{ "ScaleQuest_Math_train_1m.jsonl": 466580477, "smoltalk_1100k.jsonl": 867431700, "opc-sft-stage2-436k.jsonl": 255362659, "sciRIFF_4096_70k.jsonl": 84761820, "Table-GPT_train_13k.jsonl": 11589982, "tulu-3-sft-mixture_train_939k.jsonl": 637217331 }