msmarco-v1-passage.cos-dpr-distil.hnsw-int8.onnx.yaml

---
corpus: msmarco-passage-cos-dpr-distil
corpus_path: collections/msmarco/msmarco-passage-cos-dpr-distil/

download_url: https://rgw.cs.uwaterloo.ca/pyserini/data/msmarco-passage-cos-dpr-distil.tar
download_checksum: e20ffbc8b5e7f760af31298aefeaebbd

index_path: indexes/lucene-hnsw-int8.msmarco-v1-passage.cos-dpr-distil/
index_type: hnsw
collection_class: JsonDenseVectorCollection
generator_class: DenseVectorDocumentGenerator
index_threads: 16
index_options: -M 16 -efC 100 -quantize.int8

metrics:
  - metric: AP@1000
    command: bin/trec_eval
    params: -c -m map
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - metric: RR@10
    command: bin/trec_eval
    params: -c -M 10 -m recip_rank
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - metric: R@100
    command: bin/trec_eval
    params: -c -m recall.100
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - metric: R@1000
    command: bin/trec_eval
    params: -c -m recall.1000
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false

topic_reader: TsvInt
topics:
  - name: "[MS MARCO Passage: Dev](https://github.com/microsoft/MSMARCO-Passage-Ranking)"
    id: dev
    path: topics.msmarco-passage.dev-subset.txt
    qrel: qrels.msmarco-passage.dev-subset.txt

models:
  - name: cos-dpr-distil-hnsw-int8-onnx
    display: cosDPR-distil
    type: hnsw
    params: -encoder CosDprDistil -hits 1000 -efSearch 1000 -threads 16
    results:
      AP@1000:
        - 0.3942
      RR@10:
        - 0.3896
      R@100:
        - 0.9075
      R@1000:
        - 0.9796
    tolerance:
      AP@1000:
        - 0.003
      RR@10:
        - 0.003
      R@100:
        - 0.01
      R@1000:
        - 0.015