SixOpen
/

HARE

Feature Extraction

semantic-search

Model card Files Files and versions

SixOpen commited on 6 days ago

Commit

fed4d3d

·

verified ·

1 Parent(s): b5ceec6

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -24,7 +24,8 @@ Live Demo:
 [![Try in Spaces](https://huggingface.co/datasets/huggingface/badges/resolve/main/open-in-hf-spaces-sm.svg)](https://huggingface.co/spaces/SixOpen/HARE)
-![image](https://cdn-uploads.huggingface.co/production/uploads/65f47dc77874f3874523c628/GFqHaFy1fplauCi2mkm7M.png)
 Conventional embedding models are stateless: adding new content requires re-encoding from scratch because token representations depend on the entire sequence.
 HARE replaces 14 local sliding-window attention layers in ModernBERT-base with bidirectional RWKV linear recurrence while retaining 8 global attention layers.

 [![Try in Spaces](https://huggingface.co/datasets/huggingface/badges/resolve/main/open-in-hf-spaces-sm.svg)](https://huggingface.co/spaces/SixOpen/HARE)
+![image](https://cdn-uploads.huggingface.co/production/uploads/65f47dc77874f3874523c628/eQB_kI-cVe_xr5cNeJqVM.png)
 Conventional embedding models are stateless: adding new content requires re-encoding from scratch because token representations depend on the entire sequence.
 HARE replaces 14 local sliding-window attention layers in ModernBERT-base with bidirectional RWKV linear recurrence while retaining 8 global attention layers.