sinequa
/

passage-ranker-v1-L-en

@@ -1,84 +1,92 @@
----
-language:
-  - en
----
-# Model Card for `passage-ranker-v1-L-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-L-en`
-## Supported Languages
-The model was trained and tested in the following languages:
-- English
-## Scores
-| Metric              | Value |
-|:--------------------|------:|
-| Relevance (NDCG@10) | 0.466 |
-Note that the relevance score is computed as an average over 14 retrieval datasets (see
-[details below](#evaluation-metrics)).
-## Inference Times
-| GPU        | Batch size 32 |
-|:-----------|--------------:|
-| NVIDIA A10 |         83 ms |
-| NVIDIA T4  |        356 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: 1060 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: 109 million
-- Base language model: [English BERT-Base](https://huggingface.co/bert-base-uncased)
-- 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           |   0.466 |
-|                   |         |
-| Arguana           |   0.567 |
-| CLIMATE-FEVER     |   0.162 |
-| DBPedia Entity    |   0.363 |
-| FEVER             |   0.721 |
-| FiQA-2018         |   0.304 |
-| HotpotQA          |   0.680 |
-| MS MARCO          |   0.342 |
-| NFCorpus          |   0.346 |
-| NQ                |   0.487 |
-| Quora             |   0.779 |
-| SCIDOCS           |   0.150 |
-| SciFact           |   0.649 |
-| TREC-COVID        |   0.683 |
-| Webis-Touche-2020 |   0.287 |

+---
+language:
+  - en
+---
+# Model Card for `passage-ranker-v1-L-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-L-en`
+## Supported Languages
+The model was trained and tested in the following languages:
+- English
+## Scores
+| Metric              | Value |
+|:--------------------|------:|
+| Relevance (NDCG@10) | 0.466 |
+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              |           2 ms |          27 ms |
+| NVIDIA A10                                | FP32              |           4 ms |          82 ms |
+| NVIDIA T4                                 | FP16              |           3 ms |          63 ms |
+| NVIDIA T4                                 | FP32              |          13 ms |         342 ms |
+| NVIDIA L4                                 | FP16              |           2 ms |          39 ms |
+| NVIDIA L4                                 | FP32              |           5 ms |         119 ms |
+## Gpu Memory usage
+| Quantization type                                |   Memory   |
+|:-------------------------------------------------|-----------:|
+| FP16                                             |    550 MiB |
+| FP32                                             |   1100 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: 109 million
+- Base language model: [English BERT-Base](https://huggingface.co/bert-base-uncased)
+- 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           |   0.466 |
+|                   |         |
+| Arguana           |   0.567 |
+| CLIMATE-FEVER     |   0.162 |
+| DBPedia Entity    |   0.363 |
+| FEVER             |   0.721 |
+| FiQA-2018         |   0.304 |
+| HotpotQA          |   0.680 |
+| MS MARCO          |   0.342 |
+| NFCorpus          |   0.346 |
+| NQ                |   0.487 |
+| Quora             |   0.779 |
+| SCIDOCS           |   0.150 |
+| SciFact           |   0.649 |
+| TREC-COVID        |   0.683 |
+| Webis-Touche-2020 |   0.287 |