Upload folder using huggingface_hub
Browse files- loaders.py +5 -1
- version.py +1 -1
loaders.py
CHANGED
@@ -258,7 +258,7 @@ class LoadHF(LazyLoader):
|
|
258 |
split:
|
259 |
Optional specification of which split to load.
|
260 |
data_files:
|
261 |
-
Optional specification of particular data files to load.
|
262 |
revision:
|
263 |
Optional. The revision of the dataset. Often the commit id. Use in case you want to set the dataset version.
|
264 |
streaming (bool):
|
@@ -351,6 +351,10 @@ class LoadHF(LazyLoader):
|
|
351 |
def get_splits(self):
|
352 |
if self.splits is not None:
|
353 |
return self.splits
|
|
|
|
|
|
|
|
|
354 |
try:
|
355 |
return hf_get_dataset_splits(
|
356 |
path=self.path,
|
|
|
258 |
split:
|
259 |
Optional specification of which split to load.
|
260 |
data_files:
|
261 |
+
Optional specification of particular data files to load. When you provide a list of data_files to Hugging Face's load_dataset function without explicitly specifying the split argument, these files are automatically placed into the train split.
|
262 |
revision:
|
263 |
Optional. The revision of the dataset. Often the commit id. Use in case you want to set the dataset version.
|
264 |
streaming (bool):
|
|
|
351 |
def get_splits(self):
|
352 |
if self.splits is not None:
|
353 |
return self.splits
|
354 |
+
if self.data_files is not None:
|
355 |
+
if isinstance(self.data_files, dict):
|
356 |
+
return list(self.data_files.keys())
|
357 |
+
return ["train"]
|
358 |
try:
|
359 |
return hf_get_dataset_splits(
|
360 |
path=self.path,
|
version.py
CHANGED
@@ -1 +1 @@
|
|
1 |
-
version = "1.22.
|
|
|
1 |
+
version = "1.22.1"
|