bpe-tokenizer 0.1.2

A BPE Tokenizer library.
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76

[build-dependencies.bincode]
optional = true
version = "1.3.3"

[build-dependencies.lz4_flex]
optional = true
version = "0.11.3"

[build-dependencies.serde]
optional = true
version = "1.0.210"

[dependencies.bincode]
optional = true
version = "1.3.3"

[dependencies.lz4_flex]
optional = true
version = "0.11.3"

[dependencies.serde]
optional = true
version = "1.0.210"

[dependencies.thiserror]
version = "1.0.64"

[dependencies.unicode-segmentation]
version = "1.12.0"

[features]
default-large = ["bincode", "lz4_flex", "serde"]
default-medium = ["bincode", "lz4_flex", "serde"]
default-small = ["bincode", "lz4_flex", "serde"]

[lib]
name = "bpe_tokenizer"
path = "src/lib.rs"

[package]
authors = ["Stephen Waits <steve@waits.net>"]
autobenches = false
autobins = false
autoexamples = false
autotests = false
build = "build.rs"
categories = ["algorithms", "text-processing"]
description = "A BPE Tokenizer library."
documentation = "https://docs.rs/bpe-tokenizer/"
edition = "2021"
exclude = ["vocab/multi.wiki.bpe.vs1000000.vocab"]
homepage = "https://github.com/swaits/bpe-tokenizer/"
keywords = ["byte", "pair", "encoding", "bpe", "tokenizer"]
license-file = "LICENSE"
name = "bpe-tokenizer"
readme = "README.md"
repository = "https://github.com/swaits/bpe-tokenizer/"
rust-version = "1.64"
version = "0.1.2"

[package.metadata.docs.rs]
all-features = true

[profile.dev]
debug = 2
opt-level = 1
overflow-checks = true

[profile.release]
codegen-units = 1
debug = 0
lto = "thin"
opt-level = 3
overflow-checks = false
panic = "abort"
strip = "symbols"