open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-24 17:05:03 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Feat/unsloth example (#482)

Browse source 
* cleaned up examples

* updated failing hooks

* updated readme

* corrected linting checks
This commit is contained in:
joesharratt1229 2025-06-28 17:04:38 +01:00 • committed by GitHub
parent d9cd20c174
commit 1c98584f28
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
29 changed files with 122 additions and 2857 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/trl/grpo.py
View file

@ -27,7 +27,7 @@ class DatasetConfigItem:
@dataclass
class DatasetConfig:
dataset_size: int = field(default=1000)
dataset_size: int = field(default=10000)
developer_prompt: str = field(default="DeepSeekZero")
developer_role: str = field(default="system")
datasets: dict[str, DatasetConfigItem] = field(default=None)