{"adoption": {"forks": 234, "observed_at": "2026-08-28T04:08:03.436517+00:00", "stars": 3411}, "canonical_url": "https://ross.abutalabs.com/products/llmdatahub", "card": {"archived": false, "artifact_type": "dataset", "description": "A quick guide (especially) for trending instruction finetuning datasets ", "domain": ["large-language-models", "machine-learning", "chatbots", "awesome-lists"], "enriched": true, "function": ["machine-learning", "llm-training", "data-science"], "health_score": 20, "homepage": null, "language": null, "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["Zjh-819/LLMDataHub"], "name": "Zjh-819/LLMDataHub", "platform": ["cross-platform"], "pushed_at": "2023-11-28T09:41:28+00:00", "repo": "Zjh-819/LLMDataHub", "stars": 3411, "tags": ["awesome-list", "instruction-tuning", "sft", "rlhf", "pretraining", "multimodal", "curated-list", "finetuning-datasets", "natural-language-processing"], "topics": ["chatbot", "dataset", "llm", "chatgpt"], "urls": [], "use_cases": ["find instruction finetuning datasets for llm training", "curated list of sft datasets for chatbot training", "where to get rlhf preference data", "pretraining corpora for open-source llms", "multimodal training datasets for vision-language models", "compare chatbot finetuning datasets by size and language"], "what_it_is": "A curated catalog (awesome list) of open-source datasets for training large language models, covering alignment/SFT, domain-specific, pretraining, and multimodal corpora. Each entry includes links, size, language, usage type tags, and brief descriptions.", "when_to_avoid": ["you need the actual dataset files or download tooling rather than links", "you want code or scripts for training, not a reference list", "you need guaranteed dataset quality evaluation rather than brief descriptions"], "when_to_choose": ["you need to discover and compare open LLM training datasets before finetuning", "you want a regularly updated index of alignment, pretraining, and multimodal corpora", "you are researching dataset options for chatbot or instruction-following models"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/llmdatahub", "repo": "Zjh-819/LLMDataHub", "role": "main", "score": 30}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:03.436517+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:38:30.687716+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a81b41dca9fb49c42904b7cede2ec36b73dfa663b4ae786ed3f463b964d3c25", "fetched_at": "2026-08-28T04:08:03.436517+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zjh-819/LLMDataHub"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:03.436517+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:38:30.687716+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a81b41dca9fb49c42904b7cede2ec36b73dfa663b4ae786ed3f463b964d3c25", "fetched_at": "2026-08-28T04:08:03.436517+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zjh-819/LLMDataHub"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:38:30.687716+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a81b41dca9fb49c42904b7cede2ec36b73dfa663b4ae786ed3f463b964d3c25", "fetched_at": "2026-08-28T04:08:03.436517+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zjh-819/LLMDataHub"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:03.436517+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:03.436517+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:03.436517+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:38:30.687716+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a81b41dca9fb49c42904b7cede2ec36b73dfa663b4ae786ed3f463b964d3c25", "fetched_at": "2026-08-28T04:08:03.436517+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zjh-819/LLMDataHub"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:03.436517+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:03.436517+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:38:30.687716+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a81b41dca9fb49c42904b7cede2ec36b73dfa663b4ae786ed3f463b964d3c25", "fetched_at": "2026-08-28T04:08:03.436517+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zjh-819/LLMDataHub"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:03.436517+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:03.436517+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:03.436517+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:38:30.687716+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a81b41dca9fb49c42904b7cede2ec36b73dfa663b4ae786ed3f463b964d3c25", "fetched_at": "2026-08-28T04:08:03.436517+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zjh-819/LLMDataHub"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:03.436517+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:03.436517+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:38:30.687716+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a81b41dca9fb49c42904b7cede2ec36b73dfa663b4ae786ed3f463b964d3c25", "fetched_at": "2026-08-28T04:08:03.436517+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zjh-819/LLMDataHub"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:38:30.687716+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a81b41dca9fb49c42904b7cede2ec36b73dfa663b4ae786ed3f463b964d3c25", "fetched_at": "2026-08-28T04:08:03.436517+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zjh-819/LLMDataHub"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:38:30.687716+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a81b41dca9fb49c42904b7cede2ec36b73dfa663b4ae786ed3f463b964d3c25", "fetched_at": "2026-08-28T04:08:03.436517+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zjh-819/LLMDataHub"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:38:30.687716+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a81b41dca9fb49c42904b7cede2ec36b73dfa663b4ae786ed3f463b964d3c25", "fetched_at": "2026-08-28T04:08:03.436517+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zjh-819/LLMDataHub"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 88, "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": 1241, "days_push": 1009, "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}}