lightonai
/

LateOn-regularized

Sentence Similarity

sentence-transformers

feature-extraction

text-embeddings-inference

🇪🇺 Region: EU

Model card Files Files and versions

NohTow commited on Jul 6

Commit

98adabb

·

verified ·

1 Parent(s): 631f7b7

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -85,7 +85,7 @@ Key takeaways:
 - **Massive improvement for MUVERA/SMVE**: centered MUVERA rk=0 goes from 32.66 → 40.80 (+8.1 points), and with rk=200 reranking the gap to full PLAID drops to just 2.7 points (note: the goal of the study was making representations better, not sweeping MUVERA/SMVE parameters to get perfect scores)
 - **Cross-method transfer**: MUVERA-regularized training also boosts SMVE, and vice-versa, showing the regularization improves global compressibility rather than optimizing a single projection subspace.
-### BEIR (14 datasets, NDCG@10) — PLAID Retrieval
 LateOn-regularized maintains the strong PLAID performance of the LateOn family. For full BEIR results, see the [LateOn model card](https://huggingface.co/lightonai/LateOn).

 - **Massive improvement for MUVERA/SMVE**: centered MUVERA rk=0 goes from 32.66 → 40.80 (+8.1 points), and with rk=200 reranking the gap to full PLAID drops to just 2.7 points (note: the goal of the study was making representations better, not sweeping MUVERA/SMVE parameters to get perfect scores)
 - **Cross-method transfer**: MUVERA-regularized training also boosts SMVE, and vice-versa, showing the regularization improves global compressibility rather than optimizing a single projection subspace.
+### BEIR (15 datasets, NDCG@10) — PLAID Retrieval
 LateOn-regularized maintains the strong PLAID performance of the LateOn family. For full BEIR results, see the [LateOn model card](https://huggingface.co/lightonai/LateOn).