|
---
|
|
language:
|
|
- en
|
|
---
|
|
|
|
# Model Card for `passage-ranker-v1-XS-en`
|
|
|
|
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-en`
|
|
|
|
## Supported Languages
|
|
|
|
The model was trained and tested in the following languages:
|
|
|
|
- English
|
|
|
|
## Scores
|
|
|
|
| Metric | Value |
|
|
|:--------------------|------:|
|
|
| Relevance (NDCG@10) | 0.438 |
|
|
|
|
Note that the relevance score is computed as an average over 14 retrieval datasets (see
|
|
[details below](#evaluation-metrics)).
|
|
|
|
## Inference Times
|
|
|
|
| GPU | Quantization type | Batch size 1 | Batch size 32 |
|
|
|:------------------------------------------|:------------------|---------------:|---------------:|
|
|
| NVIDIA A10 | FP16 | 1 ms | 2 ms |
|
|
| NVIDIA A10 | FP32 | 1 ms | 8 ms |
|
|
| NVIDIA T4 | FP16 | 1 ms | 6 ms |
|
|
| NVIDIA T4 | FP32 | 3 ms | 23 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 | 200 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](https://developer.nvidia.com/cuda-gpus): above 5.0 (above 6.0 for FP16 use)
|
|
|
|
## Model Details
|
|
|
|
### Overview
|
|
|
|
- Number of parameters: 11 million
|
|
- Base language model: [English BERT-Mini](https://huggingface.co/google/bert_uncased_L-4_H-256_A-4)
|
|
- Insensitive to casing and accents
|
|
- Training procedure: [MonoBERT](https://arxiv.org/abs/1901.04085)
|
|
|
|
### Training Data
|
|
|
|
- Probably-Asked Questions
|
|
([Paper](https://arxiv.org/abs/2102.07033),
|
|
[Official Page](https://github.com/facebookresearch/PAQ))
|
|
|
|
### Evaluation Metrics
|
|
|
|
To determine the relevance score, we averaged the results that we obtained when evaluating on the datasets of the
|
|
[BEIR benchmark](https://github.com/beir-cellar/beir). Note that all these datasets are in English.
|
|
|
|
| Dataset | NDCG@10 |
|
|
|:------------------|--------:|
|
|
| Average | 0.438 |
|
|
| | |
|
|
| Arguana | 0.524 |
|
|
| CLIMATE-FEVER | 0.150 |
|
|
| DBPedia Entity | 0.338 |
|
|
| FEVER | 0.706 |
|
|
| FiQA-2018 | 0.269 |
|
|
| HotpotQA | 0.630 |
|
|
| MS MARCO | 0.328 |
|
|
| NFCorpus | 0.340 |
|
|
| NQ | 0.429 |
|
|
| Quora | 0.722 |
|
|
| SCIDOCS | 0.141 |
|
|
| SciFact | 0.627 |
|
|
| TREC-COVID | 0.628 |
|
|
| Webis-Touche-2020 | 0.306 |
|
|
|
