← Back to models

SPLADE

embedder

Produce sparse, term-weighted vectors that combine keyword precision with learned expansion.

antfly inference pull sparse-encoder-testing/splade-bert-tiny-nq-onnx
By sparse-encoder-testingLicense: apache-2.0Hugging Face source

Technical Specs

Architecture
BERT tiny / SPLADE
Parameters
4.4M
sparseONNXEnglish

Usage

Pull the model

antfly inference pull sparse-encoder-testing/splade-bert-tiny-nq-onnx

Start Antfly Inference

# With Antfly standalone (Antfly Inference enabled by default)
antfly standalone

# Or run Antfly Inference on its own, listening on 127.0.0.1:8090
antfly inference run

Use in configuration

{
  "embedders": {
    "local": {
      "provider": "antfly",
      "model": "sparse-encoder-testing/splade-bert-tiny-nq-onnx"
    }
  }
}