support deepseek-V3.1 & add no_think_prefix for hybrid thinking models #5463
Conversation
There was a problem hiding this comment.
Summary of Changes
Hello @hjh0119, 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 introduces comprehensive support for the DeepSeek-V3.1 large language model, encompassing both its base and full versions. This enhancement expands the range of available models within the system, allowing users to leverage DeepSeek-V3.1 for various inference tasks and ensuring its seamless integration.
Highlights
- New Model Type: A new model type
deepseek_v3_1has been added to categorize the new DeepSeek models, ensuring proper classification within the system. - Model Registration: Both
DeepSeek-V3.1-BaseandDeepSeek-V3.1models are now registered, making them fully available for use within the application. - Documentation Update: The documentation, in both Chinese and English, has been updated to include the newly supported DeepSeek-V3.1 models, providing clear guidance for users.
- New Test Case: A new test case has been implemented to verify the correct template encoding for DeepSeek-V3.1 models, ensuring their proper integration and 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 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. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.
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. ↩
There was a problem hiding this comment.
Code Review
This pull request adds support for the deepseek-V3.1 model, including updates to model constants, registration, templates, documentation, and a new test case. The implementation looks mostly correct, but I've identified two critical typos: one in the template registration and another in the test file. These issues need to be addressed to ensure the new model functions correctly.
PR type
disable_thinking(default)
enable_thinking
swift infer \ --model deepseek-ai/DeepSeek-V3.1 \ --response_prefix '<think>'