fix: add missing integer type mappings to dtype from_str

[JaryJay]

Added b, i16, u16, u32, u64 mappings to from_str in dtype.py.

Did this by implementing Gemini Code Assist's suggestion, which was to create a map at runtime with all the mappings from each dtype's name and short name.

This change allows b, i16, u16, u32, and u64 to be passed in as arguments when running model_gen with the mgen.dtype_choices option, e.g.:

nnsmith.model_gen ... mgen.dtype_choices="[b, i16, u16, u32, u64]"

[gemini-code-assist[bot]]

Summary of Changes

Hello @JaryJay, I'm Gemini Code Assist[^1]! 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 PR addresses a missing feature by extending the from_str function in nnsmith/abstract/dtype.py to correctly parse i16, u16, u32, and u64 data type strings. This enhancement allows these integer types to be used when configuring model_gen via mgen.dtype_choices.

Highlights

• Intent: This pull request aims to fix an oversight by adding support for i16, u16, u32, and u64 integer types to the from_str utility function in nnsmith/abstract/dtype.py. This enables users to specify these data types as arguments for model_gen using the mgen.dtype_choices option, aligning with existing support for other integer types.
• Changes: The nnsmith/abstract/dtype.py file has been modified. Specifically, the from_str function now includes mappings for the following string representations to their respective DType enum values: "u16": DType.uint16, "u32": DType.uint32, "u64": DType.uint64, and "i16": DType.int16. This expands the recognized integer types for data type parsing.
• Reviewer Activity: No specific reviewer activity has been recorded for this pull request yet.

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 :thumbsup: and :thumbsdown: 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.

[^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.