Model Card for passage-ranker-v1-XS-multilingual

This model is a passage ranker developed by Sinequa. It produces a relevance score given a query-passage pair and is used to order search results.

Model name: passage-ranker-v1-XS-multilingual

Supported Languages

The model was trained and tested in the following languages:

• English
• French
• German
• Spanish

Scores

Metric	Value
Relevance (NDCG@10)	0.453

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

Inference Times

GPU	Quantization type	Batch size 1	Batch size 32
NVIDIA A10	FP16	1 ms	2 ms
NVIDIA A10	FP32	1 ms	7 ms
NVIDIA T4	FP16	1 ms	6 ms
NVIDIA T4	FP32	1 ms	20 ms
NVIDIA L4	FP16	1 ms	3 ms
NVIDIA L4	FP32	2 ms	8 ms

Gpu Memory usage

Quantization type	Memory
FP16	150 MiB
FP32	300 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.

Requirements

• Minimal Sinequa version: 11.10.0
• Minimal Sinequa version for using FP16 models and GPUs with CUDA compute capability of 8.9+ (like NVIDIA L4): 11.11.0
• Cuda compute capability: above 5.0 (above 6.0 for FP16 use)

Model Details

Overview

• Number of parameters: 16 million
• Base language model: Homegrown Sinequa BERT-Mini (Paper) pretrained in the four supported languages
• Insensitive to casing and accents
• Training procedure: MonoBERT

Training Data

• Probably-Asked Questions (Paper, Official Page)
  • Original English dataset
  • Translated datasets for the other three supported languages

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	NDCG@10
Average	0.453
Arguana	0.516
CLIMATE-FEVER	0.159
DBPedia Entity	0.355
FEVER	0.729
FiQA-2018	0.282
HotpotQA	0.688
MS MARCO	0.334
NFCorpus	0.341
NQ	0.438
Quora	0.726
SCIDOCS	0.143
SciFact	0.630
TREC-COVID	0.664
Webis-Touche-2020	0.337

We evaluated the model on the datasets of the MIRACL benchmark to test its multilingual capacities. Note that not all training languages are part of the benchmark, so we only report the metrics for the existing languages.

Language	NDCG@10
French	0.346
German	0.368
Spanish	0.416