Initial upload of multiple checkpoints
Browse files- cache-81c81174201b2511.arrow +3 -0
- cache-c9b61836aebcd6e7.arrow +3 -0
- data-00000-of-00001.arrow +3 -0
- dataset_info.json +48 -0
- state.json +13 -0
cache-81c81174201b2511.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e359f00e59a032b5aaba088aadf78071ab7f79a23f64684cadbc65e671854d56
|
| 3 |
+
size 802720
|
cache-c9b61836aebcd6e7.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ec93b12c69ad43288f0a1134283612923397983ea7cd18323e3061a28de1320
|
| 3 |
+
size 464056
|
data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b67944c84e4fe9cfae1f4f094bbc5462e6e536a73fc83c36ac5598a095b034cb
|
| 3 |
+
size 22059080
|
dataset_info.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"builder_name": "text",
|
| 3 |
+
"citation": "",
|
| 4 |
+
"config_name": "default",
|
| 5 |
+
"dataset_name": "r_uwiki",
|
| 6 |
+
"dataset_size": 26744465,
|
| 7 |
+
"description": "",
|
| 8 |
+
"download_checksums": {
|
| 9 |
+
"hf://datasets/DataSynGen/RUwiki@b4228a7494a50cd3c13b04fce98e64640877cf44/dataset.txt": {
|
| 10 |
+
"num_bytes": 26647425,
|
| 11 |
+
"checksum": null
|
| 12 |
+
}
|
| 13 |
+
},
|
| 14 |
+
"download_size": 26647425,
|
| 15 |
+
"features": {
|
| 16 |
+
"input_ids": {
|
| 17 |
+
"feature": {
|
| 18 |
+
"dtype": "int32",
|
| 19 |
+
"_type": "Value"
|
| 20 |
+
},
|
| 21 |
+
"_type": "Sequence"
|
| 22 |
+
},
|
| 23 |
+
"attention_mask": {
|
| 24 |
+
"feature": {
|
| 25 |
+
"dtype": "int8",
|
| 26 |
+
"_type": "Value"
|
| 27 |
+
},
|
| 28 |
+
"_type": "Sequence"
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"homepage": "",
|
| 32 |
+
"license": "",
|
| 33 |
+
"size_in_bytes": 53391890,
|
| 34 |
+
"splits": {
|
| 35 |
+
"train": {
|
| 36 |
+
"name": "train",
|
| 37 |
+
"num_bytes": 26744465,
|
| 38 |
+
"num_examples": 48520,
|
| 39 |
+
"dataset_name": "r_uwiki"
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"version": {
|
| 43 |
+
"version_str": "0.0.0",
|
| 44 |
+
"major": 0,
|
| 45 |
+
"minor": 0,
|
| 46 |
+
"patch": 0
|
| 47 |
+
}
|
| 48 |
+
}
|
state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "44bd64e20003ea0a",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": null
|
| 13 |
+
}
|