mirror of
https://github.com/NousResearch/atropos.git
synced 2026-04-27 17:23:08 +00:00
Move BLEUBERI environment to community folder
- Moved environments/bleuberi to environments/community/bleuberi
- Updated .gitmodules to reflect new submodule path
- Fixed pre-commit formatting issues
- Cleaned up test output files
This commit is contained in:
parent
532024d01e
commit
0f6c06bb56
8 changed files with 16 additions and 9 deletions
12
environments/community/bleuberi/__init__.py
Normal file
12
environments/community/bleuberi/__init__.py
Normal file
|
|
@ -0,0 +1,12 @@
|
|||
"""
|
||||
BLEUBERI: BLEU-based environment for instruction following.
|
||||
|
||||
This environment uses BLEU scores as a reward function for training
|
||||
models to follow instructions. Based on the paper:
|
||||
"BLEUBERI: BLEU is a surprisingly effective reward for instruction following"
|
||||
https://arxiv.org/abs/2505.11080
|
||||
"""
|
||||
|
||||
__all__ = ["BLEUBERIEnv"]
|
||||
|
||||
from .bleuberi_env import BLEUBERIEnv # noqa
|
||||
Loading…
Add table
Add a link
Reference in a new issue