Our 5th-gen embeddings: two lightweight multilingual models with SOTA performance in retrieval, matching, clustering, and classification.
-
jina-embeddings-v5-text: Task-Targeted Embedding Distillation
Paper • 2602.15547 • Published • 26 -
jinaai/jina-embeddings-v5-text-small
Feature Extraction • Updated • 78.3k • 116 -
jinaai/jina-embeddings-v5-text-nano
Feature Extraction • Updated • 246k • 48 -
jinaai/jina-embeddings-v5-text-small-text-matching
Sentence Similarity • 0.6B • Updated • 16.2k • 10