mirror of
https://github.com/mii443/tokenizers.git
synced 2025-08-22 16:25:30 +00:00
Bump version and update Readme
This commit is contained in:
6
bindings/python/Cargo.lock
generated
6
bindings/python/Cargo.lock
generated
@ -448,15 +448,15 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "tokenizers"
|
||||
version = "0.0.7"
|
||||
version = "0.0.8"
|
||||
dependencies = [
|
||||
"pyo3 0.8.2 (registry+https://github.com/rust-lang/crates.io-index)",
|
||||
"tokenizers-lib 0.0.7",
|
||||
"tokenizers-lib 0.0.8",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "tokenizers-lib"
|
||||
version = "0.0.7"
|
||||
version = "0.0.8"
|
||||
dependencies = [
|
||||
"clap 2.33.0 (registry+https://github.com/rust-lang/crates.io-index)",
|
||||
"lazy_static 1.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
|
||||
|
@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "tokenizers"
|
||||
version = "0.0.7"
|
||||
version = "0.0.8"
|
||||
authors = ["Anthony MOI <m.anthony.moi@gmail.com>"]
|
||||
edition = "2018"
|
||||
|
||||
|
@ -61,7 +61,7 @@ bpe = models.BPE.from_files(vocab, merges)
|
||||
tokenizer = Tokenizer(bpe)
|
||||
|
||||
# Customize pre-tokenization and decoding
|
||||
tokenizer.with_pre_tokenizer(pre_tokenizers.ByteLevel.new())
|
||||
tokenizer.with_pre_tokenizer(pre_tokenizers.ByteLevel.new(True))
|
||||
tokenizer.with_decoder(decoders.ByteLevel.new())
|
||||
|
||||
# And then encode:
|
||||
@ -85,7 +85,7 @@ from tokenizers import Tokenizer, models, pre_tokenizers, decoders, trainers
|
||||
tokenizer = Tokenizer(models.BPE.empty())
|
||||
|
||||
# Customize pre-tokenization and decoding
|
||||
tokenizer.with_pre_tokenizer(pre_tokenizers.ByteLevel.new())
|
||||
tokenizer.with_pre_tokenizer(pre_tokenizers.ByteLevel.new(True))
|
||||
tokenizer.with_decoder(decoders.ByteLevel.new())
|
||||
|
||||
# And then train
|
||||
|
@ -3,7 +3,7 @@ from setuptools_rust import Binding, RustExtension
|
||||
|
||||
setup(
|
||||
name="tokenizers",
|
||||
version="0.0.7",
|
||||
version="0.0.8",
|
||||
description="Fast and Customizable Tokenizers",
|
||||
long_description=open("README.md", "r", encoding="utf-8").read(),
|
||||
long_description_content_type="text/markdown",
|
||||
|
2
tokenizers/Cargo.lock
generated
2
tokenizers/Cargo.lock
generated
@ -265,7 +265,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "tokenizers-lib"
|
||||
version = "0.0.7"
|
||||
version = "0.0.8"
|
||||
dependencies = [
|
||||
"clap 2.33.0 (registry+https://github.com/rust-lang/crates.io-index)",
|
||||
"lazy_static 1.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
|
||||
|
@ -2,7 +2,7 @@
|
||||
authors = ["Anthony MOI <m.anthony.moi@gmail.com>"]
|
||||
edition = "2018"
|
||||
name = "tokenizers-lib"
|
||||
version = "0.0.7"
|
||||
version = "0.0.8"
|
||||
[[bin]]
|
||||
name = "cli"
|
||||
path = "src/cli.rs"
|
||||
|
Reference in New Issue
Block a user