support Qwen3ForSequenceClassification#7314
support Qwen3ForSequenceClassification#7314bzantium wants to merge 2 commits intosgl-project:mainfrom
Conversation
There was a problem hiding this comment.
Summary of Changes
Hello @bzantium, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!
This pull request significantly enhances the sglang framework by integrating comprehensive support for the Qwen3ForSequenceClassification model. This enables users to leverage the advanced capabilities of Qwen3 models for various sequence classification tasks, expanding the framework's utility. The changes involve implementing the new model class, updating system configurations to recognize it, and adding corresponding documentation and unit tests to ensure proper functionality.
Highlights
- New Model Support: Implemented the
Qwen3ForSequenceClassificationmodel class, enabling thesglangframework to utilize Qwen3 models for sequence classification tasks. - Core Model Implementation: A new Python module (
python/sglang/srt/models/qwen3_classification.py) was added, defining the architecture and forward pass forQwen3ForSequenceClassification, including integration with the baseQwen3Modeland a classification head. - System Integration: Updated the model configuration (
python/sglang/srt/configs/model_config.py) to recognizeQwen3ForSequenceClassificationas a valid model type within the system'sis_generation_modelfunction. - Documentation and Testing: Added documentation for the new model in
docs/supported_models/reward_models.mdand included a test case intest/srt/models/test_reward_models.pyto verify its functionality.
Using Gemini Code Assist
The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.
Invoking Gemini
You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.
| Feature | Command | Description |
|---|---|---|
| Code Review | /gemini review |
Performs a code review for the current pull request in its current state. |
| Pull Request Summary | /gemini summary |
Provides a summary of the current pull request in its current state. |
| Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in issue comments and review comments. |
| Help | /gemini help |
Displays a list of available commands. |
Customization
To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.
Limitations & Feedback
Gemini Code Assist is currently in preview and may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments to provide feedback.
You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.
Footnotes
-
Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩
| def load_weights(self, weights: Iterable[Tuple[str, torch.Tensor]]): | ||
| # Filter out lm_head weights of Qwen3ForCausalLM | ||
| filtered_weights = [ | ||
| (name, w) for name, w in weights if not name.startswith("lm_head") | ||
| ] | ||
| return Qwen3ForCausalLM.load_weights(self, filtered_weights) |
There was a problem hiding this comment.
Consider adding a comment explaining the assumptions made about Qwen3ForCausalLM.load_weights regarding attribute access to improve maintainability.
|
Already supported in #7957 |
Motivation
This pull request introduces support for the
Qwen3ForSequenceClassificationmodel class to the sglang framework. The recently released Qwen3 model series represents a significant advancement in large language models, offering state-of-the-art performance.Modifications
Implement
qwen3_classificationmodeling and write docs and testing.Checklist