Make Microsoft.ML.OnnxRuntimeGenAI.Tokenizer a Microsoft.ML.Tokenizers.Tokenizer #970
Conversation
This file contains 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
tarekgh
reviewed
Oct 11, 2024
| while (*(byte*)(nativeUtf8 + len) != 0) ++len; | ||
|
|
||
| if (len == 0) | ||
| int byteCount = Encoding.UTF8.GetByteCount(pStr, str.Length); |
stephentoub
force-pushed
the
derivetokenizer
branch
from
4464046 to
0b759a7
Compare
|
@stephentoub is this unblocked now that #987 merged? |
luisquintanilla
suggested changes
Feb 27, 2025
| @@ -121,4 +121,8 @@ | |||
| <PackageReference Include="System.Memory" Version="4.5.5" /> | |||
| </ItemGroup> | |||
|
|
|||
| <ItemGroup> | |||
| <PackageReference Include="Microsoft.ML.Tokenizers" Version="0.22.0-preview.24378.1" /> | |||
There was a problem hiding this comment.
Update package version
Suggested change
| <PackageReference Include="Microsoft.ML.Tokenizers" Version="0.22.0-preview.24378.1" /> | |
| <PackageReference Include="Microsoft.ML.Tokenizers" Version="2.0.0-preview.1.25125.4" /> |
…s.Tokenizer This enables an ONNX Runtime GenAI tokenizer instance to be used anywhere a Microsoft.ML.Tokenizers tokenizer is accepted. If we'd prefer, rather than having Tokenizer be a base class for the ONNX Runtime one, we could instead expose some sort of `public Microsoft.ML.Tokenizer.Tokenizer AsTokenizer()` conversion method that returns a wrapper object (though that's a bit confusing given the names of the type are the same, just different namespaces).
stephentoub
force-pushed
the
derivetokenizer
branch
from
0b759a7 to
8a306e7
Compare
|
Closing and reopening the PR to trigger all the pipelines |
|
@baijumeswani looks like the builds are failing because of issues with the feed. Can you please help unblock. |
|
@stephentoub looks like you need to resolve the conflicts. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
This enables an ONNX Runtime GenAI tokenizer instance to be used anywhere a Microsoft.ML.Tokenizers tokenizer is accepted. If we'd prefer, rather than having Tokenizer be a base class for the ONNX Runtime one, we could instead expose some sort of
public Microsoft.ML.Tokenizer.Tokenizer AsTokenizer()conversion method that returns a wrapper object (though that's a bit confusing given the names of the type are the same, just different namespaces).cc: @luisquintanilla, @tarekgh