Initial commit (#1)

- Model sources and card (d858640c6d58503cc6c9d36590ed5243c5d93920)

README.md

@@ -0,0 +1,86 @@
+---
+language:
+  - en
+---
+
+# Model Card for `passage-ranker.chocolate`
+
+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.chocolate`
+
+## Supported Languages
+
+The model was trained and tested in the following languages:
+
+- English
+
+## Scores
+
+| Metric              | Value |
+|:--------------------|------:|
+| Relevance (NDCG@10) | 0.484 |
+
+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 |         22 ms |
+| NVIDIA T4  |         64 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: 550 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: 23 million
+- Base language model: [MiniLM-L6-H384-uncased](https://huggingface.co/nreimers/MiniLM-L6-H384-uncased)
+  ([Paper](https://arxiv.org/abs/2002.10957), [GitHub](https://github.com/microsoft/unilm/tree/master/minilm))
+- Insensitive to casing and accents
+- Training procedure: [MonoBERT](https://arxiv.org/abs/1901.04085)
+
+### Training Data
+
+- MS MARCO Passage Ranking
+  ([Paper](https://arxiv.org/abs/1611.09268),
+  [Official Page](https://microsoft.github.io/msmarco/),
+  [dataset on HF hub](https://huggingface.co/datasets/unicamp-dl/mmarco))
+
+### 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           |   0.486 |
+|                   |         |
+| Arguana           |   0.554 |
+| CLIMATE-FEVER     |   0.209 |
+| DBPedia Entity    |   0.367 |
+| FEVER             |   0.744 |
+| FiQA-2018         |   0.339 |
+| HotpotQA          |   0.685 |
+| MS MARCO          |   0.412 |
+| NFCorpus          |   0.352 |
+| NQ                |   0.454 |
+| Quora             |   0.818 |
+| SCIDOCS           |   0.158 |
+| SciFact           |   0.658 |
+| TREC-COVID        |   0.674 |
+| Webis-Touche-2020 |   0.345 |

config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86393158c095eeeb286403c07797c391bed615a4cb70983fbb3640199f377c2e
+size 90893101