← Catalog

rasyosef/splade-mini

Add to compare Open comparison →

Primitive: /encode · Encode · BERT

This is a SPLADE sparse retrieval model based on BERT-Mini (11M) that was trained by distilling a Cross-Encoder on the MSMARCO dataset. The cross-encoder used was ms-marco-MiniLM-L6-v2.

View on Hugging Face → Fine-tuned from prajjwal1/bert-mini

Overview

Hardware: L4RTX-PRO-6000 — drives latency, throughput & cost

Size	11M params
Tasks	/encode
License	mit
Languages	en
Latency	56 ms
Throughput	56.3K tok/s
Cost	$0.0039 /1M tok

Cost is approximate — computed from list GPU prices; your actual price depends on the provider you deploy SIE with.

Embedding

Output types	Sparse
Dimensions	sparse: 30,522
Max sequence length	512
Inputs	text

Benchmarks