{"adoption": {"forks": 2702, "observed_at": "2026-08-28T04:11:32.430834+00:00", "stars": 22194}, "canonical_url": "https://ross.abutalabs.com/products/unilm", "card": {"archived": false, "artifact_type": "library", "description": "Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities", "domain": ["machine-learning", "deep-learning", "large-language-models", "computer-vision", "artificial-intelligence"], "enriched": true, "function": ["machine-learning", "deep-learning", "nlp", "llm-training", "transformers", "computer-vision", "ocr"], "health_score": 86, "homepage": "https://aka.ms/GeneralAI", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["microsoft/unilm"], "name": "microsoft/unilm", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-26T08:16:01+00:00", "repo": "microsoft/unilm", "stars": 22194, "tags": ["pre-trained-models", "multimodal", "document-ai", "self-supervised-learning", "foundation-models", "research", "transformer-architectures", "natural-language-processing", "gpu", "linux"], "topics": ["nlp", "pre-trained-model", "unilm", "minilm", "layoutlm", "layoutxlm", "beit", "document-ai", "trocr", "beit-3", "foundation-models", "xlm-e", "deepnet", "llm", "multimodal", "mllm", "kosmos", "kosmos-1", "textdiffuser", "bitnet"], "urls": [], "use_cases": ["pretrain a transformer model on multiple languages", "extract text and layout from scanned documents", "run OCR-free document understanding", "fine-tune a multimodal large language model", "train a vision transformer for image classification", "experiment with 1-bit LLM architectures", "build a multilingual sentence embedding model"], "what_it_is": "Microsoft's collection of large-scale self-supervised pre-trained models spanning tasks, 100+ languages, and modalities (text, image, layout, audio). It includes well-known models like UniLM, LayoutLM, BEiT, TroCR, Kosmos, and BitNet, plus transformer architecture research such as DeepNet and LongNet.", "when_to_avoid": ["you need a production-ready turnkey API rather than research code", "you want a lightweight inference-only library without training pipelines", "you need a single unified model interface - the repo is a collection of separate subprojects"], "when_to_choose": ["you need state-of-the-art pre-trained models for NLP, vision, or document AI", "you want to reproduce or build on published Microsoft research models", "you need multilingual or multimodal (vision+language) model checkpoints"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/unilm", "repo": "microsoft/unilm", "role": "main", "score": 67}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.430834+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:57:41.940158+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e706d586f6c30b781ab0135883eb3a04ed033ea52736c26c27b256ff1e88fceb", "fetched_at": "2026-08-28T04:11:32.430834+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/unilm"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.430834+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:57:41.940158+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e706d586f6c30b781ab0135883eb3a04ed033ea52736c26c27b256ff1e88fceb", "fetched_at": "2026-08-28T04:11:32.430834+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/unilm"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:57:41.940158+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e706d586f6c30b781ab0135883eb3a04ed033ea52736c26c27b256ff1e88fceb", "fetched_at": "2026-08-28T04:11:32.430834+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/unilm"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.430834+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.430834+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.430834+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:57:41.940158+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e706d586f6c30b781ab0135883eb3a04ed033ea52736c26c27b256ff1e88fceb", "fetched_at": "2026-08-28T04:11:32.430834+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/unilm"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.430834+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.430834+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:57:41.940158+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e706d586f6c30b781ab0135883eb3a04ed033ea52736c26c27b256ff1e88fceb", "fetched_at": "2026-08-28T04:11:32.430834+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/unilm"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.430834+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.430834+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.430834+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:57:41.940158+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e706d586f6c30b781ab0135883eb3a04ed033ea52736c26c27b256ff1e88fceb", "fetched_at": "2026-08-28T04:11:32.430834+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/unilm"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.430834+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.430834+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:57:41.940158+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e706d586f6c30b781ab0135883eb3a04ed033ea52736c26c27b256ff1e88fceb", "fetched_at": "2026-08-28T04:11:32.430834+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/unilm"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:57:41.940158+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e706d586f6c30b781ab0135883eb3a04ed033ea52736c26c27b256ff1e88fceb", "fetched_at": "2026-08-28T04:11:32.430834+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/unilm"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:57:41.940158+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e706d586f6c30b781ab0135883eb3a04ed033ea52736c26c27b256ff1e88fceb", "fetched_at": "2026-08-28T04:11:32.430834+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/unilm"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:57:41.940158+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e706d586f6c30b781ab0135883eb3a04ed033ea52736c26c27b256ff1e88fceb", "fetched_at": "2026-08-28T04:11:32.430834+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/unilm"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 8}, "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": 2598, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 67, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}