lhoestq HF Staff commited on
Commit
908f490
·
verified ·
1 Parent(s): 1cc76ba

Sync catalog metadata

Browse files
BAAI/Infinity-Instruct/metadata/345da5df-8342-4ca2-9264-a547ac2b95e8.avro ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75270497fe260b19a1380a5fa5ce1afe297b3deab17a1039ad5f7c73d1aa41d6
3
+ size 30599
BAAI/Infinity-Instruct/metadata/snap-1-0-d874c5a0-3bcc-448b-8f32-a7509ea9185c.avro ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:594497097690bbc62a9a383a49869c32f89b71f8ab9c37dc6bf9ae984136f2dd
3
+ size 1787
BAAI/Infinity-Instruct/metadata/v1.metadata.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "location": "hf://spaces/lhoestq/tmp-faceberg-oauth/BAAI/Infinity-Instruct",
3
+ "table-uuid": "853ce067-a79c-42a4-9502-c4d43f926073",
4
+ "last-updated-ms": 1719266483,
5
+ "last-column-id": 18,
6
+ "schemas": [
7
+ {
8
+ "type": "struct",
9
+ "fields": [
10
+ {
11
+ "id": 1,
12
+ "name": "split",
13
+ "type": "string",
14
+ "required": false
15
+ },
16
+ {
17
+ "id": 2,
18
+ "name": "id",
19
+ "type": "long",
20
+ "required": false
21
+ },
22
+ {
23
+ "id": 3,
24
+ "name": "conversations",
25
+ "type": {
26
+ "type": "list",
27
+ "element-id": 8,
28
+ "element": {
29
+ "type": "struct",
30
+ "fields": [
31
+ {
32
+ "id": 9,
33
+ "name": "from",
34
+ "type": "string",
35
+ "required": false
36
+ },
37
+ {
38
+ "id": 10,
39
+ "name": "value",
40
+ "type": "string",
41
+ "required": false
42
+ }
43
+ ]
44
+ },
45
+ "element-required": false
46
+ },
47
+ "required": false
48
+ },
49
+ {
50
+ "id": 4,
51
+ "name": "label",
52
+ "type": {
53
+ "type": "struct",
54
+ "fields": [
55
+ {
56
+ "id": 11,
57
+ "name": "ability_en",
58
+ "type": {
59
+ "type": "list",
60
+ "element-id": 15,
61
+ "element": "string",
62
+ "element-required": false
63
+ },
64
+ "required": false
65
+ },
66
+ {
67
+ "id": 12,
68
+ "name": "ability_zh",
69
+ "type": {
70
+ "type": "list",
71
+ "element-id": 16,
72
+ "element": "string",
73
+ "element-required": false
74
+ },
75
+ "required": false
76
+ },
77
+ {
78
+ "id": 13,
79
+ "name": "cate_ability_en",
80
+ "type": {
81
+ "type": "list",
82
+ "element-id": 17,
83
+ "element": "string",
84
+ "element-required": false
85
+ },
86
+ "required": false
87
+ },
88
+ {
89
+ "id": 14,
90
+ "name": "cate_ability_zh",
91
+ "type": {
92
+ "type": "list",
93
+ "element-id": 18,
94
+ "element": "string",
95
+ "element-required": false
96
+ },
97
+ "required": false
98
+ }
99
+ ]
100
+ },
101
+ "required": false
102
+ },
103
+ {
104
+ "id": 5,
105
+ "name": "langdetect",
106
+ "type": "string",
107
+ "required": false
108
+ },
109
+ {
110
+ "id": 6,
111
+ "name": "source",
112
+ "type": "string",
113
+ "required": false
114
+ },
115
+ {
116
+ "id": 7,
117
+ "name": "reward",
118
+ "type": "double",
119
+ "required": false
120
+ }
121
+ ],
122
+ "schema-id": 0,
123
+ "identifier-field-ids": []
124
+ }
125
+ ],
126
+ "current-schema-id": 0,
127
+ "partition-specs": [
128
+ {
129
+ "spec-id": 0,
130
+ "fields": [
131
+ {
132
+ "source-id": 1,
133
+ "field-id": 1000,
134
+ "transform": "identity",
135
+ "name": "split"
136
+ }
137
+ ]
138
+ }
139
+ ],
140
+ "default-spec-id": 0,
141
+ "last-partition-id": 1000,
142
+ "properties": {
143
+ "write.parquet.compression-codec": "snappy",
144
+ "write.py-location-provider.impl": "faceberg.catalog.HfLocationProvider",
145
+ "write.data.path": "hf://datasets/BAAI/Infinity-Instruct/7M",
146
+ "hf.dataset.repo": "BAAI/Infinity-Instruct",
147
+ "hf.dataset.config": "7M",
148
+ "hf.dataset.revision": "bddc39a8feadbd679c30623197f4e736b7e75b48",
149
+ "hf.write.pattern": "{split}-{uuid}-iceberg.parquet",
150
+ "hf.write.split": "train",
151
+ "schema.name-mapping.default": "[{\"names\":[\"split\"],\"field-id\":1},{\"names\":[\"id\"],\"field-id\":2},{\"names\":[\"conversations\"],\"field-id\":3,\"fields\":[{\"names\":[\"element\"],\"field-id\":8,\"fields\":[{\"names\":[\"from\"],\"field-id\":9},{\"names\":[\"value\"],\"field-id\":10}]}]},{\"names\":[\"label\"],\"field-id\":4,\"fields\":[{\"names\":[\"ability_en\"],\"field-id\":11,\"fields\":[{\"names\":[\"element\"],\"field-id\":15}]},{\"names\":[\"ability_zh\"],\"field-id\":12,\"fields\":[{\"names\":[\"element\"],\"field-id\":16}]},{\"names\":[\"cate_ability_en\"],\"field-id\":13,\"fields\":[{\"names\":[\"element\"],\"field-id\":17}]},{\"names\":[\"cate_ability_zh\"],\"field-id\":14,\"fields\":[{\"names\":[\"element\"],\"field-id\":18}]}]},{\"names\":[\"langdetect\"],\"field-id\":5},{\"names\":[\"source\"],\"field-id\":6},{\"names\":[\"reward\"],\"field-id\":7}]"
152
+ },
153
+ "current-snapshot-id": 1,
154
+ "snapshots": [
155
+ {
156
+ "snapshot-id": 1,
157
+ "sequence-number": 0,
158
+ "timestamp-ms": 1719266483,
159
+ "manifest-list": "hf://spaces/lhoestq/tmp-faceberg-oauth/BAAI/Infinity-Instruct/metadata/snap-1-0-d874c5a0-3bcc-448b-8f32-a7509ea9185c.avro",
160
+ "summary": {
161
+ "operation": "append",
162
+ "added-files-size": "6054384489",
163
+ "added-data-files": "75",
164
+ "added-records": "7449106",
165
+ "changed-partition-count": "1",
166
+ "total-data-files": "75",
167
+ "total-delete-files": "0",
168
+ "total-records": "7449106",
169
+ "total-files-size": "6054384489",
170
+ "total-position-deletes": "0",
171
+ "total-equality-deletes": "0"
172
+ },
173
+ "schema-id": 0
174
+ }
175
+ ],
176
+ "snapshot-log": [],
177
+ "metadata-log": [],
178
+ "sort-orders": [
179
+ {
180
+ "order-id": 0,
181
+ "fields": []
182
+ }
183
+ ],
184
+ "default-sort-order-id": 0,
185
+ "refs": {
186
+ "main": {
187
+ "snapshot-id": 1,
188
+ "type": "branch"
189
+ }
190
+ },
191
+ "statistics": [],
192
+ "partition-statistics": [],
193
+ "format-version": 2,
194
+ "last-sequence-number": 0
195
+ }
BAAI/Infinity-Instruct/metadata/version-hint.text ADDED
@@ -0,0 +1 @@
 
 
1
+ 1
faceberg.yml CHANGED
@@ -1 +1,5 @@
1
- {}
 
 
 
 
 
1
+ BAAI:
2
+ Infinity-Instruct:
3
+ type: dataset
4
+ repo: BAAI/Infinity-Instruct
5
+ config: 7M