{"adoption": {"forks": 70, "observed_at": "2026-08-28T04:04:38.934254+00:00", "stars": 1411}, "canonical_url": "https://ross.abutalabs.com/products/self-rewarding-lm-pytorch", "card": {"archived": false, "artifact_type": "library", "description": "Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI", "domain": ["large-language-models", "deep-learning", "machine-learning", "artificial-intelligence"], "enriched": true, "function": ["llm-training", "machine-learning", "deep-learning"], "health_score": 26, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["lucidrains/self-rewarding-lm-pytorch"], "name": "lucidrains/self-rewarding-lm-pytorch", "platform": ["python"], "pushed_at": "2024-04-11T01:09:42+00:00", "repo": "lucidrains/self-rewarding-lm-pytorch", "stars": 1411, "tags": ["self-rewarding", "dpo", "spin", "transformers", "research-implementation", "pytorch", "fine-tuning", "lucidrains"], "topics": ["artificial-intelligence", "deep-learning", "transformers", "beyond-human-data", "self-rewarding"], "urls": [], "use_cases": ["train a self-rewarding language model in pytorch", "implement DPO fine-tuning for an LLM", "run SPIN training on a transformer", "fine-tune a language model with self-generated rewards", "reproduce the MetaAI self-rewarding LM paper", "build a preference optimization training pipeline"], "what_it_is": "A PyTorch library implementing the Self-Rewarding Language Model training framework from MetaAI, along with the SPIN training method. It provides trainers that combine supervised fine-tuning, self-rewarding, and direct preference optimization (DPO) for language models.", "when_to_avoid": ["you need a production-grade, fully supported LLM training framework with broad model support", "you want turnkey training of mainstream LLMs like Llama with optimized kernels", "you need extensive documentation and enterprise support"], "when_to_choose": ["you want a lightweight, hackable PyTorch implementation of self-rewarding LM or SPIN training", "you are doing research on preference optimization methods like DPO and SPIN", "you already have a transformer model and want to add self-rewarding fine-tuning stages"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/self-rewarding-lm-pytorch", "repo": "lucidrains/self-rewarding-lm-pytorch", "role": "main", "score": 16}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:38.934254+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:38:24.294459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e26601a359f97a62563f7d361baee0ec1c9e71e64a54fb1eec57c3a08c869f7f", "fetched_at": "2026-08-28T04:04:38.934254+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lucidrains/self-rewarding-lm-pytorch"}, {"content_hash": "3cee8d9160fff4648bde3e932b86125af2321964e2bfa305d2dba962d0c2526c", "fetched_at": "2026-08-29T11:51:40.049935+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/self-rewarding-lm-pytorch/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:38.934254+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:38:24.294459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e26601a359f97a62563f7d361baee0ec1c9e71e64a54fb1eec57c3a08c869f7f", "fetched_at": "2026-08-28T04:04:38.934254+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lucidrains/self-rewarding-lm-pytorch"}, {"content_hash": "3cee8d9160fff4648bde3e932b86125af2321964e2bfa305d2dba962d0c2526c", "fetched_at": "2026-08-29T11:51:40.049935+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/self-rewarding-lm-pytorch/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:38:24.294459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e26601a359f97a62563f7d361baee0ec1c9e71e64a54fb1eec57c3a08c869f7f", "fetched_at": "2026-08-28T04:04:38.934254+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lucidrains/self-rewarding-lm-pytorch"}, {"content_hash": "3cee8d9160fff4648bde3e932b86125af2321964e2bfa305d2dba962d0c2526c", "fetched_at": "2026-08-29T11:51:40.049935+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/self-rewarding-lm-pytorch/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:38.934254+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:38.934254+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:38.934254+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:38:24.294459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e26601a359f97a62563f7d361baee0ec1c9e71e64a54fb1eec57c3a08c869f7f", "fetched_at": "2026-08-28T04:04:38.934254+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lucidrains/self-rewarding-lm-pytorch"}, {"content_hash": "3cee8d9160fff4648bde3e932b86125af2321964e2bfa305d2dba962d0c2526c", "fetched_at": "2026-08-29T11:51:40.049935+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/self-rewarding-lm-pytorch/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:38.934254+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:38.934254+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:38:24.294459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e26601a359f97a62563f7d361baee0ec1c9e71e64a54fb1eec57c3a08c869f7f", "fetched_at": "2026-08-28T04:04:38.934254+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lucidrains/self-rewarding-lm-pytorch"}, {"content_hash": "3cee8d9160fff4648bde3e932b86125af2321964e2bfa305d2dba962d0c2526c", "fetched_at": "2026-08-29T11:51:40.049935+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/self-rewarding-lm-pytorch/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:38.934254+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:38.934254+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:38.934254+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:38:24.294459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e26601a359f97a62563f7d361baee0ec1c9e71e64a54fb1eec57c3a08c869f7f", "fetched_at": "2026-08-28T04:04:38.934254+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lucidrains/self-rewarding-lm-pytorch"}, {"content_hash": "3cee8d9160fff4648bde3e932b86125af2321964e2bfa305d2dba962d0c2526c", "fetched_at": "2026-08-29T11:51:40.049935+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/self-rewarding-lm-pytorch/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:38.934254+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:38.934254+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:38:24.294459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e26601a359f97a62563f7d361baee0ec1c9e71e64a54fb1eec57c3a08c869f7f", "fetched_at": "2026-08-28T04:04:38.934254+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lucidrains/self-rewarding-lm-pytorch"}, {"content_hash": "3cee8d9160fff4648bde3e932b86125af2321964e2bfa305d2dba962d0c2526c", "fetched_at": "2026-08-29T11:51:40.049935+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/self-rewarding-lm-pytorch/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:38:24.294459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e26601a359f97a62563f7d361baee0ec1c9e71e64a54fb1eec57c3a08c869f7f", "fetched_at": "2026-08-28T04:04:38.934254+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lucidrains/self-rewarding-lm-pytorch"}, {"content_hash": "3cee8d9160fff4648bde3e932b86125af2321964e2bfa305d2dba962d0c2526c", "fetched_at": "2026-08-29T11:51:40.049935+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/self-rewarding-lm-pytorch/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:38:24.294459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e26601a359f97a62563f7d361baee0ec1c9e71e64a54fb1eec57c3a08c869f7f", "fetched_at": "2026-08-28T04:04:38.934254+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lucidrains/self-rewarding-lm-pytorch"}, {"content_hash": "3cee8d9160fff4648bde3e932b86125af2321964e2bfa305d2dba962d0c2526c", "fetched_at": "2026-08-29T11:51:40.049935+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/self-rewarding-lm-pytorch/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:38:24.294459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e26601a359f97a62563f7d361baee0ec1c9e71e64a54fb1eec57c3a08c869f7f", "fetched_at": "2026-08-28T04:04:38.934254+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lucidrains/self-rewarding-lm-pytorch"}, {"content_hash": "3cee8d9160fff4648bde3e932b86125af2321964e2bfa305d2dba962d0c2526c", "fetched_at": "2026-08-29T11:51:40.049935+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/self-rewarding-lm-pytorch/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 68, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 957, "days_push": 875, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 16, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}