Downloads · 30 days
12
43% of all-time downloads
tevatron-elastic-bert-reranker-depth
utahnlp/tevatron-elastic-bert-reranker-depth
tevatron-elastic-bert-reranker-depth is a feature extraction model from utahnlp. Use it when you need embeddings to search or compare text. It is set up for transformers. The card lists the license as apache-2.0.
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 an elastic depth axis (early exit): one checkpo…
All-time downloads
28
Public
Parameters
109M
219 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors219 MB · 100%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Jul 11, 2026
- Updated
- Jul 11, 2026
- SHA
- 643e6701
Base models
Model card
From the Hugging Face model README
tevatron-elastic-bert-reranker-depth
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 an elastic depth axis (early exit): one checkpoint serves several layer counts.
- Base model:
google-bert/bert-base-uncased - Task: reranker
- Elastic axis: depth
- Training data: rlhn/rlhn-680K, max length 512,
query:/passage:prefixes.
Full-point BEIR-15 nDCG@10: 0.453.
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.
- Task
- Feature Extraction
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Jul 11, 2026
- Updated
- Jul 11, 2026