Fix data loading for DPO and other formats like parquet.

[PhilipMay]

If you want to do DPO with a locale file at the moment it is only possible with jsonl files.
This enables it for more file formats like parquet.

fixes #1282

[PhilipMay]

@filippo82 can you please review this? Many thanks.

[winglian]

Can we figure out another way of integrating this? I think it's valuable to attempt to load other file formats.

[winglian]

I'm a little wary of completely removing a working code path. We do t have a lot of test coverage of the various file loading use cases so my confidence this won't break existing use cases is low.

[PhilipMay]

Yes. You are right.
The sft code is much more complicated.
See: https://github.com/OpenAccess-AI-Collective/axolotl/blob/b2a4cb4396922fdd2242981a99e79f8b213ac4a4/src/axolotl/utils/data.py#L292-L376
But how do we fix this issue?
Should the user be forced to use jsonl if he or she wants to use a locale file?

[PhilipMay]

Can we figure out another way of integrating this? I think it's valuable to attempt to load other file formats.

I think of a step by step approach:

1. refactor the data loading logic of sft into a dedicated function - see https://github.com/OpenAccess-AI-Collective/axolotl/blob/b2a4cb4396922fdd2242981a99e79f8b213ac4a4/src/axolotl/utils/data.py#L292-L376

2. check how and if we can reuse the function for DPO data loading

[winglian]

Can we figure out another way of integrating this? I think it's valuable to attempt to load other file formats.

I think of a step by step approach:

1. refactor the data loading logic of sft into a dedicated function - see https://github.com/OpenAccess-AI-Collective/axolotl/blob/b2a4cb4396922fdd2242981a99e79f8b213ac4a4/src/axolotl/utils/data.py#L292-L376
2. check how and if we can reuse the function for DPO data loading

That all seems sound to me. 👍