Lightning-AI / Lightning-AI/litgpt
Why Alpaca is only mask_prompt=False??
Open
Nobody has claimed this yet.
help wanted
question
- Dominant language
- Python
- Stars
- 13.7k
- Forks
- 1.5k
- Avg merge
- 15h 37m
- Merged PRs (30d)
- 1
Description
litgpt/data/alpaca.py is a default data module.
but, It's mask_prompt=False... I don't know why.. I think loss must be calculated in generated answer... not prompt...
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading litgpt/data/alpaca.py and trace how mask_prompt=False affects the training loss. Compare the module's behavior with the issue's expected prompt masking, then confirm the desired loss behavior with the surrounding data-module conventions. Done means the Alpaca module calculates loss only for generated answers, with appropriate coverage if an existing test path is available.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 38/100