add dpo mix dataset

Former-commit-id: 6def3f8bfa51b2d9d73af112352ce07db972e4c9
This commit is contained in:
hiyouga
2024-04-20 01:31:38 +08:00
parent b3b5b530d1
commit 0cb596fee1
4 changed files with 59 additions and 105 deletions

View File

@@ -1,7 +1,8 @@
import json
import datasets
from typing import Any, Dict, Generator, List, Tuple
import datasets
_DESCRIPTION = "An example of dataset."
_CITATION = ""
@@ -11,34 +12,24 @@ _URL = "examples.json"
class ExampleDataset(datasets.GeneratorBasedBuilder):
VERSION = datasets.Version("0.0.0")
def _info(self) -> datasets.DatasetInfo:
features = datasets.Features({
"instruction": datasets.Value("string"),
"input": datasets.Value("string"),
"output": datasets.Value("string"),
"history": datasets.Sequence(datasets.Sequence(datasets.Value("string")))
})
features = datasets.Features(
{
"instruction": datasets.Value("string"),
"input": datasets.Value("string"),
"output": datasets.Value("string"),
"history": datasets.Sequence(datasets.Sequence(datasets.Value("string"))),
}
)
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION
description=_DESCRIPTION, features=features, homepage=_HOMEPAGE, license=_LICENSE, citation=_CITATION
)
def _split_generators(self, dl_manager: datasets.DownloadManager) -> List[datasets.SplitGenerator]:
file_path = dl_manager.download(_URL)
return [
datasets.SplitGenerator(
name=datasets.Split.TRAIN,
gen_kwargs={
"filepath": file_path
}
)
]
return [datasets.SplitGenerator(name=datasets.Split.TRAIN, gen_kwargs={"filepath": file_path})]
def _generate_examples(self, filepath: str) -> Generator[Tuple[int, Dict[str, Any]], None, None]:
example_dataset = json.load(open(filepath, "r", encoding="utf-8"))