add stage in DatasetAttr

Former-commit-id: ba94c8729dd8c90bedf7079a6978e150fc92b737
This commit is contained in:
codemayq 2023-08-23 20:54:53 +08:00
parent b032dc4c4e
commit 2b979d39f2

View File

@ -11,6 +11,7 @@ class DatasetAttr:
dataset_name: Optional[str] = None
dataset_sha1: Optional[str] = None
system_prompt: Optional[str] = None
stage: Optional[str] = None
def __repr__(self) -> str:
return self.dataset_name
@ -113,14 +114,21 @@ class DataArguments:
raise ValueError("Undefined dataset {} in dataset_info.json.".format(name))
if "hf_hub_url" in dataset_info[name]:
dataset_attr = DatasetAttr("hf_hub", dataset_name=dataset_info[name]["hf_hub_url"])
dataset_attr = DatasetAttr(
"hf_hub",
dataset_name=dataset_info[name]["hf_hub_url"],
stage=dataset_info[name].get("stage", None))
elif "script_url" in dataset_info[name]:
dataset_attr = DatasetAttr("script", dataset_name=dataset_info[name]["script_url"])
dataset_attr = DatasetAttr(
"script",
dataset_name=dataset_info[name]["script_url"],
stage=dataset_info[name].get("stage", None))
else:
dataset_attr = DatasetAttr(
"file",
dataset_name=dataset_info[name]["file_name"],
dataset_sha1=dataset_info[name].get("file_sha1", None)
dataset_sha1=dataset_info[name].get("file_sha1", None),
stage=dataset_info[name].get("stage", None)
)
if "columns" in dataset_info[name]: