sensiarion
/

embeddinggemma-300m-code-8L-distill-int8

Feature Extraction

Model card Files Files and versions

embeddinggemma-300m-code-8L-distill-int8 / mlx_encoder.py

Commit History

Add thin EmbeddingGemma code model (curvature-pruned 8L + int8 + distill/contrastive)

38bb3d8
verified

sensiarion commited on Jun 25