Moved SpecialTokens assignment after the modification to avoid "Collection Modified" error#7328

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
tarekgh merged 7 commits into from
Dec 5, 2024
Merged

Moved SpecialTokens assignment after the modification to avoid "Collection Modified" error #7328

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
6e5fbed
Moved special tokens assignment below so the collection won't be modi…
shaltielshmid Dec 2, 2024
5edde92
Added safe dictionary inversion
shaltielshmid Dec 4, 2024
84bd69d
Added storing the not-normalized special tokens
shaltielshmid Dec 4, 2024
6ae9d10
Added support for net standard
shaltielshmid Dec 4, 2024
4f06337
Added and updated tests
shaltielshmid Dec 4, 2024
0fcbe64
Merge remote-tracking branch 'dotnet/main' into bug/bert-tok-collecti…
shaltielshmid Dec 4, 2024
25a4c6d
Updated without additional memory allocation
shaltielshmid Dec 5, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
45 changes: 29 additions & 16 deletions src/Microsoft.ML.Tokenizers/Model/BertTokenizer.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand DownExpand Up@@ -762,15 +762,16 @@ private static BertTokenizer Create(

options.Normalizer ??= options.ApplyBasicTokenization ? new BertNormalizer(options.LowerCaseBeforeTokenization, options.IndividuallyTokenizeCjk, options.RemoveNonSpacingMarks) : null;

IReadOnlyDictionary<string, int>? specialTokensDict = options.SpecialTokens;
if (options.SplitOnSpecialTokens)
{
bool lowerCase = options.ApplyBasicTokenization && options.LowerCaseBeforeTokenization;
if (options.SpecialTokens is not null)
{
if (lowerCase)
{
Dictionary<string, int> dic = options.SpecialTokens.ToDictionary(kvp => kvp.Key, kvp => kvp.Value);
options.SpecialTokens = dic;
Dictionary<string, int> tempSpecialTokens = [];
specialTokensDict = tempSpecialTokens;

foreach (var kvp in options.SpecialTokens)
{
Expand All@@ -779,37 +780,49 @@ private static BertTokenizer Create(
throw new ArgumentException($"The special token '{kvp.Key}' is not in the vocabulary or assigned id value {id} different than the value {kvp.Value} in the special tokens.");
}

// Ensure that the special tokens are lowercased.
dic[kvp.Key.ToLowerInvariant()] = kvp.Value;
// Add the special token into our dictionary, normalizing it, and adding it into the
// main vocab, if needed.
AddSpecialToken(vocab, tempSpecialTokens, kvp.Key, true);
}
}
}
else
{
// Create a dictionary with the special tokens.
Dictionary<string, int> specialTokens = new Dictionary<string, int>();
options.SpecialTokens = specialTokens;

AddSpecialToken(vocab, specialTokens, options.UnknownToken, lowerCase);
AddSpecialToken(vocab, specialTokens, options.SeparatorToken, lowerCase);
AddSpecialToken(vocab, specialTokens, options.PaddingToken, lowerCase);
AddSpecialToken(vocab, specialTokens, options.ClassificationToken, lowerCase);
AddSpecialToken(vocab, specialTokens, options.MaskingToken, lowerCase);
// Create a dictionary with the special tokens - store the un-normalized forms in the options as
// that field is exposed to the public. In addition, store the normalized form for creating the
// pre-tokenizer.
Dictionary<string, int> tempSpecialTokens = [];
Dictionary<string, int> notNormalizedSpecialTokens = [];
AddSpecialToken(vocab, tempSpecialTokens, options.UnknownToken, lowerCase, notNormalizedSpecialTokens);
AddSpecialToken(vocab, tempSpecialTokens, options.SeparatorToken, lowerCase, notNormalizedSpecialTokens);
AddSpecialToken(vocab, tempSpecialTokens, options.PaddingToken, lowerCase, notNormalizedSpecialTokens);
AddSpecialToken(vocab, tempSpecialTokens, options.ClassificationToken, lowerCase, notNormalizedSpecialTokens);
AddSpecialToken(vocab, tempSpecialTokens, options.MaskingToken, lowerCase, notNormalizedSpecialTokens);

options.SpecialTokens = notNormalizedSpecialTokens;
specialTokensDict = tempSpecialTokens;
}
}

options.PreTokenizer ??= options.ApplyBasicTokenization ? PreTokenizer.CreateWordOrPunctuation(options.SplitOnSpecialTokens ? options.SpecialTokens : null) : PreTokenizer.CreateWhiteSpace();
// We set the PreTokenizer here using the normalized special tokens dict (if relevant), and therefore we can
// keep the not-normalized special tokens dict in the options passed to the WordPieceTokenizer.
options.PreTokenizer ??= options.ApplyBasicTokenization ? PreTokenizer.CreateWordOrPunctuation(options.SplitOnSpecialTokens ? specialTokensDict : null) : PreTokenizer.CreateWhiteSpace();

return new BertTokenizer(vocab, vocabReverse, options);
}

private static void AddSpecialToken(Dictionary<StringSpanOrdinalKey, int> vocab, Dictionary<string, int> specialTokens, string token, bool lowerCase)
private static void AddSpecialToken(Dictionary<StringSpanOrdinalKey, int> vocab, Dictionary<string, int> specialTokens, string token, bool lowerCase, Dictionary<string, int>? notNormalizedSpecialTokens = null)
{
if (token is null || !vocab.TryGetValue(new StringSpanOrdinalKey(token), out int id))
{
throw new ArgumentException($"The special token '{token}' is not in the vocabulary.");
}

if (notNormalizedSpecialTokens is not null)
{
notNormalizedSpecialTokens[token] = id;
}

string normalizedToken = token;
if (lowerCase)
{
Expand Down
6 changes: 3 additions & 3 deletions src/Microsoft.ML.Tokenizers/Model/WordPieceTokenizer.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand DownExpand Up@@ -42,7 +42,7 @@ internal WordPieceTokenizer(
options ??= new();

SpecialTokens = options.SpecialTokens;
SpecialTokensReverse = options.SpecialTokens is not null ? options.SpecialTokens.ToDictionary(kvp => kvp.Value, kvp => kvp.Key) : null;
SpecialTokensReverse = options.SpecialTokens is not null ? options.SpecialTokens.GroupBy(kvp => kvp.Value).ToDictionary(g => g.Key, g => g.First().Key) : null;

if (options.UnknownToken is null)
{
Expand DownExpand Up@@ -800,4 +800,4 @@ public OperationStatus Decode(IEnumerable<int> ids, Span<char> destination, bool
return OperationStatus.Done;
}
}
}
}
93 changes: 91 additions & 2 deletions test/Microsoft.ML.Tokenizers.Tests/BertTokenizerTests.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand All@@ -14,6 +14,91 @@ namespace Microsoft.ML.Tokenizers.Tests
{
public class BertTokenizerTests
{
[Fact]
public void TestWithLowerCasingExplicitSpecialTokens()
{
// Add [SPECIAL] token at end (to keep indices as is)
// Ids: 0 1 2 3 4 5 6 7 8 9 10 11 12, 13
string[] vocabTokens = ["[PAD]", "[UNK]", "[CLS]", "[SEP]", "[MASK]", "!", ",", "?", "hello", "world", "how", "are", "you", "[SPECIAL]"];

string vocabFile = WordPieceTests.CreateVocabFile(vocabTokens);

Dictionary<string, int> specialTokens = new() {
{ "[PAD]", 0 },
{ "[UNK]", 1 },
{ "[CLS]", 2 },
{ "[SEP]", 3 },
{ "[MASK]", 4 },
{ "[SPECIAL]", 13 },
};
var bertOptions = new BertOptions()
{
SpecialTokens = specialTokens
};

try
{
using Stream vocabStream = File.OpenRead(vocabFile);
BertTokenizer[] bertTokenizers = [BertTokenizer.Create(vocabFile, bertOptions), BertTokenizer.Create(vocabStream, bertOptions)];

foreach (var tokenizer in bertTokenizers)
{
Assert.NotNull(tokenizer.PreTokenizer);
Assert.Equal("[UNK]", tokenizer.UnknownToken);
Assert.Equal(1, tokenizer.UnknownTokenId);
Assert.NotNull(tokenizer.Normalizer);
Assert.NotNull(tokenizer.PreTokenizer);

Assert.True(tokenizer.SpecialTokens!.ContainsKey("[SPECIAL]"));

string text = "Hello, How are you [SPECIAL]?";
var tokens = tokenizer.EncodeToTokens(text, out string? normalizedText);
Assert.Equal("hello, how are you [special]?", normalizedText);

Assert.Equal(
[
new EncodedToken(8, "hello", new Range(0, 5)),
new EncodedToken(6, ",", new Range(5, 6)),
new EncodedToken(10, "how", new Range(7, 10)),
new EncodedToken(11, "are", new Range(11, 14)),
new EncodedToken(12, "you", new Range(15, 18)),
new EncodedToken(13, "[SPECIAL]", new Range(19, 28)),
new EncodedToken(7, "?", new Range(28, 29))
],
tokens);

var ids = tokenizer.EncodeToIds(text);
Assert.Equal([tokenizer.ClassificationTokenId, 8, 6, 10, 11, 12, 13, 7, tokenizer.SeparatorTokenId], ids);

Assert.Equal("[CLS] hello, how are you [SPECIAL]? [SEP]", tokenizer.Decode(ids));
Assert.Equal("hello, how are you?", tokenizer.Decode(ids, skipSpecialTokens: true));

tokens = tokenizer.EncodeToTokens(tokenizer.Decode(ids), out normalizedText);
Assert.Equal("[cls] hello, how are you [special]? [sep]", normalizedText);
Assert.Equal(
[
new EncodedToken(2, "[CLS]", new Range(0, 5)),
new EncodedToken(8, "hello", new Range(6, 11)),
new EncodedToken(6, ",", new Range(11, 12)),
new EncodedToken(10, "how", new Range(13, 16)),
new EncodedToken(11, "are", new Range(17, 20)),
new EncodedToken(12, "you", new Range(21, 24)),
new EncodedToken(13, "[SPECIAL]", new Range(25, 34)),
new EncodedToken(7, "?", new Range(34, 35)),
new EncodedToken(3, "[SEP]", new Range(36, 41))
],
tokens);

ids = tokenizer.EncodeToIds(normalizedText!);
Assert.Equal([tokenizer.ClassificationTokenId, tokenizer.ClassificationTokenId, 8, 6, 10, 11, 12, 13, 7, tokenizer.SeparatorTokenId, tokenizer.SeparatorTokenId], ids);
}
}
finally
{
File.Delete(vocabFile);
}
}

[Fact]
public void TestWithLowerCasing()
{
Expand All@@ -35,6 +120,10 @@ public void TestWithLowerCasing()
Assert.NotNull(tokenizer.Normalizer);
Assert.NotNull(tokenizer.PreTokenizer);

// Make sure the SpecialTokens dictionary contains the not-normalized tokens
Assert.True(tokenizer.SpecialTokens!.ContainsKey(tokenizer.UnknownToken));
Assert.True(tokenizer.SpecialTokens!.ContainsKey(tokenizer.ClassificationToken));

string text = "Hello, How are you?";
var tokens = tokenizer.EncodeToTokens(text, out string? normalizedText);
Assert.Equal("hello, how are you?", normalizedText);
Expand DownExpand Up@@ -511,4 +600,4 @@ public void TestCreateTokenTypeIdsFromSequences()
}
}
}
}
}
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
Moved SpecialTokens assignment after the modification to avoid "Collection Modified" error#7328

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

tarekgh
merged 7 commits into

from

Dec 5, 2024
 Merged


Moved SpecialTokens assignment after the modification to avoid "Collection Modified" error
#7328
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
6e5fbed

Moved special tokens assignment below so the collection won't be modi…


shaltielshmid Dec 2, 2024
5edde92

Added safe dictionary inversion


shaltielshmid Dec 4, 2024
84bd69d

Added storing the not-normalized special tokens


shaltielshmid Dec 4, 2024
6ae9d10

Added support for net standard


shaltielshmid Dec 4, 2024
4f06337

Added and updated tests


shaltielshmid Dec 4, 2024
0fcbe64

Merge remote-tracking branch 'dotnet/main' into bug/bert-tok-collecti…


shaltielshmid Dec 4, 2024
25a4c6d

Updated without additional memory allocation


shaltielshmid Dec 5, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


45 changes: 29 additions & 16 deletions
src/Microsoft.ML.Tokenizers/Model/BertTokenizer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand DownExpand Up@@ -762,15 +762,16 @@ private static BertTokenizer Create(

 options.Normalizer ??= options.ApplyBasicTokenization ? new BertNormalizer(options.LowerCaseBeforeTokenization, options.IndividuallyTokenizeCjk, options.RemoveNonSpacingMarks) : null;

 IReadOnlyDictionary<string, int>? specialTokensDict = options.SpecialTokens;
 if (options.SplitOnSpecialTokens)
 {
 bool lowerCase = options.ApplyBasicTokenization && options.LowerCaseBeforeTokenization;
 if (options.SpecialTokens is not null)
 {
 if (lowerCase)
 {
 Dictionary<string, int> dic = options.SpecialTokens.ToDictionary(kvp => kvp.Key, kvp => kvp.Value);
options.SpecialTokens = dic;
 Dictionary<string, int> tempSpecialTokens = [];
specialTokensDict = tempSpecialTokens;

 foreach (var kvp in options.SpecialTokens)
 {
Expand All@@ -779,37 +780,49 @@ private static BertTokenizer Create(
 throw new ArgumentException($"The special token '{kvp.Key}' is not in the vocabulary or assigned id value {id} different than the value {kvp.Value} in the special tokens.");
 }

 // Ensure that the special tokens are lowercased.
 dic[kvp.Key.ToLowerInvariant()] = kvp.Value;
 // Add the special token into our dictionary, normalizing it, and adding it into the
 // main vocab, if needed. 
 AddSpecialToken(vocab, tempSpecialTokens, kvp.Key, true);
 }
 }
 }
 else
 {
 // Create a dictionary with the special tokens.
 Dictionary<string, int> specialTokens = new Dictionary<string, int>();
 options.SpecialTokens = specialTokens;

 AddSpecialToken(vocab, specialTokens, options.UnknownToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.SeparatorToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.PaddingToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.ClassificationToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.MaskingToken, lowerCase);
 // Create a dictionary with the special tokens - store the un-normalized forms in the options as
 // that field is exposed to the public. In addition, store the normalized form for creating the 
 // pre-tokenizer.
 Dictionary<string, int> tempSpecialTokens = [];
 Dictionary<string, int> notNormalizedSpecialTokens = [];
 AddSpecialToken(vocab, tempSpecialTokens, options.UnknownToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.SeparatorToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.PaddingToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.ClassificationToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.MaskingToken, lowerCase, notNormalizedSpecialTokens);

 options.SpecialTokens = notNormalizedSpecialTokens;
 specialTokensDict = tempSpecialTokens;
 }
 }

 options.PreTokenizer ??= options.ApplyBasicTokenization ? PreTokenizer.CreateWordOrPunctuation(options.SplitOnSpecialTokens ? options.SpecialTokens : null) : PreTokenizer.CreateWhiteSpace();
 // We set the PreTokenizer here using the normalized special tokens dict (if relevant), and therefore we can 
 // keep the not-normalized special tokens dict in the options passed to the WordPieceTokenizer.
 options.PreTokenizer ??= options.ApplyBasicTokenization ? PreTokenizer.CreateWordOrPunctuation(options.SplitOnSpecialTokens ? specialTokensDict : null) : PreTokenizer.CreateWhiteSpace();

 return new BertTokenizer(vocab, vocabReverse, options);
 }

 private static void AddSpecialToken(Dictionary<StringSpanOrdinalKey, int> vocab, Dictionary<string, int> specialTokens, string token, bool lowerCase)
 private static void AddSpecialToken(Dictionary<StringSpanOrdinalKey, int> vocab, Dictionary<string, int> specialTokens, string token, bool lowerCase, Dictionary<string, int>? notNormalizedSpecialTokens = null)
 {
 if (token is null || !vocab.TryGetValue(new StringSpanOrdinalKey(token), out int id))
 {
 throw new ArgumentException($"The special token '{token}' is not in the vocabulary.");
 }

 if (notNormalizedSpecialTokens is not null)
 {
 notNormalizedSpecialTokens[token] = id;
 }

 string normalizedToken = token;
 if (lowerCase)
 {
Expand Down

6 changes: 3 additions & 3 deletions
src/Microsoft.ML.Tokenizers/Model/WordPieceTokenizer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand DownExpand Up@@ -42,7 +42,7 @@ internal WordPieceTokenizer(
 options ??= new();

 SpecialTokens = options.SpecialTokens;
 SpecialTokensReverse = options.SpecialTokens is not null ? options.SpecialTokens.ToDictionary(kvp => kvp.Value, kvp => kvp.Key) : null;
 SpecialTokensReverse = options.SpecialTokens is not null ? options.SpecialTokens.GroupBy(kvp => kvp.Value).ToDictionary(g => g.Key, g => g.First().Key) : null;

 if (options.UnknownToken is null)
 {
Expand DownExpand Up@@ -800,4 +800,4 @@ public OperationStatus Decode(IEnumerable<int> ids, Span<char> destination, bool
 return OperationStatus.Done;
 }
 }
}
}

93 changes: 91 additions & 2 deletions
test/Microsoft.ML.Tokenizers.Tests/BertTokenizerTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand All@@ -14,6 +14,91 @@ namespace Microsoft.ML.Tokenizers.Tests
{
 public class BertTokenizerTests
 {
 [Fact]
 public void TestWithLowerCasingExplicitSpecialTokens()
 {
 // Add [SPECIAL] token at end (to keep indices as is)
 // Ids: 0 1 2 3 4 5 6 7 8 9 10 11 12, 13 
 string[] vocabTokens = ["[PAD]", "[UNK]", "[CLS]", "[SEP]", "[MASK]", "!", ",", "?", "hello", "world", "how", "are", "you", "[SPECIAL]"];

 string vocabFile = WordPieceTests.CreateVocabFile(vocabTokens);

 Dictionary<string, int> specialTokens = new() {
 { "[PAD]", 0 },
 { "[UNK]", 1 },
 { "[CLS]", 2 },
 { "[SEP]", 3 },
 { "[MASK]", 4 },
 { "[SPECIAL]", 13 },
 };
 var bertOptions = new BertOptions()
 {
 SpecialTokens = specialTokens
 };

 try
 {
 using Stream vocabStream = File.OpenRead(vocabFile);
 BertTokenizer[] bertTokenizers = [BertTokenizer.Create(vocabFile, bertOptions), BertTokenizer.Create(vocabStream, bertOptions)];

 foreach (var tokenizer in bertTokenizers)
 {
 Assert.NotNull(tokenizer.PreTokenizer);
 Assert.Equal("[UNK]", tokenizer.UnknownToken);
 Assert.Equal(1, tokenizer.UnknownTokenId);
 Assert.NotNull(tokenizer.Normalizer);
 Assert.NotNull(tokenizer.PreTokenizer);

 Assert.True(tokenizer.SpecialTokens!.ContainsKey("[SPECIAL]"));

 string text = "Hello, How are you [SPECIAL]?";
 var tokens = tokenizer.EncodeToTokens(text, out string? normalizedText);
 Assert.Equal("hello, how are you [special]?", normalizedText);

 Assert.Equal(
 [
 new EncodedToken(8, "hello", new Range(0, 5)),
 new EncodedToken(6, ",", new Range(5, 6)),
 new EncodedToken(10, "how", new Range(7, 10)),
 new EncodedToken(11, "are", new Range(11, 14)),
 new EncodedToken(12, "you", new Range(15, 18)),
 new EncodedToken(13, "[SPECIAL]", new Range(19, 28)),
 new EncodedToken(7, "?", new Range(28, 29))
 ],
 tokens);

 var ids = tokenizer.EncodeToIds(text);
 Assert.Equal([tokenizer.ClassificationTokenId, 8, 6, 10, 11, 12, 13, 7, tokenizer.SeparatorTokenId], ids);

 Assert.Equal("[CLS] hello, how are you [SPECIAL]? [SEP]", tokenizer.Decode(ids));
 Assert.Equal("hello, how are you?", tokenizer.Decode(ids, skipSpecialTokens: true));

 tokens = tokenizer.EncodeToTokens(tokenizer.Decode(ids), out normalizedText);
 Assert.Equal("[cls] hello, how are you [special]? [sep]", normalizedText);
 Assert.Equal(
 [
 new EncodedToken(2, "[CLS]", new Range(0, 5)),
 new EncodedToken(8, "hello", new Range(6, 11)),
 new EncodedToken(6, ",", new Range(11, 12)),
 new EncodedToken(10, "how", new Range(13, 16)),
 new EncodedToken(11, "are", new Range(17, 20)),
 new EncodedToken(12, "you", new Range(21, 24)),
 new EncodedToken(13, "[SPECIAL]", new Range(25, 34)),
 new EncodedToken(7, "?", new Range(34, 35)),
 new EncodedToken(3, "[SEP]", new Range(36, 41))
 ],
 tokens);

 ids = tokenizer.EncodeToIds(normalizedText!);
 Assert.Equal([tokenizer.ClassificationTokenId, tokenizer.ClassificationTokenId, 8, 6, 10, 11, 12, 13, 7, tokenizer.SeparatorTokenId, tokenizer.SeparatorTokenId], ids);
 }
 }
 finally
 {
 File.Delete(vocabFile);
 }
 }

 [Fact]
 public void TestWithLowerCasing()
 {
Expand All@@ -35,6 +120,10 @@ public void TestWithLowerCasing()
 Assert.NotNull(tokenizer.Normalizer);
 Assert.NotNull(tokenizer.PreTokenizer);

 // Make sure the SpecialTokens dictionary contains the not-normalized tokens
 Assert.True(tokenizer.SpecialTokens!.ContainsKey(tokenizer.UnknownToken));
 Assert.True(tokenizer.SpecialTokens!.ContainsKey(tokenizer.ClassificationToken));

 string text = "Hello, How are you?";
 var tokens = tokenizer.EncodeToTokens(text, out string? normalizedText);
 Assert.Equal("hello, how are you?", normalizedText);
Expand DownExpand Up@@ -511,4 +600,4 @@ public void TestCreateTokenTypeIdsFromSequences()
 }
 }
 }
}
}

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix");
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Moved SpecialTokens assignment after the modification to avoid "Collection Modified" error#7328

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

tarekgh
merged 7 commits into

from

Dec 5, 2024
 Merged


Moved SpecialTokens assignment after the modification to avoid "Collection Modified" error
#7328
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
6e5fbed

Moved special tokens assignment below so the collection won't be modi…


shaltielshmid Dec 2, 2024
5edde92

Added safe dictionary inversion


shaltielshmid Dec 4, 2024
84bd69d

Added storing the not-normalized special tokens


shaltielshmid Dec 4, 2024
6ae9d10

Added support for net standard


shaltielshmid Dec 4, 2024
4f06337

Added and updated tests


shaltielshmid Dec 4, 2024
0fcbe64

Merge remote-tracking branch 'dotnet/main' into bug/bert-tok-collecti…


shaltielshmid Dec 4, 2024
25a4c6d

Updated without additional memory allocation


shaltielshmid Dec 5, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


45 changes: 29 additions & 16 deletions
src/Microsoft.ML.Tokenizers/Model/BertTokenizer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand DownExpand Up@@ -762,15 +762,16 @@ private static BertTokenizer Create(

 options.Normalizer ??= options.ApplyBasicTokenization ? new BertNormalizer(options.LowerCaseBeforeTokenization, options.IndividuallyTokenizeCjk, options.RemoveNonSpacingMarks) : null;

 IReadOnlyDictionary<string, int>? specialTokensDict = options.SpecialTokens;
 if (options.SplitOnSpecialTokens)
 {
 bool lowerCase = options.ApplyBasicTokenization && options.LowerCaseBeforeTokenization;
 if (options.SpecialTokens is not null)
 {
 if (lowerCase)
 {
 Dictionary<string, int> dic = options.SpecialTokens.ToDictionary(kvp => kvp.Key, kvp => kvp.Value);
options.SpecialTokens = dic;
 Dictionary<string, int> tempSpecialTokens = [];
specialTokensDict = tempSpecialTokens;

 foreach (var kvp in options.SpecialTokens)
 {
Expand All@@ -779,37 +780,49 @@ private static BertTokenizer Create(
 throw new ArgumentException($"The special token '{kvp.Key}' is not in the vocabulary or assigned id value {id} different than the value {kvp.Value} in the special tokens.");
 }

 // Ensure that the special tokens are lowercased.
 dic[kvp.Key.ToLowerInvariant()] = kvp.Value;
 // Add the special token into our dictionary, normalizing it, and adding it into the
 // main vocab, if needed. 
 AddSpecialToken(vocab, tempSpecialTokens, kvp.Key, true);
 }
 }
 }
 else
 {
 // Create a dictionary with the special tokens.
 Dictionary<string, int> specialTokens = new Dictionary<string, int>();
 options.SpecialTokens = specialTokens;

 AddSpecialToken(vocab, specialTokens, options.UnknownToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.SeparatorToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.PaddingToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.ClassificationToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.MaskingToken, lowerCase);
 // Create a dictionary with the special tokens - store the un-normalized forms in the options as
 // that field is exposed to the public. In addition, store the normalized form for creating the 
 // pre-tokenizer.
 Dictionary<string, int> tempSpecialTokens = [];
 Dictionary<string, int> notNormalizedSpecialTokens = [];
 AddSpecialToken(vocab, tempSpecialTokens, options.UnknownToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.SeparatorToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.PaddingToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.ClassificationToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.MaskingToken, lowerCase, notNormalizedSpecialTokens);

 options.SpecialTokens = notNormalizedSpecialTokens;
 specialTokensDict = tempSpecialTokens;
 }
 }

 options.PreTokenizer ??= options.ApplyBasicTokenization ? PreTokenizer.CreateWordOrPunctuation(options.SplitOnSpecialTokens ? options.SpecialTokens : null) : PreTokenizer.CreateWhiteSpace();
 // We set the PreTokenizer here using the normalized special tokens dict (if relevant), and therefore we can 
 // keep the not-normalized special tokens dict in the options passed to the WordPieceTokenizer.
 options.PreTokenizer ??= options.ApplyBasicTokenization ? PreTokenizer.CreateWordOrPunctuation(options.SplitOnSpecialTokens ? specialTokensDict : null) : PreTokenizer.CreateWhiteSpace();

 return new BertTokenizer(vocab, vocabReverse, options);
 }

 private static void AddSpecialToken(Dictionary<StringSpanOrdinalKey, int> vocab, Dictionary<string, int> specialTokens, string token, bool lowerCase)
 private static void AddSpecialToken(Dictionary<StringSpanOrdinalKey, int> vocab, Dictionary<string, int> specialTokens, string token, bool lowerCase, Dictionary<string, int>? notNormalizedSpecialTokens = null)
 {
 if (token is null || !vocab.TryGetValue(new StringSpanOrdinalKey(token), out int id))
 {
 throw new ArgumentException($"The special token '{token}' is not in the vocabulary.");
 }

 if (notNormalizedSpecialTokens is not null)
 {
 notNormalizedSpecialTokens[token] = id;
 }

 string normalizedToken = token;
 if (lowerCase)
 {
Expand Down

6 changes: 3 additions & 3 deletions
src/Microsoft.ML.Tokenizers/Model/WordPieceTokenizer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand DownExpand Up@@ -42,7 +42,7 @@ internal WordPieceTokenizer(
 options ??= new();

 SpecialTokens = options.SpecialTokens;
 SpecialTokensReverse = options.SpecialTokens is not null ? options.SpecialTokens.ToDictionary(kvp => kvp.Value, kvp => kvp.Key) : null;
 SpecialTokensReverse = options.SpecialTokens is not null ? options.SpecialTokens.GroupBy(kvp => kvp.Value).ToDictionary(g => g.Key, g => g.First().Key) : null;

 if (options.UnknownToken is null)
 {
Expand DownExpand Up@@ -800,4 +800,4 @@ public OperationStatus Decode(IEnumerable<int> ids, Span<char> destination, bool
 return OperationStatus.Done;
 }
 }
}
}

93 changes: 91 additions & 2 deletions
test/Microsoft.ML.Tokenizers.Tests/BertTokenizerTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand All@@ -14,6 +14,91 @@ namespace Microsoft.ML.Tokenizers.Tests
{
 public class BertTokenizerTests
 {
 [Fact]
 public void TestWithLowerCasingExplicitSpecialTokens()
 {
 // Add [SPECIAL] token at end (to keep indices as is)
 // Ids: 0 1 2 3 4 5 6 7 8 9 10 11 12, 13 
 string[] vocabTokens = ["[PAD]", "[UNK]", "[CLS]", "[SEP]", "[MASK]", "!", ",", "?", "hello", "world", "how", "are", "you", "[SPECIAL]"];

 string vocabFile = WordPieceTests.CreateVocabFile(vocabTokens);

 Dictionary<string, int> specialTokens = new() {
 { "[PAD]", 0 },
 { "[UNK]", 1 },
 { "[CLS]", 2 },
 { "[SEP]", 3 },
 { "[MASK]", 4 },
 { "[SPECIAL]", 13 },
 };
 var bertOptions = new BertOptions()
 {
 SpecialTokens = specialTokens
 };

 try
 {
 using Stream vocabStream = File.OpenRead(vocabFile);
 BertTokenizer[] bertTokenizers = [BertTokenizer.Create(vocabFile, bertOptions), BertTokenizer.Create(vocabStream, bertOptions)];

 foreach (var tokenizer in bertTokenizers)
 {
 Assert.NotNull(tokenizer.PreTokenizer);
 Assert.Equal("[UNK]", tokenizer.UnknownToken);
 Assert.Equal(1, tokenizer.UnknownTokenId);
 Assert.NotNull(tokenizer.Normalizer);
 Assert.NotNull(tokenizer.PreTokenizer);

 Assert.True(tokenizer.SpecialTokens!.ContainsKey("[SPECIAL]"));

 string text = "Hello, How are you [SPECIAL]?";
 var tokens = tokenizer.EncodeToTokens(text, out string? normalizedText);
 Assert.Equal("hello, how are you [special]?", normalizedText);

 Assert.Equal(
 [
 new EncodedToken(8, "hello", new Range(0, 5)),
 new EncodedToken(6, ",", new Range(5, 6)),
 new EncodedToken(10, "how", new Range(7, 10)),
 new EncodedToken(11, "are", new Range(11, 14)),
 new EncodedToken(12, "you", new Range(15, 18)),
 new EncodedToken(13, "[SPECIAL]", new Range(19, 28)),
 new EncodedToken(7, "?", new Range(28, 29))
 ],
 tokens);

 var ids = tokenizer.EncodeToIds(text);
 Assert.Equal([tokenizer.ClassificationTokenId, 8, 6, 10, 11, 12, 13, 7, tokenizer.SeparatorTokenId], ids);

 Assert.Equal("[CLS] hello, how are you [SPECIAL]? [SEP]", tokenizer.Decode(ids));
 Assert.Equal("hello, how are you?", tokenizer.Decode(ids, skipSpecialTokens: true));

 tokens = tokenizer.EncodeToTokens(tokenizer.Decode(ids), out normalizedText);
 Assert.Equal("[cls] hello, how are you [special]? [sep]", normalizedText);
 Assert.Equal(
 [
 new EncodedToken(2, "[CLS]", new Range(0, 5)),
 new EncodedToken(8, "hello", new Range(6, 11)),
 new EncodedToken(6, ",", new Range(11, 12)),
 new EncodedToken(10, "how", new Range(13, 16)),
 new EncodedToken(11, "are", new Range(17, 20)),
 new EncodedToken(12, "you", new Range(21, 24)),
 new EncodedToken(13, "[SPECIAL]", new Range(25, 34)),
 new EncodedToken(7, "?", new Range(34, 35)),
 new EncodedToken(3, "[SEP]", new Range(36, 41))
 ],
 tokens);

 ids = tokenizer.EncodeToIds(normalizedText!);
 Assert.Equal([tokenizer.ClassificationTokenId, tokenizer.ClassificationTokenId, 8, 6, 10, 11, 12, 13, 7, tokenizer.SeparatorTokenId, tokenizer.SeparatorTokenId], ids);
 }
 }
 finally
 {
 File.Delete(vocabFile);
 }
 }

 [Fact]
 public void TestWithLowerCasing()
 {
Expand All@@ -35,6 +120,10 @@ public void TestWithLowerCasing()
 Assert.NotNull(tokenizer.Normalizer);
 Assert.NotNull(tokenizer.PreTokenizer);

 // Make sure the SpecialTokens dictionary contains the not-normalized tokens
 Assert.True(tokenizer.SpecialTokens!.ContainsKey(tokenizer.UnknownToken));
 Assert.True(tokenizer.SpecialTokens!.ContainsKey(tokenizer.ClassificationToken));

 string text = "Hello, How are you?";
 var tokens = tokenizer.EncodeToTokens(text, out string? normalizedText);
 Assert.Equal("hello, how are you?", normalizedText);
Expand DownExpand Up@@ -511,4 +600,4 @@ public void TestCreateTokenTypeIdsFromSequences()
 }
 }
 }
}
}

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms");
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Moved SpecialTokens assignment after the modification to avoid "Collection Modified" error#7328

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

tarekgh
merged 7 commits into

from

Dec 5, 2024
 Merged


Moved SpecialTokens assignment after the modification to avoid "Collection Modified" error
#7328
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
6e5fbed

Moved special tokens assignment below so the collection won't be modi…


shaltielshmid Dec 2, 2024
5edde92

Added safe dictionary inversion


shaltielshmid Dec 4, 2024
84bd69d

Added storing the not-normalized special tokens


shaltielshmid Dec 4, 2024
6ae9d10

Added support for net standard


shaltielshmid Dec 4, 2024
4f06337

Added and updated tests


shaltielshmid Dec 4, 2024
0fcbe64

Merge remote-tracking branch 'dotnet/main' into bug/bert-tok-collecti…


shaltielshmid Dec 4, 2024
25a4c6d

Updated without additional memory allocation


shaltielshmid Dec 5, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


45 changes: 29 additions & 16 deletions
src/Microsoft.ML.Tokenizers/Model/BertTokenizer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand DownExpand Up@@ -762,15 +762,16 @@ private static BertTokenizer Create(

 options.Normalizer ??= options.ApplyBasicTokenization ? new BertNormalizer(options.LowerCaseBeforeTokenization, options.IndividuallyTokenizeCjk, options.RemoveNonSpacingMarks) : null;

 IReadOnlyDictionary<string, int>? specialTokensDict = options.SpecialTokens;
 if (options.SplitOnSpecialTokens)
 {
 bool lowerCase = options.ApplyBasicTokenization && options.LowerCaseBeforeTokenization;
 if (options.SpecialTokens is not null)
 {
 if (lowerCase)
 {
 Dictionary<string, int> dic = options.SpecialTokens.ToDictionary(kvp => kvp.Key, kvp => kvp.Value);
options.SpecialTokens = dic;
 Dictionary<string, int> tempSpecialTokens = [];
specialTokensDict = tempSpecialTokens;

 foreach (var kvp in options.SpecialTokens)
 {
Expand All@@ -779,37 +780,49 @@ private static BertTokenizer Create(
 throw new ArgumentException($"The special token '{kvp.Key}' is not in the vocabulary or assigned id value {id} different than the value {kvp.Value} in the special tokens.");
 }

 // Ensure that the special tokens are lowercased.
 dic[kvp.Key.ToLowerInvariant()] = kvp.Value;
 // Add the special token into our dictionary, normalizing it, and adding it into the
 // main vocab, if needed. 
 AddSpecialToken(vocab, tempSpecialTokens, kvp.Key, true);
 }
 }
 }
 else
 {
 // Create a dictionary with the special tokens.
 Dictionary<string, int> specialTokens = new Dictionary<string, int>();
 options.SpecialTokens = specialTokens;

 AddSpecialToken(vocab, specialTokens, options.UnknownToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.SeparatorToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.PaddingToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.ClassificationToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.MaskingToken, lowerCase);
 // Create a dictionary with the special tokens - store the un-normalized forms in the options as
 // that field is exposed to the public. In addition, store the normalized form for creating the 
 // pre-tokenizer.
 Dictionary<string, int> tempSpecialTokens = [];
 Dictionary<string, int> notNormalizedSpecialTokens = [];
 AddSpecialToken(vocab, tempSpecialTokens, options.UnknownToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.SeparatorToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.PaddingToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.ClassificationToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.MaskingToken, lowerCase, notNormalizedSpecialTokens);

 options.SpecialTokens = notNormalizedSpecialTokens;
 specialTokensDict = tempSpecialTokens;
 }
 }

 options.PreTokenizer ??= options.ApplyBasicTokenization ? PreTokenizer.CreateWordOrPunctuation(options.SplitOnSpecialTokens ? options.SpecialTokens : null) : PreTokenizer.CreateWhiteSpace();
 // We set the PreTokenizer here using the normalized special tokens dict (if relevant), and therefore we can 
 // keep the not-normalized special tokens dict in the options passed to the WordPieceTokenizer.
 options.PreTokenizer ??= options.ApplyBasicTokenization ? PreTokenizer.CreateWordOrPunctuation(options.SplitOnSpecialTokens ? specialTokensDict : null) : PreTokenizer.CreateWhiteSpace();

 return new BertTokenizer(vocab, vocabReverse, options);
 }

 private static void AddSpecialToken(Dictionary<StringSpanOrdinalKey, int> vocab, Dictionary<string, int> specialTokens, string token, bool lowerCase)
 private static void AddSpecialToken(Dictionary<StringSpanOrdinalKey, int> vocab, Dictionary<string, int> specialTokens, string token, bool lowerCase, Dictionary<string, int>? notNormalizedSpecialTokens = null)
 {
 if (token is null || !vocab.TryGetValue(new StringSpanOrdinalKey(token), out int id))
 {
 throw new ArgumentException($"The special token '{token}' is not in the vocabulary.");
 }

 if (notNormalizedSpecialTokens is not null)
 {
 notNormalizedSpecialTokens[token] = id;
 }

 string normalizedToken = token;
 if (lowerCase)
 {
Expand Down

6 changes: 3 additions & 3 deletions
src/Microsoft.ML.Tokenizers/Model/WordPieceTokenizer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand DownExpand Up@@ -42,7 +42,7 @@ internal WordPieceTokenizer(
 options ??= new();

 SpecialTokens = options.SpecialTokens;
 SpecialTokensReverse = options.SpecialTokens is not null ? options.SpecialTokens.ToDictionary(kvp => kvp.Value, kvp => kvp.Key) : null;
 SpecialTokensReverse = options.SpecialTokens is not null ? options.SpecialTokens.GroupBy(kvp => kvp.Value).ToDictionary(g => g.Key, g => g.First().Key) : null;

 if (options.UnknownToken is null)
 {
Expand DownExpand Up@@ -800,4 +800,4 @@ public OperationStatus Decode(IEnumerable<int> ids, Span<char> destination, bool
 return OperationStatus.Done;
 }
 }
}
}

93 changes: 91 additions & 2 deletions
test/Microsoft.ML.Tokenizers.Tests/BertTokenizerTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand All@@ -14,6 +14,91 @@ namespace Microsoft.ML.Tokenizers.Tests
{
 public class BertTokenizerTests
 {
 [Fact]
 public void TestWithLowerCasingExplicitSpecialTokens()
 {
 // Add [SPECIAL] token at end (to keep indices as is)
 // Ids: 0 1 2 3 4 5 6 7 8 9 10 11 12, 13 
 string[] vocabTokens = ["[PAD]", "[UNK]", "[CLS]", "[SEP]", "[MASK]", "!", ",", "?", "hello", "world", "how", "are", "you", "[SPECIAL]"];

 string vocabFile = WordPieceTests.CreateVocabFile(vocabTokens);

 Dictionary<string, int> specialTokens = new() {
 { "[PAD]", 0 },
 { "[UNK]", 1 },
 { "[CLS]", 2 },
 { "[SEP]", 3 },
 { "[MASK]", 4 },
 { "[SPECIAL]", 13 },
 };
 var bertOptions = new BertOptions()
 {
 SpecialTokens = specialTokens
 };

 try
 {
 using Stream vocabStream = File.OpenRead(vocabFile);
 BertTokenizer[] bertTokenizers = [BertTokenizer.Create(vocabFile, bertOptions), BertTokenizer.Create(vocabStream, bertOptions)];

 foreach (var tokenizer in bertTokenizers)
 {
 Assert.NotNull(tokenizer.PreTokenizer);
 Assert.Equal("[UNK]", tokenizer.UnknownToken);
 Assert.Equal(1, tokenizer.UnknownTokenId);
 Assert.NotNull(tokenizer.Normalizer);
 Assert.NotNull(tokenizer.PreTokenizer);

 Assert.True(tokenizer.SpecialTokens!.ContainsKey("[SPECIAL]"));

 string text = "Hello, How are you [SPECIAL]?";
 var tokens = tokenizer.EncodeToTokens(text, out string? normalizedText);
 Assert.Equal("hello, how are you [special]?", normalizedText);

 Assert.Equal(
 [
 new EncodedToken(8, "hello", new Range(0, 5)),
 new EncodedToken(6, ",", new Range(5, 6)),
 new EncodedToken(10, "how", new Range(7, 10)),
 new EncodedToken(11, "are", new Range(11, 14)),
 new EncodedToken(12, "you", new Range(15, 18)),
 new EncodedToken(13, "[SPECIAL]", new Range(19, 28)),
 new EncodedToken(7, "?", new Range(28, 29))
 ],
 tokens);

 var ids = tokenizer.EncodeToIds(text);
 Assert.Equal([tokenizer.ClassificationTokenId, 8, 6, 10, 11, 12, 13, 7, tokenizer.SeparatorTokenId], ids);

 Assert.Equal("[CLS] hello, how are you [SPECIAL]? [SEP]", tokenizer.Decode(ids));
 Assert.Equal("hello, how are you?", tokenizer.Decode(ids, skipSpecialTokens: true));

 tokens = tokenizer.EncodeToTokens(tokenizer.Decode(ids), out normalizedText);
 Assert.Equal("[cls] hello, how are you [special]? [sep]", normalizedText);
 Assert.Equal(
 [
 new EncodedToken(2, "[CLS]", new Range(0, 5)),
 new EncodedToken(8, "hello", new Range(6, 11)),
 new EncodedToken(6, ",", new Range(11, 12)),
 new EncodedToken(10, "how", new Range(13, 16)),
 new EncodedToken(11, "are", new Range(17, 20)),
 new EncodedToken(12, "you", new Range(21, 24)),
 new EncodedToken(13, "[SPECIAL]", new Range(25, 34)),
 new EncodedToken(7, "?", new Range(34, 35)),
 new EncodedToken(3, "[SEP]", new Range(36, 41))
 ],
 tokens);

 ids = tokenizer.EncodeToIds(normalizedText!);
 Assert.Equal([tokenizer.ClassificationTokenId, tokenizer.ClassificationTokenId, 8, 6, 10, 11, 12, 13, 7, tokenizer.SeparatorTokenId, tokenizer.SeparatorTokenId], ids);
 }
 }
 finally
 {
 File.Delete(vocabFile);
 }
 }

 [Fact]
 public void TestWithLowerCasing()
 {
Expand All@@ -35,6 +120,10 @@ public void TestWithLowerCasing()
 Assert.NotNull(tokenizer.Normalizer);
 Assert.NotNull(tokenizer.PreTokenizer);

 // Make sure the SpecialTokens dictionary contains the not-normalized tokens
 Assert.True(tokenizer.SpecialTokens!.ContainsKey(tokenizer.UnknownToken));
 Assert.True(tokenizer.SpecialTokens!.ContainsKey(tokenizer.ClassificationToken));

 string text = "Hello, How are you?";
 var tokens = tokenizer.EncodeToTokens(text, out string? normalizedText);
 Assert.Equal("hello, how are you?", normalizedText);
Expand DownExpand Up@@ -511,4 +600,4 @@ public void TestCreateTokenTypeIdsFromSequences()
 }
 }
 }
}
}

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links");
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
Moved SpecialTokens assignment after the modification to avoid "Collection Modified" error#7328

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

tarekgh
merged 7 commits into

from

Dec 5, 2024
 Merged


Moved SpecialTokens assignment after the modification to avoid "Collection Modified" error
#7328
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
6e5fbed

Moved special tokens assignment below so the collection won't be modi…


shaltielshmid Dec 2, 2024
5edde92

Added safe dictionary inversion


shaltielshmid Dec 4, 2024
84bd69d

Added storing the not-normalized special tokens


shaltielshmid Dec 4, 2024
6ae9d10

Added support for net standard


shaltielshmid Dec 4, 2024
4f06337

Added and updated tests


shaltielshmid Dec 4, 2024
0fcbe64

Merge remote-tracking branch 'dotnet/main' into bug/bert-tok-collecti…


shaltielshmid Dec 4, 2024
25a4c6d

Updated without additional memory allocation


shaltielshmid Dec 5, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


45 changes: 29 additions & 16 deletions
src/Microsoft.ML.Tokenizers/Model/BertTokenizer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand DownExpand Up@@ -762,15 +762,16 @@ private static BertTokenizer Create(

 options.Normalizer ??= options.ApplyBasicTokenization ? new BertNormalizer(options.LowerCaseBeforeTokenization, options.IndividuallyTokenizeCjk, options.RemoveNonSpacingMarks) : null;

 IReadOnlyDictionary<string, int>? specialTokensDict = options.SpecialTokens;
 if (options.SplitOnSpecialTokens)
 {
 bool lowerCase = options.ApplyBasicTokenization && options.LowerCaseBeforeTokenization;
 if (options.SpecialTokens is not null)
 {
 if (lowerCase)
 {
 Dictionary<string, int> dic = options.SpecialTokens.ToDictionary(kvp => kvp.Key, kvp => kvp.Value);
options.SpecialTokens = dic;
 Dictionary<string, int> tempSpecialTokens = [];
specialTokensDict = tempSpecialTokens;

 foreach (var kvp in options.SpecialTokens)
 {
Expand All@@ -779,37 +780,49 @@ private static BertTokenizer Create(
 throw new ArgumentException($"The special token '{kvp.Key}' is not in the vocabulary or assigned id value {id} different than the value {kvp.Value} in the special tokens.");
 }

 // Ensure that the special tokens are lowercased.
 dic[kvp.Key.ToLowerInvariant()] = kvp.Value;
 // Add the special token into our dictionary, normalizing it, and adding it into the
 // main vocab, if needed. 
 AddSpecialToken(vocab, tempSpecialTokens, kvp.Key, true);
 }
 }
 }
 else
 {
 // Create a dictionary with the special tokens.
 Dictionary<string, int> specialTokens = new Dictionary<string, int>();
 options.SpecialTokens = specialTokens;

 AddSpecialToken(vocab, specialTokens, options.UnknownToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.SeparatorToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.PaddingToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.ClassificationToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.MaskingToken, lowerCase);
 // Create a dictionary with the special tokens - store the un-normalized forms in the options as
 // that field is exposed to the public. In addition, store the normalized form for creating the 
 // pre-tokenizer.
 Dictionary<string, int> tempSpecialTokens = [];
 Dictionary<string, int> notNormalizedSpecialTokens = [];
 AddSpecialToken(vocab, tempSpecialTokens, options.UnknownToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.SeparatorToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.PaddingToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.ClassificationToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.MaskingToken, lowerCase, notNormalizedSpecialTokens);

 options.SpecialTokens = notNormalizedSpecialTokens;
 specialTokensDict = tempSpecialTokens;
 }
 }

 options.PreTokenizer ??= options.ApplyBasicTokenization ? PreTokenizer.CreateWordOrPunctuation(options.SplitOnSpecialTokens ? options.SpecialTokens : null) : PreTokenizer.CreateWhiteSpace();
 // We set the PreTokenizer here using the normalized special tokens dict (if relevant), and therefore we can 
 // keep the not-normalized special tokens dict in the options passed to the WordPieceTokenizer.
 options.PreTokenizer ??= options.ApplyBasicTokenization ? PreTokenizer.CreateWordOrPunctuation(options.SplitOnSpecialTokens ? specialTokensDict : null) : PreTokenizer.CreateWhiteSpace();

 return new BertTokenizer(vocab, vocabReverse, options);
 }

 private static void AddSpecialToken(Dictionary<StringSpanOrdinalKey, int> vocab, Dictionary<string, int> specialTokens, string token, bool lowerCase)
 private static void AddSpecialToken(Dictionary<StringSpanOrdinalKey, int> vocab, Dictionary<string, int> specialTokens, string token, bool lowerCase, Dictionary<string, int>? notNormalizedSpecialTokens = null)
 {
 if (token is null || !vocab.TryGetValue(new StringSpanOrdinalKey(token), out int id))
 {
 throw new ArgumentException($"The special token '{token}' is not in the vocabulary.");
 }

 if (notNormalizedSpecialTokens is not null)
 {
 notNormalizedSpecialTokens[token] = id;
 }

 string normalizedToken = token;
 if (lowerCase)
 {
Expand Down

6 changes: 3 additions & 3 deletions
src/Microsoft.ML.Tokenizers/Model/WordPieceTokenizer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand DownExpand Up@@ -42,7 +42,7 @@ internal WordPieceTokenizer(
 options ??= new();

 SpecialTokens = options.SpecialTokens;
 SpecialTokensReverse = options.SpecialTokens is not null ? options.SpecialTokens.ToDictionary(kvp => kvp.Value, kvp => kvp.Key) : null;
 SpecialTokensReverse = options.SpecialTokens is not null ? options.SpecialTokens.GroupBy(kvp => kvp.Value).ToDictionary(g => g.Key, g => g.First().Key) : null;

 if (options.UnknownToken is null)
 {
Expand DownExpand Up@@ -800,4 +800,4 @@ public OperationStatus Decode(IEnumerable<int> ids, Span<char> destination, bool
 return OperationStatus.Done;
 }
 }
}
}

93 changes: 91 additions & 2 deletions
test/Microsoft.ML.Tokenizers.Tests/BertTokenizerTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand All@@ -14,6 +14,91 @@ namespace Microsoft.ML.Tokenizers.Tests
{
 public class BertTokenizerTests
 {
 [Fact]
 public void TestWithLowerCasingExplicitSpecialTokens()
 {
 // Add [SPECIAL] token at end (to keep indices as is)
 // Ids: 0 1 2 3 4 5 6 7 8 9 10 11 12, 13 
 string[] vocabTokens = ["[PAD]", "[UNK]", "[CLS]", "[SEP]", "[MASK]", "!", ",", "?", "hello", "world", "how", "are", "you", "[SPECIAL]"];

 string vocabFile = WordPieceTests.CreateVocabFile(vocabTokens);

 Dictionary<string, int> specialTokens = new() {
 { "[PAD]", 0 },
 { "[UNK]", 1 },
 { "[CLS]", 2 },
 { "[SEP]", 3 },
 { "[MASK]", 4 },
 { "[SPECIAL]", 13 },
 };
 var bertOptions = new BertOptions()
 {
 SpecialTokens = specialTokens
 };

 try
 {
 using Stream vocabStream = File.OpenRead(vocabFile);
 BertTokenizer[] bertTokenizers = [BertTokenizer.Create(vocabFile, bertOptions), BertTokenizer.Create(vocabStream, bertOptions)];

 foreach (var tokenizer in bertTokenizers)
 {
 Assert.NotNull(tokenizer.PreTokenizer);
 Assert.Equal("[UNK]", tokenizer.UnknownToken);
 Assert.Equal(1, tokenizer.UnknownTokenId);
 Assert.NotNull(tokenizer.Normalizer);
 Assert.NotNull(tokenizer.PreTokenizer);

 Assert.True(tokenizer.SpecialTokens!.ContainsKey("[SPECIAL]"));

 string text = "Hello, How are you [SPECIAL]?";
 var tokens = tokenizer.EncodeToTokens(text, out string? normalizedText);
 Assert.Equal("hello, how are you [special]?", normalizedText);

 Assert.Equal(
 [
 new EncodedToken(8, "hello", new Range(0, 5)),
 new EncodedToken(6, ",", new Range(5, 6)),
 new EncodedToken(10, "how", new Range(7, 10)),
 new EncodedToken(11, "are", new Range(11, 14)),
 new EncodedToken(12, "you", new Range(15, 18)),
 new EncodedToken(13, "[SPECIAL]", new Range(19, 28)),
 new EncodedToken(7, "?", new Range(28, 29))
 ],
 tokens);

 var ids = tokenizer.EncodeToIds(text);
 Assert.Equal([tokenizer.ClassificationTokenId, 8, 6, 10, 11, 12, 13, 7, tokenizer.SeparatorTokenId], ids);

 Assert.Equal("[CLS] hello, how are you [SPECIAL]? [SEP]", tokenizer.Decode(ids));
 Assert.Equal("hello, how are you?", tokenizer.Decode(ids, skipSpecialTokens: true));

 tokens = tokenizer.EncodeToTokens(tokenizer.Decode(ids), out normalizedText);
 Assert.Equal("[cls] hello, how are you [special]? [sep]", normalizedText);
 Assert.Equal(
 [
 new EncodedToken(2, "[CLS]", new Range(0, 5)),
 new EncodedToken(8, "hello", new Range(6, 11)),
 new EncodedToken(6, ",", new Range(11, 12)),
 new EncodedToken(10, "how", new Range(13, 16)),
 new EncodedToken(11, "are", new Range(17, 20)),
 new EncodedToken(12, "you", new Range(21, 24)),
 new EncodedToken(13, "[SPECIAL]", new Range(25, 34)),
 new EncodedToken(7, "?", new Range(34, 35)),
 new EncodedToken(3, "[SEP]", new Range(36, 41))
 ],
 tokens);

 ids = tokenizer.EncodeToIds(normalizedText!);
 Assert.Equal([tokenizer.ClassificationTokenId, tokenizer.ClassificationTokenId, 8, 6, 10, 11, 12, 13, 7, tokenizer.SeparatorTokenId, tokenizer.SeparatorTokenId], ids);
 }
 }
 finally
 {
 File.Delete(vocabFile);
 }
 }

 [Fact]
 public void TestWithLowerCasing()
 {
Expand All@@ -35,6 +120,10 @@ public void TestWithLowerCasing()
 Assert.NotNull(tokenizer.Normalizer);
 Assert.NotNull(tokenizer.PreTokenizer);

 // Make sure the SpecialTokens dictionary contains the not-normalized tokens
 Assert.True(tokenizer.SpecialTokens!.ContainsKey(tokenizer.UnknownToken));
 Assert.True(tokenizer.SpecialTokens!.ContainsKey(tokenizer.ClassificationToken));

 string text = "Hello, How are you?";
 var tokens = tokenizer.EncodeToTokens(text, out string? normalizedText);
 Assert.Equal("hello, how are you?", normalizedText);
Expand DownExpand Up@@ -511,4 +600,4 @@ public void TestCreateTokenTypeIdsFromSequences()
 }
 }
 }
}
}

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default");
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Moved SpecialTokens assignment after the modification to avoid "Collection Modified" error#7328

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

tarekgh
merged 7 commits into

from

Dec 5, 2024
 Merged


Moved SpecialTokens assignment after the modification to avoid "Collection Modified" error
#7328
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
6e5fbed

Moved special tokens assignment below so the collection won't be modi…


shaltielshmid Dec 2, 2024
5edde92

Added safe dictionary inversion


shaltielshmid Dec 4, 2024
84bd69d

Added storing the not-normalized special tokens


shaltielshmid Dec 4, 2024
6ae9d10

Added support for net standard


shaltielshmid Dec 4, 2024
4f06337

Added and updated tests


shaltielshmid Dec 4, 2024
0fcbe64

Merge remote-tracking branch 'dotnet/main' into bug/bert-tok-collecti…


shaltielshmid Dec 4, 2024
25a4c6d

Updated without additional memory allocation


shaltielshmid Dec 5, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


45 changes: 29 additions & 16 deletions
src/Microsoft.ML.Tokenizers/Model/BertTokenizer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand DownExpand Up@@ -762,15 +762,16 @@ private static BertTokenizer Create(

 options.Normalizer ??= options.ApplyBasicTokenization ? new BertNormalizer(options.LowerCaseBeforeTokenization, options.IndividuallyTokenizeCjk, options.RemoveNonSpacingMarks) : null;

 IReadOnlyDictionary<string, int>? specialTokensDict = options.SpecialTokens;
 if (options.SplitOnSpecialTokens)
 {
 bool lowerCase = options.ApplyBasicTokenization && options.LowerCaseBeforeTokenization;
 if (options.SpecialTokens is not null)
 {
 if (lowerCase)
 {
 Dictionary<string, int> dic = options.SpecialTokens.ToDictionary(kvp => kvp.Key, kvp => kvp.Value);
options.SpecialTokens = dic;
 Dictionary<string, int> tempSpecialTokens = [];
specialTokensDict = tempSpecialTokens;

 foreach (var kvp in options.SpecialTokens)
 {
Expand All@@ -779,37 +780,49 @@ private static BertTokenizer Create(
 throw new ArgumentException($"The special token '{kvp.Key}' is not in the vocabulary or assigned id value {id} different than the value {kvp.Value} in the special tokens.");
 }

 // Ensure that the special tokens are lowercased.
 dic[kvp.Key.ToLowerInvariant()] = kvp.Value;
 // Add the special token into our dictionary, normalizing it, and adding it into the
 // main vocab, if needed. 
 AddSpecialToken(vocab, tempSpecialTokens, kvp.Key, true);
 }
 }
 }
 else
 {
 // Create a dictionary with the special tokens.
 Dictionary<string, int> specialTokens = new Dictionary<string, int>();
 options.SpecialTokens = specialTokens;

 AddSpecialToken(vocab, specialTokens, options.UnknownToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.SeparatorToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.PaddingToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.ClassificationToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.MaskingToken, lowerCase);
 // Create a dictionary with the special tokens - store the un-normalized forms in the options as
 // that field is exposed to the public. In addition, store the normalized form for creating the 
 // pre-tokenizer.
 Dictionary<string, int> tempSpecialTokens = [];
 Dictionary<string, int> notNormalizedSpecialTokens = [];
 AddSpecialToken(vocab, tempSpecialTokens, options.UnknownToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.SeparatorToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.PaddingToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.ClassificationToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.MaskingToken, lowerCase, notNormalizedSpecialTokens);

 options.SpecialTokens = notNormalizedSpecialTokens;
 specialTokensDict = tempSpecialTokens;
 }
 }

 options.PreTokenizer ??= options.ApplyBasicTokenization ? PreTokenizer.CreateWordOrPunctuation(options.SplitOnSpecialTokens ? options.SpecialTokens : null) : PreTokenizer.CreateWhiteSpace();
 // We set the PreTokenizer here using the normalized special tokens dict (if relevant), and therefore we can 
 // keep the not-normalized special tokens dict in the options passed to the WordPieceTokenizer.
 options.PreTokenizer ??= options.ApplyBasicTokenization ? PreTokenizer.CreateWordOrPunctuation(options.SplitOnSpecialTokens ? specialTokensDict : null) : PreTokenizer.CreateWhiteSpace();

 return new BertTokenizer(vocab, vocabReverse, options);
 }

 private static void AddSpecialToken(Dictionary<StringSpanOrdinalKey, int> vocab, Dictionary<string, int> specialTokens, string token, bool lowerCase)
 private static void AddSpecialToken(Dictionary<StringSpanOrdinalKey, int> vocab, Dictionary<string, int> specialTokens, string token, bool lowerCase, Dictionary<string, int>? notNormalizedSpecialTokens = null)
 {
 if (token is null || !vocab.TryGetValue(new StringSpanOrdinalKey(token), out int id))
 {
 throw new ArgumentException($"The special token '{token}' is not in the vocabulary.");
 }

 if (notNormalizedSpecialTokens is not null)
 {
 notNormalizedSpecialTokens[token] = id;
 }

 string normalizedToken = token;
 if (lowerCase)
 {
Expand Down

6 changes: 3 additions & 3 deletions
src/Microsoft.ML.Tokenizers/Model/WordPieceTokenizer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand DownExpand Up@@ -42,7 +42,7 @@ internal WordPieceTokenizer(
 options ??= new();

 SpecialTokens = options.SpecialTokens;
 SpecialTokensReverse = options.SpecialTokens is not null ? options.SpecialTokens.ToDictionary(kvp => kvp.Value, kvp => kvp.Key) : null;
 SpecialTokensReverse = options.SpecialTokens is not null ? options.SpecialTokens.GroupBy(kvp => kvp.Value).ToDictionary(g => g.Key, g => g.First().Key) : null;

 if (options.UnknownToken is null)
 {
Expand DownExpand Up@@ -800,4 +800,4 @@ public OperationStatus Decode(IEnumerable<int> ids, Span<char> destination, bool
 return OperationStatus.Done;
 }
 }
}
}

93 changes: 91 additions & 2 deletions
test/Microsoft.ML.Tokenizers.Tests/BertTokenizerTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand All@@ -14,6 +14,91 @@ namespace Microsoft.ML.Tokenizers.Tests
{
 public class BertTokenizerTests
 {
 [Fact]
 public void TestWithLowerCasingExplicitSpecialTokens()
 {
 // Add [SPECIAL] token at end (to keep indices as is)
 // Ids: 0 1 2 3 4 5 6 7 8 9 10 11 12, 13 
 string[] vocabTokens = ["[PAD]", "[UNK]", "[CLS]", "[SEP]", "[MASK]", "!", ",", "?", "hello", "world", "how", "are", "you", "[SPECIAL]"];

 string vocabFile = WordPieceTests.CreateVocabFile(vocabTokens);

 Dictionary<string, int> specialTokens = new() {
 { "[PAD]", 0 },
 { "[UNK]", 1 },
 { "[CLS]", 2 },
 { "[SEP]", 3 },
 { "[MASK]", 4 },
 { "[SPECIAL]", 13 },
 };
 var bertOptions = new BertOptions()
 {
 SpecialTokens = specialTokens
 };

 try
 {
 using Stream vocabStream = File.OpenRead(vocabFile);
 BertTokenizer[] bertTokenizers = [BertTokenizer.Create(vocabFile, bertOptions), BertTokenizer.Create(vocabStream, bertOptions)];

 foreach (var tokenizer in bertTokenizers)
 {
 Assert.NotNull(tokenizer.PreTokenizer);
 Assert.Equal("[UNK]", tokenizer.UnknownToken);
 Assert.Equal(1, tokenizer.UnknownTokenId);
 Assert.NotNull(tokenizer.Normalizer);
 Assert.NotNull(tokenizer.PreTokenizer);

 Assert.True(tokenizer.SpecialTokens!.ContainsKey("[SPECIAL]"));

 string text = "Hello, How are you [SPECIAL]?";
 var tokens = tokenizer.EncodeToTokens(text, out string? normalizedText);
 Assert.Equal("hello, how are you [special]?", normalizedText);

 Assert.Equal(
 [
 new EncodedToken(8, "hello", new Range(0, 5)),
 new EncodedToken(6, ",", new Range(5, 6)),
 new EncodedToken(10, "how", new Range(7, 10)),
 new EncodedToken(11, "are", new Range(11, 14)),
 new EncodedToken(12, "you", new Range(15, 18)),
 new EncodedToken(13, "[SPECIAL]", new Range(19, 28)),
 new EncodedToken(7, "?", new Range(28, 29))
 ],
 tokens);

 var ids = tokenizer.EncodeToIds(text);
 Assert.Equal([tokenizer.ClassificationTokenId, 8, 6, 10, 11, 12, 13, 7, tokenizer.SeparatorTokenId], ids);

 Assert.Equal("[CLS] hello, how are you [SPECIAL]? [SEP]", tokenizer.Decode(ids));
 Assert.Equal("hello, how are you?", tokenizer.Decode(ids, skipSpecialTokens: true));

 tokens = tokenizer.EncodeToTokens(tokenizer.Decode(ids), out normalizedText);
 Assert.Equal("[cls] hello, how are you [special]? [sep]", normalizedText);
 Assert.Equal(
 [
 new EncodedToken(2, "[CLS]", new Range(0, 5)),
 new EncodedToken(8, "hello", new Range(6, 11)),
 new EncodedToken(6, ",", new Range(11, 12)),
 new EncodedToken(10, "how", new Range(13, 16)),
 new EncodedToken(11, "are", new Range(17, 20)),
 new EncodedToken(12, "you", new Range(21, 24)),
 new EncodedToken(13, "[SPECIAL]", new Range(25, 34)),
 new EncodedToken(7, "?", new Range(34, 35)),
 new EncodedToken(3, "[SEP]", new Range(36, 41))
 ],
 tokens);

 ids = tokenizer.EncodeToIds(normalizedText!);
 Assert.Equal([tokenizer.ClassificationTokenId, tokenizer.ClassificationTokenId, 8, 6, 10, 11, 12, 13, 7, tokenizer.SeparatorTokenId, tokenizer.SeparatorTokenId], ids);
 }
 }
 finally
 {
 File.Delete(vocabFile);
 }
 }

 [Fact]
 public void TestWithLowerCasing()
 {
Expand All@@ -35,6 +120,10 @@ public void TestWithLowerCasing()
 Assert.NotNull(tokenizer.Normalizer);
 Assert.NotNull(tokenizer.PreTokenizer);

 // Make sure the SpecialTokens dictionary contains the not-normalized tokens
 Assert.True(tokenizer.SpecialTokens!.ContainsKey(tokenizer.UnknownToken));
 Assert.True(tokenizer.SpecialTokens!.ContainsKey(tokenizer.ClassificationToken));

 string text = "Hello, How are you?";
 var tokens = tokenizer.EncodeToTokens(text, out string? normalizedText);
 Assert.Equal("hello, how are you?", normalizedText);
Expand DownExpand Up@@ -511,4 +600,4 @@ public void TestCreateTokenTypeIdsFromSequences()
 }
 }
 }
}
}

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers");
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Moved SpecialTokens assignment after the modification to avoid "Collection Modified" error#7328

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

tarekgh
merged 7 commits into

from

Dec 5, 2024
 Merged


Moved SpecialTokens assignment after the modification to avoid "Collection Modified" error
#7328
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
6e5fbed

Moved special tokens assignment below so the collection won't be modi…


shaltielshmid Dec 2, 2024
5edde92

Added safe dictionary inversion


shaltielshmid Dec 4, 2024
84bd69d

Added storing the not-normalized special tokens


shaltielshmid Dec 4, 2024
6ae9d10

Added support for net standard


shaltielshmid Dec 4, 2024
4f06337

Added and updated tests


shaltielshmid Dec 4, 2024
0fcbe64

Merge remote-tracking branch 'dotnet/main' into bug/bert-tok-collecti…


shaltielshmid Dec 4, 2024
25a4c6d

Updated without additional memory allocation


shaltielshmid Dec 5, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


45 changes: 29 additions & 16 deletions
src/Microsoft.ML.Tokenizers/Model/BertTokenizer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand DownExpand Up@@ -762,15 +762,16 @@ private static BertTokenizer Create(

 options.Normalizer ??= options.ApplyBasicTokenization ? new BertNormalizer(options.LowerCaseBeforeTokenization, options.IndividuallyTokenizeCjk, options.RemoveNonSpacingMarks) : null;

 IReadOnlyDictionary<string, int>? specialTokensDict = options.SpecialTokens;
 if (options.SplitOnSpecialTokens)
 {
 bool lowerCase = options.ApplyBasicTokenization && options.LowerCaseBeforeTokenization;
 if (options.SpecialTokens is not null)
 {
 if (lowerCase)
 {
 Dictionary<string, int> dic = options.SpecialTokens.ToDictionary(kvp => kvp.Key, kvp => kvp.Value);
options.SpecialTokens = dic;
 Dictionary<string, int> tempSpecialTokens = [];
specialTokensDict = tempSpecialTokens;

 foreach (var kvp in options.SpecialTokens)
 {
Expand All@@ -779,37 +780,49 @@ private static BertTokenizer Create(
 throw new ArgumentException($"The special token '{kvp.Key}' is not in the vocabulary or assigned id value {id} different than the value {kvp.Value} in the special tokens.");
 }

 // Ensure that the special tokens are lowercased.
 dic[kvp.Key.ToLowerInvariant()] = kvp.Value;
 // Add the special token into our dictionary, normalizing it, and adding it into the
 // main vocab, if needed. 
 AddSpecialToken(vocab, tempSpecialTokens, kvp.Key, true);
 }
 }
 }
 else
 {
 // Create a dictionary with the special tokens.
 Dictionary<string, int> specialTokens = new Dictionary<string, int>();
 options.SpecialTokens = specialTokens;

 AddSpecialToken(vocab, specialTokens, options.UnknownToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.SeparatorToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.PaddingToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.ClassificationToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.MaskingToken, lowerCase);
 // Create a dictionary with the special tokens - store the un-normalized forms in the options as
 // that field is exposed to the public. In addition, store the normalized form for creating the 
 // pre-tokenizer.
 Dictionary<string, int> tempSpecialTokens = [];
 Dictionary<string, int> notNormalizedSpecialTokens = [];
 AddSpecialToken(vocab, tempSpecialTokens, options.UnknownToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.SeparatorToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.PaddingToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.ClassificationToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.MaskingToken, lowerCase, notNormalizedSpecialTokens);

 options.SpecialTokens = notNormalizedSpecialTokens;
 specialTokensDict = tempSpecialTokens;
 }
 }

 options.PreTokenizer ??= options.ApplyBasicTokenization ? PreTokenizer.CreateWordOrPunctuation(options.SplitOnSpecialTokens ? options.SpecialTokens : null) : PreTokenizer.CreateWhiteSpace();
 // We set the PreTokenizer here using the normalized special tokens dict (if relevant), and therefore we can 
 // keep the not-normalized special tokens dict in the options passed to the WordPieceTokenizer.
 options.PreTokenizer ??= options.ApplyBasicTokenization ? PreTokenizer.CreateWordOrPunctuation(options.SplitOnSpecialTokens ? specialTokensDict : null) : PreTokenizer.CreateWhiteSpace();

 return new BertTokenizer(vocab, vocabReverse, options);
 }

 private static void AddSpecialToken(Dictionary<StringSpanOrdinalKey, int> vocab, Dictionary<string, int> specialTokens, string token, bool lowerCase)
 private static void AddSpecialToken(Dictionary<StringSpanOrdinalKey, int> vocab, Dictionary<string, int> specialTokens, string token, bool lowerCase, Dictionary<string, int>? notNormalizedSpecialTokens = null)
 {
 if (token is null || !vocab.TryGetValue(new StringSpanOrdinalKey(token), out int id))
 {
 throw new ArgumentException($"The special token '{token}' is not in the vocabulary.");
 }

 if (notNormalizedSpecialTokens is not null)
 {
 notNormalizedSpecialTokens[token] = id;
 }

 string normalizedToken = token;
 if (lowerCase)
 {
Expand Down

6 changes: 3 additions & 3 deletions
src/Microsoft.ML.Tokenizers/Model/WordPieceTokenizer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand DownExpand Up@@ -42,7 +42,7 @@ internal WordPieceTokenizer(
 options ??= new();

 SpecialTokens = options.SpecialTokens;
 SpecialTokensReverse = options.SpecialTokens is not null ? options.SpecialTokens.ToDictionary(kvp => kvp.Value, kvp => kvp.Key) : null;
 SpecialTokensReverse = options.SpecialTokens is not null ? options.SpecialTokens.GroupBy(kvp => kvp.Value).ToDictionary(g => g.Key, g => g.First().Key) : null;

 if (options.UnknownToken is null)
 {
Expand DownExpand Up@@ -800,4 +800,4 @@ public OperationStatus Decode(IEnumerable<int> ids, Span<char> destination, bool
 return OperationStatus.Done;
 }
 }
}
}

93 changes: 91 additions & 2 deletions
test/Microsoft.ML.Tokenizers.Tests/BertTokenizerTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand All@@ -14,6 +14,91 @@ namespace Microsoft.ML.Tokenizers.Tests
{
 public class BertTokenizerTests
 {
 [Fact]
 public void TestWithLowerCasingExplicitSpecialTokens()
 {
 // Add [SPECIAL] token at end (to keep indices as is)
 // Ids: 0 1 2 3 4 5 6 7 8 9 10 11 12, 13 
 string[] vocabTokens = ["[PAD]", "[UNK]", "[CLS]", "[SEP]", "[MASK]", "!", ",", "?", "hello", "world", "how", "are", "you", "[SPECIAL]"];

 string vocabFile = WordPieceTests.CreateVocabFile(vocabTokens);

 Dictionary<string, int> specialTokens = new() {
 { "[PAD]", 0 },
 { "[UNK]", 1 },
 { "[CLS]", 2 },
 { "[SEP]", 3 },
 { "[MASK]", 4 },
 { "[SPECIAL]", 13 },
 };
 var bertOptions = new BertOptions()
 {
 SpecialTokens = specialTokens
 };

 try
 {
 using Stream vocabStream = File.OpenRead(vocabFile);
 BertTokenizer[] bertTokenizers = [BertTokenizer.Create(vocabFile, bertOptions), BertTokenizer.Create(vocabStream, bertOptions)];

 foreach (var tokenizer in bertTokenizers)
 {
 Assert.NotNull(tokenizer.PreTokenizer);
 Assert.Equal("[UNK]", tokenizer.UnknownToken);
 Assert.Equal(1, tokenizer.UnknownTokenId);
 Assert.NotNull(tokenizer.Normalizer);
 Assert.NotNull(tokenizer.PreTokenizer);

 Assert.True(tokenizer.SpecialTokens!.ContainsKey("[SPECIAL]"));

 string text = "Hello, How are you [SPECIAL]?";
 var tokens = tokenizer.EncodeToTokens(text, out string? normalizedText);
 Assert.Equal("hello, how are you [special]?", normalizedText);

 Assert.Equal(
 [
 new EncodedToken(8, "hello", new Range(0, 5)),
 new EncodedToken(6, ",", new Range(5, 6)),
 new EncodedToken(10, "how", new Range(7, 10)),
 new EncodedToken(11, "are", new Range(11, 14)),
 new EncodedToken(12, "you", new Range(15, 18)),
 new EncodedToken(13, "[SPECIAL]", new Range(19, 28)),
 new EncodedToken(7, "?", new Range(28, 29))
 ],
 tokens);

 var ids = tokenizer.EncodeToIds(text);
 Assert.Equal([tokenizer.ClassificationTokenId, 8, 6, 10, 11, 12, 13, 7, tokenizer.SeparatorTokenId], ids);

 Assert.Equal("[CLS] hello, how are you [SPECIAL]? [SEP]", tokenizer.Decode(ids));
 Assert.Equal("hello, how are you?", tokenizer.Decode(ids, skipSpecialTokens: true));

 tokens = tokenizer.EncodeToTokens(tokenizer.Decode(ids), out normalizedText);
 Assert.Equal("[cls] hello, how are you [special]? [sep]", normalizedText);
 Assert.Equal(
 [
 new EncodedToken(2, "[CLS]", new Range(0, 5)),
 new EncodedToken(8, "hello", new Range(6, 11)),
 new EncodedToken(6, ",", new Range(11, 12)),
 new EncodedToken(10, "how", new Range(13, 16)),
 new EncodedToken(11, "are", new Range(17, 20)),
 new EncodedToken(12, "you", new Range(21, 24)),
 new EncodedToken(13, "[SPECIAL]", new Range(25, 34)),
 new EncodedToken(7, "?", new Range(34, 35)),
 new EncodedToken(3, "[SEP]", new Range(36, 41))
 ],
 tokens);

 ids = tokenizer.EncodeToIds(normalizedText!);
 Assert.Equal([tokenizer.ClassificationTokenId, tokenizer.ClassificationTokenId, 8, 6, 10, 11, 12, 13, 7, tokenizer.SeparatorTokenId, tokenizer.SeparatorTokenId], ids);
 }
 }
 finally
 {
 File.Delete(vocabFile);
 }
 }

 [Fact]
 public void TestWithLowerCasing()
 {
Expand All@@ -35,6 +120,10 @@ public void TestWithLowerCasing()
 Assert.NotNull(tokenizer.Normalizer);
 Assert.NotNull(tokenizer.PreTokenizer);

 // Make sure the SpecialTokens dictionary contains the not-normalized tokens
 Assert.True(tokenizer.SpecialTokens!.ContainsKey(tokenizer.UnknownToken));
 Assert.True(tokenizer.SpecialTokens!.ContainsKey(tokenizer.ClassificationToken));

 string text = "Hello, How are you?";
 var tokens = tokenizer.EncodeToTokens(text, out string? normalizedText);
 Assert.Equal("hello, how are you?", normalizedText);
Expand DownExpand Up@@ -511,4 +600,4 @@ public void TestCreateTokenTypeIdsFromSequences()
 }
 }
 }
}
}

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode");
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
Moved SpecialTokens assignment after the modification to avoid "Collection Modified" error#7328

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

tarekgh
merged 7 commits into

from

Dec 5, 2024
 Merged


Moved SpecialTokens assignment after the modification to avoid "Collection Modified" error
#7328
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
6e5fbed

Moved special tokens assignment below so the collection won't be modi…


shaltielshmid Dec 2, 2024
5edde92

Added safe dictionary inversion


shaltielshmid Dec 4, 2024
84bd69d

Added storing the not-normalized special tokens


shaltielshmid Dec 4, 2024
6ae9d10

Added support for net standard


shaltielshmid Dec 4, 2024
4f06337

Added and updated tests


shaltielshmid Dec 4, 2024
0fcbe64

Merge remote-tracking branch 'dotnet/main' into bug/bert-tok-collecti…


shaltielshmid Dec 4, 2024
25a4c6d

Updated without additional memory allocation


shaltielshmid Dec 5, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


45 changes: 29 additions & 16 deletions
src/Microsoft.ML.Tokenizers/Model/BertTokenizer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand DownExpand Up@@ -762,15 +762,16 @@ private static BertTokenizer Create(

 options.Normalizer ??= options.ApplyBasicTokenization ? new BertNormalizer(options.LowerCaseBeforeTokenization, options.IndividuallyTokenizeCjk, options.RemoveNonSpacingMarks) : null;

 IReadOnlyDictionary<string, int>? specialTokensDict = options.SpecialTokens;
 if (options.SplitOnSpecialTokens)
 {
 bool lowerCase = options.ApplyBasicTokenization && options.LowerCaseBeforeTokenization;
 if (options.SpecialTokens is not null)
 {
 if (lowerCase)
 {
 Dictionary<string, int> dic = options.SpecialTokens.ToDictionary(kvp => kvp.Key, kvp => kvp.Value);
options.SpecialTokens = dic;
 Dictionary<string, int> tempSpecialTokens = [];
specialTokensDict = tempSpecialTokens;

 foreach (var kvp in options.SpecialTokens)
 {
Expand All@@ -779,37 +780,49 @@ private static BertTokenizer Create(
 throw new ArgumentException($"The special token '{kvp.Key}' is not in the vocabulary or assigned id value {id} different than the value {kvp.Value} in the special tokens.");
 }

 // Ensure that the special tokens are lowercased.
 dic[kvp.Key.ToLowerInvariant()] = kvp.Value;
 // Add the special token into our dictionary, normalizing it, and adding it into the
 // main vocab, if needed. 
 AddSpecialToken(vocab, tempSpecialTokens, kvp.Key, true);
 }
 }
 }
 else
 {
 // Create a dictionary with the special tokens.
 Dictionary<string, int> specialTokens = new Dictionary<string, int>();
 options.SpecialTokens = specialTokens;

 AddSpecialToken(vocab, specialTokens, options.UnknownToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.SeparatorToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.PaddingToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.ClassificationToken, lowerCase);
 AddSpecialToken(vocab, specialTokens, options.MaskingToken, lowerCase);
 // Create a dictionary with the special tokens - store the un-normalized forms in the options as
 // that field is exposed to the public. In addition, store the normalized form for creating the 
 // pre-tokenizer.
 Dictionary<string, int> tempSpecialTokens = [];
 Dictionary<string, int> notNormalizedSpecialTokens = [];
 AddSpecialToken(vocab, tempSpecialTokens, options.UnknownToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.SeparatorToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.PaddingToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.ClassificationToken, lowerCase, notNormalizedSpecialTokens);
 AddSpecialToken(vocab, tempSpecialTokens, options.MaskingToken, lowerCase, notNormalizedSpecialTokens);

 options.SpecialTokens = notNormalizedSpecialTokens;
 specialTokensDict = tempSpecialTokens;
 }
 }

 options.PreTokenizer ??= options.ApplyBasicTokenization ? PreTokenizer.CreateWordOrPunctuation(options.SplitOnSpecialTokens ? options.SpecialTokens : null) : PreTokenizer.CreateWhiteSpace();
 // We set the PreTokenizer here using the normalized special tokens dict (if relevant), and therefore we can 
 // keep the not-normalized special tokens dict in the options passed to the WordPieceTokenizer.
 options.PreTokenizer ??= options.ApplyBasicTokenization ? PreTokenizer.CreateWordOrPunctuation(options.SplitOnSpecialTokens ? specialTokensDict : null) : PreTokenizer.CreateWhiteSpace();

 return new BertTokenizer(vocab, vocabReverse, options);
 }

 private static void AddSpecialToken(Dictionary<StringSpanOrdinalKey, int> vocab, Dictionary<string, int> specialTokens, string token, bool lowerCase)
 private static void AddSpecialToken(Dictionary<StringSpanOrdinalKey, int> vocab, Dictionary<string, int> specialTokens, string token, bool lowerCase, Dictionary<string, int>? notNormalizedSpecialTokens = null)
 {
 if (token is null || !vocab.TryGetValue(new StringSpanOrdinalKey(token), out int id))
 {
 throw new ArgumentException($"The special token '{token}' is not in the vocabulary.");
 }

 if (notNormalizedSpecialTokens is not null)
 {
 notNormalizedSpecialTokens[token] = id;
 }

 string normalizedToken = token;
 if (lowerCase)
 {
Expand Down

6 changes: 3 additions & 3 deletions
src/Microsoft.ML.Tokenizers/Model/WordPieceTokenizer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand DownExpand Up@@ -42,7 +42,7 @@ internal WordPieceTokenizer(
 options ??= new();

 SpecialTokens = options.SpecialTokens;
 SpecialTokensReverse = options.SpecialTokens is not null ? options.SpecialTokens.ToDictionary(kvp => kvp.Value, kvp => kvp.Key) : null;
 SpecialTokensReverse = options.SpecialTokens is not null ? options.SpecialTokens.GroupBy(kvp => kvp.Value).ToDictionary(g => g.Key, g => g.First().Key) : null;

 if (options.UnknownToken is null)
 {
Expand DownExpand Up@@ -800,4 +800,4 @@ public OperationStatus Decode(IEnumerable<int> ids, Span<char> destination, bool
 return OperationStatus.Done;
 }
 }
}
}

93 changes: 91 additions & 2 deletions
test/Microsoft.ML.Tokenizers.Tests/BertTokenizerTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
// Licensed to the .NET Foundation under one or more agreements.
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

Expand All@@ -14,6 +14,91 @@ namespace Microsoft.ML.Tokenizers.Tests
{
 public class BertTokenizerTests
 {
 [Fact]
 public void TestWithLowerCasingExplicitSpecialTokens()
 {
 // Add [SPECIAL] token at end (to keep indices as is)
 // Ids: 0 1 2 3 4 5 6 7 8 9 10 11 12, 13 
 string[] vocabTokens = ["[PAD]", "[UNK]", "[CLS]", "[SEP]", "[MASK]", "!", ",", "?", "hello", "world", "how", "are", "you", "[SPECIAL]"];

 string vocabFile = WordPieceTests.CreateVocabFile(vocabTokens);

 Dictionary<string, int> specialTokens = new() {
 { "[PAD]", 0 },
 { "[UNK]", 1 },
 { "[CLS]", 2 },
 { "[SEP]", 3 },
 { "[MASK]", 4 },
 { "[SPECIAL]", 13 },
 };
 var bertOptions = new BertOptions()
 {
 SpecialTokens = specialTokens
 };

 try
 {
 using Stream vocabStream = File.OpenRead(vocabFile);
 BertTokenizer[] bertTokenizers = [BertTokenizer.Create(vocabFile, bertOptions), BertTokenizer.Create(vocabStream, bertOptions)];

 foreach (var tokenizer in bertTokenizers)
 {
 Assert.NotNull(tokenizer.PreTokenizer);
 Assert.Equal("[UNK]", tokenizer.UnknownToken);
 Assert.Equal(1, tokenizer.UnknownTokenId);
 Assert.NotNull(tokenizer.Normalizer);
 Assert.NotNull(tokenizer.PreTokenizer);

 Assert.True(tokenizer.SpecialTokens!.ContainsKey("[SPECIAL]"));

 string text = "Hello, How are you [SPECIAL]?";
 var tokens = tokenizer.EncodeToTokens(text, out string? normalizedText);
 Assert.Equal("hello, how are you [special]?", normalizedText);

 Assert.Equal(
 [
 new EncodedToken(8, "hello", new Range(0, 5)),
 new EncodedToken(6, ",", new Range(5, 6)),
 new EncodedToken(10, "how", new Range(7, 10)),
 new EncodedToken(11, "are", new Range(11, 14)),
 new EncodedToken(12, "you", new Range(15, 18)),
 new EncodedToken(13, "[SPECIAL]", new Range(19, 28)),
 new EncodedToken(7, "?", new Range(28, 29))
 ],
 tokens);

 var ids = tokenizer.EncodeToIds(text);
 Assert.Equal([tokenizer.ClassificationTokenId, 8, 6, 10, 11, 12, 13, 7, tokenizer.SeparatorTokenId], ids);

 Assert.Equal("[CLS] hello, how are you [SPECIAL]? [SEP]", tokenizer.Decode(ids));
 Assert.Equal("hello, how are you?", tokenizer.Decode(ids, skipSpecialTokens: true));

 tokens = tokenizer.EncodeToTokens(tokenizer.Decode(ids), out normalizedText);
 Assert.Equal("[cls] hello, how are you [special]? [sep]", normalizedText);
 Assert.Equal(
 [
 new EncodedToken(2, "[CLS]", new Range(0, 5)),
 new EncodedToken(8, "hello", new Range(6, 11)),
 new EncodedToken(6, ",", new Range(11, 12)),
 new EncodedToken(10, "how", new Range(13, 16)),
 new EncodedToken(11, "are", new Range(17, 20)),
 new EncodedToken(12, "you", new Range(21, 24)),
 new EncodedToken(13, "[SPECIAL]", new Range(25, 34)),
 new EncodedToken(7, "?", new Range(34, 35)),
 new EncodedToken(3, "[SEP]", new Range(36, 41))
 ],
 tokens);

 ids = tokenizer.EncodeToIds(normalizedText!);
 Assert.Equal([tokenizer.ClassificationTokenId, tokenizer.ClassificationTokenId, 8, 6, 10, 11, 12, 13, 7, tokenizer.SeparatorTokenId, tokenizer.SeparatorTokenId], ids);
 }
 }
 finally
 {
 File.Delete(vocabFile);
 }
 }

 [Fact]
 public void TestWithLowerCasing()
 {
Expand All@@ -35,6 +120,10 @@ public void TestWithLowerCasing()
 Assert.NotNull(tokenizer.Normalizer);
 Assert.NotNull(tokenizer.PreTokenizer);

 // Make sure the SpecialTokens dictionary contains the not-normalized tokens
 Assert.True(tokenizer.SpecialTokens!.ContainsKey(tokenizer.UnknownToken));
 Assert.True(tokenizer.SpecialTokens!.ContainsKey(tokenizer.ClassificationToken));

 string text = "Hello, How are you?";
 var tokens = tokenizer.EncodeToTokens(text, out string? normalizedText);
 Assert.Equal("hello, how are you?", normalizedText);
Expand DownExpand Up@@ -511,4 +600,4 @@ public void TestCreateTokenTypeIdsFromSequences()
 }
 }
 }
}
}