Update Readme and docs

[hiyuchang]

Description

• Add learning path
• Update readme, ensuring the Chinese/English versions consistent
• Fix typo

Checklist

Please check the following items before code is ready to be reviewed.

• Code has passed all tests
• Docstrings have been added/updated in Google Style
• Documentation has been updated
• Code is ready for review

[gemini-code-assist]

Summary of Changes

Hello @hiyuchang, 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 improves the project's documentation and user experience by introducing structured learning paths tailored to different user roles. It ensures content consistency across English and Chinese READMEs, provides a clearer quick-start guide for CPU-only environments, and refines an example configuration to be more resource-friendly. These changes aim to make the project more approachable and easier to navigate for a wider audience.

Highlights

• Learning Paths Introduced: Recommended learning paths have been added to both English and Chinese READMEs, guiding new users, algorithm researchers, and agent developers through the project.
• README Consistency and Updates: The English and Chinese README files have been synchronized, including updates to the contribution guide and an expanded list of inspiring frameworks.
• CPU Quick Start Guide: A dedicated section for CPU users has been added to the Chinese README, providing clear instructions for installing and running Trinity-RFT with the Tinker backend without a GPU.
• Documentation Typos Fixed: A minor typo in the English FAQ documentation has been corrected, and a link in the Chinese FAQ has been updated for accuracy.
• Example Configuration Adjustment: The gsm8k.yaml example configuration has been updated to reduce default GPU usage, making it more accessible for environments with limited resources.

Changelog

• README.md
  • Fixed a minor typo in a paper link.
  • Added a 'Recommended Learning Paths' section for various user types.
  • Updated the contribution guide to encourage diverse contributions and highlight active development.
• README_zh.md
  • Removed a redundant entry regarding Tinker backend support.
  • Fixed a typo in a paper link.
  • Added a '推荐阅读顺序' (Recommended Learning Paths) section, mirroring the English version.
  • Introduced a '使用 CPU 快速上手' (Quick Start for CPU Users) section with installation and example commands for the Tinker backend.
  • Updated installation recommendations to guide users based on GPU availability and development goals.
  • Adjusted formatting for installation method sub-headings (Conda, venv, uv).
  • Changed the '通过 PyPI 安装' (Install via PyPI) heading level.
  • Revised the contribution guide to be more welcoming and detailed, including a link to good-first-issues.
  • Added 'rLLM' to the list of inspiring frameworks.
• docs/sphinx_doc/source/main.md
  • Added a link to the 'RFT without local GPU (Tinker Backend)' tutorial.
  • Included 'Megatron-LM' in the list of LLM training frameworks.
  • Added 'rLLM' to the list of inspiring RL frameworks.
• docs/sphinx_doc/source/tutorial/faq.md
  • Corrected a typo from 'Yoy' to 'You'.
• docs/sphinx_doc/source_zh/main.md
  • Added a link to the '在无GPU环境下运行RFT训练（Tinker 后端）' tutorial.
  • Added 'rLLM' to the list of inspiring RL frameworks.
• docs/sphinx_doc/source_zh/tutorial/faq.md
  • Updated the link for the GPU configuration guide to point to the Chinese version.
• examples/grpo_gsm8k/gsm8k.yaml
  • Reduced gpu_per_node from 8 to 2.
  • Reduced explorer.rollout_model.engine_num from 2 to 1.

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 by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

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 pull request 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

1. 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. ↩

[gemini-code-assist]

Code Review

This pull request updates several documentation files, including the English and Chinese READMEs, to add recommended learning paths, improve consistency, and fix typos. The changes are generally good and improve the documentation's clarity and structure. I've identified a few areas where links could be improved for a better user experience, such as pointing to rendered documentation pages instead of source files and using more maintainable links for issue lists. Overall, this is a valuable contribution to the project's documentation.