bigscience-workshop / bigscience-workshop/petals
content of 'labels' when doing prompt tuning of llama-2 on QA
Open
- Dominant language
- Python
- Stars
- 10.6k
- Forks
- 650
- PR merge metrics
- No merged PRs in 30d
Description
I saw that on classification tasks, the 'labels' are target values. When using CausalLM model to tune it on QA dataset, the format should be
1) input_ids: Q; labels:A or
2) input_ids: Q+A, labels: Q+A or
3) input_ids: Q+A, labels: IGNORE_TOKENs+A ?
Thank you!
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.