{"adoption": {"forks": 310, "observed_at": "2026-08-28T04:06:32.743012+00:00", "stars": 2270}, "canonical_url": "https://ross.abutalabs.com/products/dataflex", "card": {"archived": false, "artifact_type": "framework", "description": "Data-centric LLM training with dynamic sample selection, domain mixture optimization, and example reweighting inside the LLaMA-Factory training loop.", "domain": ["large-language-models", "machine-learning", "data-science", "deep-learning"], "enriched": true, "function": ["machine-learning", "llm-training", "data-science", "etl"], "health_score": 98, "homepage": "https://opendcai.github.io/DataFlex-Doc/", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["OpenDCAI/DataFlex"], "name": "OpenDCAI/DataFlex", "platform": ["python"], "pushed_at": "2026-08-26T15:12:03+00:00", "repo": "OpenDCAI/DataFlex", "stars": 2270, "tags": ["data-selection", "data-mixture", "data-reweighting", "data-centric-ai", "llama-factory", "training-data-scheduling", "gpu", "linux"], "topics": ["data-mixture", "data-science", "data-selection", "data-reweighting", "data", "model-training", "data-model-interaction"], "urls": [], "use_cases": ["dynamically select training samples for LLM fine-tuning", "optimize domain mixture of training data", "reweight training examples during model training", "improve reproducibility of LLM training experiments", "focus training on hard samples", "train larger models with DeepSpeed ZeRO-3 gradient computation"], "what_it_is": "DataFlex is a data-centric training framework built on LLaMA-Factory that dynamically schedules LLM training data during optimization. It provides reproducible implementations of data selection, data mixture optimization, and example reweighting inside the training loop.", "when_to_avoid": ["you train models outside the LLaMA-Factory ecosystem", "you need a general-purpose data pipeline unrelated to LLM training", "you require a fully stable, long-proven production system"], "when_to_choose": ["you already use LLaMA-Factory and want smarter data scheduling", "you need reproducible data selection, mixture, and reweighting in one framework", "you want to improve model performance by curating training data dynamically"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/dataflex", "repo": "OpenDCAI/DataFlex", "role": "main", "score": 67}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:32.743012+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:41:49.237890+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8bbeaf5a53b102a0e8ccc0e5b95c24f2742d8f3e5c10b4a2baeece2daac35dd4", "fetched_at": "2026-08-28T04:06:32.743012+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenDCAI/DataFlex"}, {"content_hash": "1260f20fe66e89fddabd6a262174f3aa797a7831c060523348234f9e49d7298c", "fetched_at": "2026-08-29T10:22:15.078471+00:00", "kind": "homepage", "missing": false, "url": "https://opendcai.github.io/DataFlex-Doc/"}, {"content_hash": "ce308c4f78518394659217844c0448c208d3a6dc6551b0bb24779b9e36b472d8", "fetched_at": "2026-08-29T10:22:15.081142+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dataflex/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:32.743012+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:41:49.237890+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8bbeaf5a53b102a0e8ccc0e5b95c24f2742d8f3e5c10b4a2baeece2daac35dd4", "fetched_at": "2026-08-28T04:06:32.743012+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenDCAI/DataFlex"}, {"content_hash": "1260f20fe66e89fddabd6a262174f3aa797a7831c060523348234f9e49d7298c", "fetched_at": "2026-08-29T10:22:15.078471+00:00", "kind": "homepage", "missing": false, "url": "https://opendcai.github.io/DataFlex-Doc/"}, {"content_hash": "ce308c4f78518394659217844c0448c208d3a6dc6551b0bb24779b9e36b472d8", "fetched_at": "2026-08-29T10:22:15.081142+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dataflex/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:41:49.237890+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8bbeaf5a53b102a0e8ccc0e5b95c24f2742d8f3e5c10b4a2baeece2daac35dd4", "fetched_at": "2026-08-28T04:06:32.743012+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenDCAI/DataFlex"}, {"content_hash": "1260f20fe66e89fddabd6a262174f3aa797a7831c060523348234f9e49d7298c", "fetched_at": "2026-08-29T10:22:15.078471+00:00", "kind": "homepage", "missing": false, "url": "https://opendcai.github.io/DataFlex-Doc/"}, {"content_hash": "ce308c4f78518394659217844c0448c208d3a6dc6551b0bb24779b9e36b472d8", "fetched_at": "2026-08-29T10:22:15.081142+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dataflex/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:32.743012+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:32.743012+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:32.743012+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:41:49.237890+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8bbeaf5a53b102a0e8ccc0e5b95c24f2742d8f3e5c10b4a2baeece2daac35dd4", "fetched_at": "2026-08-28T04:06:32.743012+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenDCAI/DataFlex"}, {"content_hash": "1260f20fe66e89fddabd6a262174f3aa797a7831c060523348234f9e49d7298c", "fetched_at": "2026-08-29T10:22:15.078471+00:00", "kind": "homepage", "missing": false, "url": "https://opendcai.github.io/DataFlex-Doc/"}, {"content_hash": "ce308c4f78518394659217844c0448c208d3a6dc6551b0bb24779b9e36b472d8", "fetched_at": "2026-08-29T10:22:15.081142+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dataflex/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:32.743012+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:32.743012+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:41:49.237890+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8bbeaf5a53b102a0e8ccc0e5b95c24f2742d8f3e5c10b4a2baeece2daac35dd4", "fetched_at": "2026-08-28T04:06:32.743012+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenDCAI/DataFlex"}, {"content_hash": "1260f20fe66e89fddabd6a262174f3aa797a7831c060523348234f9e49d7298c", "fetched_at": "2026-08-29T10:22:15.078471+00:00", "kind": "homepage", "missing": false, "url": "https://opendcai.github.io/DataFlex-Doc/"}, {"content_hash": "ce308c4f78518394659217844c0448c208d3a6dc6551b0bb24779b9e36b472d8", "fetched_at": "2026-08-29T10:22:15.081142+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dataflex/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:32.743012+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:32.743012+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:32.743012+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:41:49.237890+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8bbeaf5a53b102a0e8ccc0e5b95c24f2742d8f3e5c10b4a2baeece2daac35dd4", "fetched_at": "2026-08-28T04:06:32.743012+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenDCAI/DataFlex"}, {"content_hash": "1260f20fe66e89fddabd6a262174f3aa797a7831c060523348234f9e49d7298c", "fetched_at": "2026-08-29T10:22:15.078471+00:00", "kind": "homepage", "missing": false, "url": "https://opendcai.github.io/DataFlex-Doc/"}, {"content_hash": "ce308c4f78518394659217844c0448c208d3a6dc6551b0bb24779b9e36b472d8", "fetched_at": "2026-08-29T10:22:15.081142+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dataflex/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:32.743012+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:32.743012+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:41:49.237890+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8bbeaf5a53b102a0e8ccc0e5b95c24f2742d8f3e5c10b4a2baeece2daac35dd4", "fetched_at": "2026-08-28T04:06:32.743012+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenDCAI/DataFlex"}, {"content_hash": "1260f20fe66e89fddabd6a262174f3aa797a7831c060523348234f9e49d7298c", "fetched_at": "2026-08-29T10:22:15.078471+00:00", "kind": "homepage", "missing": false, "url": "https://opendcai.github.io/DataFlex-Doc/"}, {"content_hash": "ce308c4f78518394659217844c0448c208d3a6dc6551b0bb24779b9e36b472d8", "fetched_at": "2026-08-29T10:22:15.081142+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dataflex/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:41:49.237890+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8bbeaf5a53b102a0e8ccc0e5b95c24f2742d8f3e5c10b4a2baeece2daac35dd4", "fetched_at": "2026-08-28T04:06:32.743012+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenDCAI/DataFlex"}, {"content_hash": "1260f20fe66e89fddabd6a262174f3aa797a7831c060523348234f9e49d7298c", "fetched_at": "2026-08-29T10:22:15.078471+00:00", "kind": "homepage", "missing": false, "url": "https://opendcai.github.io/DataFlex-Doc/"}, {"content_hash": "ce308c4f78518394659217844c0448c208d3a6dc6551b0bb24779b9e36b472d8", "fetched_at": "2026-08-29T10:22:15.081142+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dataflex/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:41:49.237890+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8bbeaf5a53b102a0e8ccc0e5b95c24f2742d8f3e5c10b4a2baeece2daac35dd4", "fetched_at": "2026-08-28T04:06:32.743012+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenDCAI/DataFlex"}, {"content_hash": "1260f20fe66e89fddabd6a262174f3aa797a7831c060523348234f9e49d7298c", "fetched_at": "2026-08-29T10:22:15.078471+00:00", "kind": "homepage", "missing": false, "url": "https://opendcai.github.io/DataFlex-Doc/"}, {"content_hash": "ce308c4f78518394659217844c0448c208d3a6dc6551b0bb24779b9e36b472d8", "fetched_at": "2026-08-29T10:22:15.081142+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dataflex/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:41:49.237890+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8bbeaf5a53b102a0e8ccc0e5b95c24f2742d8f3e5c10b4a2baeece2daac35dd4", "fetched_at": "2026-08-28T04:06:32.743012+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenDCAI/DataFlex"}, {"content_hash": "1260f20fe66e89fddabd6a262174f3aa797a7831c060523348234f9e49d7298c", "fetched_at": "2026-08-29T10:22:15.078471+00:00", "kind": "homepage", "missing": false, "url": "https://opendcai.github.io/DataFlex-Doc/"}, {"content_hash": "ce308c4f78518394659217844c0448c208d3a6dc6551b0bb24779b9e36b472d8", "fetched_at": "2026-08-29T10:22:15.081142+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dataflex/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 27, "rhythm": 48}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 389, "days_push": 7, "days_rel": 139, "gap_med": null, "n_releases_24m": 1}, "score": 67, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}