docs(config): align example precision and format with spec table

[rishi-jat]

The example in docs/config.md used values (fp16, pytorch) that did not match the documented precision and format values in the specification table.

This PR updates the example to use float16 and pt to ensure internal consistency.

[gemini-code-assist]

Summary of Changes

Hello, 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 focuses on enhancing the accuracy and internal consistency of the documentation. It rectifies discrepancies in an example configuration by aligning its values with the established specification, thereby improving clarity and reducing potential confusion for users referencing the documentation.

Highlights

• Documentation Update: Updated the example configuration in docs/config.md to use pt for the format and float16 for precision, ensuring consistency with the documented specification table.

Changelog

• docs/config.md
  • Updated the format field in the example configuration from pytorch to pt.
  • Updated the precision field in the example configuration from fp16 to float16.

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. ↩

[Copilot]

Pull request overview

Updates the model artifact configuration documentation example to match the supported format and precision values defined in the same document, keeping the config spec internally consistent.

Changes:

• Changed example config.format from pytorch to pt
• Changed example config.precision from fp16 to float16

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[gemini-code-assist]

Code Review

This pull request corrects the example in docs/config.md to align with the specification table in the same file. My review points out that this change creates inconsistencies with code comments in a Go source file and also highlights an opportunity to strengthen the JSON schema. Addressing these points would improve the overall consistency and robustness of the project.

[gemini-code-assist]

While these changes align the example with the specification, they also highlight inconsistencies in other parts of the repository that should be addressed for overall project consistency.

1. Go source code: The comments in specs-go/v1/config.go are now out of sync with this documentation.
   • The comment for ModelConfig.Format (line 31) still mentions pytorch.
   • The comment for ModelConfig.Precision (line 37) still mentions fp16.
2. JSON Schema: The schema in schema/config-schema.json could be strengthened to enforce allowed values. For example, the format property could use an enum to list the valid formats ("onnx", "safetensors", "gguf", "pt"). This would help prevent future inconsistencies.

Please consider addressing these related inconsistencies in this PR or a follow-up to improve overall project quality.

[rishi-jat]

/cc @chlins
/cc @aftersnow
/cc @bergwolf