Conversation
Signed-off-by: Haiming94 <[email protected]>
Summary of ChangesHello @Haiming94, 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 primarily focuses on updating and localizing the documentation for the LongContext-ICL Annotation challenge. It introduces a new, detailed Chinese guide for participants while simplifying the English overview, making the project more accessible to a broader audience and potentially centralizing detailed English information elsewhere. Highlights
🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console. Using Gemini Code AssistThe 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 by creating a comment using either
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 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
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request adds a Chinese version of the README and simplifies the English version. My review focuses on the documentation changes. In the new Chinese README (READMD_cn.md), I've pointed out a typo in the filename, a minor issue in a shell command, and incorrect markdown formatting for a list. For the English README.md, I've raised concerns about the removal of significant sections containing the competition's introduction, objectives, and details, which makes the document less helpful for newcomers. I also noted the removal of a useful environment setup command for NVIDIA users. Addressing these points will improve the quality and clarity of the project's documentation.
| @@ -0,0 +1,70 @@ | |||
| # 超长长上下文场景中LLM自动数据标注挑战赛 | |||
There was a problem hiding this comment.
The filename READMD_cn.md appears to contain a typo. For consistency and discoverability, it should likely be README_cn.md.
| - Teams are required to submit their technical reports and complete source code to the official OpenSeek GitHub repository designated by the competition. | ||
|
|
||
| - For additional details, please refer to [FlagOS platform](https://flagos.io/RaceDetail?id=296fmsd8&lang=en). All competition-related information is subject to the announcements published on the official platform. | ||
| --- |
There was a problem hiding this comment.
The 'Introduction', 'Objectives', and 'Challenge Details' sections have been removed. This content provided crucial context about the competition for new users, including a link to the FlagOS platform for more details. Removing it significantly reduces the README's usefulness. Please consider restoring this information or linking to where it can be found.
| ```bash | ||
| hf download Qwen/Qwen3-4B --local-dir Qwen3-4B | ||
| # or | ||
| modelscope download --model Qwen/Qwen3-4B |
There was a problem hiding this comment.
This line has a trailing space. While it may not break the command, it's best practice to remove it to prevent potential copy-paste errors.
| modelscope download --model Qwen/Qwen3-4B | |
| modelscope download --model Qwen/Qwen3-4B |
| * 定义新的指令模板、 | ||
| * 定义新的上下文示例选择策略 | ||
| * 定义新的模型推理、标注方案 | ||
| * 添加自定义后处理逻辑 |
There was a problem hiding this comment.
The markdown for this list is not formatted correctly, which prevents it from rendering as a bulleted list. There should be a space after each asterisk (*). Additionally, the trailing 、 on the first item is unnecessary in a list format.
| * 定义新的指令模板、 | |
| * 定义新的上下文示例选择策略 | |
| * 定义新的模型推理、标注方案 | |
| * 添加自定义后处理逻辑 | |
| * 定义新的指令模板 | |
| * 定义新的上下文示例选择策略 | |
| * 定义新的模型推理、标注方案 | |
| * 添加自定义后处理逻辑 |
| flagScale | ||
| ``` | ||
|
|
||
| On NVIDIA platforms, it is recommended to create the environment using: `cd src && bash create_env_nvidia.sh` |
There was a problem hiding this comment.
This helpful instruction for setting up the environment on NVIDIA platforms has been removed. Since the create_env_nvidia.sh script is still part of the project, this command is useful for users. Was the removal intentional? If not, it would be beneficial to restore it.
1 participant
No description provided.