tokenizers 0.4.4-x86_64-darwin → 0.5.1-x86_64-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.
Binary file
Binary file
Binary file
@@ -1,8 +1,8 @@
1
1
  module Tokenizers
2
2
  module Decoders
3
3
  class Metaspace
4
- def self.new(replacement: "\u2581", add_prefix_space: true)
5
- _new(replacement, add_prefix_space)
4
+ def self.new(replacement: "\u2581", prepend_scheme: "always", split: true)
5
+ _new(replacement, prepend_scheme, split)
6
6
  end
7
7
  end
8
8
  end
@@ -1,7 +1,7 @@
1
1
  module Tokenizers
2
2
  module FromPretrained
3
3
  # for user agent
4
- TOKENIZERS_VERSION = "0.15.2"
4
+ TOKENIZERS_VERSION = "0.20.0"
5
5
 
6
6
  # use Ruby for downloads
7
7
  # this avoids the need to vendor OpenSSL on Linux
@@ -67,7 +67,7 @@ module Tokenizers
67
67
  end
68
68
  end
69
69
 
70
- options[:content_length_proc] = -> (_) { puts "Downloading..." }
70
+ options[:content_length_proc] = ->(_) { puts "Downloading..." }
71
71
 
72
72
  # string options are headers
73
73
  tempfile = URI.parse(url).open(headers.merge(options))
@@ -1,8 +1,8 @@
1
1
  module Tokenizers
2
2
  module PreTokenizers
3
3
  class Metaspace
4
- def self.new(replacement: "\u2581", add_prefix_space: true)
5
- _new(replacement, add_prefix_space)
4
+ def self.new(replacement: "\u2581", prepend_scheme: "always", split: true)
5
+ _new(replacement, prepend_scheme, split)
6
6
  end
7
7
  end
8
8
  end
@@ -1,3 +1,3 @@
1
1
  module Tokenizers
2
- VERSION = "0.4.4"
2
+ VERSION = "0.5.1"
3
3
  end
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: 0.4.4
4
+ version: 0.5.1
5
5
  platform: x86_64-darwin
6
6
  authors:
7
7
  - Andrew Kane
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2024-02-27 00:00:00.000000000 Z
11
+ date: 2024-08-13 00:00:00.000000000 Z
12
12
  dependencies: []
13
13
  description:
14
14
  email: andrew@ankane.org
@@ -23,7 +23,6 @@ files:
23
23
  - LICENSE.txt
24
24
  - README.md
25
25
  - lib/tokenizers.rb
26
- - lib/tokenizers/3.0/tokenizers.bundle
27
26
  - lib/tokenizers/3.1/tokenizers.bundle
28
27
  - lib/tokenizers/3.2/tokenizers.bundle
29
28
  - lib/tokenizers/3.3/tokenizers.bundle
@@ -68,7 +67,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
68
67
  requirements:
69
68
  - - ">="
70
69
  - !ruby/object:Gem::Version
71
- version: '3.0'
70
+ version: '3.1'
72
71
  - - "<"
73
72
  - !ruby/object:Gem::Version
74
73
  version: 3.4.dev
Binary file