Support OpenAI OSS Models with Tiktoken tokenizer #7494
Merged
Conversation
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
There was a problem hiding this comment.
Pull Request Overview
This PR adds support for OpenAI OSS (Open Source Software) models using the Tiktoken tokenizer by introducing a new encoding type o200k_harmony and supporting the gpt-oss model family.
- Introduces a new
O200kHarmonyencoding with specialized special tokens for OSS models - Adds comprehensive test coverage for the new tokenizer functionality
- Expands model name mappings to include various OpenAI model variations and fine-tuned models
Reviewed Changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| src/Microsoft.ML.Tokenizers/Model/TiktokenTokenizer.cs | Adds O200kHarmony encoding support, new special tokens, and expanded model mappings for gpt-oss and fine-tuned models |
| test/Microsoft.ML.Tokenizers.Tests/TiktokenTests.cs | Adds comprehensive test coverage for the new OSS tokenizer including encoding tests and special token validation |
stephentoub
approved these changes
Aug 9, 2025
|
Thanks |
|
We should also add gpt-5: |
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Outdated suggestions cannot be applied.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.
Fixes #7491