{"adoption": {"forks": 212, "observed_at": "2026-08-28T04:06:42.409398+00:00", "stars": 2428}, "canonical_url": "https://ross.abutalabs.com/products/marin", "card": {"archived": false, "artifact_type": "framework", "description": "Open-source framework for the research and development of foundation models.", "domain": ["large-language-models", "machine-learning", "deep-learning", "artificial-intelligence"], "enriched": true, "function": ["llm-training", "machine-learning", "etl", "data-science", "benchmarking"], "health_score": 100, "homepage": "https://marin.community", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["marin-community/marin"], "name": "marin-community/marin", "platform": ["python", "cloud"], "pushed_at": "2026-08-26T21:33:20+00:00", "repo": "marin-community/marin", "stars": 2428, "tags": ["foundation-models", "pretraining", "posttraining", "data-curation", "scaling-laws", "tpu", "open-science", "mixture-of-experts", "tokenization", "evaluation", "data-engineering", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["pretrain a large language model from scratch on TPUs", "curate and filter pretraining datasets like Nemotron-CC or StarCoderData", "run scaling law experiments across compute budgets", "run posttraining and SFT experiments on open LLMs", "evaluate and compare LLM checkpoints reproducibly", "train audio-text, DNA, or protein foundation models", "reproduce and share ML experiments with full provenance"], "what_it_is": "Marin is an open-source Python framework and research program for training foundation models, covering the full pipeline from data curation, filtering, and tokenization through pretraining, posttraining, and evaluation. It emphasizes open development, documenting every experiment, dataset, and checkpoint in real time, and includes artifacts like the Delphi scaling suite and frontier mixture-of-experts training runs.", "when_to_avoid": ["you just need to fine-tune a small model quickly with a high-level API like HF Trainer or LoRA tooling", "you need production inference serving rather than training research", "you lack access to significant TPU/GPU compute for large-scale training"], "when_to_choose": ["you want an open, reproducible pipeline for LLM pretraining and posttraining research", "you need data curation, tokenization, training, and evaluation in one framework", "you want to run scaling suites or mixture-of-experts experiments on TPU research clouds", "you value open science with preregistered experiments and shared checkpoints"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/marin", "repo": "marin-community/marin", "role": "main", "score": 78}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.409398+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:31:33.445814+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f6637dd6bb47ef148f3fb83a4af0f9fe05e630c696a5bed060dbc888fcf7b7c", "fetched_at": "2026-08-28T04:06:42.409398+00:00", "kind": "readme", "missing": false, "url": "https://github.com/marin-community/marin"}, {"content_hash": "448181b97c2301d41e1953bfa16d1c7c223f45256f16cddf8a1d8dbfb196e8c5", "fetched_at": "2026-08-29T10:12:51.143329+00:00", "kind": "homepage", "missing": false, "url": "https://marin.community"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.409398+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:31:33.445814+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f6637dd6bb47ef148f3fb83a4af0f9fe05e630c696a5bed060dbc888fcf7b7c", "fetched_at": "2026-08-28T04:06:42.409398+00:00", "kind": "readme", "missing": false, "url": "https://github.com/marin-community/marin"}, {"content_hash": "448181b97c2301d41e1953bfa16d1c7c223f45256f16cddf8a1d8dbfb196e8c5", "fetched_at": "2026-08-29T10:12:51.143329+00:00", "kind": "homepage", "missing": false, "url": "https://marin.community"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:31:33.445814+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f6637dd6bb47ef148f3fb83a4af0f9fe05e630c696a5bed060dbc888fcf7b7c", "fetched_at": "2026-08-28T04:06:42.409398+00:00", "kind": "readme", "missing": false, "url": "https://github.com/marin-community/marin"}, {"content_hash": "448181b97c2301d41e1953bfa16d1c7c223f45256f16cddf8a1d8dbfb196e8c5", "fetched_at": "2026-08-29T10:12:51.143329+00:00", "kind": "homepage", "missing": false, "url": "https://marin.community"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.409398+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.409398+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.409398+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:31:33.445814+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f6637dd6bb47ef148f3fb83a4af0f9fe05e630c696a5bed060dbc888fcf7b7c", "fetched_at": "2026-08-28T04:06:42.409398+00:00", "kind": "readme", "missing": false, "url": "https://github.com/marin-community/marin"}, {"content_hash": "448181b97c2301d41e1953bfa16d1c7c223f45256f16cddf8a1d8dbfb196e8c5", "fetched_at": "2026-08-29T10:12:51.143329+00:00", "kind": "homepage", "missing": false, "url": "https://marin.community"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.409398+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.409398+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:31:33.445814+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f6637dd6bb47ef148f3fb83a4af0f9fe05e630c696a5bed060dbc888fcf7b7c", "fetched_at": "2026-08-28T04:06:42.409398+00:00", "kind": "readme", "missing": false, "url": "https://github.com/marin-community/marin"}, {"content_hash": "448181b97c2301d41e1953bfa16d1c7c223f45256f16cddf8a1d8dbfb196e8c5", "fetched_at": "2026-08-29T10:12:51.143329+00:00", "kind": "homepage", "missing": false, "url": "https://marin.community"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.409398+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.409398+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.409398+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:31:33.445814+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f6637dd6bb47ef148f3fb83a4af0f9fe05e630c696a5bed060dbc888fcf7b7c", "fetched_at": "2026-08-28T04:06:42.409398+00:00", "kind": "readme", "missing": false, "url": "https://github.com/marin-community/marin"}, {"content_hash": "448181b97c2301d41e1953bfa16d1c7c223f45256f16cddf8a1d8dbfb196e8c5", "fetched_at": "2026-08-29T10:12:51.143329+00:00", "kind": "homepage", "missing": false, "url": "https://marin.community"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.409398+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.409398+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:31:33.445814+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f6637dd6bb47ef148f3fb83a4af0f9fe05e630c696a5bed060dbc888fcf7b7c", "fetched_at": "2026-08-28T04:06:42.409398+00:00", "kind": "readme", "missing": false, "url": "https://github.com/marin-community/marin"}, {"content_hash": "448181b97c2301d41e1953bfa16d1c7c223f45256f16cddf8a1d8dbfb196e8c5", "fetched_at": "2026-08-29T10:12:51.143329+00:00", "kind": "homepage", "missing": false, "url": "https://marin.community"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:31:33.445814+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f6637dd6bb47ef148f3fb83a4af0f9fe05e630c696a5bed060dbc888fcf7b7c", "fetched_at": "2026-08-28T04:06:42.409398+00:00", "kind": "readme", "missing": false, "url": "https://github.com/marin-community/marin"}, {"content_hash": "448181b97c2301d41e1953bfa16d1c7c223f45256f16cddf8a1d8dbfb196e8c5", "fetched_at": "2026-08-29T10:12:51.143329+00:00", "kind": "homepage", "missing": false, "url": "https://marin.community"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:31:33.445814+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f6637dd6bb47ef148f3fb83a4af0f9fe05e630c696a5bed060dbc888fcf7b7c", "fetched_at": "2026-08-28T04:06:42.409398+00:00", "kind": "readme", "missing": false, "url": "https://github.com/marin-community/marin"}, {"content_hash": "448181b97c2301d41e1953bfa16d1c7c223f45256f16cddf8a1d8dbfb196e8c5", "fetched_at": "2026-08-29T10:12:51.143329+00:00", "kind": "homepage", "missing": false, "url": "https://marin.community"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:31:33.445814+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f6637dd6bb47ef148f3fb83a4af0f9fe05e630c696a5bed060dbc888fcf7b7c", "fetched_at": "2026-08-28T04:06:42.409398+00:00", "kind": "readme", "missing": false, "url": "https://github.com/marin-community/marin"}, {"content_hash": "448181b97c2301d41e1953bfa16d1c7c223f45256f16cddf8a1d8dbfb196e8c5", "fetched_at": "2026-08-29T10:12:51.143329+00:00", "kind": "homepage", "missing": false, "url": "https://marin.community"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 63, "rhythm": 60}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["prerelease_only"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 894, "days_push": 7, "days_rel": 20, "gap_med": 0, "n_releases_24m": 16}, "score": 78, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}