
17
+ end
18
+ end
metadata ADDED
@@ -0,0 +1,57 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: tokenizers
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.2.0
5
+ platform: x86_64-linux
6
+ authors:
7
+ - Andrew Kane
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2022-12-11 00:00:00.000000000 Z
12
+ dependencies: []
13
+ description:
14
+ email: andrew@ankane.org
15
+ executables: []
16
+ extensions: []
17
+ extra_rdoc_files: []
18
+ files:
19
+ - CHANGELOG.md
20
+ - Cargo.lock
21
+ - Cargo.toml
22
+ - LICENSE-THIRD-PARTY.txt
23
+ - LICENSE.txt
24
+ - README.md
25
+ - lib/tokenizers.rb
26
+ - lib/tokenizers/2.7/tokenizers.so
27
+ - lib/tokenizers/3.0/tokenizers.so
28
+ - lib/tokenizers/3.1/tokenizers.so
29
+ - lib/tokenizers/char_bpe_tokenizer.rb
30
+ - lib/tokenizers/version.rb
31
+ homepage: https://github.com/ankane/tokenizers-ruby
32
+ licenses:
33
+ - Apache-2.0
34
+ metadata: {}
35
+ post_install_message:
36
+ rdoc_options: []
37
+ require_paths:
38
+ - lib
39
+ required_ruby_version: !ruby/object:Gem::Requirement
40
+ requirements:
41
+ - - ">="
42
+ - !ruby/object:Gem::Version
43
+ version: '2.7'
44
+ - - "<"
45
+ - !ruby/object:Gem::Version
46
+ version: 3.2.dev
47
+ required_rubygems_version: !ruby/object:Gem::Requirement
48
+ requirements:
49
+ - - ">="
50
+ - !ruby/object:Gem::Version
51
+ version: '0'
52
+ requirements: []
53
+ rubygems_version: 3.3.22
54
+ signing_key:
55
+ specification_version: 4
56
+ summary: Fast state-of-the-art tokenizers for Ruby
57
+ test_files: []