tokenizers 0.1.0 → 0.1.1
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 +4 -0
- data/Cargo.lock +2 -2
- data/Cargo.toml +1 -1
- data/README.md +2 -2
- data/ext/tokenizers/extconf.rb +6 -3
- data/lib/tokenizers/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 6aeb772fccbd1a8ae0991f31b47bbb51fc74b97c51ea085bafa4951797f3e994
|
4
|
+
data.tar.gz: 342e05d37471d31f6738fef1a50e5f50d521fc10173723d79156bb689cbfdbe9
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 38ac5e532c3b17130c30dd010bc109689036f8a363790bfb39a858f126154c04c81325732bbd0c4ad4aca808c8e48b6c0c1b5f2ce5b043f42c92c5409b7b0c6e
|
7
|
+
data.tar.gz: 8164092df944f67ddfb1c85c61dadd62a0bf731332f9c1fa64d8ee7daf58710688116dddf3caf2fedd60fedd1b5b76cfd632c83a880e4e19b1e2061174baea3f
|
data/CHANGELOG.md
CHANGED
data/Cargo.lock
CHANGED
@@ -1254,9 +1254,9 @@ dependencies = [
|
|
1254
1254
|
|
1255
1255
|
[[package]]
|
1256
1256
|
name = "rutie"
|
1257
|
-
version = "0.8.
|
1257
|
+
version = "0.8.4"
|
1258
1258
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
1259
|
-
checksum = "
|
1259
|
+
checksum = "5d97db4cbb9739b48364c38cc9a6ebabdc07b42bd87b60ab448e1f29eaebb2ac"
|
1260
1260
|
dependencies = [
|
1261
1261
|
"lazy_static",
|
1262
1262
|
"libc",
|
data/Cargo.toml
CHANGED
data/README.md
CHANGED
@@ -1,4 +1,4 @@
|
|
1
|
-
# Tokenizers
|
1
|
+
# Tokenizers Ruby
|
2
2
|
|
3
3
|
:slightly_smiling_face: Fast state-of-the-art [tokenizers](https://github.com/huggingface/tokenizers) for Ruby
|
4
4
|
|
@@ -12,7 +12,7 @@ Add this line to your application’s Gemfile:
|
|
12
12
|
gem "tokenizers"
|
13
13
|
```
|
14
14
|
|
15
|
-
Note: Rust
|
15
|
+
Note: Rust and pkg-config are currently required for installation, and it can take 5-10 minutes to compile the extension.
|
16
16
|
|
17
17
|
## Getting Started
|
18
18
|
|
data/ext/tokenizers/extconf.rb
CHANGED
@@ -1,7 +1,10 @@
|
|
1
|
+
require "pathname"
|
2
|
+
|
3
|
+
dest = Pathname.new(__dir__).relative_path_from(Pathname.pwd).join("../../lib/tokenizers/ext.#{RbConfig::CONFIG["DLEXT"]}")
|
4
|
+
|
1
5
|
File.write "Makefile", <<~EOS
|
2
6
|
install:
|
3
|
-
\tcargo build --release
|
4
|
-
\tmv target/release/libtokenizers.#{RbConfig::CONFIG["SOEXT"]}
|
7
|
+
\tcargo build --release --target-dir target
|
8
|
+
\tmv target/release/libtokenizers.#{RbConfig::CONFIG["SOEXT"]} #{dest}
|
5
9
|
clean:
|
6
|
-
\tcargo clean
|
7
10
|
EOS
|
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: 0.1.
|
4
|
+
version: 0.1.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Andrew Kane
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2022-
|
11
|
+
date: 2022-06-29 00:00:00.000000000 Z
|
12
12
|
dependencies: []
|
13
13
|
description:
|
14
14
|
email: andrew@ankane.org
|