{"adoption": {"forks": 160, "observed_at": "2026-08-28T04:05:04.960571+00:00", "stars": 1567}, "canonical_url": "https://ross.abutalabs.com/products/google-research-flan", "card": {"archived": false, "artifact_type": "dataset", "description": null, "domain": ["large-language-models", "machine-learning", "artificial-intelligence"], "enriched": true, "function": ["machine-learning", "llm-training", "data-generation", "etl"], "health_score": 74, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "stable", "member_repos": ["google-research/FLAN"], "name": "google-research/FLAN", "platform": ["python"], "pushed_at": "2026-07-02T11:25:30+00:00", "repo": "google-research/FLAN", "stars": 1567, "tags": ["instruction-tuning", "flan", "seqio", "dataset-generation", "research", "google-research", "zero-shot-learning", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["generate instruction tuning data for fine-tuning LLMs", "reproduce the Flan 2021 SeqIO mixtures", "build the Flan Collection for training models like Flan-T5", "research zero-shot generalization of finetuned language models", "mix diverse NLP task datasets for prompt-based training"], "what_it_is": "Google Research's repository for generating the FLAN instruction tuning dataset collections, including the original Flan 2021 and the expanded Flan Collection used to train Flan-T5 and Flan-PaLM. It provides Python/SeqIO code to produce instruction tuning mixtures from many NLP tasks.", "when_to_avoid": ["you want a ready-to-download dataset rather than generation code", "you need a general-purpose ML framework unrelated to instruction tuning", "you want inference or serving tools for Flan models"], "when_to_choose": ["you need the canonical FLAN instruction tuning datasets for LLM training", "you use SeqIO/T5X and want reproducible Flan mixtures", "you are researching instruction tuning or zero-shot prompting"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/google-research-flan", "repo": "google-research/FLAN", "role": "main", "score": 73}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:04.960571+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:59:00.395141+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "38a12f7b33784ebcf385436fa9a592074c3ba8d7eaacacf28e6a682786988273", "fetched_at": "2026-08-28T04:05:04.960571+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research/FLAN"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:04.960571+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:59:00.395141+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "38a12f7b33784ebcf385436fa9a592074c3ba8d7eaacacf28e6a682786988273", "fetched_at": "2026-08-28T04:05:04.960571+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research/FLAN"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:59:00.395141+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "38a12f7b33784ebcf385436fa9a592074c3ba8d7eaacacf28e6a682786988273", "fetched_at": "2026-08-28T04:05:04.960571+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research/FLAN"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:04.960571+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:04.960571+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:04.960571+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:59:00.395141+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "38a12f7b33784ebcf385436fa9a592074c3ba8d7eaacacf28e6a682786988273", "fetched_at": "2026-08-28T04:05:04.960571+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research/FLAN"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:04.960571+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:04.960571+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:59:00.395141+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "38a12f7b33784ebcf385436fa9a592074c3ba8d7eaacacf28e6a682786988273", "fetched_at": "2026-08-28T04:05:04.960571+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research/FLAN"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:04.960571+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:04.960571+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:04.960571+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:59:00.395141+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "38a12f7b33784ebcf385436fa9a592074c3ba8d7eaacacf28e6a682786988273", "fetched_at": "2026-08-28T04:05:04.960571+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research/FLAN"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:04.960571+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:04.960571+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:59:00.395141+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "38a12f7b33784ebcf385436fa9a592074c3ba8d7eaacacf28e6a682786988273", "fetched_at": "2026-08-28T04:05:04.960571+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research/FLAN"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:59:00.395141+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "38a12f7b33784ebcf385436fa9a592074c3ba8d7eaacacf28e6a682786988273", "fetched_at": "2026-08-28T04:05:04.960571+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research/FLAN"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:59:00.395141+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "38a12f7b33784ebcf385436fa9a592074c3ba8d7eaacacf28e6a682786988273", "fetched_at": "2026-08-28T04:05:04.960571+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research/FLAN"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:59:00.395141+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "38a12f7b33784ebcf385436fa9a592074c3ba8d7eaacacf28e6a682786988273", "fetched_at": "2026-08-28T04:05:04.960571+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research/FLAN"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 90, "longevity": 100, "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": 1838, "days_push": 62, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 73, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}