[WIP] System Prompt Mapping for Instruct DS

[jaysonfrancis]

To support instruct datasets that may have system prompts defined per row, e.g; (system, input, output), otherwise, fall back to a fixed new_system_prompt, or None.

Are there alternatives to this I may have overlooked? Otherwise, I can proceed with adding tests/docs. Thanks!

---

Context

What is the purpose of this PR? Is it to

• add a new feature
• fix a bug
• update tests and/or documentation
• other (please add here)

Please link to any issues this PR addresses.

Changelog

What are the changes made in this PR?
*

Test plan

Please make sure to do each of the following if applicable to your PR. If you're unsure about any one of these just ask and we will happily help. We also have a contributing page for some guidance on contributing.

• run pre-commit hooks and linters (make sure you've first installed via pre-commit install)
• add unit tests for any new functionality
• update docstrings for any new or updated methods or classes
• run unit tests via pytest tests
• run recipe tests via pytest tests -m integration_test
• manually run any new or modified recipes with sufficient proof of correctness
• include relevant commands and any other artifacts in this summary (pastes of loss curves, eval results, etc.)

UX

If your function changed a public API, please add a dummy example of what the user experience will look like when calling it.
Here is a docstring example
and a tutorial example

• I did not change any public API
• I have added an example to docs or docstrings

---

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/torchtune/2514

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[RdoubleA]

Sorry I know this was a draft but had some early thoughts. Could you share some HF datasets that have a system column?

[jaysonfrancis]

Sorry I know this was a draft but had some early thoughts. Could you share some HF datasets that have a system column?

Thanks for feedback @RdoubleA

There aren't many, but here are a few examples; here, here, here. It may also be useful for consolidated datasets.

Yes your comments make sense. Any thoughts on the case if "system" is in sample dict and not in column map, but user has defined a fixed, "new_system_prompt" ?