Spaces:
Paused
Paused
c4 - more data
Browse files
src/calibration_datasets.py
CHANGED
@@ -240,6 +240,12 @@ class C4Dataset(CalibrationDataset):
|
|
240 |
"en/c4-train.00002-of-01024.json.gz",
|
241 |
"en/c4-train.00003-of-01024.json.gz",
|
242 |
"en/c4-train.00004-of-01024.json.gz",
|
|
|
|
|
|
|
|
|
|
|
|
|
243 |
],
|
244 |
},
|
245 |
"split": "train"
|
|
|
240 |
"en/c4-train.00002-of-01024.json.gz",
|
241 |
"en/c4-train.00003-of-01024.json.gz",
|
242 |
"en/c4-train.00004-of-01024.json.gz",
|
243 |
+
"en/c4-train.00005-of-01024.json.gz",
|
244 |
+
"en/c4-train.00006-of-01024.json.gz",
|
245 |
+
"en/c4-train.00007-of-01024.json.gz",
|
246 |
+
"en/c4-train.00008-of-01024.json.gz",
|
247 |
+
"en/c4-train.00009-of-01024.json.gz",
|
248 |
+
"en/c4-train.00010-of-01024.json.gz",
|
249 |
],
|
250 |
},
|
251 |
"split": "train"
|