tokenizers 0.4.4-x86_64-linux → 0.5.0-x86_64-linux
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 +4 -4
- data/CHANGELOG.md +6 -0
- data/Cargo.lock +55 -72
- data/LICENSE-THIRD-PARTY.txt +107 -647
- data/lib/tokenizers/3.1/tokenizers.so +0 -0
- data/lib/tokenizers/3.2/tokenizers.so +0 -0
- data/lib/tokenizers/3.3/tokenizers.so +0 -0
- data/lib/tokenizers/decoders/metaspace.rb +2 -2
- data/lib/tokenizers/from_pretrained.rb +1 -1
- data/lib/tokenizers/pre_tokenizers/metaspace.rb +2 -2
- data/lib/tokenizers/version.rb +1 -1
- metadata +3 -4
- data/lib/tokenizers/3.0/tokenizers.so +0 -0
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",
|
5
|
-
_new(replacement,
|
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
|
@@ -1,8 +1,8 @@
|
|
1
1
|
module Tokenizers
|
2
2
|
module PreTokenizers
|
3
3
|
class Metaspace
|
4
|
-
def self.new(replacement: "\u2581",
|
5
|
-
_new(replacement,
|
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
|
data/lib/tokenizers/version.rb
CHANGED
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
|
+
version: 0.5.0
|
5
5
|
platform: x86_64-linux
|
6
6
|
authors:
|
7
7
|
- Andrew Kane
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2024-
|
11
|
+
date: 2024-05-21 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.so
|
27
26
|
- lib/tokenizers/3.1/tokenizers.so
|
28
27
|
- lib/tokenizers/3.2/tokenizers.so
|
29
28
|
- lib/tokenizers/3.3/tokenizers.so
|
@@ -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.
|
70
|
+
version: '3.1'
|
72
71
|
- - "<"
|
73
72
|
- !ruby/object:Gem::Version
|
74
73
|
version: 3.4.dev
|
Binary file
|