768-dimensional DPR vectors
According to the model card, the model maps sentences and paragraphs to a 768-dimensional dense vector space.
Open Source Model Profile · sentence-transformers
facebook-dpr-question_encoder-multiset-base
facebook-dpr-question_encoder-multiset-base is a 109M-parameter BERT encoder from sentence-transformers. Its model card describes a DPR port mapping sentences and paragraphs to 768-dimensional vectors.
- Publisher
- sentence-transformers
- Task
- sentence-similarity
- Model type
- bert
- License
- apache-2.0
- Library
- sentence-transformers
- Publication status
- Accepted · not indexed
Model overview
facebook-dpr-question_encoder-multiset-base is published by sentence-transformers as a sentence-similarity model. The captured configuration identifies BertModel with model type bert, and Safetensors metadata reports 109,482,752 parameters. According to the model card, it is a sentence-transformers port of the DPR model.
Recorded capabilities
CLS pooling setup
The card's architecture section describes a Transformer plus pooling block with CLS-token pooling and 768 embedding width.
Dual library path
According to the model card, users can load it with SentenceTransformer or Transformers with explicit CLS pooling code.
Use cases in the source record
- Semantic search and clustering using the card's 768-dimensional sentence and paragraph vectors.
- Sentence-embedding work with the sentence-transformers library or direct Transformers pooling.
Limitations and unknowns
- No evaluation results were extracted from this record.
- No context-window value was extracted from this record; the card mentions max_seq_length 509 without a verified context-window claim.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: sentence-transformers/facebook-dpr-question_encoder-multiset-base
Captured: Unknown. Processed: 2026-09-07T19:34:57.763262+00:00.
sentence-transformers/facebook-dpr-question_encoder-multiset-base This is a port of the DPR Model to 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/facebook-dpr…
F001F002F003F004F005F006F007F008F009F010F011F012F013F014F015