Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents
Paper
•
2310.19923
•
Published
•
14
jina-embeddings-v2
The V2 family of Jina Embeddings supports encoding large documents with 8k sequence length.
-
-
Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings
Paper • 2402.17016 • Published • 5 -
jinaai/jina-embeddings-v2-base-en
Feature Extraction • 0.1B • Updated • 185k • 726 -
jinaai/jina-embeddings-v2-base-zh
Feature Extraction • 0.2B • Updated • 21k • 243 -
jinaai/jina-embeddings-v2-small-en
Feature Extraction • 0.0B • Updated • 688k • 137 -
jinaai/jina-embeddings-v2-base-de
Feature Extraction • 0.2B • Updated • 24.5k • 80 -
jinaai/jina-embeddings-v2-base-es
Feature Extraction • 0.2B • Updated • 16.7k • 34 -
jinaai/jina-embeddings-v2-base-code
Feature Extraction • 0.2B • Updated • 88.3k • 115