regression.dl20-passage.bge-base-en-v1.5.parquet.hnsw-int8.onnx.yaml Maven / Gradle / Ivy

Go to download
---
corpus: msmarco-passage-bge-base-en-v1.5.parquet
corpus_path: collections/msmarco/msmarco-passage-bge-base-en-v1.5.parquet/

download_url: https://rgw.cs.uwaterloo.ca/pyserini/data/msmarco-passage-bge-base-en-v1.5.parquet.tar
download_checksum: a55b3cb338ec4a1b1c36825bf0854648

index_path: indexes/lucene-hnsw-int8.msmarco-v1-passage.bge-base-en-v1.5/
index_type: hnsw
collection_class: ParquetDenseVectorCollection
generator_class: DenseVectorDocumentGenerator
index_threads: 16
index_options: -M 16 -efC 100 -quantize.int8

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

topic_reader: TsvInt
topics:
  - name: "[DL20 (Passage)](https://trec.nist.gov/data/deep2020.html)"
    id: dl20
    path: topics.dl20.txt
    qrel: qrels.dl20-passage.txt

models:
  - name: bge-hnsw-int8-onnx
    display: BGE-base-en-v1.5
    type: hnsw
    params: -encoder BgeBaseEn15 -hits 1000 -efSearch 1000 -threads 16
    results:
      AP@1000:
        - 0.4650
      nDCG@10:
        - 0.6780
      R@100:
        - 0.7169
      R@1000:
        - 0.8503
    tolerance:
      AP@1000:
        - 0.015
      nDCG@10:
        - 0.008
      R@100:
        - 0.02
      R@1000:
        - 0.02