Open
Conversation
update reasong_parse
update args
Contributor
Author
|
@DarkSharpness please review it |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 PR introduces a parser for separating reasoning content from the actual generated content. By adding the --reasoning-parser flag at startup, the system can automatically extract reasoning_content and content fields in both streaming and non-streaming modes. The argument following --reasoning-parser specifies the model type (e.g., qwen3); if left blank, the system will automatically infer the model type from hf_config. Additionally, a test script has been added to the test folder to verify that the streaming output correctly separates these two fields when the flag is enabled. Please refer to the image below for the actual effect.
Furthermore, omitting the --reasoning-parser flag will have no impact on existing functionality, ensuring that generation continues to work as expected.