cactus-compute / cactus-compute/needle
Why re-implement constrained decoding?
Open
- Dominant language
- Python
- Stars
- 11k
- Forks
- 710
- Avg merge
- 1d 21h
- Merged PRs (30d)
- 25
Description
I was wondering why you [re-implemented constrained decoding](https://github.com/cactus-compute/needle/blob/main/needle/model/constrained.py) in this repository? Is there something that does not work with existing methods?
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reading needle/model/constrained.py and reviewing the repository's constrained-decoding implementation. Compare it with the existing methods referenced by the issue, if they can be identified, and establish the reason for reimplementation and its limitations. The issue is done when that rationale is clearly documented.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100