Preparing rc1 release. (#1056)

* Preparing rc1 release. * Fixing test_alignment_methods * Fixing the overflowing sequence_id issue (LayoutLMv2 tests caught this). * Adding overly complex overflowing test.
huggingface · Sep 12, 2022 · 7bfab48 · 7bfab48
1 parent 06025e4
commit 7bfab48
Show file tree

Hide file tree

Showing 15 changed files with 417 additions and 14 deletions.
diff --git a/bindings/node/CHANGELOG.md b/bindings/node/CHANGELOG.md
@@ -1,3 +1,8 @@
+## [0.13.0] 
+
+- [#1008] `Decoder` is now a composable trait, but without being backward incompatible
+- [#1047, #1051, #1052] `Processor` is now a composable trait, but without being backward incompatible
+
 ## [0.12.1] 
 
 - [#938] **Reverted breaking change**. https://github.com/huggingface/transformers/issues/16520
@@ -160,6 +165,13 @@ The files must now be provided first when calling `tokenizer.train(files, traine
 - Actually add special tokens in tokenizers implementations ([acef252](https://github.com/huggingface/tokenizers/commit/acef252dacc43adc414175cfc325668ad1488753))
 
 
+[#956]: https://github.com/huggingface/tokenizers/pull/956
+[#1008]: https://github.com/huggingface/tokenizers/pull/1008
+[#1009]: https://github.com/huggingface/tokenizers/pull/1009
+[#1047]: https://github.com/huggingface/tokenizers/pull/1047
+[#1055]: https://github.com/huggingface/tokenizers/pull/1055
+[#1051]: https://github.com/huggingface/tokenizers/pull/1051
+[#1052]: https://github.com/huggingface/tokenizers/pull/1052
 [#938]: https://github.com/huggingface/tokenizers/pull/938
 [#939]: https://github.com/huggingface/tokenizers/pull/939
 [#952]: https://github.com/huggingface/tokenizers/pull/952

diff --git a/bindings/node/package.json b/bindings/node/package.json
@@ -1,6 +1,6 @@
 {
     "name": "tokenizers",
-    "version": "0.12.1",
+    "version": "0.13.0",
     "description": "",
     "main": "./dist/index.js",
     "types": "./dist/index.d.ts",

diff --git a/bindings/python/CHANGELOG.md b/bindings/python/CHANGELOG.md
@@ -4,6 +4,16 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.13.0] 
+
+- [#956] PyO3 version upgrade
+- [#1055] M1 automated builds
+- [#1008] `Decoder` is now a composable trait, but without being backward incompatible
+- [#1047, #1051, #1052] `Processor` is now a composable trait, but without being backward incompatible
+
+Both trait changes warrant a "major" number since, despite best efforts to not break backward
+  compatibility, the code is different enough that we cannot be exactly sure.
+
 ## [0.12.1] 
 
 - [#938] **Reverted breaking change**. https://github.com/huggingface/transformers/issues/16520
@@ -376,6 +386,13 @@ delimiter (Works like `.split(delimiter)`)
 - Fix a bug that was causing crashes in Python 3.5
 
 
+[#956]: https://github.com/huggingface/tokenizers/pull/956
+[#1008]: https://github.com/huggingface/tokenizers/pull/1008
+[#1009]: https://github.com/huggingface/tokenizers/pull/1009
+[#1047]: https://github.com/huggingface/tokenizers/pull/1047
+[#1055]: https://github.com/huggingface/tokenizers/pull/1055
+[#1051]: https://github.com/huggingface/tokenizers/pull/1051
+[#1052]: https://github.com/huggingface/tokenizers/pull/1052
 [#938]: https://github.com/huggingface/tokenizers/pull/938
 [#939]: https://github.com/huggingface/tokenizers/pull/939
 [#952]: https://github.com/huggingface/tokenizers/pull/952

diff --git a/bindings/python/Cargo.lock b/bindings/python/Cargo.lock
diff --git a/bindings/python/py_src/tokenizers/__init__.py b/bindings/python/py_src/tokenizers/__init__.py
@@ -1,4 +1,4 @@
-__version__ = "0.12.1.dev0"
+__version__ = "0.13.0.dev0"
 
 from typing import Tuple, Union, Tuple, List
 from enum import Enum

diff --git a/bindings/python/setup.py b/bindings/python/setup.py
@@ -8,7 +8,7 @@
 
 setup(
     name="tokenizers",
-    version="0.12.1.dev0",
+    version="0.13.0.dev0",
     description="Fast and Customizable Tokenizers",
     long_description=open("README.md", "r", encoding="utf-8").read(),
     long_description_content_type="text/markdown",

diff --git a/tokenizers/CHANGELOG.md b/tokenizers/CHANGELOG.md
@@ -4,6 +4,15 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.13.0] 
+
+- [#1009] `unstable_wasm` feature to support building on Wasm (it's unstable !)
+- [#1008] `Decoder` is now a composable trait, but without being backward incompatible
+- [#1047, #1051, #1052] `Processor` is now a composable trait, but without being backward incompatible
+
+Both trait changes warrant a "major" number since, despite best efforts to not break backward
+  compatibility, the code is different enough that we cannot be exactly sure.
+
 ## [0.12.1] 
 
 - [#938] **Reverted breaking change**. https://github.com/huggingface/transformers/issues/16520
@@ -157,6 +166,13 @@ split up in multiple bytes
 - [#174]: The `LongestFirst` truncation strategy had a bug
 
 
+[#956]: https://github.com/huggingface/tokenizers/pull/956
+[#1008]: https://github.com/huggingface/tokenizers/pull/1008
+[#1009]: https://github.com/huggingface/tokenizers/pull/1009
+[#1047]: https://github.com/huggingface/tokenizers/pull/1047
+[#1055]: https://github.com/huggingface/tokenizers/pull/1055
+[#1051]: https://github.com/huggingface/tokenizers/pull/1051
+[#1052]: https://github.com/huggingface/tokenizers/pull/1052
 [#938]: https://github.com/huggingface/tokenizers/pull/938
 [#939]: https://github.com/huggingface/tokenizers/pull/939
 [#952]: https://github.com/huggingface/tokenizers/pull/952

diff --git a/tokenizers/Cargo.toml b/tokenizers/Cargo.toml
@@ -2,7 +2,7 @@
 authors = ["Anthony MOI <[email protected]>"]
 edition = "2018"
 name = "tokenizers"
-version = "0.12.1"
+version = "0.13.0"
 homepage = "https://github.com/huggingface/tokenizers"
 repository = "https://github.com/huggingface/tokenizers"
 documentation = "https://docs.rs/tokenizers/"

diff --git a/tokenizers/src/pre_tokenizers/byte_level.rs b/tokenizers/src/pre_tokenizers/byte_level.rs
@@ -484,7 +484,7 @@ mod tests {
         );
         let expected = Encoding::new(
             vec![0; 5],
-            vec![],
+            vec![0; 5],
             vec![
                 "Ġ".into(),
                 "ĠĠĠĠHelloĠĠ".into(),
@@ -508,7 +508,7 @@ mod tests {
 
         let pair_expected = Encoding::new(
             vec![0; 10],
-            vec![],
+            vec![0, 0, 0, 0, 0, 1, 1, 1, 1, 1],
             vec![
                 "Ġ".into(),
                 "ĠĠĠĠHelloĠĠ".into(),

diff --git a/tokenizers/src/processors/bert.rs b/tokenizers/src/processors/bert.rs
@@ -195,4 +195,91 @@ mod tests {
             bert
         );
     }
+
+    #[test]
+    fn bert_processing() {
+        let processor = BertProcessing::default();
+        assert_eq!(processor.added_tokens(false), 2);
+        assert_eq!(processor.added_tokens(true), 3);
+
+        use crate::Token;
+        let encoding = Encoding::from_tokens(
+            vec![
+                Token::new(12, "Hello".into(), (0, 5)),
+                Token::new(14, "there".into(), (6, 11)),
+            ],
+            0,
+        );
+        let pair = Encoding::from_tokens(vec![Token::new(15, "pair".into(), (0, 4))], 0);
+        let single_encoding = processor.process(encoding.clone(), None, true).unwrap();
+        assert_eq!(
+            single_encoding,
+            Encoding::new(
+                vec![101, 12, 14, 102],
+                vec![0, 0, 0, 0],
+                vec![
+                    "[CLS]".into(),
+                    "Hello".into(),
+                    "there".into(),
+                    "[SEP]".into()
+                ],
+                vec![None, None, None, None],
+                vec![(0, 0), (0, 5), (6, 11), (0, 0)],
+                vec![1, 0, 0, 1],
+                vec![1, 1, 1, 1],
+                vec![],
+                HashMap::from_iter(vec![(0, 1..3)]),
+            )
+        );
+        assert_eq!(single_encoding.token_to_sequence(2), Some(0));
+        assert_eq!(single_encoding.token_to_sequence(3), None);
+        let pair_encoding = processor
+            .process(encoding.clone(), Some(pair.clone()), true)
+            .unwrap();
+        assert_eq!(
+            pair_encoding,
+            Encoding::new(
+                vec![101, 12, 14, 102, 15, 102],
+                vec![0, 0, 0, 0, 1, 1],
+                vec![
+                    "[CLS]".into(),
+                    "Hello".into(),
+                    "there".into(),
+                    "[SEP]".into(),
+                    "pair".into(),
+                    "[SEP]".into()
+                ],
+                vec![None, None, None, None, None, None],
+                vec![(0, 0), (0, 5), (6, 11), (0, 0), (0, 4), (0, 0)],
+                vec![1, 0, 0, 1, 0, 1],
+                vec![1, 1, 1, 1, 1, 1],
+                vec![],
+                HashMap::from_iter(vec![(0, 1..3), (1, 4..5)]),
+            )
+        );
+        assert_eq!(pair_encoding.token_to_sequence(2), Some(0));
+        assert_eq!(pair_encoding.token_to_sequence(3), None);
+        assert_eq!(pair_encoding.token_to_sequence(4), Some(1));
+        assert_eq!(pair_encoding.token_to_sequence(5), None);
+
+        // No special tokens
+        let pair_encoding = processor.process(encoding, Some(pair), false).unwrap();
+        assert_eq!(
+            pair_encoding,
+            Encoding::new(
+                vec![12, 14, 15],
+                vec![0, 0, 1],
+                vec!["Hello".into(), "there".into(), "pair".into(),],
+                vec![None, None, None],
+                vec![(0, 5), (6, 11), (0, 4)],
+                vec![0, 0, 0],
+                vec![1, 1, 1],
+                vec![],
+                HashMap::from_iter(vec![(0, 0..2), (1, 2..3)]),
+            )
+        );
+        assert_eq!(pair_encoding.token_to_sequence(0), Some(0));
+        assert_eq!(pair_encoding.token_to_sequence(1), Some(0));
+        assert_eq!(pair_encoding.token_to_sequence(2), Some(1));
+    }
 }
diff --git a/tokenizers/src/processors/roberta.rs b/tokenizers/src/processors/roberta.rs
@@ -146,7 +146,7 @@ impl PostProcessor for RobertaProcessing {
                     )
                 } else {
                     let pair_ids = [&[self.sep.1], encoding.get_ids(), &[self.sep.1]].concat();
-                    let pair_type_ids = vec![0; encoding.get_ids().len() + 2];
+                    let pair_type_ids = vec![1; encoding.get_ids().len() + 2];
                     let pair_tokens = [
                         &[self.sep.0.clone()],
                         encoding.get_tokens(),
@@ -176,7 +176,7 @@ impl PostProcessor for RobertaProcessing {
                             .map(|encoding| {
                                 let pair_ids =
                                     [&[self.sep.1], encoding.get_ids(), &[self.sep.1]].concat();
-                                let pair_type_ids = vec![0; encoding.get_ids().len() + 2];
+                                let pair_type_ids = vec![1; encoding.get_ids().len() + 2];
                                 let pair_tokens = [
                                     &[self.sep.0.clone()],
                                     encoding.get_tokens(),
@@ -240,4 +240,88 @@ mod tests {
             roberta
         );
     }
+
+    #[test]
+    fn roberta_processing() {
+        let processor = RobertaProcessing::default();
+        assert_eq!(processor.added_tokens(false), 2);
+        assert_eq!(processor.added_tokens(true), 4);
+
+        use crate::Token;
+        let encoding = Encoding::from_tokens(
+            vec![
+                Token::new(12, "Hello".into(), (0, 5)),
+                Token::new(14, "there".into(), (6, 11)),
+            ],
+            0,
+        );
+        let pair = Encoding::from_tokens(vec![Token::new(15, "pair".into(), (0, 4))], 0);
+        let single_encoding = processor.process(encoding.clone(), None, true).unwrap();
+        assert_eq!(
+            single_encoding,
+            Encoding::new(
+                vec![0, 12, 14, 2],
+                vec![0, 0, 0, 0],
+                vec!["<s>".into(), "Hello".into(), "there".into(), "</s>".into()],
+                vec![None, None, None, None],
+                vec![(0, 0), (0, 5), (6, 11), (0, 0)],
+                vec![1, 0, 0, 1],
+                vec![1, 1, 1, 1],
+                vec![],
+                HashMap::from_iter(vec![(0, 1..3)]),
+            )
+        );
+        assert_eq!(single_encoding.token_to_sequence(2), Some(0));
+        assert_eq!(single_encoding.token_to_sequence(3), None);
+        let pair_encoding = processor
+            .process(encoding.clone(), Some(pair.clone()), true)
+            .unwrap();
+        assert_eq!(
+            pair_encoding,
+            Encoding::new(
+                vec![0, 12, 14, 2, 2, 15, 2],
+                vec![0, 0, 0, 0, 1, 1, 1],
+                vec![
+                    "<s>".into(),
+                    "Hello".into(),
+                    "there".into(),
+                    "</s>".into(),
+                    "</s>".into(),
+                    "pair".into(),
+                    "</s>".into()
+                ],
+                vec![None, None, None, None, None, None, None],
+                vec![(0, 0), (0, 5), (6, 11), (0, 0), (0, 0), (0, 4), (0, 0)],
+                vec![1, 0, 0, 1, 1, 0, 1],
+                vec![1, 1, 1, 1, 1, 1, 1],
+                vec![],
+                HashMap::from_iter(vec![(0, 1..3), (1, 5..6)]),
+            )
+        );
+        assert_eq!(pair_encoding.token_to_sequence(2), Some(0));
+        assert_eq!(pair_encoding.token_to_sequence(3), None);
+        assert_eq!(pair_encoding.token_to_sequence(4), None);
+        assert_eq!(pair_encoding.token_to_sequence(5), Some(1));
+        assert_eq!(pair_encoding.token_to_sequence(6), None);
+
+        // No special tokens
+        let pair_encoding = processor.process(encoding, Some(pair), false).unwrap();
+        assert_eq!(
+            pair_encoding,
+            Encoding::new(
+                vec![12, 14, 15],
+                vec![0, 0, 1],
+                vec!["Hello".into(), "there".into(), "pair".into(),],
+                vec![None, None, None],
+                vec![(0, 5), (6, 11), (0, 4)],
+                vec![0, 0, 0],
+                vec![1, 1, 1],
+                vec![],
+                HashMap::from_iter(vec![(0, 0..2), (1, 2..3)]),
+            )
+        );
+        assert_eq!(pair_encoding.token_to_sequence(0), Some(0));
+        assert_eq!(pair_encoding.token_to_sequence(1), Some(0));
+        assert_eq!(pair_encoding.token_to_sequence(2), Some(1));
+    }
 }
diff --git a/tokenizers/src/processors/sequence.rs b/tokenizers/src/processors/sequence.rs
@@ -47,7 +47,7 @@ mod tests {
     fn process_chain() {
         let start = Encoding::new(
             vec![0; 5],
-            vec![],
+            vec![0; 5],
             vec![
                 "Ġ".into(),
                 "ĠĠĠĠHelloĠĠ".into(),
@@ -67,7 +67,7 @@ mod tests {
         let sequence = Sequence::new(vec![PostProcessorWrapper::ByteLevel(bytelevel)]);
         let expected = Encoding::new(
             vec![0; 5],
-            vec![],
+            vec![0; 5],
             vec![
                 "Ġ".into(),
                 "ĠĠĠĠHelloĠĠ".into(),
@@ -94,7 +94,7 @@ mod tests {
 
         let pair_expected = Encoding::new(
             vec![0; 10],
-            vec![],
+            vec![0, 0, 0, 0, 0, 1, 1, 1, 1, 1],
             vec![
                 "Ġ".into(),
                 "ĠĠĠĠHelloĠĠ".into(),