{"adoption": {"forks": 55, "observed_at": "2026-08-28T04:03:47.596984+00:00", "stars": 1154}, "canonical_url": "https://ross.abutalabs.com/products/awesome-instruction-dataset", "card": {"archived": false, "artifact_type": "dataset", "description": "A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)", "domain": ["large-language-models", "machine-learning", "artificial-intelligence", "awesome-lists"], "enriched": true, "function": ["machine-learning", "llm-training", "data-science"], "health_score": 20, "homepage": null, "language": null, "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["yaodongC/awesome-instruction-dataset"], "name": "yaodongC/awesome-instruction-dataset", "platform": ["cross-platform"], "pushed_at": "2024-01-04T21:14:59+00:00", "repo": "yaodongC/awesome-instruction-dataset", "stars": 1154, "tags": ["instruction-tuning", "rlhf", "llm-datasets", "awesome-list", "multimodal", "fine-tuning", "chat-models"], "topics": ["llama", "awsome-lists", "datasets", "gpt-3", "gpt-4", "instruction-following", "instruction-tuning", "language-model"], "urls": [], "use_cases": ["find open datasets to fine-tune an instruction-following LLM", "locate RLHF and red-teaming datasets for chat model training", "compare instruction tuning datasets by size and language", "find multimodal image-instruction-answer datasets for vision-language models", "source training data for building an Alpaca or LLaMA-style model"], "what_it_is": "A curated awesome-list of open-source instruction tuning datasets for training text and multimodal instruction-following LLMs like ChatGPT, LLaMA, and Alpaca. It catalogs datasets with size, language, task, and generation-method tags, including visual instruction tuning and RLHF/red-teaming datasets.", "when_to_avoid": ["you need the datasets themselves rather than links to them", "you want actively maintained, up-to-date dataset listings", "you need a tool or library for dataset processing rather than a catalog"], "when_to_choose": ["you need a curated index of instruction tuning and RLHF datasets", "you are training or fine-tuning a chat LLM and want training data options", "you want both text and visual instruction datasets in one place"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/awesome-instruction-dataset", "repo": "yaodongC/awesome-instruction-dataset", "role": "main", "score": 30}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.596984+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:33:24.427506+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e7f452b1e5b5190dc41c42588d0272a4bfcf088cdb7fc93c3690816c11a7a45", "fetched_at": "2026-08-28T04:03:47.596984+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yaodongC/awesome-instruction-dataset"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.596984+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:33:24.427506+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e7f452b1e5b5190dc41c42588d0272a4bfcf088cdb7fc93c3690816c11a7a45", "fetched_at": "2026-08-28T04:03:47.596984+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yaodongC/awesome-instruction-dataset"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:33:24.427506+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e7f452b1e5b5190dc41c42588d0272a4bfcf088cdb7fc93c3690816c11a7a45", "fetched_at": "2026-08-28T04:03:47.596984+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yaodongC/awesome-instruction-dataset"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.596984+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.596984+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.596984+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:33:24.427506+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e7f452b1e5b5190dc41c42588d0272a4bfcf088cdb7fc93c3690816c11a7a45", "fetched_at": "2026-08-28T04:03:47.596984+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yaodongC/awesome-instruction-dataset"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.596984+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.596984+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:33:24.427506+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e7f452b1e5b5190dc41c42588d0272a4bfcf088cdb7fc93c3690816c11a7a45", "fetched_at": "2026-08-28T04:03:47.596984+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yaodongC/awesome-instruction-dataset"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.596984+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.596984+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.596984+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:33:24.427506+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e7f452b1e5b5190dc41c42588d0272a4bfcf088cdb7fc93c3690816c11a7a45", "fetched_at": "2026-08-28T04:03:47.596984+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yaodongC/awesome-instruction-dataset"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.596984+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.596984+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:33:24.427506+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e7f452b1e5b5190dc41c42588d0272a4bfcf088cdb7fc93c3690816c11a7a45", "fetched_at": "2026-08-28T04:03:47.596984+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yaodongC/awesome-instruction-dataset"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:33:24.427506+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e7f452b1e5b5190dc41c42588d0272a4bfcf088cdb7fc93c3690816c11a7a45", "fetched_at": "2026-08-28T04:03:47.596984+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yaodongC/awesome-instruction-dataset"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:33:24.427506+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e7f452b1e5b5190dc41c42588d0272a4bfcf088cdb7fc93c3690816c11a7a45", "fetched_at": "2026-08-28T04:03:47.596984+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yaodongC/awesome-instruction-dataset"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:33:24.427506+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e7f452b1e5b5190dc41c42588d0272a4bfcf088cdb7fc93c3690816c11a7a45", "fetched_at": "2026-08-28T04:03:47.596984+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yaodongC/awesome-instruction-dataset"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 89, "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": 1253, "days_push": 972, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 30, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}