Skip to content

Huggingface direct download to format command - #373

Merged
lukehinds merged 4 commits into
mainfrom
dl-and-format
Oct 15, 2025
Merged

Huggingface direct download to format command#373
lukehinds merged 4 commits into
mainfrom
dl-and-format

Conversation

@lukehinds

Copy link
Copy Markdown
Collaborator

This allows users to pull from huggingface datasets are run the formatter against the target dataset.

deepfabric format --repo "org/dataset-name" --format harmony

@gemini-code-assist

Copy link
Copy Markdown
Contributor

Summary of Changes

Hello @lukehinds, 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 upgrades the deepfabric tool's format command by enabling direct integration with Hugging Face datasets. Users can now specify a Hugging Face repository ID and an optional split to load datasets directly for formatting, streamlining the data preparation workflow. The changes also introduce new formatter options for TRL SFTTrainer and include comprehensive documentation updates to reflect these new capabilities and align with current LLM model naming conventions.

Highlights

  • Hugging Face Direct Download: The deepfabric format command now supports directly pulling datasets from Hugging Face repositories using the --repo and --split arguments, eliminating the need for local downloads.
  • New Formatter Support: Added support for trl_sft_tools and trl (as an alias) formatters, enhancing compatibility with Hugging Face TRL SFTTrainer.
  • Model Name Updates in Documentation: Extensive updates across CLI, API, and example documentation to reflect newer LLM model names, such as claude-sonnet-4-5 replacing claude-3-opus and gpt-4-turbo replacing gpt-3.5-turbo.
  • Dependency Update: The outlines dependency has been updated from version 1.2.5 to 1.2.7.
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 gemini-code-assist Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request introduces a valuable feature by allowing direct dataset formatting from Hugging Face repositories, which greatly improves usability. The implementation is clean, and the documentation updates are thorough. I've included a few suggestions to enhance error handling and correct some minor typos in the documentation.

Comment thread deepfabric/format_command.py Outdated
Comment thread deepfabric/format_command.py Outdated
Comment thread docs/examples/advanced-workflows.md
Comment thread docs/examples/advanced-workflows.md
Comment thread docs/guide/instruction-formats/chain-of-thought/configuration/yaml-config.md Outdated
@lukehinds
lukehinds merged commit 9ef08b4 into main Oct 15, 2025
3 checks passed
@lukehinds
lukehinds deleted the dl-and-format branch October 15, 2025 07:57
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant