AI正在发生 未来正在更新mmBERTscandi-base-embedding
mmBERTscandi-base-embedding is finetuned on the Scandinavian (Danish, Norwegian, Swedish) text embeddings dataset from DDSC (nordic-embedding-training-data) using jonasaise/scandmmBERT-base-scandinavian/jhu-clsp/mmBERT-base as the base model via the sentence-transformers framework. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
译文尚未就绪，显示来源原文
mmBERTscandi-base-embedding is finetuned on the Scandinavian (Danish, Norwegian, Swedish) text embeddings dataset from DDSC (nordic-embedding-training-data) using jonasaise/scandmmBERT-base-scandinavian/jhu-clsp/mmBERT-base as the base model via the sentence-transformers framework. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.