huggingface / huggingface/alignment-handbook
Role of `prompt` field in SFT
Open
- Dominant language
- Python
- Stars
- 5.7k
- Forks
- 490
- Avg merge
- 2m
- Merged PRs (30d)
- 1
Description
I am planning to run SFT on real chatlogs so naturally I don't have the `prompt` field like in the Ultrachat dataset. AFAICT, this field is not used to perform SFT so I think I can keep it as an empty string. The code that converts the datapoint into a single string only uses the messages field:
https://github.com/huggingface/alignment-handbook/blob/61a11a5c7d66179ed0a930b0dd12e532fce701dd/src/alignment/data.py#L36C1-L42
Am I missing something here?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.