{"adoption": {"forks": 171, "observed_at": "2026-08-28T04:04:35.912253+00:00", "stars": 1391}, "canonical_url": "https://ross.abutalabs.com/products/lm-human-preferences", "card": {"archived": true, "artifact_type": "library", "description": "Code for the paper Fine-Tuning Language Models from Human Preferences", "domain": ["large-language-models", "machine-learning", "reinforcement-learning"], "enriched": true, "function": ["machine-learning", "llm-training", "reinforcement-learning"], "health_score": 10, "homepage": "https://openai.com/blog/fine-tuning-gpt-2/", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "abandoned", "member_repos": ["openai/lm-human-preferences"], "name": "openai/lm-human-preferences", "platform": ["python"], "pushed_at": "2023-07-25T16:48:57+00:00", "repo": "openai/lm-human-preferences", "stars": 1391, "tags": ["rlhf", "reward-model", "human-preferences", "gpt-2", "research-code", "tensorflow", "archived", "research", "linux", "gpu"], "topics": [], "urls": [], "use_cases": ["reproduce the fine-tuning from human preferences paper", "train a reward model from human preference labels", "fine-tune GPT-2 with reinforcement learning from human feedback", "study early RLHF implementations", "download released human preference labels for experiments"], "what_it_is": "OpenAI's research code for the paper 'Fine-Tuning Language Models from Human Preferences', implementing reward model training from human labels and RL fine-tuning of GPT-2 language models. It is an archived repository provided as-is with no updates expected.", "when_to_avoid": ["you need a modern, maintained RLHF library (use trl or similar)", "you need to fine-tune models larger than small GPT-2", "you need up-to-date TensorFlow or GPU support", "you want production-ready training pipelines"], "when_to_choose": ["you want to study or reproduce the original 2019 RLHF research code", "you need the exact reward modeling and PPO fine-tuning setup from the paper", "you want access to the released human preference label datasets"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/lm-human-preferences", "repo": "openai/lm-human-preferences", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:35.912253+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:39:37.029986+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5ff805a00ae41c5e984dfd2ac23dafe77d4768d841ffad2c79ac451545aa9455", "fetched_at": "2026-08-28T04:04:35.912253+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/lm-human-preferences"}, {"content_hash": "3657513dae3daaf78cf3b66e4c84fd78a73e2eb7d1e659ff68887d3169f25f22", "fetched_at": "2026-08-29T11:54:43.699701+00:00", "kind": "homepage", "missing": false, "url": "https://openai.com/blog/fine-tuning-gpt-2/"}, {"content_hash": "de4b627b33e34c6378d078a5da3cbfcc942df598db166981f7cd976535c0a501", "fetched_at": "2026-08-29T11:54:43.708983+00:00", "kind": "site_page", "missing": false, "url": "https://openai.com/about"}, {"content_hash": "d617c5215f2a3c25137a2ffb371a818fc9c246fffe03713dcd7b757690335d76", "fetched_at": "2026-08-29T11:54:43.711000+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/api/docs"}, {"content_hash": "7d240c906018bf9c33351c36a70813e1afb8403553ceaca27c8029f0e671e3a7", "fetched_at": "2026-08-29T11:54:43.713277+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:35.912253+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:39:37.029986+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5ff805a00ae41c5e984dfd2ac23dafe77d4768d841ffad2c79ac451545aa9455", "fetched_at": "2026-08-28T04:04:35.912253+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/lm-human-preferences"}, {"content_hash": "3657513dae3daaf78cf3b66e4c84fd78a73e2eb7d1e659ff68887d3169f25f22", "fetched_at": "2026-08-29T11:54:43.699701+00:00", "kind": "homepage", "missing": false, "url": "https://openai.com/blog/fine-tuning-gpt-2/"}, {"content_hash": "de4b627b33e34c6378d078a5da3cbfcc942df598db166981f7cd976535c0a501", "fetched_at": "2026-08-29T11:54:43.708983+00:00", "kind": "site_page", "missing": false, "url": "https://openai.com/about"}, {"content_hash": "d617c5215f2a3c25137a2ffb371a818fc9c246fffe03713dcd7b757690335d76", "fetched_at": "2026-08-29T11:54:43.711000+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/api/docs"}, {"content_hash": "7d240c906018bf9c33351c36a70813e1afb8403553ceaca27c8029f0e671e3a7", "fetched_at": "2026-08-29T11:54:43.713277+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:39:37.029986+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5ff805a00ae41c5e984dfd2ac23dafe77d4768d841ffad2c79ac451545aa9455", "fetched_at": "2026-08-28T04:04:35.912253+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/lm-human-preferences"}, {"content_hash": "3657513dae3daaf78cf3b66e4c84fd78a73e2eb7d1e659ff68887d3169f25f22", "fetched_at": "2026-08-29T11:54:43.699701+00:00", "kind": "homepage", "missing": false, "url": "https://openai.com/blog/fine-tuning-gpt-2/"}, {"content_hash": "de4b627b33e34c6378d078a5da3cbfcc942df598db166981f7cd976535c0a501", "fetched_at": "2026-08-29T11:54:43.708983+00:00", "kind": "site_page", "missing": false, "url": "https://openai.com/about"}, {"content_hash": "d617c5215f2a3c25137a2ffb371a818fc9c246fffe03713dcd7b757690335d76", "fetched_at": "2026-08-29T11:54:43.711000+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/api/docs"}, {"content_hash": "7d240c906018bf9c33351c36a70813e1afb8403553ceaca27c8029f0e671e3a7", "fetched_at": "2026-08-29T11:54:43.713277+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:35.912253+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:35.912253+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:35.912253+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:39:37.029986+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5ff805a00ae41c5e984dfd2ac23dafe77d4768d841ffad2c79ac451545aa9455", "fetched_at": "2026-08-28T04:04:35.912253+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/lm-human-preferences"}, {"content_hash": "3657513dae3daaf78cf3b66e4c84fd78a73e2eb7d1e659ff68887d3169f25f22", "fetched_at": "2026-08-29T11:54:43.699701+00:00", "kind": "homepage", "missing": false, "url": "https://openai.com/blog/fine-tuning-gpt-2/"}, {"content_hash": "de4b627b33e34c6378d078a5da3cbfcc942df598db166981f7cd976535c0a501", "fetched_at": "2026-08-29T11:54:43.708983+00:00", "kind": "site_page", "missing": false, "url": "https://openai.com/about"}, {"content_hash": "d617c5215f2a3c25137a2ffb371a818fc9c246fffe03713dcd7b757690335d76", "fetched_at": "2026-08-29T11:54:43.711000+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/api/docs"}, {"content_hash": "7d240c906018bf9c33351c36a70813e1afb8403553ceaca27c8029f0e671e3a7", "fetched_at": "2026-08-29T11:54:43.713277+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:35.912253+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:35.912253+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:39:37.029986+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5ff805a00ae41c5e984dfd2ac23dafe77d4768d841ffad2c79ac451545aa9455", "fetched_at": "2026-08-28T04:04:35.912253+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/lm-human-preferences"}, {"content_hash": "3657513dae3daaf78cf3b66e4c84fd78a73e2eb7d1e659ff68887d3169f25f22", "fetched_at": "2026-08-29T11:54:43.699701+00:00", "kind": "homepage", "missing": false, "url": "https://openai.com/blog/fine-tuning-gpt-2/"}, {"content_hash": "de4b627b33e34c6378d078a5da3cbfcc942df598db166981f7cd976535c0a501", "fetched_at": "2026-08-29T11:54:43.708983+00:00", "kind": "site_page", "missing": false, "url": "https://openai.com/about"}, {"content_hash": "d617c5215f2a3c25137a2ffb371a818fc9c246fffe03713dcd7b757690335d76", "fetched_at": "2026-08-29T11:54:43.711000+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/api/docs"}, {"content_hash": "7d240c906018bf9c33351c36a70813e1afb8403553ceaca27c8029f0e671e3a7", "fetched_at": "2026-08-29T11:54:43.713277+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:35.912253+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:35.912253+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:35.912253+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:39:37.029986+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5ff805a00ae41c5e984dfd2ac23dafe77d4768d841ffad2c79ac451545aa9455", "fetched_at": "2026-08-28T04:04:35.912253+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/lm-human-preferences"}, {"content_hash": "3657513dae3daaf78cf3b66e4c84fd78a73e2eb7d1e659ff68887d3169f25f22", "fetched_at": "2026-08-29T11:54:43.699701+00:00", "kind": "homepage", "missing": false, "url": "https://openai.com/blog/fine-tuning-gpt-2/"}, {"content_hash": "de4b627b33e34c6378d078a5da3cbfcc942df598db166981f7cd976535c0a501", "fetched_at": "2026-08-29T11:54:43.708983+00:00", "kind": "site_page", "missing": false, "url": "https://openai.com/about"}, {"content_hash": "d617c5215f2a3c25137a2ffb371a818fc9c246fffe03713dcd7b757690335d76", "fetched_at": "2026-08-29T11:54:43.711000+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/api/docs"}, {"content_hash": "7d240c906018bf9c33351c36a70813e1afb8403553ceaca27c8029f0e671e3a7", "fetched_at": "2026-08-29T11:54:43.713277+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:35.912253+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:35.912253+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:39:37.029986+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5ff805a00ae41c5e984dfd2ac23dafe77d4768d841ffad2c79ac451545aa9455", "fetched_at": "2026-08-28T04:04:35.912253+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/lm-human-preferences"}, {"content_hash": "3657513dae3daaf78cf3b66e4c84fd78a73e2eb7d1e659ff68887d3169f25f22", "fetched_at": "2026-08-29T11:54:43.699701+00:00", "kind": "homepage", "missing": false, "url": "https://openai.com/blog/fine-tuning-gpt-2/"}, {"content_hash": "de4b627b33e34c6378d078a5da3cbfcc942df598db166981f7cd976535c0a501", "fetched_at": "2026-08-29T11:54:43.708983+00:00", "kind": "site_page", "missing": false, "url": "https://openai.com/about"}, {"content_hash": "d617c5215f2a3c25137a2ffb371a818fc9c246fffe03713dcd7b757690335d76", "fetched_at": "2026-08-29T11:54:43.711000+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/api/docs"}, {"content_hash": "7d240c906018bf9c33351c36a70813e1afb8403553ceaca27c8029f0e671e3a7", "fetched_at": "2026-08-29T11:54:43.713277+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:39:37.029986+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5ff805a00ae41c5e984dfd2ac23dafe77d4768d841ffad2c79ac451545aa9455", "fetched_at": "2026-08-28T04:04:35.912253+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/lm-human-preferences"}, {"content_hash": "3657513dae3daaf78cf3b66e4c84fd78a73e2eb7d1e659ff68887d3169f25f22", "fetched_at": "2026-08-29T11:54:43.699701+00:00", "kind": "homepage", "missing": false, "url": "https://openai.com/blog/fine-tuning-gpt-2/"}, {"content_hash": "de4b627b33e34c6378d078a5da3cbfcc942df598db166981f7cd976535c0a501", "fetched_at": "2026-08-29T11:54:43.708983+00:00", "kind": "site_page", "missing": false, "url": "https://openai.com/about"}, {"content_hash": "d617c5215f2a3c25137a2ffb371a818fc9c246fffe03713dcd7b757690335d76", "fetched_at": "2026-08-29T11:54:43.711000+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/api/docs"}, {"content_hash": "7d240c906018bf9c33351c36a70813e1afb8403553ceaca27c8029f0e671e3a7", "fetched_at": "2026-08-29T11:54:43.713277+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:39:37.029986+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5ff805a00ae41c5e984dfd2ac23dafe77d4768d841ffad2c79ac451545aa9455", "fetched_at": "2026-08-28T04:04:35.912253+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/lm-human-preferences"}, {"content_hash": "3657513dae3daaf78cf3b66e4c84fd78a73e2eb7d1e659ff68887d3169f25f22", "fetched_at": "2026-08-29T11:54:43.699701+00:00", "kind": "homepage", "missing": false, "url": "https://openai.com/blog/fine-tuning-gpt-2/"}, {"content_hash": "de4b627b33e34c6378d078a5da3cbfcc942df598db166981f7cd976535c0a501", "fetched_at": "2026-08-29T11:54:43.708983+00:00", "kind": "site_page", "missing": false, "url": "https://openai.com/about"}, {"content_hash": "d617c5215f2a3c25137a2ffb371a818fc9c246fffe03713dcd7b757690335d76", "fetched_at": "2026-08-29T11:54:43.711000+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/api/docs"}, {"content_hash": "7d240c906018bf9c33351c36a70813e1afb8403553ceaca27c8029f0e671e3a7", "fetched_at": "2026-08-29T11:54:43.713277+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:39:37.029986+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5ff805a00ae41c5e984dfd2ac23dafe77d4768d841ffad2c79ac451545aa9455", "fetched_at": "2026-08-28T04:04:35.912253+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/lm-human-preferences"}, {"content_hash": "3657513dae3daaf78cf3b66e4c84fd78a73e2eb7d1e659ff68887d3169f25f22", "fetched_at": "2026-08-29T11:54:43.699701+00:00", "kind": "homepage", "missing": false, "url": "https://openai.com/blog/fine-tuning-gpt-2/"}, {"content_hash": "de4b627b33e34c6378d078a5da3cbfcc942df598db166981f7cd976535c0a501", "fetched_at": "2026-08-29T11:54:43.708983+00:00", "kind": "site_page", "missing": false, "url": "https://openai.com/about"}, {"content_hash": "d617c5215f2a3c25137a2ffb371a818fc9c246fffe03713dcd7b757690335d76", "fetched_at": "2026-08-29T11:54:43.711000+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/api/docs"}, {"content_hash": "7d240c906018bf9c33351c36a70813e1afb8403553ceaca27c8029f0e671e3a7", "fetched_at": "2026-08-29T11:54:43.713277+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases", "archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2545, "days_push": 1135, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}