Add support for uneven splits for large data

[anuragg1209]

Motivation and Context

Add support for uneven splits for large datasets, ensuring that batches are filled during fine-tuning, while also preserving the current functionality of equal-size splits.

Public API Changes

• No Public API changes
• Yes, Public API changes (Details below)

---

How Has This Been Tested?

---

Checklist

• The changes have been tested locally.
• Documentation has been updated (if the public API or usage changes).
• A entry has been added to CHANGELOG.md (if relevant for users).
• The code follows the project's style guidelines.
• I have considered the impact of these changes on the public API.

---

[gemini-code-assist]

Code Review

This pull request introduces support for uneven data splits, which is a valuable addition for handling large datasets during fine-tuning. The changes to the public API in TabPFNClassifier and TabPFNRegressor are well-designed, using a keyword-only argument with a default that preserves existing behavior.

However, I've identified a critical bug in the implementation of the uneven splitting logic in src/tabpfn/utils.py which could lead to incorrect behavior. Additionally, the new functionality is not covered by tests, which is a significant gap. My review includes a suggested fix for the bug and a recommendation to add comprehensive test cases for the new code path.

[Copilot]

Pull Request Overview

This PR adds support for uneven data splits as an alternative to the existing equal-size splitting behavior. The new functionality allows chunks to be filled to maximum capacity during fine-tuning while preserving backward compatibility.

• Adds a new equal_split_size parameter to control splitting behavior
• Implements uneven splitting that creates chunks of max_data_size with remainder handling
• Updates all relevant APIs to support the new parameter while maintaining backward compatibility

Reviewed Changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
src/tabpfn/utils.py	Adds core uneven splitting logic with equal_split_size parameter
src/tabpfn/base.py	Updates helper function to pass through the new parameter
src/tabpfn/classifier.py	Adds equal_split_size parameter to classifier's public API
src/tabpfn/regressor.py	Adds equal_split_size parameter to regressor's public API
tests/test_ft_utils.py	Updates all test calls to include the new parameter

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[noahho]

Great, LGTM!