-
Notifications
You must be signed in to change notification settings - Fork 1.9k
Tokenizers Support #6272
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.
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
Merged
Tokenizers Support #6272
Changes from all commits
Commits
Show all changes
3 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,91 @@ | ||
| // 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. | ||
|
|
||
| using System; | ||
| using System.Collections.Generic; | ||
| using System.Text; | ||
|
|
||
| namespace Microsoft.ML.Tokenizers | ||
| { | ||
| /// <summary> | ||
| /// Represent a token added by the user on top of the existing Model vocabulary. | ||
| /// AddedToken can be configured to specify the behavior they should have in various situations | ||
| /// like: | ||
| /// - Whether they should only match single words | ||
| /// - Whether to include any WhiteSpace on its left or right | ||
| /// </summary> | ||
| public struct AddedToken : IEquatable<AddedToken> | ||
| { | ||
| /// <summary> | ||
| /// Gets or sets the content of the added token | ||
| /// </summary> | ||
| public string Content { get; set; } | ||
|
|
||
| /// <summary> | ||
| /// Gets or sets whether this token must be a single word or can break words | ||
| /// </summary> | ||
| internal bool SingleWord { get; set; } | ||
|
|
||
| /// <summary> | ||
| /// Gets or sets whether this token should strip WhiteSpaces on its left | ||
| /// </summary> | ||
| internal bool LeftStrip { get; set; } | ||
|
|
||
| /// <summary> | ||
| /// Gets or sets whether this token should strip WhiteSpaces on its right | ||
| /// </summary> | ||
| internal bool RightStrip { get; set; } | ||
|
|
||
| /// <summary> | ||
| /// Gets or sets whether this token should be normalized | ||
| /// </summary> | ||
| internal bool Normalized { get; set; } | ||
|
|
||
| /// <summary> | ||
| /// Gets or sets whether this token is special | ||
| /// </summary> | ||
| internal bool Special { get; set; } | ||
|
|
||
| /// <summary> | ||
| /// Create a new AddedToken object. | ||
| /// </summary> | ||
| public AddedToken() | ||
| { | ||
| Content = ""; | ||
| SingleWord = LeftStrip = RightStrip = Special = false; | ||
| Normalized = true; | ||
| } | ||
|
|
||
| /// <summary> | ||
| /// Create a new AddedToken object from the given content, specifying if it is intended to be a | ||
| /// special token. Special tokens are not normalized by default. | ||
| /// </summary> | ||
| /// <param name="content">The content of the added token.</param> | ||
| /// <param name="special">Indicate whether this token is special.</param> | ||
| public AddedToken(string content, bool special = false) : this() | ||
| { | ||
| Content = content ?? ""; | ||
| Special = special; | ||
| Normalized = !special; | ||
| } | ||
|
|
||
| /// <summary> | ||
| /// Determines whether two token instances are equal. | ||
| /// </summary> | ||
| /// <param name="other">The token to compare with the current token.</param> | ||
| public bool Equals(AddedToken other) => Content == other.Content; | ||
|
|
||
| // We only want to hash on the content. AddedToken cannot be added multiple times with different options | ||
| /// <summary> | ||
| /// Returns the hash code for the current token. | ||
| /// </summary> | ||
| public override int GetHashCode() => Content.GetHashCode(); | ||
|
|
||
|
|
||
| /// <summary> | ||
| /// Defines an implicit conversion of a string object to AddedToken. | ||
| /// </summary> | ||
| public static implicit operator AddedToken(string token) => new AddedToken(token); | ||
| } | ||
| } | ||
13 changes: 13 additions & 0 deletions
13
src/Microsoft.ML.Tokenizers/Microsoft.ML.Tokenizers.csproj
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,13 @@ | ||
| <Project Sdk="Microsoft.NET.Sdk"> | ||
| <Import Project="$(RepoRoot)eng/pkg/Pack.props" /> | ||
|
|
||
| <PropertyGroup> | ||
| <TargetFramework>netstandard2.0</TargetFramework> | ||
| <Nullable>enable</Nullable> | ||
| <PackageDescription>Microsoft.ML.Tokenizers contains the implmentation of the tokenization used in the NLP transforms.</PackageDescription> | ||
| </PropertyGroup> | ||
|
|
||
| <ItemGroup> | ||
| <PackageReference Include="System.Text.Json" Version="$(SystemTextJsonVersion)" /> | ||
| </ItemGroup> | ||
| </Project> |
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.