Upload data-manifest.json with huggingface_hub
Browse files- data-manifest.json +43 -0
data-manifest.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": "SlayerLab/slayer-pl-8x3b",
|
| 3 |
+
"dataset_revision": "d50df04a6ad46876fa559a87cca5d3e2a96e7098",
|
| 4 |
+
"tokenizer_sha256": "0640d3bd3674d7a6e59c540d945a2ad275a12e1bcaeb6007c37a90751f9815dd",
|
| 5 |
+
"train_tokens": 100257792,
|
| 6 |
+
"val_tokens": 752314,
|
| 7 |
+
"train_sha256": "427f3145901320cb499f6a4f7e5fb0b7855f9a3c6f3f5d4d020d2d58af4b85b8",
|
| 8 |
+
"val_sha256": "cb0460fc1f9f6462687f172e362e3b342c30db93f15c5bd5ff91f7a9d4231678",
|
| 9 |
+
"components": {
|
| 10 |
+
"web": {
|
| 11 |
+
"component": "web",
|
| 12 |
+
"sha256": "5cbb6dfa3a276a30db3c2034105ffffa75cc29b767456e7d75c305f9bd7ec562",
|
| 13 |
+
"tokens": 63000319,
|
| 14 |
+
"val_tokens": 150462,
|
| 15 |
+
"documents": 59951
|
| 16 |
+
},
|
| 17 |
+
"core": {
|
| 18 |
+
"component": "core",
|
| 19 |
+
"sha256": "ea0b4b901ace3780501b02a3972f014f77ce722315476e6f93681616958e0a99",
|
| 20 |
+
"tokens": 19248201,
|
| 21 |
+
"val_tokens": 275917,
|
| 22 |
+
"documents": 1550
|
| 23 |
+
},
|
| 24 |
+
"legal": {
|
| 25 |
+
"component": "legal",
|
| 26 |
+
"sha256": "6d4cc2f604d76452cd7e7ea52d1a04826f5e44f09bb035ba0853232fe373e74a",
|
| 27 |
+
"tokens": 8014804,
|
| 28 |
+
"val_tokens": 175506,
|
| 29 |
+
"documents": 1530
|
| 30 |
+
},
|
| 31 |
+
"en": {
|
| 32 |
+
"component": "en",
|
| 33 |
+
"sha256": "f3d451b7a202d7748a598c6c958c38cbd42bfc981c8d2fcbc3cdd721276b935a",
|
| 34 |
+
"tokens": 10005866,
|
| 35 |
+
"val_tokens": 150429,
|
| 36 |
+
"documents": 8550
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"masking": "Email addresses and 9 digit phone patterns only. No guarantee of complete personal-data redaction.",
|
| 40 |
+
"licenses": "Permissive web, core, legal and English partitions; share-alike partitions excluded.",
|
| 41 |
+
"seed": 20261023,
|
| 42 |
+
"order": "document-hash holdout, 4096-token blocks shuffled, EOS 0 between documents"
|
| 43 |
+
}
|