{"adoption": {"forks": 374, "observed_at": "2026-08-28T04:09:04.178513+00:00", "stars": 4980}, "canonical_url": "https://ross.abutalabs.com/products/redpajama-data", "card": {"archived": false, "artifact_type": "dataset", "description": "The RedPajama-Data repository contains code for preparing large datasets for training large language models.", "domain": ["large-language-models", "machine-learning"], "enriched": true, "function": ["etl", "data-generation", "nlp", "llm-training"], "health_score": 71, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["togethercomputer/RedPajama-Data"], "name": "togethercomputer/RedPajama-Data", "platform": ["python", "cloud"], "pushed_at": "2026-06-03T16:00:12+00:00", "repo": "togethercomputer/RedPajama-Data", "stars": 4980, "tags": ["common-crawl", "llm-training-data", "data-pipeline", "deduplication", "quality-signals", "open-dataset", "data-engineering", "natural-language-processing", "docker", "linux"], "topics": [], "urls": [], "use_cases": ["build a large pretraining corpus for an LLM", "reproduce the LLaMA training dataset", "deduplicate web crawl text at scale", "compute quality signals for CommonCrawl documents", "filter multilingual web data for model training"], "what_it_is": "RedPajama-Data provides code and pipelines for building RedPajama-V2, an open dataset with over 30 trillion tokens of web text for training large language models. It processes CommonCrawl snapshots with quality signal computation and deduplication steps.", "when_to_avoid": ["you need a small curated dataset rather than web-scale crawl data", "you lack the storage and compute to process terabytes of CommonCrawl data", "you only need inference tooling rather than training data preparation"], "when_to_choose": ["you need a massive open web-scale corpus for LLM pretraining", "you want reproducible pipelines for cleaning and deduplicating CommonCrawl data", "you need quality annotations to filter training documents"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/redpajama-data", "repo": "togethercomputer/RedPajama-Data", "role": "main", "score": 68}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.178513+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:17:42.262016+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "63b166f0506bdeb91ad4d072f1b923267669cf9c95eea193af18f1f2760e5621", "fetched_at": "2026-08-28T04:09:04.178513+00:00", "kind": "readme", "missing": false, "url": "https://github.com/togethercomputer/RedPajama-Data"}, {"content_hash": "a1b4b8c744d1074dd4b023301f488d53f7f93e66a7fa271ba42d37ad2d896b70", "fetched_at": "2026-08-29T08:58:48.699984+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/redpajama-data/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.178513+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:17:42.262016+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "63b166f0506bdeb91ad4d072f1b923267669cf9c95eea193af18f1f2760e5621", "fetched_at": "2026-08-28T04:09:04.178513+00:00", "kind": "readme", "missing": false, "url": "https://github.com/togethercomputer/RedPajama-Data"}, {"content_hash": "a1b4b8c744d1074dd4b023301f488d53f7f93e66a7fa271ba42d37ad2d896b70", "fetched_at": "2026-08-29T08:58:48.699984+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/redpajama-data/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:17:42.262016+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "63b166f0506bdeb91ad4d072f1b923267669cf9c95eea193af18f1f2760e5621", "fetched_at": "2026-08-28T04:09:04.178513+00:00", "kind": "readme", "missing": false, "url": "https://github.com/togethercomputer/RedPajama-Data"}, {"content_hash": "a1b4b8c744d1074dd4b023301f488d53f7f93e66a7fa271ba42d37ad2d896b70", "fetched_at": "2026-08-29T08:58:48.699984+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/redpajama-data/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.178513+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.178513+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.178513+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:17:42.262016+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "63b166f0506bdeb91ad4d072f1b923267669cf9c95eea193af18f1f2760e5621", "fetched_at": "2026-08-28T04:09:04.178513+00:00", "kind": "readme", "missing": false, "url": "https://github.com/togethercomputer/RedPajama-Data"}, {"content_hash": "a1b4b8c744d1074dd4b023301f488d53f7f93e66a7fa271ba42d37ad2d896b70", "fetched_at": "2026-08-29T08:58:48.699984+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/redpajama-data/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.178513+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.178513+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:17:42.262016+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "63b166f0506bdeb91ad4d072f1b923267669cf9c95eea193af18f1f2760e5621", "fetched_at": "2026-08-28T04:09:04.178513+00:00", "kind": "readme", "missing": false, "url": "https://github.com/togethercomputer/RedPajama-Data"}, {"content_hash": "a1b4b8c744d1074dd4b023301f488d53f7f93e66a7fa271ba42d37ad2d896b70", "fetched_at": "2026-08-29T08:58:48.699984+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/redpajama-data/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.178513+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.178513+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.178513+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:17:42.262016+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "63b166f0506bdeb91ad4d072f1b923267669cf9c95eea193af18f1f2760e5621", "fetched_at": "2026-08-28T04:09:04.178513+00:00", "kind": "readme", "missing": false, "url": "https://github.com/togethercomputer/RedPajama-Data"}, {"content_hash": "a1b4b8c744d1074dd4b023301f488d53f7f93e66a7fa271ba42d37ad2d896b70", "fetched_at": "2026-08-29T08:58:48.699984+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/redpajama-data/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.178513+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.178513+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:17:42.262016+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "63b166f0506bdeb91ad4d072f1b923267669cf9c95eea193af18f1f2760e5621", "fetched_at": "2026-08-28T04:09:04.178513+00:00", "kind": "readme", "missing": false, "url": "https://github.com/togethercomputer/RedPajama-Data"}, {"content_hash": "a1b4b8c744d1074dd4b023301f488d53f7f93e66a7fa271ba42d37ad2d896b70", "fetched_at": "2026-08-29T08:58:48.699984+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/redpajama-data/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:17:42.262016+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "63b166f0506bdeb91ad4d072f1b923267669cf9c95eea193af18f1f2760e5621", "fetched_at": "2026-08-28T04:09:04.178513+00:00", "kind": "readme", "missing": false, "url": "https://github.com/togethercomputer/RedPajama-Data"}, {"content_hash": "a1b4b8c744d1074dd4b023301f488d53f7f93e66a7fa271ba42d37ad2d896b70", "fetched_at": "2026-08-29T08:58:48.699984+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/redpajama-data/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:17:42.262016+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "63b166f0506bdeb91ad4d072f1b923267669cf9c95eea193af18f1f2760e5621", "fetched_at": "2026-08-28T04:09:04.178513+00:00", "kind": "readme", "missing": false, "url": "https://github.com/togethercomputer/RedPajama-Data"}, {"content_hash": "a1b4b8c744d1074dd4b023301f488d53f7f93e66a7fa271ba42d37ad2d896b70", "fetched_at": "2026-08-29T08:58:48.699984+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/redpajama-data/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:17:42.262016+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "63b166f0506bdeb91ad4d072f1b923267669cf9c95eea193af18f1f2760e5621", "fetched_at": "2026-08-28T04:09:04.178513+00:00", "kind": "readme", "missing": false, "url": "https://github.com/togethercomputer/RedPajama-Data"}, {"content_hash": "a1b4b8c744d1074dd4b023301f488d53f7f93e66a7fa271ba42d37ad2d896b70", "fetched_at": "2026-08-29T08:58:48.699984+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/redpajama-data/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 85, "longevity": 88, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1237, "days_push": 91, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 68, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}