768-dimensional sentence embeddings
According to the model card, the model maps sentences and paragraphs to 768-dimensional dense vectors through a Transformer plus pooling stack.
Open Source Model Profile · sentence-transformers
stsb-xlm-r-multilingual
stsb-xlm-r-multilingual is a 278M-parameter XLM-RoBERTa sentence-embedding model from sentence-transformers with 768-dimensional vectors.
- Publisher
- sentence-transformers
- Task
- sentence-similarity
- Model type
- xlm-roberta
- License
- apache-2.0
- Library
- sentence-transformers
- Publication status
- Accepted · not indexed
Model overview
stsb-xlm-r-multilingual is published by sentence-transformers as an xlm-roberta sentence-similarity model. The captured configuration identifies XLMRobertaModel and Safetensors metadata reports 278,044,162 parameters. According to the model card, it produces 768-dimensional sentence embeddings for clustering and semantic search, with card data recording apache-2.0.
Recorded capabilities
Clustering and semantic-search use
According to the model card, the publisher describes clustering and semantic search as tasks, with SentenceTransformer and Transformers usage examples.
128-length mean-pooling setup
According to the model card, the documented stack uses maximum sequence length 128 with mean-token pooling and no CLS-token pooling.
Use cases in the source record
- Semantic search and clustering using the publisher's documented 768-dimensional SentenceTransformer encoding workflow.
- Custom embedding pipelines that pass inputs through the Transformer and apply the documented mean-pooling operation.
Limitations and unknowns
- No evaluation results, training dataset details, or supported-language list was extracted.
- Provider state is historical snapshot data and should be refreshed before being presented as current.
Source and provenance
Source: sentence-transformers/stsb-xlm-r-multilingual
Captured: Unknown. Processed: 2026-09-07T19:34:57.811581+00:00.
sentence-transformers/stsb-xlm-r-multilingual This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. Usage (Sentence-Transformers) Using this model becomes easy when you have sentence-transformers installed: pip install -U sentence-transformers Then you can use the model like this: from sentence_transformers import SentenceTransformer sentences = [ "This is an example sentence" , "Each sentence is converted" ] model = SentenceTransformer( 'sentence-transformers/stsb-xlm-r-multilingual' ) embeddings = model.encode(sent…
F001F002F003F004F005F006F007F008F010F011F012F013F014F015F016