metadata

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sparse-encoder
  - sparse
  - splade
  - generated_from_trainer
  - dataset_size:99000
  - loss:SpladeLoss
  - loss:SparseMultipleNegativesRankingLoss
  - loss:FlopsLoss
base_model: distilbert/distilbert-base-uncased
widget:
  - source_sentence: Time Travel Is It Possible?
    sentences:
      - Why can you not accelerate to faster than light?
      - Is time travel possible? If yes how
      - >-
        What do you hAve to say about time travel (I am not science student but
        I read it on net and its so exciting topic but still no clear idea that
        is it possible or it's just a rumour)?
  - source_sentence: How can one be a good product manager?
    sentences:
      - How Do I become a product manager?
      - Can you make online friends with other people on Quora?
      - How do I become a product designer?
  - source_sentence: >-
      How do I start a business? Where can I get a funding in India if I have a
      really good idea?
    sentences:
      - >-
        I have an awesome app/website idea which may get more than a billion
        users. But I don't have required money and coding skills. I tried
        crowd-funding but didn't help. What should I do?
      - How do I get funding for my web based startup idea?
      - What is the most powerful dog?
  - source_sentence: What are your favorite questions asked on Quora?
    sentences:
      - What are your favorite Quora questions and answers?
      - How do you become a Successfull Game Developer?
      - Who is your favorite Quora follower?
  - source_sentence: Which laptop is best under 25000 INR?
    sentences:
      - Why was the 1000 rupee note replaced with a 2000 rupee note?
      - What is the best laptop under 45k?
      - What are the best laptops under 25k?
datasets:
  - sentence-transformers/quora-duplicates
pipeline_tag: feature-extraction
library_name: sentence-transformers
metrics:
  - dot_accuracy@1
  - dot_accuracy@3
  - dot_accuracy@5
  - dot_accuracy@10
  - dot_precision@1
  - dot_precision@3
  - dot_precision@5
  - dot_precision@10
  - dot_recall@1
  - dot_recall@3
  - dot_recall@5
  - dot_recall@10
  - dot_ndcg@10
  - dot_mrr@10
  - dot_map@100
  - row_non_zero_mean_query
  - row_sparsity_mean_query
  - row_non_zero_mean_corpus
  - row_sparsity_mean_corpus
model-index:
  - name: splade-distilbert-base-uncased trained on Quora Duplicates Questions
    results:
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoClimateFEVER
          type: NanoClimateFEVER
        metrics:
          - type: dot_accuracy@1
            value: 0.2
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.34
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.38
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.46
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.2
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.12
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.084
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.05800000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.08833333333333332
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.15333333333333332
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.17166666666666663
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.2223333333333333
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.19096782240643292
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.27904761904761904
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.1448665229843916
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 83.12000274658203
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.997276782989502
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 196.82540893554688
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.9935513138771057
            name: Row Sparsity Mean Corpus
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoDBPedia
          type: NanoDBPedia
        metrics:
          - type: dot_accuracy@1
            value: 0.46
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.66
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.76
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.82
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.46
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.4599999999999999
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.41200000000000003
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.34800000000000003
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.024992243870767848
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.08610042820194802
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.1356349864336842
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.2108700010340366
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.4008410950979539
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5753888888888887
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.23475075762293293
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 110.18000030517578
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.9963901042938232
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 146.9065399169922
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.9951868057250977
            name: Row Sparsity Mean Corpus
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoFEVER
          type: NanoFEVER
        metrics:
          - type: dot_accuracy@1
            value: 0.56
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.64
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.72
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.82
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.56
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2333333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.15600000000000003
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.088
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.5266666666666666
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.6333333333333333
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.7133333333333333
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.8133333333333332
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6697436984572378
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6316349206349205
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.6281723194238796
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 96.77999877929688
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.9968292117118835
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 219.1212921142578
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.9928209185600281
            name: Row Sparsity Mean Corpus
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoFiQA2018
          type: NanoFiQA2018
        metrics:
          - type: dot_accuracy@1
            value: 0.14
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.32
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.36
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.44
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.14
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.12
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.10400000000000001
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.068
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.06783333333333333
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.14569047619047618
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.20004761904761903
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.2636825396825397
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.19745078204560165
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.23552380952380955
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.14731140504396462
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 80.33999633789062
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.9973678588867188
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 125.915771484375
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.9958745241165161
            name: Row Sparsity Mean Corpus
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoHotpotQA
          type: NanoHotpotQA
        metrics:
          - type: dot_accuracy@1
            value: 0.46
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.66
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.72
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.84
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.46
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.25333333333333335
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.176
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.11
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.23
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.38
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.44
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.55
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.4642094806420616
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5762777777777778
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.3781729878529178
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 87.26000213623047
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.9971410632133484
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 166.47190856933594
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.9945458173751831
            name: Row Sparsity Mean Corpus
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoMSMARCO
          type: NanoMSMARCO
        metrics:
          - type: dot_accuracy@1
            value: 0.16
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.26
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.36
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.46
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.16
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.08666666666666666
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.07200000000000001
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.046000000000000006
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.16
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.26
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.36
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.46
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.2889744107825637
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.23699999999999996
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.2547054047317205
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 96.05999755859375
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.996852695941925
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 105.46202850341797
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.9965446591377258
            name: Row Sparsity Mean Corpus
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNFCorpus
          type: NanoNFCorpus
        metrics:
          - type: dot_accuracy@1
            value: 0.28
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.36
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.4
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.44
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.28
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.18666666666666665
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.18
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.14800000000000002
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.01004738213752895
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.017620026805744985
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.031161291315801767
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.04364801295748046
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.16900908943281664
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.3281666666666666
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.04873203232918475
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 122.94000244140625
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.9959720373153687
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 199.5936279296875
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.9934607744216919
            name: Row Sparsity Mean Corpus
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNQ
          type: NanoNQ
        metrics:
          - type: dot_accuracy@1
            value: 0.18
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.34
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.4
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.48
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.18
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.11333333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.08
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.04800000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.17
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.32
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.38
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.46
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.30557584177037744
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.26749206349206345
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.26111102151483273
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 79.22000122070312
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.9974044561386108
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 145.250244140625
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.995241105556488
            name: Row Sparsity Mean Corpus
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoQuoraRetrieval
          type: NanoQuoraRetrieval
        metrics:
          - type: dot_accuracy@1
            value: 0.92
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.96
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 1
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 1
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.92
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.3733333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.256
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.132
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.8206666666666667
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.8986666666666667
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.9726666666666667
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.9826666666666667
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.9456812009077233
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.95
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.9232605046294702
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 73.83999633789062
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.9975807070732117
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 74.96769714355469
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.9975438117980957
            name: Row Sparsity Mean Corpus
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoSCIDOCS
          type: NanoSCIDOCS
        metrics:
          - type: dot_accuracy@1
            value: 0.36
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.5
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.62
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.36
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.26
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.19199999999999995
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.12399999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.07666666666666666
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.16166666666666665
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.19766666666666666
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.25466666666666665
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.2640445339047696
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.45502380952380955
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.18681370322897212
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 95.91999816894531
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.9968574047088623
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 184.44908142089844
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.9939568638801575
            name: Row Sparsity Mean Corpus
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoArguAna
          type: NanoArguAna
        metrics:
          - type: dot_accuracy@1
            value: 0.1
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.28
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.32
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.38
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.1
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.09333333333333332
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.064
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.038000000000000006
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.1
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.28
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.32
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.38
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.24652298080535653
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.2033571428571429
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.2089304613637203
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 181.27999877929688
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.9940606951713562
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 160.55982971191406
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.9947395324707031
            name: Row Sparsity Mean Corpus
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoSciFact
          type: NanoSciFact
        metrics:
          - type: dot_accuracy@1
            value: 0.38
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.56
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.64
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.66
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.38
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.19333333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.14
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.07200000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.365
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.54
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.61
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.63
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5012811403788975
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4666666666666666
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.4647112383054177
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 90.80000305175781
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.9970251321792603
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 197.8948211669922
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.9935163259506226
            name: Row Sparsity Mean Corpus
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoTouche2020
          type: NanoTouche2020
        metrics:
          - type: dot_accuracy@1
            value: 0.4897959183673469
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.7551020408163265
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.8367346938775511
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.9387755102040817
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.4897959183673469
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.43537414965986393
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.42857142857142855
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.336734693877551
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.03231843040459851
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.08325211008018112
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.13623768956747034
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.20745266217275266
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.3790647958645717
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6323372206025266
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.2305586843086588
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 78.7755126953125
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.9974190592765808
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 140.8109588623047
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.9953866004943848
            name: Row Sparsity Mean Corpus
      - task:
          type: sparse-nano-beir
          name: Sparse Nano BEIR
        dataset:
          name: NanoBEIR mean
          type: NanoBEIR_mean
        metrics:
          - type: dot_accuracy@1
            value: 0.3607535321821036
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.510392464678179
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.578210361067504
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.6491365777080063
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.3607535321821036
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2252851909994767
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.18035164835164832
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.1243642072213501
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.20557882485227402
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.3045894647137193
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.3591088399767622
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.42143486275744696
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.3864128363458742
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.44907050659091463
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.31631515718000486
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 98.19350081223708
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.9967828622231116
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 158.7868622999925
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.994797619489523
            name: Row Sparsity Mean Corpus

splade-distilbert-base-uncased trained on Quora Duplicates Questions

This is a SPLADE Sparse Encoder model finetuned from distilbert/distilbert-base-uncased on the quora-duplicates dataset using the sentence-transformers library. It maps sentences & paragraphs to a 30522-dimensional sparse vector space and can be used for semantic search and sparse retrieval.

Model Details

Model Description

Model Type: SPLADE Sparse Encoder
Base model: distilbert/distilbert-base-uncased
Maximum Sequence Length: 256 tokens
Output Dimensionality: 30522 dimensions
Similarity Function: Dot Product
Training Dataset:
- quora-duplicates
Language: en
License: apache-2.0

Model Sources

Documentation: Sentence Transformers Documentation
Documentation: Sparse Encoder Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sparse Encoders on Hugging Face

Full Model Architecture

SparseEncoder(
  (0): MLMTransformer({'max_seq_length': 256, 'do_lower_case': False}) with MLMTransformer model: DistilBertForMaskedLM 
  (1): SpladePooling({'pooling_strategy': 'max', 'activation_function': 'relu', 'word_embedding_dimension': 30522})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SparseEncoder

# Download from the 🤗 Hub
model = SparseEncoder("xin0920/splade-distilbert-base-uncased-msmarco-mrl")
# Run inference
sentences = [
    'Which laptop is best under 25000 INR?',
    'What are the best laptops under 25k?',
    'What is the best laptop under 45k?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# (3, 30522)

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Sparse Information Retrieval

Datasets: NanoClimateFEVER, NanoDBPedia, NanoFEVER, NanoFiQA2018, NanoHotpotQA, NanoMSMARCO, NanoNFCorpus, NanoNQ, NanoQuoraRetrieval, NanoSCIDOCS, NanoArguAna, NanoSciFact and NanoTouche2020
Evaluated with SparseInformationRetrievalEvaluator

Metric	NanoClimateFEVER	NanoDBPedia	NanoFEVER	NanoFiQA2018	NanoHotpotQA	NanoMSMARCO	NanoNFCorpus	NanoNQ	NanoQuoraRetrieval	NanoSCIDOCS	NanoArguAna	NanoSciFact	NanoTouche2020
dot_accuracy@1	0.2	0.46	0.56	0.14	0.46	0.16	0.28	0.18	0.92	0.36	0.1	0.38	0.4898
dot_accuracy@3	0.34	0.66	0.64	0.32	0.66	0.26	0.36	0.34	0.96	0.5	0.28	0.56	0.7551
dot_accuracy@5	0.38	0.76	0.72	0.36	0.72	0.36	0.4	0.4	1.0	0.62	0.32	0.64	0.8367
dot_accuracy@10	0.46	0.82	0.82	0.44	0.84	0.46	0.44	0.48	1.0	0.7	0.38	0.66	0.9388
dot_precision@1	0.2	0.46	0.56	0.14	0.46	0.16	0.28	0.18	0.92	0.36	0.1	0.38	0.4898
dot_precision@3	0.12	0.46	0.2333	0.12	0.2533	0.0867	0.1867	0.1133	0.3733	0.26	0.0933	0.1933	0.4354
dot_precision@5	0.084	0.412	0.156	0.104	0.176	0.072	0.18	0.08	0.256	0.192	0.064	0.14	0.4286
dot_precision@10	0.058	0.348	0.088	0.068	0.11	0.046	0.148	0.048	0.132	0.124	0.038	0.072	0.3367
dot_recall@1	0.0883	0.025	0.5267	0.0678	0.23	0.16	0.01	0.17	0.8207	0.0767	0.1	0.365	0.0323
dot_recall@3	0.1533	0.0861	0.6333	0.1457	0.38	0.26	0.0176	0.32	0.8987	0.1617	0.28	0.54	0.0833
dot_recall@5	0.1717	0.1356	0.7133	0.2	0.44	0.36	0.0312	0.38	0.9727	0.1977	0.32	0.61	0.1362
dot_recall@10	0.2223	0.2109	0.8133	0.2637	0.55	0.46	0.0436	0.46	0.9827	0.2547	0.38	0.63	0.2075
dot_ndcg@10	0.191	0.4008	0.6697	0.1975	0.4642	0.289	0.169	0.3056	0.9457	0.264	0.2465	0.5013	0.3791
dot_mrr@10	0.279	0.5754	0.6316	0.2355	0.5763	0.237	0.3282	0.2675	0.95	0.455	0.2034	0.4667	0.6323
dot_map@100	0.1449	0.2348	0.6282	0.1473	0.3782	0.2547	0.0487	0.2611	0.9233	0.1868	0.2089	0.4647	0.2306
row_non_zero_mean_query	83.12	110.18	96.78	80.34	87.26	96.06	122.94	79.22	73.84	95.92	181.28	90.8	78.7755
row_sparsity_mean_query	0.9973	0.9964	0.9968	0.9974	0.9971	0.9969	0.996	0.9974	0.9976	0.9969	0.9941	0.997	0.9974
row_non_zero_mean_corpus	196.8254	146.9065	219.1213	125.9158	166.4719	105.462	199.5936	145.2502	74.9677	184.4491	160.5598	197.8948	140.811
row_sparsity_mean_corpus	0.9936	0.9952	0.9928	0.9959	0.9945	0.9965	0.9935	0.9952	0.9975	0.994	0.9947	0.9935	0.9954

Sparse Nano BEIR

Dataset: NanoBEIR_mean

Evaluated with SparseNanoBEIREvaluator with these parameters:

{
    "dataset_names": [
        "climatefever",
        "dbpedia",
        "fever",
        "fiqa2018",
        "hotpotqa",
        "msmarco",
        "nfcorpus",
        "nq",
        "quoraretrieval",
        "scidocs",
        "arguana",
        "scifact",
        "touche2020"
    ]
}

Metric	Value
dot_accuracy@1	0.3608
dot_accuracy@3	0.5104
dot_accuracy@5	0.5782
dot_accuracy@10	0.6491
dot_precision@1	0.3608
dot_precision@3	0.2253
dot_precision@5	0.1804
dot_precision@10	0.1244
dot_recall@1	0.2056
dot_recall@3	0.3046
dot_recall@5	0.3591
dot_recall@10	0.4214
dot_ndcg@10	0.3864
dot_mrr@10	0.4491
dot_map@100	0.3163
row_non_zero_mean_query	98.1935
row_sparsity_mean_query	0.9968
row_non_zero_mean_corpus	158.7869
row_sparsity_mean_corpus	0.9948

Training Details

Training Dataset

quora-duplicates

Dataset: quora-duplicates at 451a485
Size: 99,000 training samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 6 tokens mean: 14.1 tokens max: 39 tokens	min: 6 tokens mean: 13.83 tokens max: 41 tokens	min: 6 tokens mean: 15.21 tokens max: 75 tokens

Samples:

anchor	positive	negative
`What are the best GMAT coaching institutes in Delhi NCR?`	`Which are the best GMAT coaching institutes in Delhi/NCR?`	`What are the best GMAT coaching institutes in Delhi-Noida Area?`
`Is a third world war coming?`	`Is World War 3 more imminent than expected?`	`Since the UN is unable to control terrorism and groups like ISIS, al-Qaeda and countries that promote terrorism (even though it consumed those countries), can we assume that the world is heading towards World War III?`
`Should I build iOS or Android apps first?`	`Should people choose Android or iOS first to build their App?`	`How much more effort is it to build your app on both iOS and Android?`

Loss: SpladeLoss with these parameters:

{'loss': SparseMultipleNegativesRankingLoss(
  (model): SparseEncoder(
    (0): MLMTransformer({'max_seq_length': 256, 'do_lower_case': False}) with MLMTransformer model: DistilBertForMaskedLM 
    (1): SpladePooling({'pooling_strategy': 'max', 'activation_function': 'relu', 'word_embedding_dimension': None})
  )
  (cross_entropy_loss): CrossEntropyLoss()
), 'lambda_corpus': 3e-05, 'lambda_query': 5e-05}

Evaluation Dataset

quora-duplicates

Dataset: quora-duplicates at 451a485
Size: 1,000 evaluation samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 6 tokens mean: 14.05 tokens max: 40 tokens	min: 6 tokens mean: 14.14 tokens max: 44 tokens	min: 6 tokens mean: 14.56 tokens max: 60 tokens

Samples:

anchor	positive	negative
`What happens if we use petrol in diesel vehicles?`	`Why can't we use petrol in diesel?`	`Why are diesel engines noisier than petrol engines?`
`Why is Saltwater taffy candy imported in Switzerland?`	`Why is Saltwater taffy candy imported in Laos?`	`Is salt a consumer product?`
`Which is your favourite film in 2016?`	`What movie is the best movie of 2016?`	`What will the best movie of 2017 be?`

Loss: SpladeLoss with these parameters:

{'loss': SparseMultipleNegativesRankingLoss(
  (model): SparseEncoder(
    (0): MLMTransformer({'max_seq_length': 256, 'do_lower_case': False}) with MLMTransformer model: DistilBertForMaskedLM 
    (1): SpladePooling({'pooling_strategy': 'max', 'activation_function': 'relu', 'word_embedding_dimension': None})
  )
  (cross_entropy_loss): CrossEntropyLoss()
), 'lambda_corpus': 3e-05, 'lambda_query': 5e-05}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 12
per_device_eval_batch_size: 12
learning_rate: 2e-05
num_train_epochs: 1
bf16: True
load_best_model_at_end: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 12
per_device_eval_batch_size: 12
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 2e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 1
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: True
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: True
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: True
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	NanoClimateFEVER_dot_ndcg@10	NanoDBPedia_dot_ndcg@10	NanoFEVER_dot_ndcg@10	NanoFiQA2018_dot_ndcg@10	NanoHotpotQA_dot_ndcg@10	NanoMSMARCO_dot_ndcg@10	NanoNFCorpus_dot_ndcg@10	NanoNQ_dot_ndcg@10	NanoQuoraRetrieval_dot_ndcg@10	NanoSCIDOCS_dot_ndcg@10	NanoArguAna_dot_ndcg@10	NanoSciFact_dot_ndcg@10	NanoTouche2020_dot_ndcg@10	NanoBEIR_mean_dot_ndcg@10
0.1938	200	12.7715	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3876	400	0.2719	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5814	600	0.234	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7752	800	0.2068	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9690	1000	0.2041	-	-	-	-	-	-	-	-	-	-	-	-	-	-
-1	-1	-	0.1910	0.4008	0.6697	0.1975	0.4642	0.2890	0.1690	0.3056	0.9457	0.2640	0.2465	0.5013	0.3791	0.3864

Framework Versions

Python: 3.9.22
Sentence Transformers: 4.2.0.dev0
Transformers: 4.52.1
PyTorch: 2.6.0+cu124
Accelerate: 1.7.0
Datasets: 3.6.0
Tokenizers: 0.21.1

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

SpladeLoss

@misc{formal2022distillationhardnegativesampling,
      title={From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective},
      author={Thibault Formal and Carlos Lassance and Benjamin Piwowarski and Stéphane Clinchant},
      year={2022},
      eprint={2205.04733},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2205.04733},
}

SparseMultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

FlopsLoss

@article{paria2020minimizing,
    title={Minimizing flops to learn efficient sparse representations},
    author={Paria, Biswajit and Yeh, Chih-Kuan and Yen, Ian EH and Xu, Ning and Ravikumar, Pradeep and P{'o}czos, Barnab{'a}s},
    journal={arXiv preprint arXiv:2004.05665},
    year={2020}
    }