{"data":{"slug":"redpajama","etype":"dataset","name":"RedPajama","cat":"Curated Corpus","subtitle":"The open reproduction of Llama's training mix.","summary":"Together AI and partners rebuilt Meta's disclosed Llama data recipe in the open — 1.2T tokens in v1, 30T documented in v2 — giving the open ecosystem a transparent, auditable base corpus.","attrs":null,"kf":null,"aliases":["RedPajama-v2"],"ticker":null,"exchange":null,"hq":null,"founded":null,"website":null,"status":null,"region":null,"asof":"2026-01-15","sources":[{"url":"https://github.com/togethercomputer/RedPajama-Data","label":"RedPajama"}]},"meta":{"found":true,"count":1,"served_from":"site cache (no live upstream calls)","as_of":"2026-10-14T02:57:38+00:00","disclaimer":"Research and information only — not investment advice. Structured records carry basis labels (vendor spec / reported / estimate); market quotes are delayed/indicative.","attribution":"Records compiled from vendor documentation, official filings and reputable public reporting; market quotes via financial data providers. See /data-sources."}}