Hugging Face's logo

m3hrdadfi
/
psgs_w100-nq-exact

Model card Files Community
m3hrdadfi commited on
Commit
9381251
·
1 Parent(s): 137dace

Upload 18 files

Browse files
Files changed (18) hide show
  1. hf_dataset/data-00141-of-00157.arrow +3 -0
  2. hf_dataset/data-00142-of-00157.arrow +3 -0
  3. hf_dataset/data-00143-of-00157.arrow +3 -0
  4. hf_dataset/data-00144-of-00157.arrow +3 -0
  5. hf_dataset/data-00145-of-00157.arrow +3 -0
  6. hf_dataset/data-00146-of-00157.arrow +3 -0
  7. hf_dataset/data-00147-of-00157.arrow +3 -0
  8. hf_dataset/data-00148-of-00157.arrow +3 -0
  9. hf_dataset/data-00149-of-00157.arrow +3 -0
  10. hf_dataset/data-00150-of-00157.arrow +3 -0
  11. hf_dataset/data-00151-of-00157.arrow +3 -0
  12. hf_dataset/data-00152-of-00157.arrow +3 -0
  13. hf_dataset/data-00153-of-00157.arrow +3 -0
  14. hf_dataset/data-00154-of-00157.arrow +3 -0
  15. hf_dataset/data-00155-of-00157.arrow +3 -0
  16. hf_dataset/data-00156-of-00157.arrow +3 -0
  17. hf_dataset/dataset_info.json +422 -0
  18. hf_dataset/state.json +483 -0
hf_dataset/data-00141-of-00157.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74fc8f0a7736fb6c9464fb8607551d2f634f20ce47a792ebca9f8ddc03cdae76
3
+ size 499687096
hf_dataset/data-00142-of-00157.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26f5593fac99090e9bc08440b76f5bfcda54b6e68ad878e88e0ab82671019510
3
+ size 499884560
hf_dataset/data-00143-of-00157.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c514da909d8836e10f177157f837f657bb11a0dd6b13a483c66e694781da0397
3
+ size 499842112
hf_dataset/data-00144-of-00157.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d9d9457ca340c0e81b1480ccc9dba15b3a6bbd05d2c6dd0a4a1cd1909ef66df
3
+ size 499975496
hf_dataset/data-00145-of-00157.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2a831eef12e9d1e2700e9c0b8f39bc3df7e597f6719cd3192bda28eea522e27
3
+ size 499988032
hf_dataset/data-00146-of-00157.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:351a4807d7d765f33cc6d34ff575202a04e53ed796b8b5c55ec164bc3a0780b4
3
+ size 499998184
hf_dataset/data-00147-of-00157.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed62a5ce1412d2861be12c4bf5bffb36dd111295d76656e0c74df9f138bbe95c
3
+ size 500045920
hf_dataset/data-00148-of-00157.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0470f1f28ef47851f6150014fb2f968c89ec83581240dbfec5b9ddd092c7cd39
3
+ size 500019216
hf_dataset/data-00149-of-00157.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed47910828e4b8a736386c2d07cfb9d1b540d89984c79473a27106c651b9436a
3
+ size 500170664
hf_dataset/data-00150-of-00157.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cd7f54fcafec2cb79829a7b639b1bac72c44422e35fbf3ef1049049561e9d8d
3
+ size 500243512
hf_dataset/data-00151-of-00157.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab16830d3abed851898cb275411195c5a0868030176bebf6633b994d4de57d21
3
+ size 499921992
hf_dataset/data-00152-of-00157.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dccb14543e0119d711d1c9f900bc13e3e24c0f446706b3815b53a1fa34b450a
3
+ size 499985136
hf_dataset/data-00153-of-00157.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f77996239efd139eae3e1faa47c71ac25157ef03b0c68ce41a787a6375476b9
3
+ size 500098496
hf_dataset/data-00154-of-00157.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c30f5af6677199f232eed5fca82f7c98b23a8ef77960de4b79692497abb9f4d
3
+ size 500139240
hf_dataset/data-00155-of-00157.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1f7a58d266c4baea3e687ded66686df51072b0bd06c911588c6a71cc4129008
3
+ size 500030840
hf_dataset/data-00156-of-00157.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60b814b92e8df76a79becb1a7a8a9650d5dd5ede78a9df751120e1b4d0fb5d88
3
+ size 500264440
hf_dataset/dataset_info.json ADDED
@@ -0,0 +1,422 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "builder_name": "wiki_dpr",
3
+ "citation": "\n@misc{karpukhin2020dense,\n title={Dense Passage Retrieval for Open-Domain Question Answering},\n author={Vladimir Karpukhin and Barlas O\u011fuz and Sewon Min and Patrick Lewis and Ledell Wu and Sergey Edunov and Danqi Chen and Wen-tau Yih},\n year={2020},\n eprint={2004.04906},\n archivePrefix={arXiv},\n primaryClass={cs.CL}\n}\n",
4
+ "config_name": "psgs_w100.nq.exact",
5
+ "dataset_size": 78419248156,
6
+ "description": "\nThis is the wikipedia split used to evaluate the Dense Passage Retrieval (DPR) model.\nIt contains 21M passages from wikipedia along with their DPR embeddings.\nThe wikipedia articles were split into multiple, disjoint text blocks of 100 words as passages.\n",
7
+ "download_checksums": {
8
+ "https://dl.fbaipublicfiles.com/dpr/wikipedia_split/psgs_w100.tsv.gz": {
9
+ "num_bytes": 4694541059,
10
+ "checksum": null
11
+ },
12
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_0": {
13
+ "num_bytes": 1324693633,
14
+ "checksum": null
15
+ },
16
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_1": {
17
+ "num_bytes": 1324804738,
18
+ "checksum": null
19
+ },
20
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_2": {
21
+ "num_bytes": 1325065657,
22
+ "checksum": null
23
+ },
24
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_3": {
25
+ "num_bytes": 1325225044,
26
+ "checksum": null
27
+ },
28
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_4": {
29
+ "num_bytes": 1325225044,
30
+ "checksum": null
31
+ },
32
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_5": {
33
+ "num_bytes": 1325225044,
34
+ "checksum": null
35
+ },
36
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_6": {
37
+ "num_bytes": 1325225044,
38
+ "checksum": null
39
+ },
40
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_7": {
41
+ "num_bytes": 1325225044,
42
+ "checksum": null
43
+ },
44
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_8": {
45
+ "num_bytes": 1325225044,
46
+ "checksum": null
47
+ },
48
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_9": {
49
+ "num_bytes": 1325225044,
50
+ "checksum": null
51
+ },
52
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_10": {
53
+ "num_bytes": 1325225044,
54
+ "checksum": null
55
+ },
56
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_11": {
57
+ "num_bytes": 1325225044,
58
+ "checksum": null
59
+ },
60
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_12": {
61
+ "num_bytes": 1325225044,
62
+ "checksum": null
63
+ },
64
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_13": {
65
+ "num_bytes": 1325225044,
66
+ "checksum": null
67
+ },
68
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_14": {
69
+ "num_bytes": 1325225044,
70
+ "checksum": null
71
+ },
72
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_15": {
73
+ "num_bytes": 1325225044,
74
+ "checksum": null
75
+ },
76
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_16": {
77
+ "num_bytes": 1325225044,
78
+ "checksum": null
79
+ },
80
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_17": {
81
+ "num_bytes": 1325225044,
82
+ "checksum": null
83
+ },
84
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_18": {
85
+ "num_bytes": 1325225044,
86
+ "checksum": null
87
+ },
88
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_19": {
89
+ "num_bytes": 1325225044,
90
+ "checksum": null
91
+ },
92
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_20": {
93
+ "num_bytes": 1325225044,
94
+ "checksum": null
95
+ },
96
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_21": {
97
+ "num_bytes": 1325225044,
98
+ "checksum": null
99
+ },
100
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_22": {
101
+ "num_bytes": 1325225044,
102
+ "checksum": null
103
+ },
104
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_23": {
105
+ "num_bytes": 1325312389,
106
+ "checksum": null
107
+ },
108
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_24": {
109
+ "num_bytes": 1325645350,
110
+ "checksum": null
111
+ },
112
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_25": {
113
+ "num_bytes": 1325645350,
114
+ "checksum": null
115
+ },
116
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_26": {
117
+ "num_bytes": 1325645350,
118
+ "checksum": null
119
+ },
120
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_27": {
121
+ "num_bytes": 1325645350,
122
+ "checksum": null
123
+ },
124
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_28": {
125
+ "num_bytes": 1325645350,
126
+ "checksum": null
127
+ },
128
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_29": {
129
+ "num_bytes": 1325645350,
130
+ "checksum": null
131
+ },
132
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_30": {
133
+ "num_bytes": 1325645350,
134
+ "checksum": null
135
+ },
136
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_31": {
137
+ "num_bytes": 1325645350,
138
+ "checksum": null
139
+ },
140
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_32": {
141
+ "num_bytes": 1325645350,
142
+ "checksum": null
143
+ },
144
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_33": {
145
+ "num_bytes": 1325645350,
146
+ "checksum": null
147
+ },
148
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_34": {
149
+ "num_bytes": 1325645350,
150
+ "checksum": null
151
+ },
152
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_35": {
153
+ "num_bytes": 1325645350,
154
+ "checksum": null
155
+ },
156
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_36": {
157
+ "num_bytes": 1325645350,
158
+ "checksum": null
159
+ },
160
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_37": {
161
+ "num_bytes": 1325645350,
162
+ "checksum": null
163
+ },
164
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_38": {
165
+ "num_bytes": 1325645350,
166
+ "checksum": null
167
+ },
168
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_39": {
169
+ "num_bytes": 1325645350,
170
+ "checksum": null
171
+ },
172
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_40": {
173
+ "num_bytes": 1325645350,
174
+ "checksum": null
175
+ },
176
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_41": {
177
+ "num_bytes": 1325645350,
178
+ "checksum": null
179
+ },
180
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_42": {
181
+ "num_bytes": 1325645350,
182
+ "checksum": null
183
+ },
184
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_43": {
185
+ "num_bytes": 1325645350,
186
+ "checksum": null
187
+ },
188
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_44": {
189
+ "num_bytes": 1325645350,
190
+ "checksum": null
191
+ },
192
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_45": {
193
+ "num_bytes": 1325645350,
194
+ "checksum": null
195
+ },
196
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_46": {
197
+ "num_bytes": 1325645350,
198
+ "checksum": null
199
+ },
200
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_47": {
201
+ "num_bytes": 1325645350,
202
+ "checksum": null
203
+ },
204
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_48": {
205
+ "num_bytes": 1325645350,
206
+ "checksum": null
207
+ },
208
+ "https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_49": {
209
+ "num_bytes": 1325645350,
210
+ "checksum": null
211
+ }
212
+ },
213
+ "download_size": 70965697456,
214
+ "features": {
215
+ "id": {
216
+ "dtype": "string",
217
+ "_type": "Value"
218
+ },
219
+ "text": {
220
+ "dtype": "string",
221
+ "_type": "Value"
222
+ },
223
+ "title": {
224
+ "dtype": "string",
225
+ "_type": "Value"
226
+ },
227
+ "embeddings": {
228
+ "feature": {
229
+ "dtype": "float32",
230
+ "_type": "Value"
231
+ },
232
+ "_type": "Sequence"
233
+ }
234
+ },
235
+ "homepage": "https://github.com/facebookresearch/DPR",
236
+ "license": "",
237
+ "post_processed": {
238
+ "resources_checksums": {
239
+ "train": {
240
+ "embeddings_index": {
241
+ "num_bytes": 37996397866,
242
+ "checksum": "d2d36d189010bd79f4add038f416c62db18442c54df335a381e8d1fdaaaf10c2"
243
+ }
244
+ }
245
+ }
246
+ },
247
+ "post_processing_size": 37996397866,
248
+ "size_in_bytes": 187381343478,
249
+ "splits": {
250
+ "train": {
251
+ "name": "train",
252
+ "num_bytes": 78419248156,
253
+ "num_examples": 21015300,
254
+ "shard_lengths": [
255
+ 134000,
256
+ 134000,
257
+ 134000,
258
+ 134000,
259
+ 134000,
260
+ 135000,
261
+ 135000,
262
+ 135000,
263
+ 135000,
264
+ 135000,
265
+ 135000,
266
+ 135000,
267
+ 134000,
268
+ 134000,
269
+ 135000,
270
+ 134000,
271
+ 135000,
272
+ 135000,
273
+ 135000,
274
+ 135000,
275
+ 134000,
276
+ 135000,
277
+ 135000,
278
+ 135000,
279
+ 135000,
280
+ 135000,
281
+ 135000,
282
+ 135000,
283
+ 135000,
284
+ 135000,
285
+ 135000,
286
+ 135000,
287
+ 135000,
288
+ 135000,
289
+ 135000,
290
+ 135000,
291
+ 135000,
292
+ 135000,
293
+ 135000,
294
+ 135000,
295
+ 135000,
296
+ 135000,
297
+ 135000,
298
+ 135000,
299
+ 135000,
300
+ 135000,
301
+ 135000,
302
+ 135000,
303
+ 135000,
304
+ 135000,
305
+ 135000,
306
+ 135000,
307
+ 135000,
308
+ 135000,
309
+ 135000,
310
+ 135000,
311
+ 135000,
312
+ 135000,
313
+ 135000,
314
+ 135000,
315
+ 135000,
316
+ 135000,
317
+ 135000,
318
+ 135000,
319
+ 135000,
320
+ 135000,
321
+ 135000,
322
+ 135000,
323
+ 135000,
324
+ 135000,
325
+ 135000,
326
+ 135000,
327
+ 135000,
328
+ 135000,
329
+ 135000,
330
+ 134000,
331
+ 135000,
332
+ 134000,
333
+ 134000,
334
+ 135000,
335
+ 135000,
336
+ 134000,
337
+ 134000,
338
+ 134000,
339
+ 134000,
340
+ 134000,
341
+ 134000,
342
+ 134000,
343
+ 134000,
344
+ 134000,
345
+ 134000,
346
+ 134000,
347
+ 134000,
348
+ 134000,
349
+ 134000,
350
+ 134000,
351
+ 134000,
352
+ 134000,
353
+ 134000,
354
+ 134000,
355
+ 134000,
356
+ 134000,
357
+ 134000,
358
+ 134000,
359
+ 134000,
360
+ 134000,
361
+ 134000,
362
+ 134000,
363
+ 134000,
364
+ 134000,
365
+ 134000,
366
+ 134000,
367
+ 134000,
368
+ 134000,
369
+ 134000,
370
+ 134000,
371
+ 134000,
372
+ 134000,
373
+ 134000,
374
+ 134000,
375
+ 134000,
376
+ 134000,
377
+ 134000,
378
+ 134000,
379
+ 134000,
380
+ 134000,
381
+ 134000,
382
+ 134000,
383
+ 134000,
384
+ 134000,
385
+ 134000,
386
+ 134000,
387
+ 134000,
388
+ 134000,
389
+ 134000,
390
+ 134000,
391
+ 134000,
392
+ 134000,
393
+ 134000,
394
+ 134000,
395
+ 134000,
396
+ 134000,
397
+ 134000,
398
+ 134000,
399
+ 134000,
400
+ 134000,
401
+ 134000,
402
+ 134000,
403
+ 134000,
404
+ 134000,
405
+ 134000,
406
+ 134000,
407
+ 134000,
408
+ 134000,
409
+ 134000,
410
+ 134000,
411
+ 42300
412
+ ],
413
+ "dataset_name": "wiki_dpr"
414
+ }
415
+ },
416
+ "version": {
417
+ "version_str": "0.0.0",
418
+ "major": 0,
419
+ "minor": 0,
420
+ "patch": 0
421
+ }
422
+ }
hf_dataset/state.json ADDED
@@ -0,0 +1,483 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00157.arrow"
5
+ },
6
+ {
7
+ "filename": "data-00001-of-00157.arrow"
8
+ },
9
+ {
10
+ "filename": "data-00002-of-00157.arrow"
11
+ },
12
+ {
13
+ "filename": "data-00003-of-00157.arrow"
14
+ },
15
+ {
16
+ "filename": "data-00004-of-00157.arrow"
17
+ },
18
+ {
19
+ "filename": "data-00005-of-00157.arrow"
20
+ },
21
+ {
22
+ "filename": "data-00006-of-00157.arrow"
23
+ },
24
+ {
25
+ "filename": "data-00007-of-00157.arrow"
26
+ },
27
+ {
28
+ "filename": "data-00008-of-00157.arrow"
29
+ },
30
+ {
31
+ "filename": "data-00009-of-00157.arrow"
32
+ },
33
+ {
34
+ "filename": "data-00010-of-00157.arrow"
35
+ },
36
+ {
37
+ "filename": "data-00011-of-00157.arrow"
38
+ },
39
+ {
40
+ "filename": "data-00012-of-00157.arrow"
41
+ },
42
+ {
43
+ "filename": "data-00013-of-00157.arrow"
44
+ },
45
+ {
46
+ "filename": "data-00014-of-00157.arrow"
47
+ },
48
+ {
49
+ "filename": "data-00015-of-00157.arrow"
50
+ },
51
+ {
52
+ "filename": "data-00016-of-00157.arrow"
53
+ },
54
+ {
55
+ "filename": "data-00017-of-00157.arrow"
56
+ },
57
+ {
58
+ "filename": "data-00018-of-00157.arrow"
59
+ },
60
+ {
61
+ "filename": "data-00019-of-00157.arrow"
62
+ },
63
+ {
64
+ "filename": "data-00020-of-00157.arrow"
65
+ },
66
+ {
67
+ "filename": "data-00021-of-00157.arrow"
68
+ },
69
+ {
70
+ "filename": "data-00022-of-00157.arrow"
71
+ },
72
+ {
73
+ "filename": "data-00023-of-00157.arrow"
74
+ },
75
+ {
76
+ "filename": "data-00024-of-00157.arrow"
77
+ },
78
+ {
79
+ "filename": "data-00025-of-00157.arrow"
80
+ },
81
+ {
82
+ "filename": "data-00026-of-00157.arrow"
83
+ },
84
+ {
85
+ "filename": "data-00027-of-00157.arrow"
86
+ },
87
+ {
88
+ "filename": "data-00028-of-00157.arrow"
89
+ },
90
+ {
91
+ "filename": "data-00029-of-00157.arrow"
92
+ },
93
+ {
94
+ "filename": "data-00030-of-00157.arrow"
95
+ },
96
+ {
97
+ "filename": "data-00031-of-00157.arrow"
98
+ },
99
+ {
100
+ "filename": "data-00032-of-00157.arrow"
101
+ },
102
+ {
103
+ "filename": "data-00033-of-00157.arrow"
104
+ },
105
+ {
106
+ "filename": "data-00034-of-00157.arrow"
107
+ },
108
+ {
109
+ "filename": "data-00035-of-00157.arrow"
110
+ },
111
+ {
112
+ "filename": "data-00036-of-00157.arrow"
113
+ },
114
+ {
115
+ "filename": "data-00037-of-00157.arrow"
116
+ },
117
+ {
118
+ "filename": "data-00038-of-00157.arrow"
119
+ },
120
+ {
121
+ "filename": "data-00039-of-00157.arrow"
122
+ },
123
+ {
124
+ "filename": "data-00040-of-00157.arrow"
125
+ },
126
+ {
127
+ "filename": "data-00041-of-00157.arrow"
128
+ },
129
+ {
130
+ "filename": "data-00042-of-00157.arrow"
131
+ },
132
+ {
133
+ "filename": "data-00043-of-00157.arrow"
134
+ },
135
+ {
136
+ "filename": "data-00044-of-00157.arrow"
137
+ },
138
+ {
139
+ "filename": "data-00045-of-00157.arrow"
140
+ },
141
+ {
142
+ "filename": "data-00046-of-00157.arrow"
143
+ },
144
+ {
145
+ "filename": "data-00047-of-00157.arrow"
146
+ },
147
+ {
148
+ "filename": "data-00048-of-00157.arrow"
149
+ },
150
+ {
151
+ "filename": "data-00049-of-00157.arrow"
152
+ },
153
+ {
154
+ "filename": "data-00050-of-00157.arrow"
155
+ },
156
+ {
157
+ "filename": "data-00051-of-00157.arrow"
158
+ },
159
+ {
160
+ "filename": "data-00052-of-00157.arrow"
161
+ },
162
+ {
163
+ "filename": "data-00053-of-00157.arrow"
164
+ },
165
+ {
166
+ "filename": "data-00054-of-00157.arrow"
167
+ },
168
+ {
169
+ "filename": "data-00055-of-00157.arrow"
170
+ },
171
+ {
172
+ "filename": "data-00056-of-00157.arrow"
173
+ },
174
+ {
175
+ "filename": "data-00057-of-00157.arrow"
176
+ },
177
+ {
178
+ "filename": "data-00058-of-00157.arrow"
179
+ },
180
+ {
181
+ "filename": "data-00059-of-00157.arrow"
182
+ },
183
+ {
184
+ "filename": "data-00060-of-00157.arrow"
185
+ },
186
+ {
187
+ "filename": "data-00061-of-00157.arrow"
188
+ },
189
+ {
190
+ "filename": "data-00062-of-00157.arrow"
191
+ },
192
+ {
193
+ "filename": "data-00063-of-00157.arrow"
194
+ },
195
+ {
196
+ "filename": "data-00064-of-00157.arrow"
197
+ },
198
+ {
199
+ "filename": "data-00065-of-00157.arrow"
200
+ },
201
+ {
202
+ "filename": "data-00066-of-00157.arrow"
203
+ },
204
+ {
205
+ "filename": "data-00067-of-00157.arrow"
206
+ },
207
+ {
208
+ "filename": "data-00068-of-00157.arrow"
209
+ },
210
+ {
211
+ "filename": "data-00069-of-00157.arrow"
212
+ },
213
+ {
214
+ "filename": "data-00070-of-00157.arrow"
215
+ },
216
+ {
217
+ "filename": "data-00071-of-00157.arrow"
218
+ },
219
+ {
220
+ "filename": "data-00072-of-00157.arrow"
221
+ },
222
+ {
223
+ "filename": "data-00073-of-00157.arrow"
224
+ },
225
+ {
226
+ "filename": "data-00074-of-00157.arrow"
227
+ },
228
+ {
229
+ "filename": "data-00075-of-00157.arrow"
230
+ },
231
+ {
232
+ "filename": "data-00076-of-00157.arrow"
233
+ },
234
+ {
235
+ "filename": "data-00077-of-00157.arrow"
236
+ },
237
+ {
238
+ "filename": "data-00078-of-00157.arrow"
239
+ },
240
+ {
241
+ "filename": "data-00079-of-00157.arrow"
242
+ },
243
+ {
244
+ "filename": "data-00080-of-00157.arrow"
245
+ },
246
+ {
247
+ "filename": "data-00081-of-00157.arrow"
248
+ },
249
+ {
250
+ "filename": "data-00082-of-00157.arrow"
251
+ },
252
+ {
253
+ "filename": "data-00083-of-00157.arrow"
254
+ },
255
+ {
256
+ "filename": "data-00084-of-00157.arrow"
257
+ },
258
+ {
259
+ "filename": "data-00085-of-00157.arrow"
260
+ },
261
+ {
262
+ "filename": "data-00086-of-00157.arrow"
263
+ },
264
+ {
265
+ "filename": "data-00087-of-00157.arrow"
266
+ },
267
+ {
268
+ "filename": "data-00088-of-00157.arrow"
269
+ },
270
+ {
271
+ "filename": "data-00089-of-00157.arrow"
272
+ },
273
+ {
274
+ "filename": "data-00090-of-00157.arrow"
275
+ },
276
+ {
277
+ "filename": "data-00091-of-00157.arrow"
278
+ },
279
+ {
280
+ "filename": "data-00092-of-00157.arrow"
281
+ },
282
+ {
283
+ "filename": "data-00093-of-00157.arrow"
284
+ },
285
+ {
286
+ "filename": "data-00094-of-00157.arrow"
287
+ },
288
+ {
289
+ "filename": "data-00095-of-00157.arrow"
290
+ },
291
+ {
292
+ "filename": "data-00096-of-00157.arrow"
293
+ },
294
+ {
295
+ "filename": "data-00097-of-00157.arrow"
296
+ },
297
+ {
298
+ "filename": "data-00098-of-00157.arrow"
299
+ },
300
+ {
301
+ "filename": "data-00099-of-00157.arrow"
302
+ },
303
+ {
304
+ "filename": "data-00100-of-00157.arrow"
305
+ },
306
+ {
307
+ "filename": "data-00101-of-00157.arrow"
308
+ },
309
+ {
310
+ "filename": "data-00102-of-00157.arrow"
311
+ },
312
+ {
313
+ "filename": "data-00103-of-00157.arrow"
314
+ },
315
+ {
316
+ "filename": "data-00104-of-00157.arrow"
317
+ },
318
+ {
319
+ "filename": "data-00105-of-00157.arrow"
320
+ },
321
+ {
322
+ "filename": "data-00106-of-00157.arrow"
323
+ },
324
+ {
325
+ "filename": "data-00107-of-00157.arrow"
326
+ },
327
+ {
328
+ "filename": "data-00108-of-00157.arrow"
329
+ },
330
+ {
331
+ "filename": "data-00109-of-00157.arrow"
332
+ },
333
+ {
334
+ "filename": "data-00110-of-00157.arrow"
335
+ },
336
+ {
337
+ "filename": "data-00111-of-00157.arrow"
338
+ },
339
+ {
340
+ "filename": "data-00112-of-00157.arrow"
341
+ },
342
+ {
343
+ "filename": "data-00113-of-00157.arrow"
344
+ },
345
+ {
346
+ "filename": "data-00114-of-00157.arrow"
347
+ },
348
+ {
349
+ "filename": "data-00115-of-00157.arrow"
350
+ },
351
+ {
352
+ "filename": "data-00116-of-00157.arrow"
353
+ },
354
+ {
355
+ "filename": "data-00117-of-00157.arrow"
356
+ },
357
+ {
358
+ "filename": "data-00118-of-00157.arrow"
359
+ },
360
+ {
361
+ "filename": "data-00119-of-00157.arrow"
362
+ },
363
+ {
364
+ "filename": "data-00120-of-00157.arrow"
365
+ },
366
+ {
367
+ "filename": "data-00121-of-00157.arrow"
368
+ },
369
+ {
370
+ "filename": "data-00122-of-00157.arrow"
371
+ },
372
+ {
373
+ "filename": "data-00123-of-00157.arrow"
374
+ },
375
+ {
376
+ "filename": "data-00124-of-00157.arrow"
377
+ },
378
+ {
379
+ "filename": "data-00125-of-00157.arrow"
380
+ },
381
+ {
382
+ "filename": "data-00126-of-00157.arrow"
383
+ },
384
+ {
385
+ "filename": "data-00127-of-00157.arrow"
386
+ },
387
+ {
388
+ "filename": "data-00128-of-00157.arrow"
389
+ },
390
+ {
391
+ "filename": "data-00129-of-00157.arrow"
392
+ },
393
+ {
394
+ "filename": "data-00130-of-00157.arrow"
395
+ },
396
+ {
397
+ "filename": "data-00131-of-00157.arrow"
398
+ },
399
+ {
400
+ "filename": "data-00132-of-00157.arrow"
401
+ },
402
+ {
403
+ "filename": "data-00133-of-00157.arrow"
404
+ },
405
+ {
406
+ "filename": "data-00134-of-00157.arrow"
407
+ },
408
+ {
409
+ "filename": "data-00135-of-00157.arrow"
410
+ },
411
+ {
412
+ "filename": "data-00136-of-00157.arrow"
413
+ },
414
+ {
415
+ "filename": "data-00137-of-00157.arrow"
416
+ },
417
+ {
418
+ "filename": "data-00138-of-00157.arrow"
419
+ },
420
+ {
421
+ "filename": "data-00139-of-00157.arrow"
422
+ },
423
+ {
424
+ "filename": "data-00140-of-00157.arrow"
425
+ },
426
+ {
427
+ "filename": "data-00141-of-00157.arrow"
428
+ },
429
+ {
430
+ "filename": "data-00142-of-00157.arrow"
431
+ },
432
+ {
433
+ "filename": "data-00143-of-00157.arrow"
434
+ },
435
+ {
436
+ "filename": "data-00144-of-00157.arrow"
437
+ },
438
+ {
439
+ "filename": "data-00145-of-00157.arrow"
440
+ },
441
+ {
442
+ "filename": "data-00146-of-00157.arrow"
443
+ },
444
+ {
445
+ "filename": "data-00147-of-00157.arrow"
446
+ },
447
+ {
448
+ "filename": "data-00148-of-00157.arrow"
449
+ },
450
+ {
451
+ "filename": "data-00149-of-00157.arrow"
452
+ },
453
+ {
454
+ "filename": "data-00150-of-00157.arrow"
455
+ },
456
+ {
457
+ "filename": "data-00151-of-00157.arrow"
458
+ },
459
+ {
460
+ "filename": "data-00152-of-00157.arrow"
461
+ },
462
+ {
463
+ "filename": "data-00153-of-00157.arrow"
464
+ },
465
+ {
466
+ "filename": "data-00154-of-00157.arrow"
467
+ },
468
+ {
469
+ "filename": "data-00155-of-00157.arrow"
470
+ },
471
+ {
472
+ "filename": "data-00156-of-00157.arrow"
473
+ }
474
+ ],
475
+ "_fingerprint": "207c715a3e2e112c",
476
+ "_format_columns": [
477
+ "embeddings"
478
+ ],
479
+ "_format_kwargs": {},
480
+ "_format_type": "numpy",
481
+ "_output_all_columns": true,
482
+ "_split": "train"
483
+ }