{ "dataset": "SlayerLab/slayer-pl-8x3b", "dataset_revision": "d50df04a6ad46876fa559a87cca5d3e2a96e7098", "tokenizer_sha256": "0640d3bd3674d7a6e59c540d945a2ad275a12e1bcaeb6007c37a90751f9815dd", "train_tokens": 100257792, "val_tokens": 752314, "train_sha256": "427f3145901320cb499f6a4f7e5fb0b7855f9a3c6f3f5d4d020d2d58af4b85b8", "val_sha256": "cb0460fc1f9f6462687f172e362e3b342c30db93f15c5bd5ff91f7a9d4231678", "components": { "web": { "component": "web", "sha256": "5cbb6dfa3a276a30db3c2034105ffffa75cc29b767456e7d75c305f9bd7ec562", "tokens": 63000319, "val_tokens": 150462, "documents": 59951 }, "core": { "component": "core", "sha256": "ea0b4b901ace3780501b02a3972f014f77ce722315476e6f93681616958e0a99", "tokens": 19248201, "val_tokens": 275917, "documents": 1550 }, "legal": { "component": "legal", "sha256": "6d4cc2f604d76452cd7e7ea52d1a04826f5e44f09bb035ba0853232fe373e74a", "tokens": 8014804, "val_tokens": 175506, "documents": 1530 }, "en": { "component": "en", "sha256": "f3d451b7a202d7748a598c6c958c38cbd42bfc981c8d2fcbc3cdd721276b935a", "tokens": 10005866, "val_tokens": 150429, "documents": 8550 } }, "masking": "Email addresses and 9 digit phone patterns only. No guarantee of complete personal-data redaction.", "licenses": "Permissive web, core, legal and English partitions; share-alike partitions excluded.", "seed": 20261023, "order": "document-hash holdout, 4096-token blocks shuffled, EOS 0 between documents" }