tokenizers 0.5.2-arm64-darwin → 0.5.3-arm64-darwin

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: a00c67519f2c2bb09c0fad42f396006a341be62b41d751096ef772158ed30c7d
4
- data.tar.gz: 977b690303058422c76c41ebde6a8fd9981063cb88423aff535faf8a5c31d5a1
3
+ metadata.gz: dbf96bf34bc5b762a120c8bb0d9d20b637eccaf31b1650d45b46c722b4c7f1b4
4
+ data.tar.gz: 056b0d1dd8d14dbb52c311caa9aba9973ac9ea0ea3b9e26377e2fc69cc4ce598
5
5
  SHA512:
6
- metadata.gz: 7c7ac23930faa7c58cb3c1f282c3fafb1937bc097facaaa45cfdd74f7dc0c59dee57896bfbbd5fd052e6ae3bc849affb4109dbc59a2a75ee4c4f9e644c441c65
7
- data.tar.gz: 9bd2569f96710bc58aeeabd39d991ff56f13682dd86a271cc03dad2205e2a6732bb60c9eab06138405c2cf7d77df0196321d6cf7df6eac6b4f74caabb6d0a9e6
6
+ metadata.gz: c4488747d73279ac570b62a9afa3c8d7751d8b5a30684142a7879538a1450a31955b87cf498c7e671e80a92671166fb210ff992d04d3fa76e21d284884bef86e
7
+ data.tar.gz: 97151485dc583f4dfd9bd4cb4457dd411c1bf9a8953800fe28d532d2ac300a6214220f09a06b8b4e3fb052067f159d010b59feb5cc1e5396225f3d248206d469
data/CHANGELOG.md CHANGED
@@ -1,3 +1,8 @@
1
+ ## 0.5.3 (2024-09-17)
2
+
3
+ - Added `AddedToken` class
4
+ - Added precompiled gem for Windows
5
+
1
6
  ## 0.5.2 (2024-08-26)
2
7
 
3
8
  - Added `from_str` method to `Tokenizer`
data/Cargo.lock CHANGED
@@ -724,7 +724,7 @@ dependencies = [
724
724
 
725
725
  [[package]]
726
726
  name = "tokenizers"
727
- version = "0.5.2"
727
+ version = "0.5.3"
728
728
  dependencies = [
729
729
  "magnus",
730
730
  "onig",
Binary file
Binary file
Binary file
@@ -0,0 +1,7 @@
1
+ module Tokenizers
2
+ class AddedToken
3
+ def self.new(content, **kwargs)
4
+ _new(content, kwargs)
5
+ end
6
+ end
7
+ end
@@ -1,3 +1,3 @@
1
1
  module Tokenizers
2
- VERSION = "0.5.2"
2
+ VERSION = "0.5.3"
3
3
  end
data/lib/tokenizers.rb CHANGED
@@ -42,6 +42,7 @@ require_relative "tokenizers/trainers/word_level_trainer"
42
42
  require_relative "tokenizers/trainers/word_piece_trainer"
43
43
 
44
44
  # other
45
+ require_relative "tokenizers/added_token"
45
46
  require_relative "tokenizers/char_bpe_tokenizer"
46
47
  require_relative "tokenizers/encoding"
47
48
  require_relative "tokenizers/from_pretrained"
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: tokenizers
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.5.2
4
+ version: 0.5.3
5
5
  platform: arm64-darwin
6
6
  authors:
7
7
  - Andrew Kane
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2024-08-26 00:00:00.000000000 Z
11
+ date: 2024-09-17 00:00:00.000000000 Z
12
12
  dependencies: []
13
13
  description:
14
14
  email: andrew@ankane.org
@@ -26,6 +26,7 @@ files:
26
26
  - lib/tokenizers/3.1/tokenizers.bundle
27
27
  - lib/tokenizers/3.2/tokenizers.bundle
28
28
  - lib/tokenizers/3.3/tokenizers.bundle
29
+ - lib/tokenizers/added_token.rb
29
30
  - lib/tokenizers/char_bpe_tokenizer.rb
30
31
  - lib/tokenizers/decoders/bpe_decoder.rb
31
32
  - lib/tokenizers/decoders/ctc.rb