metadata

language:
  - en

Model Card for `vectorizer-v1-S-en`

This model is a vectorizer developed by Sinequa. It produces an embedding vector given a passage or a query. The passage vectors are stored in our vector index and the query vector is used at query time to look up relevant passages in the index.

Model name: vectorizer-v1-S-en

Supported Languages

The model was trained and tested in the following languages:

English

Scores

Metric	Value
Relevance (Recall@100)	0.456

Note that the relevance score is computed as an average over 14 retrieval datasets (see details below).

Inference Times

GPU	Batch size 1 (at query time)	Batch size 32 (at indexing)
NVIDIA A10	2 ms	14 ms
NVIDIA T4	4 ms	52 ms

The inference times only measure the time the model takes to process a single batch, it does not include pre- or post-processing steps like the tokenization.

Requirements

Minimal Sinequa version: 11.10.0
GPU memory usage: 330 MiB

Note that GPU memory usage only includes how much GPU memory the actual model consumes on an NVIDIA T4 GPU with a batch size of 32. It does not include the fix amount of memory that is consumed by the ONNX Runtime upon initialization which can be around 0.5 to 1 GiB depending on the used GPU.

Model Details

Overview

Number of parameters: 29 million
Base language model: English BERT-Small
Insensitive to casing and accents
Output dimensions: 256 (reduced with an additional dense layer)
Training procedure: TBD

Training Data

TBD

Evaluation Metrics

To determine the relevance score, we averaged the results that we obtained when evaluating on the datasets of the BEIR benchmark. Note that all these datasets are in English.

Dataset	Recall@100
Average	0.456

Arguana	0.832
CLIMATE-FEVER	0.342
DBPedia Entity	0.299
FEVER	0.660
FiQA-2018	0.301
HotpotQA	0.434
MS MARCO	0.610
NFCorpus	0.159
NQ	0.671
Quora	0.966
SCIDOCS	0.194
SciFact	0.592
TREC-COVID	0.037
Webis-Touche-2020	0.285

Model Card for vectorizer-v1-S-en