ONNX adapters that translate a chunk's embedding from one model's space into another's, without re-embedding. From the Queryn pipeline.
-
QuerynAi/queryn-adapter-ada-002_to_bge-m3
Feature Extraction • Updated • 9 -
QuerynAi/queryn-adapter-ada-002_to_fastembed-bge-small
Feature Extraction • Updated • 9 -
QuerynAi/queryn-adapter-ada-002_to_me5-large
Feature Extraction • Updated • 6 -
QuerynAi/queryn-adapter-ada-002_to_nemotron-1b-free
Feature Extraction • Updated • 6