paraphrase-multilingual-MiniLM-L12-v2
A multilingual sentence embedding model provided by SentenceTransformers that outputs 384-dimensional vectors and supports cross-lingual semantic similarity computation. It is commonly used for semantic retrieval and RAG.
Timeline (last 90 days)
Different embedding models have different output dimensions: paraphrase-multilingual-MiniLM-L12-v2 is 384 dimensions, the BERT-base series is 768 dimensions, OpenAI text-embedding-3-small is 1536 dimensions, and text-embedding-3-large and Google gemini-embedding-001 are 3072 dimensions.
When using the paraphrase-multilingual-MiniLM-L12-v2 model for semantic retrieval, for the query 'Where is the kitten?', 'The cat sat on the mat.' scores 0.560 and ranks first, the Spanish sentence 'El gato duerme en la alfombra.' scores 0.480 and ranks second, and the two sentences share no words at all.
paraphrase-multilingual-MiniLM-L12-v2 is a multilingual sentence embedding model provided by the Sentence Transformers library; it compresses the output of a 12-layer Transformer encoder into a 384-dimensional vector through mean pooling and supports about 50 languages.
paraphrase-multilingual-MiniLM-L12-v2 reads at most 128 tokens, and the excess is silently truncated, which is one of the reasons RAG needs to split documents into chunks.
paraphrase-multilingual-MiniLM-L12-v2 is a lightweight open-source sentence vector model that supports multiple languages.
All Facts (5)
Different embedding models have different output dimensions: paraphrase-multilingual-MiniLM-L12-v2 is 384 dimensions, the BERT-base series is 768 dimensions, OpenAI text-embedding-3-small is 1536 dimensions, and text-embedding-3-large and Google gemini-embedding-001 are 3072 dimensions.
50%UnverifiedWhen using the paraphrase-multilingual-MiniLM-L12-v2 model for semantic retrieval, for the query 'Where is the kitten?', 'The cat sat on the mat.' scores 0.560 and ranks first, the Spanish sentence 'El gato duerme en la alfombra.' scores 0.480 and ranks second, and the two sentences share no words at all.
50%Unverifiedparaphrase-multilingual-MiniLM-L12-v2 is a multilingual sentence embedding model provided by the Sentence Transformers library; it compresses the output of a 12-layer Transformer encoder into a 384-dimensional vector through mean pooling and supports about 50 languages.
50%Unverifiedparaphrase-multilingual-MiniLM-L12-v2 reads at most 128 tokens, and the excess is silently truncated, which is one of the reasons RAG needs to split documents into chunks.
50%Unverifiedparaphrase-multilingual-MiniLM-L12-v2 is a lightweight open-source sentence vector model that supports multiple languages.
50%