{"adoption": {"forks": 147, "observed_at": "2026-08-28T04:04:50.830048+00:00", "stars": 1480}, "canonical_url": "https://ross.abutalabs.com/products/awesome-llms-datasets", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Summarize existing representative LLMs text datasets.", "domain": ["large-language-models", "tutorials"], "enriched": true, "function": ["documentation", "data-science"], "health_score": 63, "homepage": null, "language": null, "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["lmmlzn/Awesome-LLMs-Datasets"], "name": "lmmlzn/Awesome-LLMs-Datasets", "platform": [], "pushed_at": "2026-03-11T03:47:03+00:00", "repo": "lmmlzn/Awesome-LLMs-Datasets", "stars": 1480, "tags": ["awesome-list", "llm-datasets", "survey", "curated-list", "research", "natural-language-processing", "datasets", "web-server"], "topics": [], "urls": [], "use_cases": ["find pre-training corpora for training an LLM", "discover instruction fine-tuning datasets", "find preference datasets for RLHF", "locate evaluation benchmarks for LLMs", "find RAG training datasets", "survey of LLM datasets for research paper"], "what_it_is": "A curated awesome-list summarizing representative text datasets for large language models across pre-training, instruction fine-tuning, preference, evaluation, and traditional NLP dimensions, with newer sections for multimodal and RAG datasets. It accompanies the survey paper 'Datasets for Large Language Models: A Comprehensive Survey' and is regularly updated.", "when_to_avoid": ["you need the datasets themselves rather than references to them", "you need detailed per-dataset metadata, which since 2025 is only summarized with pointers to papers", "you need multimodal dataset coverage beyond the gradually updated sections"], "when_to_choose": ["you need a comprehensive, categorized index of LLM text datasets", "you want links to papers and dataset details across many languages and domains", "you want a maintained list tied to a peer-reviewed survey"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/awesome-llms-datasets", "repo": "lmmlzn/Awesome-LLMs-Datasets", "role": "main", "score": 58}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:50.830048+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:34:15.496450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9f067a7faeb742ac50c23cbbd3b09927f7c5d2b114bcedd06ffd76c390d8b85", "fetched_at": "2026-08-28T04:04:50.830048+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lmmlzn/Awesome-LLMs-Datasets"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:50.830048+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:34:15.496450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9f067a7faeb742ac50c23cbbd3b09927f7c5d2b114bcedd06ffd76c390d8b85", "fetched_at": "2026-08-28T04:04:50.830048+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lmmlzn/Awesome-LLMs-Datasets"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:34:15.496450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9f067a7faeb742ac50c23cbbd3b09927f7c5d2b114bcedd06ffd76c390d8b85", "fetched_at": "2026-08-28T04:04:50.830048+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lmmlzn/Awesome-LLMs-Datasets"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:50.830048+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:50.830048+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:50.830048+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:34:15.496450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9f067a7faeb742ac50c23cbbd3b09927f7c5d2b114bcedd06ffd76c390d8b85", "fetched_at": "2026-08-28T04:04:50.830048+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lmmlzn/Awesome-LLMs-Datasets"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:50.830048+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:50.830048+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:34:15.496450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9f067a7faeb742ac50c23cbbd3b09927f7c5d2b114bcedd06ffd76c390d8b85", "fetched_at": "2026-08-28T04:04:50.830048+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lmmlzn/Awesome-LLMs-Datasets"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:50.830048+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:50.830048+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:50.830048+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:34:15.496450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9f067a7faeb742ac50c23cbbd3b09927f7c5d2b114bcedd06ffd76c390d8b85", "fetched_at": "2026-08-28T04:04:50.830048+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lmmlzn/Awesome-LLMs-Datasets"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:50.830048+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:50.830048+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:34:15.496450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9f067a7faeb742ac50c23cbbd3b09927f7c5d2b114bcedd06ffd76c390d8b85", "fetched_at": "2026-08-28T04:04:50.830048+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lmmlzn/Awesome-LLMs-Datasets"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:34:15.496450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9f067a7faeb742ac50c23cbbd3b09927f7c5d2b114bcedd06ffd76c390d8b85", "fetched_at": "2026-08-28T04:04:50.830048+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lmmlzn/Awesome-LLMs-Datasets"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:34:15.496450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9f067a7faeb742ac50c23cbbd3b09927f7c5d2b114bcedd06ffd76c390d8b85", "fetched_at": "2026-08-28T04:04:50.830048+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lmmlzn/Awesome-LLMs-Datasets"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:34:15.496450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9f067a7faeb742ac50c23cbbd3b09927f7c5d2b114bcedd06ffd76c390d8b85", "fetched_at": "2026-08-28T04:04:50.830048+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lmmlzn/Awesome-LLMs-Datasets"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 71, "longevity": 68, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 959, "days_push": 175, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 58, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}