CoolFace
Modelpublic

utahnlp/tevatron-elastic-modernbert-reranker-plain

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face
0likes5downloads
Model Card

tevatron-elastic-modernbert-reranker-plain

A reranker trained with Tevatron-Elastic, which trains one checkpoint to serve many operating points along the depth / width / token compression axes. This checkpoint is a single full-size operating point (baseline).

  • Base model: answerdotai/ModernBERT-base
  • Task: reranker
  • Elastic axis: plain
  • Training data: rlhn/rlhn-680K, max length 512, query:/passage: prefixes.

Full-point BEIR-15 nDCG@10: 0.457.

Load with the Tevatron-Elastic framework and select an operating point with prune_to / encode_at; see the repository for usage. Part of a release of 20 checkpoints (3 backbones, retrieval and reranking, all compression axes) accompanying the Tevatron-Elastic paper. Reported as a reproducibility resource, not a state-of-the-art claim.