{"adoption": {"forks": 201, "observed_at": "2026-08-28T04:06:43.467608+00:00", "stars": 2394}, "canonical_url": "https://ross.abutalabs.com/products/rl4lms", "card": {"archived": false, "artifact_type": "library", "description": "A modular RL library to fine-tune language models to human preferences", "domain": ["reinforcement-learning", "machine-learning", "large-language-models"], "enriched": true, "function": ["machine-learning", "reinforcement-learning", "llm-training", "nlp", "benchmarking"], "health_score": 20, "homepage": "https://rl4lms.apps.allenai.org/", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["allenai/RL4LMs"], "name": "allenai/RL4LMs", "platform": ["python"], "pushed_at": "2024-03-01T14:03:46+00:00", "repo": "allenai/RL4LMs", "stars": 2394, "tags": ["rlhf", "text-generation", "ppo", "nlpо", "reward-functions", "fine-tuning", "human-preferences", "actor-critic", "natural-language-processing"], "topics": ["language-modeling", "nlp", "reinforcement-learning", "dialogue-generation", "machine-translation", "natural-language-processing", "summarization", "table-to-text", "text-generation"], "urls": [], "use_cases": ["fine-tune language models with reinforcement learning", "train LMs to optimize reward functions like ROUGE or sentiment scores", "run RLHF-style training on summarization or translation tasks", "benchmark on-policy RL algorithms on NLP generation tasks", "apply PPO or NLPO to GPT-2 or T5 models", "optimize text generation models on custom datasets"], "what_it_is": "RL4LMs is a modular Python library from AllenAI for fine-tuning language models with reinforcement learning to align with human preferences. It provides customizable building blocks including on-policy algorithms (PPO, A2C, TRPO, NLPO), reward functions, NLG metrics, datasets, and actor-critic policies for causal and seq2seq LMs.", "when_to_avoid": ["you need modern large-scale RLHF infrastructure for instruction-tuned chat models", "you only need supervised fine-tuning without reinforcement learning", "you require active development and support for the latest LLM architectures"], "when_to_choose": ["you want to fine-tune causal or seq2seq LMs with RL algorithms like PPO or NLPO", "you need a library of NLG metrics usable as reward functions", "you want a tested, benchmarked framework for RL-based text generation experiments"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/rl4lms", "repo": "allenai/RL4LMs", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:43.467608+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:34:24.014706+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3eb52c0cc897f6f3b7e16625719faed3515dfa5a126834223c8697fd751f8f30", "fetched_at": "2026-08-28T04:06:43.467608+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/RL4LMs"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:43.467608+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:34:24.014706+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3eb52c0cc897f6f3b7e16625719faed3515dfa5a126834223c8697fd751f8f30", "fetched_at": "2026-08-28T04:06:43.467608+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/RL4LMs"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:34:24.014706+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3eb52c0cc897f6f3b7e16625719faed3515dfa5a126834223c8697fd751f8f30", "fetched_at": "2026-08-28T04:06:43.467608+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/RL4LMs"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:43.467608+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:43.467608+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:43.467608+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:34:24.014706+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3eb52c0cc897f6f3b7e16625719faed3515dfa5a126834223c8697fd751f8f30", "fetched_at": "2026-08-28T04:06:43.467608+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/RL4LMs"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:43.467608+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:43.467608+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:34:24.014706+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3eb52c0cc897f6f3b7e16625719faed3515dfa5a126834223c8697fd751f8f30", "fetched_at": "2026-08-28T04:06:43.467608+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/RL4LMs"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:43.467608+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:43.467608+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:43.467608+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:34:24.014706+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3eb52c0cc897f6f3b7e16625719faed3515dfa5a126834223c8697fd751f8f30", "fetched_at": "2026-08-28T04:06:43.467608+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/RL4LMs"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:43.467608+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:43.467608+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:34:24.014706+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3eb52c0cc897f6f3b7e16625719faed3515dfa5a126834223c8697fd751f8f30", "fetched_at": "2026-08-28T04:06:43.467608+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/RL4LMs"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:34:24.014706+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3eb52c0cc897f6f3b7e16625719faed3515dfa5a126834223c8697fd751f8f30", "fetched_at": "2026-08-28T04:06:43.467608+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/RL4LMs"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:34:24.014706+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3eb52c0cc897f6f3b7e16625719faed3515dfa5a126834223c8697fd751f8f30", "fetched_at": "2026-08-28T04:06:43.467608+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/RL4LMs"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:34:24.014706+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3eb52c0cc897f6f3b7e16625719faed3515dfa5a126834223c8697fd751f8f30", "fetched_at": "2026-08-28T04:06:43.467608+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/RL4LMs"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "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": 1476, "days_push": 915, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}