---
tags:
- ColBERT
- PyLate
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:640000
- loss:Distillation
base_model: bclavie/mini-base
datasets:
- lightonai/ms-marco-en-bge-gemma-unnormalized
pipeline_tag: sentence-similarity
library_name: PyLate
license: apache-2.0
metrics:
- MaxSim_accuracy@1
- MaxSim_accuracy@3
- MaxSim_accuracy@5
- MaxSim_accuracy@10
- MaxSim_precision@1
- MaxSim_precision@3
- MaxSim_precision@5
- MaxSim_precision@10
- MaxSim_recall@1
- MaxSim_recall@3
- MaxSim_recall@5
- MaxSim_recall@10
- MaxSim_ndcg@10
- MaxSim_mrr@10
- MaxSim_map@100
model-index:
- name: ColBERT MUVERA Small
  results:
  - task:
      type: py-late-information-retrieval
      name: Py Late Information Retrieval
    dataset:
      name: NanoClimateFEVER
      type: NanoClimateFEVER
    metrics:
    - type: MaxSim_accuracy@1
      value: 0.28
      name: Maxsim Accuracy@1
    - type: MaxSim_accuracy@3
      value: 0.38
      name: Maxsim Accuracy@3
    - type: MaxSim_accuracy@5
      value: 0.52
      name: Maxsim Accuracy@5
    - type: MaxSim_accuracy@10
      value: 0.64
      name: Maxsim Accuracy@10
    - type: MaxSim_precision@1
      value: 0.28
      name: Maxsim Precision@1
    - type: MaxSim_precision@3
      value: 0.14666666666666667
      name: Maxsim Precision@3
    - type: MaxSim_precision@5
      value: 0.12
      name: Maxsim Precision@5
    - type: MaxSim_precision@10
      value: 0.08
      name: Maxsim Precision@10
    - type: MaxSim_recall@1
      value: 0.13166666666666665
      name: Maxsim Recall@1
    - type: MaxSim_recall@3
      value: 0.21
      name: Maxsim Recall@3
    - type: MaxSim_recall@5
      value: 0.265
      name: Maxsim Recall@5
    - type: MaxSim_recall@10
      value: 0.335
      name: Maxsim Recall@10
    - type: MaxSim_ndcg@10
      value: 0.27666051264859415
      name: Maxsim Ndcg@10
    - type: MaxSim_mrr@10
      value: 0.3671349206349206
      name: Maxsim Mrr@10
    - type: MaxSim_map@100
      value: 0.22158617300046946
      name: Maxsim Map@100
  - task:
      type: py-late-information-retrieval
      name: Py Late Information Retrieval
    dataset:
      name: NanoDBPedia
      type: NanoDBPedia
    metrics:
    - type: MaxSim_accuracy@1
      value: 0.8
      name: Maxsim Accuracy@1
    - type: MaxSim_accuracy@3
      value: 0.88
      name: Maxsim Accuracy@3
    - type: MaxSim_accuracy@5
      value: 0.92
      name: Maxsim Accuracy@5
    - type: MaxSim_accuracy@10
      value: 0.96
      name: Maxsim Accuracy@10
    - type: MaxSim_precision@1
      value: 0.8
      name: Maxsim Precision@1
    - type: MaxSim_precision@3
      value: 0.6333333333333332
      name: Maxsim Precision@3
    - type: MaxSim_precision@5
      value: 0.556
      name: Maxsim Precision@5
    - type: MaxSim_precision@10
      value: 0.48399999999999993
      name: Maxsim Precision@10
    - type: MaxSim_recall@1
      value: 0.10583280294731091
      name: Maxsim Recall@1
    - type: MaxSim_recall@3
      value: 0.1747980000610803
      name: Maxsim Recall@3
    - type: MaxSim_recall@5
      value: 0.2211728749541224
      name: Maxsim Recall@5
    - type: MaxSim_recall@10
      value: 0.3392671917074792
      name: Maxsim Recall@10
    - type: MaxSim_ndcg@10
      value: 0.6189072509940752
      name: Maxsim Ndcg@10
    - type: MaxSim_mrr@10
      value: 0.8510238095238097
      name: Maxsim Mrr@10
    - type: MaxSim_map@100
      value: 0.47586135688175013
      name: Maxsim Map@100
  - task:
      type: py-late-information-retrieval
      name: Py Late Information Retrieval
    dataset:
      name: NanoFEVER
      type: NanoFEVER
    metrics:
    - type: MaxSim_accuracy@1
      value: 0.88
      name: Maxsim Accuracy@1
    - type: MaxSim_accuracy@3
      value: 0.96
      name: Maxsim Accuracy@3
    - type: MaxSim_accuracy@5
      value: 1.0
      name: Maxsim Accuracy@5
    - type: MaxSim_accuracy@10
      value: 1.0
      name: Maxsim Accuracy@10
    - type: MaxSim_precision@1
      value: 0.88
      name: Maxsim Precision@1
    - type: MaxSim_precision@3
      value: 0.33333333333333326
      name: Maxsim Precision@3
    - type: MaxSim_precision@5
      value: 0.21199999999999997
      name: Maxsim Precision@5
    - type: MaxSim_precision@10
      value: 0.10799999999999997
      name: Maxsim Precision@10
    - type: MaxSim_recall@1
      value: 0.8166666666666668
      name: Maxsim Recall@1
    - type: MaxSim_recall@3
      value: 0.9133333333333333
      name: Maxsim Recall@3
    - type: MaxSim_recall@5
      value: 0.9633333333333333
      name: Maxsim Recall@5
    - type: MaxSim_recall@10
      value: 0.9733333333333333
      name: Maxsim Recall@10
    - type: MaxSim_ndcg@10
      value: 0.9208334669406996
      name: Maxsim Ndcg@10
    - type: MaxSim_mrr@10
      value: 0.929
      name: Maxsim Mrr@10
    - type: MaxSim_map@100
      value: 0.8912380952380953
      name: Maxsim Map@100
  - task:
      type: py-late-information-retrieval
      name: Py Late Information Retrieval
    dataset:
      name: NanoFiQA2018
      type: NanoFiQA2018
    metrics:
    - type: MaxSim_accuracy@1
      value: 0.44
      name: Maxsim Accuracy@1
    - type: MaxSim_accuracy@3
      value: 0.56
      name: Maxsim Accuracy@3
    - type: MaxSim_accuracy@5
      value: 0.68
      name: Maxsim Accuracy@5
    - type: MaxSim_accuracy@10
      value: 0.76
      name: Maxsim Accuracy@10
    - type: MaxSim_precision@1
      value: 0.44
      name: Maxsim Precision@1
    - type: MaxSim_precision@3
      value: 0.26666666666666666
      name: Maxsim Precision@3
    - type: MaxSim_precision@5
      value: 0.22
      name: Maxsim Precision@5
    - type: MaxSim_precision@10
      value: 0.13599999999999998
      name: Maxsim Precision@10
    - type: MaxSim_recall@1
      value: 0.22257936507936507
      name: Maxsim Recall@1
    - type: MaxSim_recall@3
      value: 0.36418253968253966
      name: Maxsim Recall@3
    - type: MaxSim_recall@5
      value: 0.5042063492063492
      name: Maxsim Recall@5
    - type: MaxSim_recall@10
      value: 0.5963968253968254
      name: Maxsim Recall@10
    - type: MaxSim_ndcg@10
      value: 0.4781894440800092
      name: Maxsim Ndcg@10
    - type: MaxSim_mrr@10
      value: 0.5321666666666666
      name: Maxsim Mrr@10
    - type: MaxSim_map@100
      value: 0.39543817074336585
      name: Maxsim Map@100
  - task:
      type: py-late-information-retrieval
      name: Py Late Information Retrieval
    dataset:
      name: NanoHotpotQA
      type: NanoHotpotQA
    metrics:
    - type: MaxSim_accuracy@1
      value: 0.84
      name: Maxsim Accuracy@1
    - type: MaxSim_accuracy@3
      value: 0.96
      name: Maxsim Accuracy@3
    - type: MaxSim_accuracy@5
      value: 0.98
      name: Maxsim Accuracy@5
    - type: MaxSim_accuracy@10
      value: 0.98
      name: Maxsim Accuracy@10
    - type: MaxSim_precision@1
      value: 0.84
      name: Maxsim Precision@1
    - type: MaxSim_precision@3
      value: 0.5066666666666666
      name: Maxsim Precision@3
    - type: MaxSim_precision@5
      value: 0.324
      name: Maxsim Precision@5
    - type: MaxSim_precision@10
      value: 0.17399999999999996
      name: Maxsim Precision@10
    - type: MaxSim_recall@1
      value: 0.42
      name: Maxsim Recall@1
    - type: MaxSim_recall@3
      value: 0.76
      name: Maxsim Recall@3
    - type: MaxSim_recall@5
      value: 0.81
      name: Maxsim Recall@5
    - type: MaxSim_recall@10
      value: 0.87
      name: Maxsim Recall@10
    - type: MaxSim_ndcg@10
      value: 0.813477163259318
      name: Maxsim Ndcg@10
    - type: MaxSim_mrr@10
      value: 0.8973333333333333
      name: Maxsim Mrr@10
    - type: MaxSim_map@100
      value: 0.7469519155158202
      name: Maxsim Map@100
  - task:
      type: py-late-information-retrieval
      name: Py Late Information Retrieval
    dataset:
      name: NanoMSMARCO
      type: NanoMSMARCO
    metrics:
    - type: MaxSim_accuracy@1
      value: 0.48
      name: Maxsim Accuracy@1
    - type: MaxSim_accuracy@3
      value: 0.64
      name: Maxsim Accuracy@3
    - type: MaxSim_accuracy@5
      value: 0.68
      name: Maxsim Accuracy@5
    - type: MaxSim_accuracy@10
      value: 0.8
      name: Maxsim Accuracy@10
    - type: MaxSim_precision@1
      value: 0.48
      name: Maxsim Precision@1
    - type: MaxSim_precision@3
      value: 0.21333333333333332
      name: Maxsim Precision@3
    - type: MaxSim_precision@5
      value: 0.136
      name: Maxsim Precision@5
    - type: MaxSim_precision@10
      value: 0.08
      name: Maxsim Precision@10
    - type: MaxSim_recall@1
      value: 0.48
      name: Maxsim Recall@1
    - type: MaxSim_recall@3
      value: 0.64
      name: Maxsim Recall@3
    - type: MaxSim_recall@5
      value: 0.68
      name: Maxsim Recall@5
    - type: MaxSim_recall@10
      value: 0.8
      name: Maxsim Recall@10
    - type: MaxSim_ndcg@10
      value: 0.6277729303272284
      name: Maxsim Ndcg@10
    - type: MaxSim_mrr@10
      value: 0.574547619047619
      name: Maxsim Mrr@10
    - type: MaxSim_map@100
      value: 0.585980942367483
      name: Maxsim Map@100
  - task:
      type: py-late-information-retrieval
      name: Py Late Information Retrieval
    dataset:
      name: NanoNFCorpus
      type: NanoNFCorpus
    metrics:
    - type: MaxSim_accuracy@1
      value: 0.5
      name: Maxsim Accuracy@1
    - type: MaxSim_accuracy@3
      value: 0.62
      name: Maxsim Accuracy@3
    - type: MaxSim_accuracy@5
      value: 0.64
      name: Maxsim Accuracy@5
    - type: MaxSim_accuracy@10
      value: 0.74
      name: Maxsim Accuracy@10
    - type: MaxSim_precision@1
      value: 0.5
      name: Maxsim Precision@1
    - type: MaxSim_precision@3
      value: 0.4
      name: Maxsim Precision@3
    - type: MaxSim_precision@5
      value: 0.3440000000000001
      name: Maxsim Precision@5
    - type: MaxSim_precision@10
      value: 0.292
      name: Maxsim Precision@10
    - type: MaxSim_recall@1
      value: 0.06602691624937523
      name: Maxsim Recall@1
    - type: MaxSim_recall@3
      value: 0.09818050757008642
      name: Maxsim Recall@3
    - type: MaxSim_recall@5
      value: 0.11806464030634821
      name: Maxsim Recall@5
    - type: MaxSim_recall@10
      value: 0.15514192209178235
      name: Maxsim Recall@10
    - type: MaxSim_ndcg@10
      value: 0.37561452677051027
      name: Maxsim Ndcg@10
    - type: MaxSim_mrr@10
      value: 0.5691666666666667
      name: Maxsim Mrr@10
    - type: MaxSim_map@100
      value: 0.18300178358234423
      name: Maxsim Map@100
  - task:
      type: py-late-information-retrieval
      name: Py Late Information Retrieval
    dataset:
      name: NanoNQ
      type: NanoNQ
    metrics:
    - type: MaxSim_accuracy@1
      value: 0.56
      name: Maxsim Accuracy@1
    - type: MaxSim_accuracy@3
      value: 0.76
      name: Maxsim Accuracy@3
    - type: MaxSim_accuracy@5
      value: 0.78
      name: Maxsim Accuracy@5
    - type: MaxSim_accuracy@10
      value: 0.82
      name: Maxsim Accuracy@10
    - type: MaxSim_precision@1
      value: 0.56
      name: Maxsim Precision@1
    - type: MaxSim_precision@3
      value: 0.2533333333333333
      name: Maxsim Precision@3
    - type: MaxSim_precision@5
      value: 0.16399999999999998
      name: Maxsim Precision@5
    - type: MaxSim_precision@10
      value: 0.088
      name: Maxsim Precision@10
    - type: MaxSim_recall@1
      value: 0.54
      name: Maxsim Recall@1
    - type: MaxSim_recall@3
      value: 0.71
      name: Maxsim Recall@3
    - type: MaxSim_recall@5
      value: 0.75
      name: Maxsim Recall@5
    - type: MaxSim_recall@10
      value: 0.79
      name: Maxsim Recall@10
    - type: MaxSim_ndcg@10
      value: 0.6818400710905007
      name: Maxsim Ndcg@10
    - type: MaxSim_mrr@10
      value: 0.6597222222222223
      name: Maxsim Mrr@10
    - type: MaxSim_map@100
      value: 0.6459882013890279
      name: Maxsim Map@100
  - task:
      type: py-late-information-retrieval
      name: Py Late Information Retrieval
    dataset:
      name: NanoQuoraRetrieval
      type: NanoQuoraRetrieval
    metrics:
    - type: MaxSim_accuracy@1
      value: 0.86
      name: Maxsim Accuracy@1
    - type: MaxSim_accuracy@3
      value: 0.98
      name: Maxsim Accuracy@3
    - type: MaxSim_accuracy@5
      value: 0.98
      name: Maxsim Accuracy@5
    - type: MaxSim_accuracy@10
      value: 1.0
      name: Maxsim Accuracy@10
    - type: MaxSim_precision@1
      value: 0.86
      name: Maxsim Precision@1
    - type: MaxSim_precision@3
      value: 0.40666666666666657
      name: Maxsim Precision@3
    - type: MaxSim_precision@5
      value: 0.264
      name: Maxsim Precision@5
    - type: MaxSim_precision@10
      value: 0.13799999999999998
      name: Maxsim Precision@10
    - type: MaxSim_recall@1
      value: 0.764
      name: Maxsim Recall@1
    - type: MaxSim_recall@3
      value: 0.9453333333333334
      name: Maxsim Recall@3
    - type: MaxSim_recall@5
      value: 0.97
      name: Maxsim Recall@5
    - type: MaxSim_recall@10
      value: 0.9966666666666666
      name: Maxsim Recall@10
    - type: MaxSim_ndcg@10
      value: 0.9414269581610836
      name: Maxsim Ndcg@10
    - type: MaxSim_mrr@10
      value: 0.9228571428571428
      name: Maxsim Mrr@10
    - type: MaxSim_map@100
      value: 0.9205543345543344
      name: Maxsim Map@100
  - task:
      type: py-late-information-retrieval
      name: Py Late Information Retrieval
    dataset:
      name: NanoSCIDOCS
      type: NanoSCIDOCS
    metrics:
    - type: MaxSim_accuracy@1
      value: 0.5
      name: Maxsim Accuracy@1
    - type: MaxSim_accuracy@3
      value: 0.74
      name: Maxsim Accuracy@3
    - type: MaxSim_accuracy@5
      value: 0.76
      name: Maxsim Accuracy@5
    - type: MaxSim_accuracy@10
      value: 0.82
      name: Maxsim Accuracy@10
    - type: MaxSim_precision@1
      value: 0.5
      name: Maxsim Precision@1
    - type: MaxSim_precision@3
      value: 0.3933333333333333
      name: Maxsim Precision@3
    - type: MaxSim_precision@5
      value: 0.292
      name: Maxsim Precision@5
    - type: MaxSim_precision@10
      value: 0.18599999999999997
      name: Maxsim Precision@10
    - type: MaxSim_recall@1
      value: 0.10466666666666667
      name: Maxsim Recall@1
    - type: MaxSim_recall@3
      value: 0.24366666666666664
      name: Maxsim Recall@3
    - type: MaxSim_recall@5
      value: 0.29966666666666664
      name: Maxsim Recall@5
    - type: MaxSim_recall@10
      value: 0.3826666666666666
      name: Maxsim Recall@10
    - type: MaxSim_ndcg@10
      value: 0.39084995006976664
      name: Maxsim Ndcg@10
    - type: MaxSim_mrr@10
      value: 0.6197222222222222
      name: Maxsim Mrr@10
    - type: MaxSim_map@100
      value: 0.3153590016638529
      name: Maxsim Map@100
  - task:
      type: py-late-information-retrieval
      name: Py Late Information Retrieval
    dataset:
      name: NanoArguAna
      type: NanoArguAna
    metrics:
    - type: MaxSim_accuracy@1
      value: 0.28
      name: Maxsim Accuracy@1
    - type: MaxSim_accuracy@3
      value: 0.56
      name: Maxsim Accuracy@3
    - type: MaxSim_accuracy@5
      value: 0.64
      name: Maxsim Accuracy@5
    - type: MaxSim_accuracy@10
      value: 0.84
      name: Maxsim Accuracy@10
    - type: MaxSim_precision@1
      value: 0.28
      name: Maxsim Precision@1
    - type: MaxSim_precision@3
      value: 0.18666666666666668
      name: Maxsim Precision@3
    - type: MaxSim_precision@5
      value: 0.12800000000000003
      name: Maxsim Precision@5
    - type: MaxSim_precision@10
      value: 0.08399999999999999
      name: Maxsim Precision@10
    - type: MaxSim_recall@1
      value: 0.28
      name: Maxsim Recall@1
    - type: MaxSim_recall@3
      value: 0.56
      name: Maxsim Recall@3
    - type: MaxSim_recall@5
      value: 0.64
      name: Maxsim Recall@5
    - type: MaxSim_recall@10
      value: 0.84
      name: Maxsim Recall@10
    - type: MaxSim_ndcg@10
      value: 0.5432952971404568
      name: Maxsim Ndcg@10
    - type: MaxSim_mrr@10
      value: 0.450484126984127
      name: Maxsim Mrr@10
    - type: MaxSim_map@100
      value: 0.4551681906230779
      name: Maxsim Map@100
  - task:
      type: py-late-information-retrieval
      name: Py Late Information Retrieval
    dataset:
      name: NanoSciFact
      type: NanoSciFact
    metrics:
    - type: MaxSim_accuracy@1
      value: 0.7
      name: Maxsim Accuracy@1
    - type: MaxSim_accuracy@3
      value: 0.82
      name: Maxsim Accuracy@3
    - type: MaxSim_accuracy@5
      value: 0.84
      name: Maxsim Accuracy@5
    - type: MaxSim_accuracy@10
      value: 0.88
      name: Maxsim Accuracy@10
    - type: MaxSim_precision@1
      value: 0.7
      name: Maxsim Precision@1
    - type: MaxSim_precision@3
      value: 0.29333333333333333
      name: Maxsim Precision@3
    - type: MaxSim_precision@5
      value: 0.18799999999999997
      name: Maxsim Precision@5
    - type: MaxSim_precision@10
      value: 0.09799999999999998
      name: Maxsim Precision@10
    - type: MaxSim_recall@1
      value: 0.665
      name: Maxsim Recall@1
    - type: MaxSim_recall@3
      value: 0.81
      name: Maxsim Recall@3
    - type: MaxSim_recall@5
      value: 0.84
      name: Maxsim Recall@5
    - type: MaxSim_recall@10
      value: 0.87
      name: Maxsim Recall@10
    - type: MaxSim_ndcg@10
      value: 0.7883940477308562
      name: Maxsim Ndcg@10
    - type: MaxSim_mrr@10
      value: 0.7645238095238096
      name: Maxsim Mrr@10
    - type: MaxSim_map@100
      value: 0.7622104923007755
      name: Maxsim Map@100
  - task:
      type: py-late-information-retrieval
      name: Py Late Information Retrieval
    dataset:
      name: NanoTouche2020
      type: NanoTouche2020
    metrics:
    - type: MaxSim_accuracy@1
      value: 0.673469387755102
      name: Maxsim Accuracy@1
    - type: MaxSim_accuracy@3
      value: 0.9183673469387755
      name: Maxsim Accuracy@3
    - type: MaxSim_accuracy@5
      value: 0.9591836734693877
      name: Maxsim Accuracy@5
    - type: MaxSim_accuracy@10
      value: 1.0
      name: Maxsim Accuracy@10
    - type: MaxSim_precision@1
      value: 0.673469387755102
      name: Maxsim Precision@1
    - type: MaxSim_precision@3
      value: 0.6326530612244898
      name: Maxsim Precision@3
    - type: MaxSim_precision@5
      value: 0.6040816326530614
      name: Maxsim Precision@5
    - type: MaxSim_precision@10
      value: 0.5020408163265305
      name: Maxsim Precision@10
    - type: MaxSim_recall@1
      value: 0.04919462393895531
      name: Maxsim Recall@1
    - type: MaxSim_recall@3
      value: 0.13143050077268048
      name: Maxsim Recall@3
    - type: MaxSim_recall@5
      value: 0.20505385244507174
      name: Maxsim Recall@5
    - type: MaxSim_recall@10
      value: 0.3259510245836729
      name: Maxsim Recall@10
    - type: MaxSim_ndcg@10
      value: 0.5631037374817277
      name: Maxsim Ndcg@10
    - type: MaxSim_mrr@10
      value: 0.7906462585034014
      name: Maxsim Mrr@10
    - type: MaxSim_map@100
      value: 0.41297955687388305
      name: Maxsim Map@100
  - task:
      type: nano-beir
      name: Nano BEIR
    dataset:
      name: NanoBEIR mean
      type: NanoBEIR_mean
    metrics:
    - type: MaxSim_accuracy@1
      value: 0.5994976452119309
      name: Maxsim Accuracy@1
    - type: MaxSim_accuracy@3
      value: 0.7521821036106752
      name: Maxsim Accuracy@3
    - type: MaxSim_accuracy@5
      value: 0.7983987441130298
      name: Maxsim Accuracy@5
    - type: MaxSim_accuracy@10
      value: 0.8646153846153847
      name: Maxsim Accuracy@10
    - type: MaxSim_precision@1
      value: 0.5994976452119309
      name: Maxsim Precision@1
    - type: MaxSim_precision@3
      value: 0.3589220303506017
      name: Maxsim Precision@3
    - type: MaxSim_precision@5
      value: 0.2732370486656201
      name: Maxsim Precision@5
    - type: MaxSim_precision@10
      value: 0.18846467817896384
      name: Maxsim Precision@10
    - type: MaxSim_recall@1
      value: 0.35735643909346215
      name: Maxsim Recall@1
    - type: MaxSim_recall@3
      value: 0.5046865293399786
      name: Maxsim Recall@3
    - type: MaxSim_recall@5
      value: 0.5589613628393763
      name: Maxsim Recall@5
    - type: MaxSim_recall@10
      value: 0.6364941254189559
      name: Maxsim Recall@10
    - type: MaxSim_ndcg@10
      value: 0.6169511812842173
      name: Maxsim Ndcg@10
    - type: MaxSim_mrr@10
      value: 0.6867945229373801
      name: Maxsim Mrr@10
    - type: MaxSim_map@100
      value: 0.5394090934410984
      name: Maxsim Map@100
---

# ColBERT MUVERA Small

This is a [PyLate](https://github.com/lightonai/pylate) model finetuned from [bclavie/mini-base](https://huggingface.co/bclavie/mini-base) on the [msmarco-en-bge-gemma-unnormalized](https://huggingface.co/datasets/lightonai/ms-marco-en-bge-gemma-unnormalized) dataset. It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator.

This model is trained with un-normalized scores, making it compatible with [MUVERA fixed-dimensional encoding](https://arxiv.org/abs/2405.19504).

## Usage (txtai)

This model can be used to build embeddings databases with [txtai](https://github.com/neuml/txtai) for semantic search and/or as a knowledge source for retrieval augmented generation (RAG).

_Note: txtai 9.0+ is required for late interaction model support_

```python
import txtai

embeddings = txtai.Embeddings(
  sparse="neuml/colbert-muvera-small",
  content=True
)
embeddings.index(documents())

# Run a query
embeddings.search("query to run")
```

Late interaction models excel as reranker pipelines.

```python
from txtai.pipeline import Reranker, Similarity

similarity = Similarity(path="neuml/colbert-muvera-small", lateencode=True)
ranker = Reranker(embeddings, similarity)
ranker("query to run")
```

## Usage (PyLate)

Alternatively, the model can be loaded with [PyLate](https://github.com/lightonai/pylate).

```python
from pylate import rank, models

queries = [
    "query A",
    "query B",
]

documents = [
    ["document A", "document B"],
    ["document 1", "document C", "document B"],
]

documents_ids = [
    [1, 2],
    [1, 3, 2],
]

model = models.ColBERT(
    model_name_or_path="neuml/colbert-muvera-small",
)

queries_embeddings = model.encode(
    queries,
    is_query=True,
)

documents_embeddings = model.encode(
    documents,
    is_query=False,
)

reranked_documents = rank.rerank(
    documents_ids=documents_ids,
    queries_embeddings=queries_embeddings,
    documents_embeddings=documents_embeddings,
)
```

## Full Model Architecture

```
ColBERT(
  (0): Transformer({'max_seq_length': 299, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Dense({'in_features': 384, 'out_features': 128, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
)
```

## Evaluation

### BEIR Subset

The following table shows a subset of BEIR scored with the [txtai benchmarks script](https://github.com/neuml/txtai/blob/master/examples/benchmarks.py). 

Scores reported are `ndcg@10` and grouped into the following three categories.

#### FULL multi-vector maxsim

| Model             | Parameters | ArguAna  | NFCorpus | SciFact | Average |
|:------------------|:-----------|:---------|:---------|:--------|:--------|
| [AnswerAI ColBERT Small v1](https://huggingface.co/answerdotai/answerai-colbert-small-v1) | 33M | 0.4440 | 0.3649 | 0.7423 | 0.5171 |
| [ColBERT v2](https://huggingface.co/colbert-ir/colbertv2.0) | 110M | 0.4595 | 0.3165 | 0.6456 | 0.4739 |
| [ColBERT MUVERA Micro](https://huggingface.co/neuml/colbert-muvera-micro) | 4M | 0.3947 | 0.3235 | 0.6676 | 0.4619 |
| [**ColBERT MUVERA Small**](https://huggingface.co/neuml/colbert-muvera-small) | **33M** | **0.4455** | **0.3502** | **0.7145** | **0.5034** |
| [GTE ModernColBERT v1](https://huggingface.co/lightonai/GTE-ModernColBERT-v1) | 149M | 0.4946 | 0.3717 | 0.7529 | 0.5397 |

#### MUVERA encoding + maxsim re-ranking of the top 100 results per MUVERA paper

| Model             | Parameters | ArguAna  | NFCorpus | SciFact | Average |
|:------------------|:-----------|:---------|:---------|:--------|:--------|
| [AnswerAI ColBERT Small v1](https://huggingface.co/answerdotai/answerai-colbert-small-v1) | 33M | 0.0317 | 0.1135 | 0.0836 | 0.0763 |
| [ColBERT v2](https://huggingface.co/colbert-ir/colbertv2.0) | 110M | 0.4562 | 0.3025 | 0.6278 | 0.4622 |
| [ColBERT MUVERA Micro](https://huggingface.co/neuml/colbert-muvera-micro) | 4M| 0.3849 | 0.3095 | 0.6464 | 0.4469 |
| [**ColBERT MUVERA Small**](https://huggingface.co/neuml/colbert-muvera-small) | **33M** | **0.4451** | **0.3537** | **0.7148** | **0.5045** |
| [GTE ModernColBERT v1](https://huggingface.co/lightonai/GTE-ModernColBERT-v1) | 149M | 0.0265 | 0.1052 | 0.0556 | 0.0624 | 

#### MUVERA encoding only

| Model             | Parameters | ArguAna  | NFCorpus | SciFact | Average |
|:------------------|:-----------|:---------|:---------|:--------|:--------|
| [AnswerAI ColBERT Small v1](https://huggingface.co/answerdotai/answerai-colbert-small-v1) | 33M | 0.0024 | 0.0201 | 0.0047 | 0.0091 |
| [ColBERT v2](https://huggingface.co/colbert-ir/colbertv2.0) | 110M | 0.3463 | 0.2356 | 0.5002 | 0.3607 |
| [ColBERT MUVERA Micro](https://huggingface.co/neuml/colbert-muvera-micro) | 4M | 0.2795 | 0.2348 | 0.4875 | 0.3339 |
| [**ColBERT MUVERA Small**](https://huggingface.co/neuml/colbert-muvera-small) | **33M** | **0.3850** | **0.2928** | **0.6357** | **0.4378** | 
| [GTE ModernColBERT v1](https://huggingface.co/lightonai/GTE-ModernColBERT-v1) | 149M | 0.0003 | 0.0203 |0.0013 | 0.0073 | 

_Note: The scores reported don't match scores reported in the respective papers due to different default settings in the txtai benchmark scripts._

As noted earlier, models trained with min-max score normalization don't perform well with MUVERA encoding. See this [GitHub Issue](https://github.com/lightonai/pylate/issues/142) for more.

**In reviewing the scores, this model is surprisingly and unreasonably competitive with the original ColBERT v2 model at only 3% of the size!**

### Nano BEIR
* Dataset: `NanoBEIR_mean`
* Evaluated with <code>pylate.evaluation.nano_beir_evaluator.NanoBEIREvaluator</code>

| Metric              | Value     |
|:--------------------|:----------|
| MaxSim_accuracy@1   | 0.5995    |
| MaxSim_accuracy@3   | 0.7522    |
| MaxSim_accuracy@5   | 0.7984    |
| MaxSim_accuracy@10  | 0.8646    |
| MaxSim_precision@1  | 0.5995    |
| MaxSim_precision@3  | 0.3589    |
| MaxSim_precision@5  | 0.2732    |
| MaxSim_precision@10 | 0.1885    |
| MaxSim_recall@1     | 0.3574    |
| MaxSim_recall@3     | 0.5047    |
| MaxSim_recall@5     | 0.559     |
| MaxSim_recall@10    | 0.6365    |
| **MaxSim_ndcg@10**  | **0.617** |
| MaxSim_mrr@10       | 0.6868    |
| MaxSim_map@100      | 0.5394    |

## Training Details

### Training Hyperparameters

#### Non-Default Hyperparameters

- `eval_strategy`: steps
- `gradient_accumulation_steps`: 4
- `learning_rate`: 3e-06
- `num_train_epochs`: 1
- `warmup_ratio`: 0.05
- `bf16`: True

#### All Hyperparameters
<details><summary>Click to expand</summary>

- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: steps
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 8
- `per_device_eval_batch_size`: 8
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 4
- `eval_accumulation_steps`: None
- `torch_empty_cache_steps`: None
- `learning_rate`: 3e-06
- `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`: 0.05
- `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`: False
- `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

</details>

### Framework Versions
- Python: 3.10.18
- Sentence Transformers: 4.0.2
- PyLate: 1.3.0
- Transformers: 4.52.3
- PyTorch: 2.8.0+cu128
- Accelerate: 1.10.1
- Datasets: 4.0.0
- Tokenizers: 0.21.4

## Citation

### BibTeX

#### Sentence Transformers
```bibtex
@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"
}
```

#### PyLate
```bibtex
@misc{PyLate,
title={PyLate: Flexible Training and Retrieval for Late Interaction Models},
author={Chaffin, Antoine and Sourty, Raphaël},
url={https://github.com/lightonai/pylate},
year={2024}
}
```