{"adoption": {"forks": 158, "observed_at": "2026-08-28T04:05:10.460761+00:00", "stars": 1606}, "canonical_url": "https://ross.abutalabs.com/products/alpacadatacleaned", "card": {"archived": false, "artifact_type": "dataset", "description": "Alpaca dataset from Stanford, cleaned and curated", "domain": ["large-language-models", "machine-learning"], "enriched": true, "function": ["machine-learning", "data-science", "etl"], "health_score": 63, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["gururise/AlpacaDataCleaned"], "name": "gururise/AlpacaDataCleaned", "platform": ["python"], "pushed_at": "2026-03-07T14:15:41+00:00", "repo": "gururise/AlpacaDataCleaned", "stars": 1606, "tags": ["alpaca", "llm-training-data", "instruction-tuning", "data-cleaning", "lora", "fine-tuning", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["fine-tune a llama model with cleaner instruction data", "get a better alpaca dataset than the original stanford one", "improve lora fine-tuning loss curves", "download cleaned instruction tuning data for 7b models", "compare fine-tuning datasets by benchmark results", "train an alpaca-style chatbot on curated data"], "what_it_is": "A cleaned and curated version of the Stanford Alpaca instruction-tuning dataset used to train the Alpaca LLM. It fixes quality issues in the GPT-3-generated original data and provides benchmark comparisons showing improved fine-tuning results.", "when_to_avoid": ["you need a large-scale modern instruction dataset rather than a cleaned 2023-era one", "you are not doing LLM fine-tuning", "you need multilingual instruction data"], "when_to_choose": ["you are fine-tuning LLaMA-family models with LoRA and want higher-quality instruction data", "you saw poor results or loss curves with the original Alpaca dataset", "you want benchmarked evidence that a dataset improves model performance"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/alpacadatacleaned", "repo": "gururise/AlpacaDataCleaned", "role": "main", "score": 62}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.460761+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:52:13.846408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7142eb60353c9b88b50107f355514443f99f677c21f097e0a0e61e85b82607f0", "fetched_at": "2026-08-28T04:05:10.460761+00:00", "kind": "readme", "missing": false, "url": "https://github.com/gururise/AlpacaDataCleaned"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.460761+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:52:13.846408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7142eb60353c9b88b50107f355514443f99f677c21f097e0a0e61e85b82607f0", "fetched_at": "2026-08-28T04:05:10.460761+00:00", "kind": "readme", "missing": false, "url": "https://github.com/gururise/AlpacaDataCleaned"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:52:13.846408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7142eb60353c9b88b50107f355514443f99f677c21f097e0a0e61e85b82607f0", "fetched_at": "2026-08-28T04:05:10.460761+00:00", "kind": "readme", "missing": false, "url": "https://github.com/gururise/AlpacaDataCleaned"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.460761+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.460761+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.460761+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:52:13.846408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7142eb60353c9b88b50107f355514443f99f677c21f097e0a0e61e85b82607f0", "fetched_at": "2026-08-28T04:05:10.460761+00:00", "kind": "readme", "missing": false, "url": "https://github.com/gururise/AlpacaDataCleaned"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.460761+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.460761+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:52:13.846408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7142eb60353c9b88b50107f355514443f99f677c21f097e0a0e61e85b82607f0", "fetched_at": "2026-08-28T04:05:10.460761+00:00", "kind": "readme", "missing": false, "url": "https://github.com/gururise/AlpacaDataCleaned"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.460761+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.460761+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.460761+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:52:13.846408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7142eb60353c9b88b50107f355514443f99f677c21f097e0a0e61e85b82607f0", "fetched_at": "2026-08-28T04:05:10.460761+00:00", "kind": "readme", "missing": false, "url": "https://github.com/gururise/AlpacaDataCleaned"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.460761+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.460761+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:52:13.846408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7142eb60353c9b88b50107f355514443f99f677c21f097e0a0e61e85b82607f0", "fetched_at": "2026-08-28T04:05:10.460761+00:00", "kind": "readme", "missing": false, "url": "https://github.com/gururise/AlpacaDataCleaned"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:52:13.846408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7142eb60353c9b88b50107f355514443f99f677c21f097e0a0e61e85b82607f0", "fetched_at": "2026-08-28T04:05:10.460761+00:00", "kind": "readme", "missing": false, "url": "https://github.com/gururise/AlpacaDataCleaned"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:52:13.846408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7142eb60353c9b88b50107f355514443f99f677c21f097e0a0e61e85b82607f0", "fetched_at": "2026-08-28T04:05:10.460761+00:00", "kind": "readme", "missing": false, "url": "https://github.com/gururise/AlpacaDataCleaned"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:52:13.846408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7142eb60353c9b88b50107f355514443f99f677c21f097e0a0e61e85b82607f0", "fetched_at": "2026-08-28T04:05:10.460761+00:00", "kind": "readme", "missing": false, "url": "https://github.com/gururise/AlpacaDataCleaned"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 71, "longevity": 90, "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": 1261, "days_push": 179, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 62, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}