GitLab

Update the PyTorch installation guide in both English and Chinese READMEs to explicitly
recommend using torch==2.3.1 and torchvision==0.18.1 for CUDA 11.8. Emphasize the
importance of specifying these versions to avoid compatibility issues with higher,
unsupported versions.

- Change the pip install command in README_zh-CN.md to reflect the new version 0.6.2b1.
- Include a notice about the pre-release of version 0.6.2beta, cautioning users about its未经完整QA测试的状态，并提供回退到0.6.1版本的指导。
- Verify the installed version with `magic-pdf --version` after installation to ensure
 the correct version is installed, addressing feedback about incorrect versions due to
 mirror source and dependency conflicts.

fix(readme): add China mirror for pip install in README_zh-CNAdd China mirror links for `pip install` commands in the Chinese README to improve
accessibility and speed up package installation for users in China.

I created Japanese translated README.

Update the installation guide in README_zh-CN.md to clarify that the pre-compiled
whl packages are only compatible with 64-bit systems running Python 3.10 on
windows/linux/macOS. Add a note warning that the packages are not compatible with
32-bit systems or non-mac ARM platforms, and suggest manual compilation for
unsupported systems.

feat(readme): add instructions for config file setup and model weight path configurationUpdate the README_zh-CN.md to include detailed steps for copying the
configuration template to the user directory and configuring the 'models-dir'
to point to the downloaded model weight files. This ensures users have a clear
guideline on setting up the configuration file correctly, preventing program
failures due to missing model files.

文末增加友情链接，便于给labelllm\labelu仓库引流