@@ -5,7 +5,29 @@ All notable changes to this project will be documented in this file.
5
5
The format is based on [ Keep a Changelog] ( https://keepachangelog.com/en/1.0.0/ ) ,
6
6
and this project adheres to [ Semantic Versioning] ( https://semver.org/spec/v2.0.0.html ) .
7
7
8
- ## [ Unreleased]
8
+ ## [ v0.4.0] - 2023-08-09
9
+
10
+ ### Added
11
+
12
+ - Support for training a tokenizer from scratch. See ` Tokenizers.Tokenizer.train_from_files/3 `
13
+ and ` Tokenizers.Model ` for available models.
14
+
15
+ - Support for changing tokenizer configuration, such as ` Tokenizers.Tokenizer.set_padding/2 `
16
+ and ` Tokenizers.Tokenizer.set_truncation/2 ` . See the "Configuration" functions group in
17
+ ` Tokenizers.Tokenizer ` .
18
+
19
+ - Support for apply multiple encoding transformations without additional data copies,
20
+ see ` Tokenizers.Encoding.Transformation ` . Transformations can be passed to
21
+ ` Tokenizers.Tokenizer.encode/3 ` via ` :encoding_transformations ` or applied via
22
+ ` Tokenizers.Encoding.transform/2 ` .
23
+
24
+ ### Changed
25
+
26
+ - ** (Breaking)** ` Tokenizers.Tokenizer.encode/3 ` no longer accepts a batch of inputs,
27
+ to encode a batch use ` Tokenizers.Tokenizer.encode_batch/3 ` instead
28
+
29
+ - ** (Breaking)** ` Tokenizers.Tokenizer.decode/3 ` no longer accepts a batch of inputs,
30
+ to encode a batch use ` Tokenizers.Tokenizer.decode_batch/3 ` instead
9
31
10
32
## [ v0.3.2] - 2023-04-19
11
33
@@ -61,7 +83,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
61
83
62
84
First release.
63
85
64
- [ Unreleased ] : https://github.com/elixir-nx/tokenizers/compare/v0.3.2...HEAD
86
+ [ v0.4.0 ] : https://github.com/elixir-nx/tokenizers/compare/v0.3.2...v0.4.0
65
87
[ v0.3.2 ] : https://github.com/elixir-nx/tokenizers/compare/v0.3.1...v0.3.2
66
88
[ v0.3.1 ] : https://github.com/elixir-nx/tokenizers/compare/v0.3.0...v0.3.1
67
89
[ v0.3.0 ] : https://github.com/elixir-nx/tokenizers/compare/v0.2.0...v0.3.0
0 commit comments