Update dataset#9543
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request refactors dataset loading by moving the core loading logic into a new load_dataset method on BaseArguments, which simplifies both sft.py and driver_utils.py. However, the changes in driver_utils.py introduce a regression by removing the preprocessing logic and restricting the supported RLHF types to only grpo and gkd via an assertion. The review feedback correctly identifies that this breaks support for other RLHF types (such as dpo and kto) and provides actionable suggestions to restore the template parameter and conditionally apply the preprocessing steps.
Important
The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.
2 participants
No description provided.