{"schemaVersion":"hugging-bay.ranking.v1","generatedAt":"2026-10-21T03:19:34.003Z","slug":"commercial-datasets","title":"Commercial Datasets","description":"Permissive-license datasets and evaluation resources that are easier to review for commercial product work.","webUrl":"https://huggingbay.xyz/rankings/commercial-datasets","rows":[{"readiness":"unknown","downloadReady":null,"hostedFileCount":null,"mirroredBytes":null,"readinessCheckedAt":null,"readinessSource":"unavailable","degraded":true,"stale":false,"reasonCodes":[],"serveExplanation":{"readiness":"unknown","downloadReady":null,"hostedFileCount":null,"mirroredBytes":null,"readinessCheckedAt":null,"readinessSource":"unavailable","degraded":true,"stale":false,"reasonCodes":[]},"id":"hf-dataset-helsinki-nlp-opus-ubuntu","owner":"Helsinki-NLP","name":"opus_ubuntu","repo":"Helsinki-NLP/opus_ubuntu","type":"dataset","summary":"Dataset from Hugging Face for translation: Helsinki-NLP/opus_ubuntu · datasets","publisher":"Helsinki-NLP","sourceUrl":"https://huggingface.co/datasets/Helsinki-NLP/opus_ubuntu","license":"bsd-3-clause","licenseState":"known","licenseLabel":"bsd-3-clause","visibility":"public","verificationStatus":"unknown","scanStatus":"passed","cardCompleteness":92,"tags":["huggingface-import","external-catalog","dataset","bsd-3-clause","task_categories:translation","annotations_creators:crowdsourced","annotations_creators:expert-generated","language_creators:found","multilinguality:multilingual","source_datasets:original","language:ace","language:af","language:ak","language:am","language:an","language:ang","language:ar","language:ary","language:as","language:ast","language:az","language:ba","language:bal","language:be"],"task":"translation","modality":"text","framework":"datasets","formats":["gitattributes","md","parquet"],"baseModel":null,"derivedFrom":null,"cardMetadata":{"source":"huggingface-cardData","license":"","metrics":[],"datasets":[],"paperIds":[],"repoType":"dataset","baseModel":"","languages":["ace","af","ak","am","an","ang","ar","ary","as","ast","az","ba"],"sourceUrl":"https://huggingface.co/datasets/Helsinki-NLP/opus_ubuntu","evalResults":[],"libraryName":"datasets","pipelineTag":"translation","cardDataKeys":["annotations_creators","config_names","configs","dataset_info","language","language_bcp47","language_creators","license","multilinguality","pretty_name","size_categories","source_datasets","task_categories","task_ids"],"semanticText":"translation datasets dataset ace af ak am an ang ar ary as ast az ba","semanticTerms":["translation","datasets","dataset","ace","af","ak","am","an","ang","ar","ary","as","ast","az","ba"],"siblingSample":[{"lfs":false,"path":".gitattributes","sizeBytes":1174},{"lfs":false,"path":"README.md","sizeBytes":9737},{"lfs":true,"path":"as-bs/train-00000-of-00001.parquet","sizeBytes":470874},{"lfs":true,"path":"az-cs/train-00000-of-00001.parquet","sizeBytes":14637},{"lfs":true,"path":"bg-de/train-00000-of-00001.parquet","sizeBytes":16278},{"lfs":true,"path":"bn-ga/train-00000-of-00001.parquet","sizeBytes":272247},{"lfs":true,"path":"br-es_PR/train-00000-of-00001.parquet","sizeBytes":8194},{"lfs":true,"path":"br-hi/train-00000-of-00001.parquet","sizeBytes":641803},{"lfs":true,"path":"br-la/train-00000-of-00001.parquet","sizeBytes":17723},{"lfs":true,"path":"br-uz/train-00000-of-00001.parquet","sizeBytes":62660},{"lfs":true,"path":"br-yi/train-00000-of-00001.parquet","sizeBytes":77870},{"lfs":true,"path":"bs-szl/train-00000-of-00001.parquet","sizeBytes":30035}],"modelIndexNames":[]},"worksWith":[],"runtimeFit":{"level":"unknown","hardware":"","sizeLabel":"unknown","runners":[],"runtimeFiles":[],"warnings":[]},"sizeBytes":1623232,"sizeKnown":true,"sizeLabel":"1.5 MB","sizeReason":"","declaredSizeBytes":1623232,"defaultDownloadBytes":null,"mirrorCount":1,"downloadCount":396,"stars":4,"citations":0,"updatedAt":"2026-07-11T06:45:57.054Z","createdAt":"2026-06-30T04:03:44.154Z","version":"hf-mirror-4dc07f7","upstream":{"gated":false,"repoId":"Helsinki-NLP/opus_ubuntu","private":false,"repoUrl":"https://huggingface.co/datasets/Helsinki-NLP/opus_ubuntu","disabled":false,"provider":"huggingface","repoType":"dataset","revision":"4dc07f768ea537e979b48b824c1fe254918d1f76","fetchedAt":"2026-07-11T06:45:20.098Z","importMode":"mirrored-release","licenseRaw":["bsd-3-clause"]},"hosting":{"status":"unknown","approvedAt":"2026-07-11T06:45:57.054Z","approvedBy":"reviewed-large-mirror-worker","mirroredAt":"2026-07-11T06:45:57.054Z","mirroredBytes":null,"mirroredFiles":null,"storageProvider":"local","hosted":null,"hostedFiles":null,"verified":false,"completeRunnable":false,"runReady":false,"refreshedAt":"2026-10-21T03:17:05.084Z","stale":false,"downloadReady":null,"serveAuthority":"live-serve-decision","bytesOnStorage":false},"mirrorCompletion":{"state":"unknown","completeRunnable":null,"verified":null,"runReady":null,"commandsAvailable":false,"manifestFinal":false,"hosted":false,"serveAuthority":"unbound","hostedFiles":0,"individuallyHashedFiles":0,"weightsHosted":null,"weightCountState":"not-snapshot-bound","strictlyDownloadableFiles":0,"strictlyDownloadableHashedFiles":0,"strictlyDownloadableWeights":null,"strictWeightCountState":"not-snapshot-bound","totalFiles":10,"scope":"file-inventory-only"},"decentralizedDistribution":{"protocol":"bittorrent-magnet-metadata","verifiedFallbacks":0,"pendingReviewRequests":0,"reviewRequired":true,"policy":"Peer-assisted fallbacks are metadata only until Hugging Bay review confirms source, license, provenance, and safety. Gated/private bypasses are not allowed."},"hostingStatus":"unknown","hosted":null,"fileCount":10,"publicDownloadableFileCount":null,"externalFileCount":10,"servingCountsRefreshedAt":"2026-10-21T03:17:05.084Z","servingCountsStale":false,"signals":{"size":{"known":true,"bytes":1623232,"label":"1.5 MB","reason":""},"demand":{"mirrorRequests":0,"upstreamDownloads":396,"upstreamStars":4,"label":"396 upstream downloads","basis":"upstream-downloads"},"trust":{"score":0,"level":"metadata-checked","label":"Unknown","trustImpact":"none","checks":[{"id":"license","label":"License","status":"pass","detail":"bsd-3-clause"},{"id":"provenance","label":"Provenance","status":"pass","detail":"Helsinki-NLP/opus_ubuntu"},{"id":"scan","label":"Scan","status":"pass","detail":"passed"},{"id":"hosting","label":"Hosted files","status":"warn","detail":"external metadata only"},{"id":"manifest","label":"Byte manifest integrity","status":"warn","detail":"not final yet"}],"strengths":["License: bsd-3-clause","Provenance: Helsinki-NLP/opus_ubuntu","Scan: passed"],"gaps":["Hosted files: external metadata only","Byte manifest integrity: not final yet"]},"readiness":{"score":0,"level":"unknown","hostedFinal":false,"hostedFiles":null,"externalFiles":null,"totalFiles":10},"action":{"id":"request-mirror","label":"Request a complete representation","detail":"Capture demand for a reviewed, immutable representation with complete selected bytes.","href":"/artifact/hf-dataset-helsinki-nlp-opus-ubuntu/mirrors"}},"sampleFiles":[{"path":"as-bs/train-00000-of-00001.parquet","sizeBytes":470874,"format":"parquet","risk":"low","downloadPolicy":"external","sourceKind":"external-hf"},{"path":"az-cs/train-00000-of-00001.parquet","sizeBytes":14637,"format":"parquet","risk":"low","downloadPolicy":"external","sourceKind":"external-hf"},{"path":"bg-de/train-00000-of-00001.parquet","sizeBytes":16278,"format":"parquet","risk":"low","downloadPolicy":"external","sourceKind":"external-hf"},{"path":"bn-ga/train-00000-of-00001.parquet","sizeBytes":272247,"format":"parquet","risk":"low","downloadPolicy":"external","sourceKind":"external-hf"},{"path":"br-es_PR/train-00000-of-00001.parquet","sizeBytes":8194,"format":"parquet","risk":"low","downloadPolicy":"external","sourceKind":"external-hf"}],"reason":"Download availability is being checked.","contentControls":{"state":"not assessed","basis":"no_explicit_uploader_evidence","matchedTerms":[],"assessedAt":null},"contentControlsLabel":"Content controls: not assessed.","contentControlsAttribution":{"upstream":{"provider":"huggingface","repoId":"Helsinki-NLP/opus_ubuntu"}},"artifactUrl":"https://huggingbay.xyz/artifact/hf-dataset-helsinki-nlp-opus-ubuntu","metadataUrl":"https://huggingbay.xyz/api/artifacts/hf-dataset-helsinki-nlp-opus-ubuntu/metadata.json"}],"stale":true,"staleSource":"last-known-good","snapshotAt":"2026-10-21T03:19:34.003Z","staleAgeMs":4404955,"note":{"summary":"Downloadable doesn't mean tested: this record says whether the exact file can be downloaded now, not that the model is complete or that it runs."}}