{"adoption": {"forks": 394, "observed_at": "2026-08-28T04:08:58.839329+00:00", "stars": 4757}, "canonical_url": "https://ross.abutalabs.com/products/llm-datasets", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Curated list of datasets and tools for post-training.", "domain": ["large-language-models", "machine-learning", "artificial-intelligence", "awesome-lists", "tutorials"], "enriched": true, "function": ["llm-training", "data-science", "etl"], "health_score": 68, "homepage": "https://mlabonne.github.io/blog", "language": null, "license": null, "license_family": "other", "maturity": "active", "member_repos": ["mlabonne/llm-datasets"], "name": "mlabonne/llm-datasets", "platform": ["cross-platform"], "pushed_at": "2026-04-29T18:17:40+00:00", "repo": "mlabonne/llm-datasets", "stars": 4757, "tags": ["curated-list", "datasets", "post-training", "fine-tuning", "sft", "instruction-datasets", "llm"], "topics": ["data", "dataset", "llm"], "urls": [], "use_cases": ["find datasets for fine-tuning an LLM", "curated list of instruction tuning datasets", "datasets for supervised fine-tuning of language models", "post-training data for LLMs", "where to get SFT training data", "reasoning datasets with verified traces", "compare open LLM training datasets"], "what_it_is": "A curated list of datasets and tools for post-training large language models, covering supervised fine-tuning, preference, and reasoning datasets. It catalogs permissively licensed instruction datasets with metadata like sample counts, thinking traces, and licensing notes.", "when_to_avoid": ["you need a tool that generates or processes datasets rather than a list of them", "you want pre-trained models or inference tooling instead of training data", "you need a formal benchmark rather than a curated catalog"], "when_to_choose": ["you are selecting training data for fine-tuning or post-training an LLM", "you want a regularly updated catalog of permissively licensed instruction datasets", "you need guidance on what makes a high-quality LLM dataset"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/llm-datasets", "repo": "mlabonne/llm-datasets", "role": "main", "score": 60}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:58.839329+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:18:52.717164+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31a176059a5d836c29b4238c8db132baeffaef7b9267467aa7de6b8f2de1968b", "fetched_at": "2026-08-28T04:08:58.839329+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mlabonne/llm-datasets"}, {"content_hash": "4fd183164a7863e88ad8af4467a2a8ffca99481827689fb58da5dfbc88f2ac61", "fetched_at": "2026-08-29T09:02:41.261504+00:00", "kind": "homepage", "missing": false, "url": "https://mlabonne.github.io/blog"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:58.839329+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:18:52.717164+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31a176059a5d836c29b4238c8db132baeffaef7b9267467aa7de6b8f2de1968b", "fetched_at": "2026-08-28T04:08:58.839329+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mlabonne/llm-datasets"}, {"content_hash": "4fd183164a7863e88ad8af4467a2a8ffca99481827689fb58da5dfbc88f2ac61", "fetched_at": "2026-08-29T09:02:41.261504+00:00", "kind": "homepage", "missing": false, "url": "https://mlabonne.github.io/blog"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:18:52.717164+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31a176059a5d836c29b4238c8db132baeffaef7b9267467aa7de6b8f2de1968b", "fetched_at": "2026-08-28T04:08:58.839329+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mlabonne/llm-datasets"}, {"content_hash": "4fd183164a7863e88ad8af4467a2a8ffca99481827689fb58da5dfbc88f2ac61", "fetched_at": "2026-08-29T09:02:41.261504+00:00", "kind": "homepage", "missing": false, "url": "https://mlabonne.github.io/blog"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:58.839329+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:58.839329+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:58.839329+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:18:52.717164+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31a176059a5d836c29b4238c8db132baeffaef7b9267467aa7de6b8f2de1968b", "fetched_at": "2026-08-28T04:08:58.839329+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mlabonne/llm-datasets"}, {"content_hash": "4fd183164a7863e88ad8af4467a2a8ffca99481827689fb58da5dfbc88f2ac61", "fetched_at": "2026-08-29T09:02:41.261504+00:00", "kind": "homepage", "missing": false, "url": "https://mlabonne.github.io/blog"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:58.839329+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:58.839329+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:18:52.717164+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31a176059a5d836c29b4238c8db132baeffaef7b9267467aa7de6b8f2de1968b", "fetched_at": "2026-08-28T04:08:58.839329+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mlabonne/llm-datasets"}, {"content_hash": "4fd183164a7863e88ad8af4467a2a8ffca99481827689fb58da5dfbc88f2ac61", "fetched_at": "2026-08-29T09:02:41.261504+00:00", "kind": "homepage", "missing": false, "url": "https://mlabonne.github.io/blog"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:58.839329+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:58.839329+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:58.839329+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:18:52.717164+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31a176059a5d836c29b4238c8db132baeffaef7b9267467aa7de6b8f2de1968b", "fetched_at": "2026-08-28T04:08:58.839329+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mlabonne/llm-datasets"}, {"content_hash": "4fd183164a7863e88ad8af4467a2a8ffca99481827689fb58da5dfbc88f2ac61", "fetched_at": "2026-08-29T09:02:41.261504+00:00", "kind": "homepage", "missing": false, "url": "https://mlabonne.github.io/blog"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:58.839329+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:58.839329+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:18:52.717164+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31a176059a5d836c29b4238c8db132baeffaef7b9267467aa7de6b8f2de1968b", "fetched_at": "2026-08-28T04:08:58.839329+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mlabonne/llm-datasets"}, {"content_hash": "4fd183164a7863e88ad8af4467a2a8ffca99481827689fb58da5dfbc88f2ac61", "fetched_at": "2026-08-29T09:02:41.261504+00:00", "kind": "homepage", "missing": false, "url": "https://mlabonne.github.io/blog"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:18:52.717164+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31a176059a5d836c29b4238c8db132baeffaef7b9267467aa7de6b8f2de1968b", "fetched_at": "2026-08-28T04:08:58.839329+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mlabonne/llm-datasets"}, {"content_hash": "4fd183164a7863e88ad8af4467a2a8ffca99481827689fb58da5dfbc88f2ac61", "fetched_at": "2026-08-29T09:02:41.261504+00:00", "kind": "homepage", "missing": false, "url": "https://mlabonne.github.io/blog"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:18:52.717164+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31a176059a5d836c29b4238c8db132baeffaef7b9267467aa7de6b8f2de1968b", "fetched_at": "2026-08-28T04:08:58.839329+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mlabonne/llm-datasets"}, {"content_hash": "4fd183164a7863e88ad8af4467a2a8ffca99481827689fb58da5dfbc88f2ac61", "fetched_at": "2026-08-29T09:02:41.261504+00:00", "kind": "homepage", "missing": false, "url": "https://mlabonne.github.io/blog"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:18:52.717164+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31a176059a5d836c29b4238c8db132baeffaef7b9267467aa7de6b8f2de1968b", "fetched_at": "2026-08-28T04:08:58.839329+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mlabonne/llm-datasets"}, {"content_hash": "4fd183164a7863e88ad8af4467a2a8ffca99481827689fb58da5dfbc88f2ac61", "fetched_at": "2026-08-29T09:02:41.261504+00:00", "kind": "homepage", "missing": false, "url": "https://mlabonne.github.io/blog"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 79, "longevity": 61, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 858, "days_push": 126, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 60, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}