FacebookAI/xlm-roberta-large
Explore FacebookAI/xlm-roberta-large: model specifications, capabilities, benchmark results, platform pricing and original sources.
huggingface/FacebookAI/xlm-roberta-large
Specifications & capabilities
- Published model ID
- xlm-roberta-large
Evaluations
1–13 / 13
29.344%
- source id
- mteb
- leaderboard name
- MTEB Bitext Mining
- dimension
- embedding
- metric
- Average task score
- rank
- 175
- sample size
- 3
- aggregation scope
- subsets
- eng_Latn-fra_Latn
- fr-en
- fra_Latn-eng_Latn
- task_count
- 2
- task_names
- DiaBlaBitextMining
- FloresBitextMining
- sample_size
- 3
- subset_count
- 3
- subset_sample
- eng_Latn-fra_Latn
- fr-en
- fra_Latn-eng_Latn
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- source model id
- FacebookAI/xlm-roberta-large
Original result ↗19.141%
- source id
- mteb
- leaderboard name
- MTEB Bitext Mining
- dimension
- embedding
- metric
- Average task score
- rank
- 234
- sample size
- 2
- aggregation scope
- task_count
- 2
- task_names
- BornholmBitextMining
- NorwegianCourtsBitextMining
- sample_size
- 2
- subset_count
- 1
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- model_revision_sample
- c23d21b0620b635a76227c604d44e43a9f0ee389
- source model id
- FacebookAI/xlm-roberta-large
Original result ↗53.437%
- source id
- mteb
- leaderboard name
- MTEB Pair Classification
- dimension
- embedding
- metric
- Average task score
- rank
- 311
- sample size
- 1
- aggregation scope
- task_count
- 1
- sample_size
- 1
- subset_count
- 1
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- source model id
- FacebookAI/xlm-roberta-large
Original result ↗54.328%
- source id
- mteb
- leaderboard name
- MTEB Other
- dimension
- embedding
- metric
- Average task score
- rank
- 378
- sample size
- 4
- aggregation scope
- splits
- test
- test.full
- validation.full
- task_count
- 3
- task_names
- OpusparcusPC
- SICKFr
- SummEvalFr
- sample_size
- 4
- subset_count
- 2
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- source model id
- FacebookAI/xlm-roberta-large
Original result ↗54.101%
- source id
- mteb
- leaderboard name
- MTEB Classification
- dimension
- embedding
- metric
- Average task score
- rank
- 417
- sample size
- 220
- aggregation scope
- subsets
- Danish
- Norwegian_b
- Norwegian_n
- Swedish
- af
- am
- ar
- az
- bn
- cy
- da
- de
- default
- el
- en
- es
- fa
- fi
- fr
- he
- hi
- hu
- hy
- id
- is
- it
- ja
- jv
- ka
- km
- kn
- ko
- lv
- ml
- mn
- ms
- my
- nb
- nl
- pl
- pt
- ro
- ru
- sl
- sq
- sv
- sw
- ta
- te
- th
- tl
- tr
- ur
- vi
- zh-CN
- zh-TW
- task_count
- 13
- task_names
- AngryTweetsClassification
- DKHateClassification
- DalajClassification
- DanishPoliticalCommentsClassification
- LccSentimentClassification
- MassiveIntentClassification
- MassiveScenarioClassification
- NoRecClassification
- NordicLangClassification
- NorwegianParliamentClassification
- ScalaClassification
- SweRecClassification
- SwedishSentimentClassification
- sample_size
- 220
- subset_count
- 56
- subset_sample
- Danish
- Norwegian_b
- Norwegian_n
- Swedish
- af
- am
- ar
- az
- bn
- cy
- da
- de
- default
- el
- en
- es
- fa
- fi
- fr
- he
- hi
- hu
- hy
- id
- is
- it
- ja
- jv
- ka
- km
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- model_revision_sample
- c23d21b0620b635a76227c604d44e43a9f0ee389
- source model id
- FacebookAI/xlm-roberta-large
Original result ↗48.904%
- source id
- mteb
- leaderboard name
- MTEB Semantic Similarity
- dimension
- embedding
- metric
- Average task score
- rank
- 483
- sample size
- 2
- aggregation scope
- task_count
- 2
- task_names
- STS22
- STSBenchmarkMultilingualSTS
- sample_size
- 2
- subset_count
- 1
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- source model id
- FacebookAI/xlm-roberta-large
Original result ↗32.498%
- source id
- mteb
- leaderboard name
- MTEB Clustering
- dimension
- embedding
- metric
- Average task score
- rank
- 519
- sample size
- 7
- aggregation scope
- splits
- articles
- headlines
- summaries
- test
- task_count
- 6
- task_names
- SNLHierarchicalClusteringP2P
- SNLHierarchicalClusteringS2S
- SwednClusteringP2P
- SwednClusteringS2S
- VGHierarchicalClusteringP2P
- VGHierarchicalClusteringS2S
- sample_size
- 7
- subset_count
- 1
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- model_revision_sample
- c23d21b0620b635a76227c604d44e43a9f0ee389
- source model id
- FacebookAI/xlm-roberta-large
Original result ↗25.104%
- source id
- mteb
- leaderboard name
- MTEB Clustering
- dimension
- embedding
- metric
- Average task score
- rank
- 589
- sample size
- 11
- aggregation scope
- task_count
- 11
- task_names
- AlloProfClusteringP2P
- AlloProfClusteringS2S
- BlurbsClusteringP2P
- BlurbsClusteringS2S
- HALClusteringS2S
- MLSUMClusteringP2P
- MLSUMClusteringS2S
- MasakhaNEWSClusteringP2P
- MasakhaNEWSClusteringS2S
- TenKGnadClusteringP2P
- TenKGnadClusteringS2S
- sample_size
- 11
- subset_count
- 3
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- source model id
- FacebookAI/xlm-roberta-large
Original result ↗36.129%
- source id
- mteb
- leaderboard name
- MTEB Classification
- dimension
- embedding
- metric
- Average task score
- rank
- 600
- sample size
- 4
- aggregation scope
- task_count
- 4
- task_names
- AmazonReviewsClassification
- MTOPDomainClassification
- MTOPIntentClassification
- MasakhaNEWSClassification
- sample_size
- 4
- subset_count
- 2
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- source model id
- FacebookAI/xlm-roberta-large
Original result ↗35.971%
- source id
- mteb
- leaderboard name
- MTEB Overall
- dimension
- embedding
- metric
- Average task score
- rank
- 841
- sample size
- 236
- source model id
- FacebookAI/xlm-roberta-large
Original result ↗10.085%
- source id
- mteb
- leaderboard name
- MTEB Retrieval
- dimension
- embedding
- metric
- Average task score
- rank
- 849
- sample size
- 7
- aggregation scope
- task_count
- 7
- task_names
- DanFeverRetrieval
- NorQuadRetrieval
- SNLRetrieval
- SweFaqRetrieval
- SwednRetrieval
- TV2Nordretrieval
- TwitterHjerneRetrieval
- sample_size
- 7
- subset_count
- 1
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- model_revision_sample
- c23d21b0620b635a76227c604d44e43a9f0ee389
- source model id
- FacebookAI/xlm-roberta-large
Original result ↗4.144%
- source id
- mteb
- leaderboard name
- MTEB Retrieval
- dimension
- embedding
- metric
- Average task score
- rank
- 875
- sample size
- 5
- aggregation scope
- task_count
- 5
- task_names
- AlloprofRetrieval
- BSARDRetrieval
- MintakaRetrieval
- SyntecRetrieval
- XPQARetrieval
- sample_size
- 5
- subset_count
- 3
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- source model id
- FacebookAI/xlm-roberta-large
Original result ↗29.082%
- source id
- mteb
- leaderboard name
- MTEB Overall
- dimension
- embedding
- metric
- Average task score
- rank
- 901
- sample size
- 30
- aggregation scope
- splits
- dev
- test
- test.full
- validation.full
- subsets
- default
- eng_Latn-fra_Latn
- fr
- fr-en
- fra
- fra-fra
- fra_Latn-eng_Latn
- task_count
- 28
- task_names
- AlloProfClusteringP2P
- AlloProfClusteringS2S
- AlloprofRetrieval
- AmazonReviewsClassification
- BSARDRetrieval
- BlurbsClusteringP2P
- BlurbsClusteringS2S
- DiaBlaBitextMining
- FloresBitextMining
- HALClusteringS2S
- MLSUMClusteringP2P
- MLSUMClusteringS2S
- MTOPDomainClassification
- MTOPIntentClassification
- MasakhaNEWSClassification
- MasakhaNEWSClusteringP2P
- MasakhaNEWSClusteringS2S
- MintakaRetrieval
- OpusparcusPC
- PawsXPairClassification
- SICKFr
- STS22
- STSBenchmarkMultilingualSTS
- SummEvalFr
- SyntecRetrieval
- TenKGnadClusteringP2P
- TenKGnadClusteringS2S
- XPQARetrieval
- sample_size
- 30
- subset_count
- 7
- subset_sample
- default
- eng_Latn-fra_Latn
- fr
- fr-en
- fra
- fra-fra
- fra_Latn-eng_Latn
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- source model id
- FacebookAI/xlm-roberta-large
Original result ↗Provider specifications & access
1–5 / 5
- source model id
- HuggingFace/facebookai-xlm-roberta-large@1
- hosting
- foundry-managed-compute
- license
- mit
- source model id
- HuggingFace/facebookai-xlm-roberta-large@2
- hosting
- foundry-managed-compute
- license
- mit
- source model id
- HuggingFace/facebookai-xlm-roberta-large@3
- hosting
- foundry-managed-compute
- license
- mit
- source model id
- HuggingFace/facebookai-xlm-roberta-large@4
- hosting
- foundry-managed-compute
- license
- mit
- source model id
- HuggingFace/facebookai-xlm-roberta-large@5
- hosting
- foundry-managed-compute
- license
- mit
Safety assessments
1–1 / 1
31 / 100
- source id
- stanfordFMTI
- canonical model id
- huggingface/FacebookAI/xlm-roberta-large
- taxonomy
- transparency
- hazard category
- transparency
- hazard name
- Organization transparency
- policy area
- Meta
- assessment type
- organization-level disclosure
- metric
- disclosure_score
- result label
- 31 / 100
- sample size
- 100
- updated at
- 2026-11-09T18:08:05.227Z
Hugging Face model card
1–1 / 1
- downloads
- 3072220
- likes
- 555
- pipeline tag
- fill-mask
- library name
- transformers
- License
- mit
Explore more models