We are finetuning MPT-7B (or 40B) on Pile of Law and Legal Bench. We are then taking a convex combination with an instruct model.
- Few shot prompt MPT models (their context length is 65k compared to 2k for Falcon)
forked from NomosArtificial/static-eval
-
Notifications
You must be signed in to change notification settings - Fork 0
tomohiro-sawada/llm-law-hackathon
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
No description, website, or topics provided.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published
Languages
- Python 99.2%
- Shell 0.8%