Adding MT Sample clinical note dataset (#804)

* Adding clinical note dataset

* Fix flake8 issues

* Fix prepare.py for straggling commas, replace assistant with Rosey in prompt

Co-authored-by: Yada P <yadapruk@Tests-MacBook-Pro.local>
This commit is contained in:
Yada Pruksachatkun
2023-01-23 14:24:43 +01:00
committed by GitHub
co-authored by Yada P
parent cb7b3e190a
commit d1d185edb6
6 changed files with 329 additions and 0 deletions
@@ -0,0 +1,21 @@
from dataclasses import dataclass
import datasets
@dataclass
class OpenAssistantConfig(datasets.BuilderConfig):
"""BuilderConfig for OpenAssistant datasets."""
name: str = None
version: datasets.Version = None
description: str = None
schema: str = None
subset_id: str = None
features = datasets.Features(
{
"conversation": datasets.Value("string"),
}
)