{"adoption": {"forks": 110, "observed_at": "2026-08-28T04:05:00.663530+00:00", "stars": 1541}, "canonical_url": "https://ross.abutalabs.com/products/rlhf-reward-modeling", "card": {"archived": false, "artifact_type": "library", "description": "Recipes to train reward model for RLHF.", "domain": ["large-language-models", "reinforcement-learning", "machine-learning", "artificial-intelligence"], "enriched": true, "function": ["machine-learning", "llm-training", "deep-learning"], "health_score": 31, "homepage": "https://rlhflow.github.io/", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["RLHFlow/RLHF-Reward-Modeling"], "name": "RLHFlow/RLHF-Reward-Modeling", "platform": ["python"], "pushed_at": "2025-04-24T11:39:23+00:00", "repo": "RLHFlow/RLHF-Reward-Modeling", "stars": 1541, "tags": ["rlhf", "reward-model", "bradley-terry", "preference-model", "prm", "armorm", "rewardbench", "llama3", "gpu", "linux"], "topics": ["llm", "rlhf", "reward-models", "llama3"], "urls": [], "use_cases": ["train a bradley-terry reward model for rlhf", "train a pairwise preference model on human preference data", "build a multi-objective reward model with mixture-of-experts aggregation", "train process-supervised and outcome-supervised reward models for math", "reduce length bias in reward modeling", "reproduce state-of-the-art rewardbench results"], "what_it_is": "A collection of training recipes for reward models used in RLHF, covering Bradley-Terry reward models, pairwise preference models, ArmoRM, process/outcome-supervised math reward models, and decision-tree reward models. It provides reproducible code, data, and hyperparameters for state-of-the-art reward modeling research.", "when_to_avoid": ["you just want to run inference with an existing reward model", "you need a full end-to-end RLHF training pipeline including PPO or DPO", "you are not working with large language models"], "when_to_choose": ["you need to train a reward model for RLHF fine-tuning of LLMs", "you want reproducible recipes for multiple reward modeling techniques", "you are doing research on preference modeling or reward hacking mitigation"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/rlhf-reward-modeling", "repo": "RLHFlow/RLHF-Reward-Modeling", "role": "main", "score": 33}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.663530+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:30:47.081200+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31e127a042a96f46ee0a8c53d47f459fecb03e0910620e6ea79d222d5f3e2314", "fetched_at": "2026-08-28T04:05:00.663530+00:00", "kind": "readme", "missing": false, "url": "https://github.com/RLHFlow/RLHF-Reward-Modeling"}, {"content_hash": "7eeeb8336f4a5cc8f6e541e2208f9a259d8936fc4f5ea080298c060730be1f52", "fetched_at": "2026-08-29T11:32:14.777976+00:00", "kind": "homepage", "missing": false, "url": "https://rlhflow.github.io/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.663530+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:30:47.081200+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31e127a042a96f46ee0a8c53d47f459fecb03e0910620e6ea79d222d5f3e2314", "fetched_at": "2026-08-28T04:05:00.663530+00:00", "kind": "readme", "missing": false, "url": "https://github.com/RLHFlow/RLHF-Reward-Modeling"}, {"content_hash": "7eeeb8336f4a5cc8f6e541e2208f9a259d8936fc4f5ea080298c060730be1f52", "fetched_at": "2026-08-29T11:32:14.777976+00:00", "kind": "homepage", "missing": false, "url": "https://rlhflow.github.io/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:30:47.081200+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31e127a042a96f46ee0a8c53d47f459fecb03e0910620e6ea79d222d5f3e2314", "fetched_at": "2026-08-28T04:05:00.663530+00:00", "kind": "readme", "missing": false, "url": "https://github.com/RLHFlow/RLHF-Reward-Modeling"}, {"content_hash": "7eeeb8336f4a5cc8f6e541e2208f9a259d8936fc4f5ea080298c060730be1f52", "fetched_at": "2026-08-29T11:32:14.777976+00:00", "kind": "homepage", "missing": false, "url": "https://rlhflow.github.io/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.663530+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.663530+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.663530+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:30:47.081200+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31e127a042a96f46ee0a8c53d47f459fecb03e0910620e6ea79d222d5f3e2314", "fetched_at": "2026-08-28T04:05:00.663530+00:00", "kind": "readme", "missing": false, "url": "https://github.com/RLHFlow/RLHF-Reward-Modeling"}, {"content_hash": "7eeeb8336f4a5cc8f6e541e2208f9a259d8936fc4f5ea080298c060730be1f52", "fetched_at": "2026-08-29T11:32:14.777976+00:00", "kind": "homepage", "missing": false, "url": "https://rlhflow.github.io/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.663530+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.663530+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:30:47.081200+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31e127a042a96f46ee0a8c53d47f459fecb03e0910620e6ea79d222d5f3e2314", "fetched_at": "2026-08-28T04:05:00.663530+00:00", "kind": "readme", "missing": false, "url": "https://github.com/RLHFlow/RLHF-Reward-Modeling"}, {"content_hash": "7eeeb8336f4a5cc8f6e541e2208f9a259d8936fc4f5ea080298c060730be1f52", "fetched_at": "2026-08-29T11:32:14.777976+00:00", "kind": "homepage", "missing": false, "url": "https://rlhflow.github.io/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.663530+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.663530+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.663530+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:30:47.081200+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31e127a042a96f46ee0a8c53d47f459fecb03e0910620e6ea79d222d5f3e2314", "fetched_at": "2026-08-28T04:05:00.663530+00:00", "kind": "readme", "missing": false, "url": "https://github.com/RLHFlow/RLHF-Reward-Modeling"}, {"content_hash": "7eeeb8336f4a5cc8f6e541e2208f9a259d8936fc4f5ea080298c060730be1f52", "fetched_at": "2026-08-29T11:32:14.777976+00:00", "kind": "homepage", "missing": false, "url": "https://rlhflow.github.io/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.663530+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.663530+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:30:47.081200+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31e127a042a96f46ee0a8c53d47f459fecb03e0910620e6ea79d222d5f3e2314", "fetched_at": "2026-08-28T04:05:00.663530+00:00", "kind": "readme", "missing": false, "url": "https://github.com/RLHFlow/RLHF-Reward-Modeling"}, {"content_hash": "7eeeb8336f4a5cc8f6e541e2208f9a259d8936fc4f5ea080298c060730be1f52", "fetched_at": "2026-08-29T11:32:14.777976+00:00", "kind": "homepage", "missing": false, "url": "https://rlhflow.github.io/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:30:47.081200+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31e127a042a96f46ee0a8c53d47f459fecb03e0910620e6ea79d222d5f3e2314", "fetched_at": "2026-08-28T04:05:00.663530+00:00", "kind": "readme", "missing": false, "url": "https://github.com/RLHFlow/RLHF-Reward-Modeling"}, {"content_hash": "7eeeb8336f4a5cc8f6e541e2208f9a259d8936fc4f5ea080298c060730be1f52", "fetched_at": "2026-08-29T11:32:14.777976+00:00", "kind": "homepage", "missing": false, "url": "https://rlhflow.github.io/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:30:47.081200+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31e127a042a96f46ee0a8c53d47f459fecb03e0910620e6ea79d222d5f3e2314", "fetched_at": "2026-08-28T04:05:00.663530+00:00", "kind": "readme", "missing": false, "url": "https://github.com/RLHFlow/RLHF-Reward-Modeling"}, {"content_hash": "7eeeb8336f4a5cc8f6e541e2208f9a259d8936fc4f5ea080298c060730be1f52", "fetched_at": "2026-08-29T11:32:14.777976+00:00", "kind": "homepage", "missing": false, "url": "https://rlhflow.github.io/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:30:47.081200+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31e127a042a96f46ee0a8c53d47f459fecb03e0910620e6ea79d222d5f3e2314", "fetched_at": "2026-08-28T04:05:00.663530+00:00", "kind": "readme", "missing": false, "url": "https://github.com/RLHFlow/RLHF-Reward-Modeling"}, {"content_hash": "7eeeb8336f4a5cc8f6e541e2208f9a259d8936fc4f5ea080298c060730be1f52", "fetched_at": "2026-08-29T11:32:14.777976+00:00", "kind": "homepage", "missing": false, "url": "https://rlhflow.github.io/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 18, "longevity": 63, "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": 895, "days_push": 496, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 33, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}