768-dim semantic vectors
According to the model card, the model maps sentences and paragraphs to a 768-dimensional dense vector space for semantic search.
Open Source Model Profile · sentence-transformers
multi-qa-mpnet-base-dot-v1
multi-qa-mpnet-base-dot-v1 is a 109.49M-parameter MPNet sentence-similarity model from sentence-transformers. According to the model card, it maps sentences to 768-dim vectors for semantic search.
- Publisher
- sentence-transformers
- Task
- sentence-similarity
- Model type
- mpnet
- License
- Unknown
- Library
- sentence-transformers
- Publication status
- Accepted · not indexed
Model overview
multi-qa-mpnet-base-dot-v1 is published by sentence-transformers as a sentence-similarity embedding model. The captured configuration identifies MPNetForMaskedLM with model type mpnet and 109486978 Safetensors parameters. According to the model card, it was trained on 215M question-answer pairs for semantic search with dot-score similarity.
Recorded capabilities
215M QA training pairs
The model card says it was trained on 215M question-answer pairs, with a detailed per-dataset table totaling 214988242 tuples.
Dot-product with CLS pooling
According to the model card, training used MultipleNegativesRankingLoss with CLS-pooling, dot-product similarity, and scale 1.
Multiple serving paths
The model card documents sentence-transformers usage, Transformers CLS-pooling code, and Text Embeddings Inference deployment.
Use cases in the source record
- Semantic search workflows that encode queries and passages into 768-dim vectors and rank them with dot scores.
- Retrieval experiments using sentence-transformers, Transformers CLS-pooling, or Text Embeddings Inference serving.
Limitations and unknowns
- No evaluation results were extracted from this record.
- No license value was extracted for this record.
- According to the model card, inputs are truncated at 512 word pieces and the model was trained only up to 250 word pieces, so longer text may work less well.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: sentence-transformers/multi-qa-mpnet-base-dot-v1
Captured: Unknown. Processed: 2026-09-07T19:34:57.819890+00:00.
multi-qa-mpnet-base-dot-v1 This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and was designed for semantic search . It has been trained on 215M (question, answer) pairs from diverse sources. For an introduction to semantic search, have a look at: SBERT.net - 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, util query = "How many people live in London?" docs = [ "Around 9 Mi…
F001F002F003F004F005F006F007F008F009F010F011F012F014F015F017F019F021F022F023