---
language:
- en
tags:
- ColBERT
- PyLate
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:640000
- loss:Distillation
datasets:
- lightonai/ms-marco-en-bge-gemma
pipeline_tag: sentence-similarity
library_name: PyLate
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: PyLate
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: 0.6
name: Maxsim Accuracy@3
- type: MaxSim_accuracy@5
value: 0.66
name: Maxsim Accuracy@5
- type: MaxSim_accuracy@10
value: 0.8
name: Maxsim Accuracy@10
- type: MaxSim_precision@1
value: 0.28
name: Maxsim Precision@1
- type: MaxSim_precision@3
value: 0.21333333333333332
name: Maxsim Precision@3
- type: MaxSim_precision@5
value: 0.15600000000000003
name: Maxsim Precision@5
- type: MaxSim_precision@10
value: 0.11399999999999999
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.14166666666666664
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.28
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.3233333333333333
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.4433333333333333
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.3514515373411296
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.4419126984126984
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.26787129909036694
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: 0.9
name: Maxsim Accuracy@3
- type: MaxSim_accuracy@5
value: 0.92
name: Maxsim Accuracy@5
- type: MaxSim_accuracy@10
value: 0.94
name: Maxsim Accuracy@10
- type: MaxSim_precision@1
value: 0.8
name: Maxsim Precision@1
- type: MaxSim_precision@3
value: 0.68
name: Maxsim Precision@3
- type: MaxSim_precision@5
value: 0.64
name: Maxsim Precision@5
- type: MaxSim_precision@10
value: 0.556
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.10146114576120233
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.1811253111210503
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.25584250683060056
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.38805909088160134
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.6860171601389934
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.8573333333333334
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.5296825033597241
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: 0.86
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: 0.86
name: Maxsim Precision@1
- type: MaxSim_precision@3
value: 0.32666666666666666
name: Maxsim Precision@3
- type: MaxSim_precision@5
value: 0.20799999999999996
name: Maxsim Precision@5
- type: MaxSim_precision@10
value: 0.10399999999999998
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.8166666666666668
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.9066666666666667
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.9566666666666667
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.9566666666666667
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.908144200292094
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.92
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.8814609006793713
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: 0.52
name: Maxsim Accuracy@1
- type: MaxSim_accuracy@3
value: 0.64
name: Maxsim Accuracy@3
- type: MaxSim_accuracy@5
value: 0.7
name: Maxsim Accuracy@5
- type: MaxSim_accuracy@10
value: 0.82
name: Maxsim Accuracy@10
- type: MaxSim_precision@1
value: 0.52
name: Maxsim Precision@1
- type: MaxSim_precision@3
value: 0.3
name: Maxsim Precision@3
- type: MaxSim_precision@5
value: 0.23199999999999996
name: Maxsim Precision@5
- type: MaxSim_precision@10
value: 0.144
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.3260793650793651
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.4550714285714285
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.5179523809523809
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.638452380952381
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.5521515882834523
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.6033809523809524
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.485613722262918
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: 0.9
name: Maxsim Accuracy@1
- type: MaxSim_accuracy@3
value: 0.98
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: 0.9
name: Maxsim Precision@1
- type: MaxSim_precision@3
value: 0.5333333333333333
name: Maxsim Precision@3
- type: MaxSim_precision@5
value: 0.3399999999999999
name: Maxsim Precision@5
- type: MaxSim_precision@10
value: 0.17399999999999996
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.45
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.8
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.85
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.87
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.8419623803570458
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.9440000000000001
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.7820805143551045
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: 0.52
name: Maxsim Accuracy@1
- type: MaxSim_accuracy@3
value: 0.68
name: Maxsim Accuracy@3
- type: MaxSim_accuracy@5
value: 0.76
name: Maxsim Accuracy@5
- type: MaxSim_accuracy@10
value: 0.86
name: Maxsim Accuracy@10
- type: MaxSim_precision@1
value: 0.52
name: Maxsim Precision@1
- type: MaxSim_precision@3
value: 0.22666666666666666
name: Maxsim Precision@3
- type: MaxSim_precision@5
value: 0.15200000000000002
name: Maxsim Precision@5
- type: MaxSim_precision@10
value: 0.08599999999999998
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.52
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.68
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.76
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.86
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.6811314480568632
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.6250238095238094
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.6333976362474815
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: 0.44
name: Maxsim Accuracy@1
- type: MaxSim_accuracy@3
value: 0.6
name: Maxsim Accuracy@3
- type: MaxSim_accuracy@5
value: 0.62
name: Maxsim Accuracy@5
- type: MaxSim_accuracy@10
value: 0.72
name: Maxsim Accuracy@10
- type: MaxSim_precision@1
value: 0.44
name: Maxsim Precision@1
- type: MaxSim_precision@3
value: 0.3933333333333333
name: Maxsim Precision@3
- type: MaxSim_precision@5
value: 0.35200000000000004
name: Maxsim Precision@5
- type: MaxSim_precision@10
value: 0.264
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.04230874849281337
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.08146626368119848
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.09815206535035287
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.12479201912898642
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.33242903156565573
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.5284126984126984
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.15006576918781514
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: 0.5
name: Maxsim Accuracy@1
- type: MaxSim_accuracy@3
value: 0.74
name: Maxsim Accuracy@3
- type: MaxSim_accuracy@5
value: 0.86
name: Maxsim Accuracy@5
- type: MaxSim_accuracy@10
value: 0.9
name: Maxsim Accuracy@10
- type: MaxSim_precision@1
value: 0.5
name: Maxsim Precision@1
- type: MaxSim_precision@3
value: 0.24666666666666667
name: Maxsim Precision@3
- type: MaxSim_precision@5
value: 0.17599999999999993
name: Maxsim Precision@5
- type: MaxSim_precision@10
value: 0.09599999999999997
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.49
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.7
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.82
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.86
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.6841974176648971
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.6358888888888888
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.6241807081807081
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: 0.88
name: Maxsim Accuracy@1
- type: MaxSim_accuracy@3
value: 0.98
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: 0.3999999999999999
name: Maxsim Precision@3
- type: MaxSim_precision@5
value: 0.25999999999999995
name: Maxsim Precision@5
- type: MaxSim_precision@10
value: 0.13799999999999998
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.7673333333333333
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.9386666666666668
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.9793333333333334
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.9966666666666666
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.9419539850914371
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.934
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.9163896103896104
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: 0.72
name: Maxsim Accuracy@3
- type: MaxSim_accuracy@5
value: 0.82
name: Maxsim Accuracy@5
- type: MaxSim_accuracy@10
value: 0.84
name: Maxsim Accuracy@10
- type: MaxSim_precision@1
value: 0.5
name: Maxsim Precision@1
- type: MaxSim_precision@3
value: 0.36666666666666664
name: Maxsim Precision@3
- type: MaxSim_precision@5
value: 0.284
name: Maxsim Precision@5
- type: MaxSim_precision@10
value: 0.182
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.10566666666666666
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.22666666666666666
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.29166666666666663
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.37166666666666665
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.3831880691359888
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.6239999999999999
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.29330717965633857
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: 0.16
name: Maxsim Accuracy@1
- type: MaxSim_accuracy@3
value: 0.56
name: Maxsim Accuracy@3
- type: MaxSim_accuracy@5
value: 0.66
name: Maxsim Accuracy@5
- type: MaxSim_accuracy@10
value: 0.76
name: Maxsim Accuracy@10
- type: MaxSim_precision@1
value: 0.16
name: Maxsim Precision@1
- type: MaxSim_precision@3
value: 0.18666666666666668
name: Maxsim Precision@3
- type: MaxSim_precision@5
value: 0.13200000000000003
name: Maxsim Precision@5
- type: MaxSim_precision@10
value: 0.07600000000000001
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.16
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.56
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.66
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.76
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.461790847680295
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.365547619047619
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.3743204230050349
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: 0.74
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: 0.74
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: 0.09799999999999999
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.705
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.795
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.83
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.87
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.8015954255022331
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.786388888888889
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.780149020175336
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: 0.7959183673469388
name: Maxsim Accuracy@1
- type: MaxSim_accuracy@3
value: 0.9795918367346939
name: Maxsim Accuracy@3
- type: MaxSim_accuracy@5
value: 0.9795918367346939
name: Maxsim Accuracy@5
- type: MaxSim_accuracy@10
value: 1.0
name: Maxsim Accuracy@10
- type: MaxSim_precision@1
value: 0.7959183673469388
name: Maxsim Precision@1
- type: MaxSim_precision@3
value: 0.7142857142857143
name: Maxsim Precision@3
- type: MaxSim_precision@5
value: 0.6653061224489795
name: Maxsim Precision@5
- type: MaxSim_precision@10
value: 0.5244897959183673
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.054514709716006485
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.14494235624957325
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.2233145114601526
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.3397163035501697
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.6049106751999275
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.8770651117589893
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.4446934096215408
name: Maxsim Map@100
- task:
type: nano-beir
name: Nano BEIR
dataset:
name: NanoBEIR mean
type: NanoBEIR_mean
metrics:
- type: MaxSim_accuracy@1
value: 0.6073783359497645
name: Maxsim Accuracy@1
- type: MaxSim_accuracy@3
value: 0.7815070643642071
name: Maxsim Accuracy@3
- type: MaxSim_accuracy@5
value: 0.8322762951334379
name: Maxsim Accuracy@5
- type: MaxSim_accuracy@10
value: 0.8861538461538461
name: Maxsim Accuracy@10
- type: MaxSim_precision@1
value: 0.6073783359497645
name: Maxsim Precision@1
- type: MaxSim_precision@3
value: 0.3754578754578754
name: Maxsim Precision@3
- type: MaxSim_precision@5
value: 0.2911773940345369
name: Maxsim Precision@5
- type: MaxSim_precision@10
value: 0.19665306122448975
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.36005363864482465
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.5192004122787115
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.5820201126610375
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.652257932911267
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.6331479820238474
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.7033041538959905
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.5510163612470269
name: Maxsim Map@100
---
# PyLate
This is a [PyLate](https://github.com/lightonai/pylate) model trained on the [`lightonai/ms-marco-en-bge-gemma`](https://huggingface.co/datasets/lightonai/ms-marco-en-bge-gemma) dataset. It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator.
## Model Details
This model is an alias of [`robro612/modernbert_xtr_kd_256`](https://huggingface.co/robro612/modernbert_xtr_kd_k256). It was KD-trained on [`lightonai/ms-marco-en-bge-gemma`](https://huggingface.co/datasets/lightonai/ms-marco-en-bge-gemma) and contrastively trained on [`bclavie/msmarco-10m-triplets`](https://huggingface.co/datasets/bclavie/msmarco-10m-triplets) with XTR's `k_train` set to 256.
### Model Description
- **Model Type:** PyLate model
- **Document Length:** 512 tokens
- **Query Length:** 32 tokens
- **Output Dimensionality:** 128 tokens
- **Similarity Function:** MaxSim
- **Training Dataset:**
- [train](https://huggingface.co/datasets/lightonai/ms-marco-en-bge-gemma)
- **Language:** en
### Model Sources
- **Documentation:** [PyLate Documentation](https://lightonai.github.io/pylate/)
- **Repository:** [PyLate on GitHub](https://github.com/lightonai/pylate)
- **Hugging Face:** [PyLate models on Hugging Face](https://huggingface.co/models?library=PyLate)
### Full Model Architecture
```
ColBERT(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
(1): Dense({'in_features': 768, 'out_features': 128, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'use_residual': False})
)
```
## Usage
First install the PyLate library:
```bash
pip install -U pylate
```
### Retrieval
Use this model with PyLate to index and retrieve documents. The index uses [FastPLAID](https://github.com/lightonai/fast-plaid) for efficient similarity search.
#### Indexing documents
Load the ColBERT model and initialize the PLAID index, then encode and index your documents:
```python
from pylate import indexes, models, retrieve
# Step 1: Load the ColBERT model
model = models.ColBERT(
model_name_or_path="pylate_model_id",
)
# Step 2: Initialize the PLAID index
index = indexes.PLAID(
index_folder="pylate-index",
index_name="index",
override=True, # This overwrites the existing index if any
)
# Step 3: Encode the documents
documents_ids = ["1", "2", "3"]
documents = ["document 1 text", "document 2 text", "document 3 text"]
documents_embeddings = model.encode(
documents,
batch_size=32,
is_query=False, # Ensure that it is set to False to indicate that these are documents, not queries
show_progress_bar=True,
)
# Step 4: Add document embeddings to the index by providing embeddings and corresponding ids
index.add_documents(
documents_ids=documents_ids,
documents_embeddings=documents_embeddings,
)
```
Note that you do not have to recreate the index and encode the documents every time. Once you have created an index and added the documents, you can re-use the index later by loading it:
```python
# To load an index, simply instantiate it with the correct folder/name and without overriding it
index = indexes.PLAID(
index_folder="pylate-index",
index_name="index",
)
```
#### Retrieving top-k documents for queries
Once the documents are indexed, you can retrieve the top-k most relevant documents for a given set of queries.
To do so, initialize the ColBERT retriever with the index you want to search in, encode the queries and then retrieve the top-k documents to get the top matches ids and relevance scores:
```python
# Step 1: Initialize the ColBERT retriever
retriever = retrieve.ColBERT(index=index)
# Step 2: Encode the queries
queries_embeddings = model.encode(
["query for document 3", "query for document 1"],
batch_size=32,
is_query=True, # # Ensure that it is set to False to indicate that these are queries
show_progress_bar=True,
)
# Step 3: Retrieve top-k documents
scores = retriever.retrieve(
queries_embeddings=queries_embeddings,
k=10, # Retrieve the top 10 matches for each query
)
```
### Reranking
If you only want to use the ColBERT model to perform reranking on top of your first-stage retrieval pipeline without building an index, you can simply use rank function and pass the queries and documents to rerank:
```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="pylate_model_id",
)
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,
)
```
## Evaluation
### Metrics
#### Py Late Information Retrieval
* Dataset: `['NanoClimateFEVER', 'NanoDBPedia', 'NanoFEVER', 'NanoFiQA2018', 'NanoHotpotQA', 'NanoMSMARCO', 'NanoNFCorpus', 'NanoNQ', 'NanoQuoraRetrieval', 'NanoSCIDOCS', 'NanoArguAna', 'NanoSciFact', 'NanoTouche2020']`
* Evaluated with pylate.evaluation.pylate_information_retrieval_evaluator.PyLateInformationRetrievalEvaluator
| Metric | NanoClimateFEVER | NanoDBPedia | NanoFEVER | NanoFiQA2018 | NanoHotpotQA | NanoMSMARCO | NanoNFCorpus | NanoNQ | NanoQuoraRetrieval | NanoSCIDOCS | NanoArguAna | NanoSciFact | NanoTouche2020 |
|:--------------------|:-----------------|:------------|:-----------|:-------------|:-------------|:------------|:-------------|:-----------|:-------------------|:------------|:------------|:------------|:---------------|
| MaxSim_accuracy@1 | 0.28 | 0.8 | 0.86 | 0.52 | 0.9 | 0.52 | 0.44 | 0.5 | 0.88 | 0.5 | 0.16 | 0.74 | 0.7959 |
| MaxSim_accuracy@3 | 0.6 | 0.9 | 0.96 | 0.64 | 0.98 | 0.68 | 0.6 | 0.74 | 0.98 | 0.72 | 0.56 | 0.82 | 0.9796 |
| MaxSim_accuracy@5 | 0.66 | 0.92 | 1.0 | 0.7 | 1.0 | 0.76 | 0.62 | 0.86 | 1.0 | 0.82 | 0.66 | 0.84 | 0.9796 |
| MaxSim_accuracy@10 | 0.8 | 0.94 | 1.0 | 0.82 | 1.0 | 0.86 | 0.72 | 0.9 | 1.0 | 0.84 | 0.76 | 0.88 | 1.0 |
| MaxSim_precision@1 | 0.28 | 0.8 | 0.86 | 0.52 | 0.9 | 0.52 | 0.44 | 0.5 | 0.88 | 0.5 | 0.16 | 0.74 | 0.7959 |
| MaxSim_precision@3 | 0.2133 | 0.68 | 0.3267 | 0.3 | 0.5333 | 0.2267 | 0.3933 | 0.2467 | 0.4 | 0.3667 | 0.1867 | 0.2933 | 0.7143 |
| MaxSim_precision@5 | 0.156 | 0.64 | 0.208 | 0.232 | 0.34 | 0.152 | 0.352 | 0.176 | 0.26 | 0.284 | 0.132 | 0.188 | 0.6653 |
| MaxSim_precision@10 | 0.114 | 0.556 | 0.104 | 0.144 | 0.174 | 0.086 | 0.264 | 0.096 | 0.138 | 0.182 | 0.076 | 0.098 | 0.5245 |
| MaxSim_recall@1 | 0.1417 | 0.1015 | 0.8167 | 0.3261 | 0.45 | 0.52 | 0.0423 | 0.49 | 0.7673 | 0.1057 | 0.16 | 0.705 | 0.0545 |
| MaxSim_recall@3 | 0.28 | 0.1811 | 0.9067 | 0.4551 | 0.8 | 0.68 | 0.0815 | 0.7 | 0.9387 | 0.2267 | 0.56 | 0.795 | 0.1449 |
| MaxSim_recall@5 | 0.3233 | 0.2558 | 0.9567 | 0.518 | 0.85 | 0.76 | 0.0982 | 0.82 | 0.9793 | 0.2917 | 0.66 | 0.83 | 0.2233 |
| MaxSim_recall@10 | 0.4433 | 0.3881 | 0.9567 | 0.6385 | 0.87 | 0.86 | 0.1248 | 0.86 | 0.9967 | 0.3717 | 0.76 | 0.87 | 0.3397 |
| **MaxSim_ndcg@10** | **0.3515** | **0.686** | **0.9081** | **0.5522** | **0.842** | **0.6811** | **0.3324** | **0.6842** | **0.942** | **0.3832** | **0.4618** | **0.8016** | **0.6049** |
| MaxSim_mrr@10 | 0.4419 | 0.8573 | 0.92 | 0.6034 | 0.944 | 0.625 | 0.5284 | 0.6359 | 0.934 | 0.624 | 0.3655 | 0.7864 | 0.8771 |
| MaxSim_map@100 | 0.2679 | 0.5297 | 0.8815 | 0.4856 | 0.7821 | 0.6334 | 0.1501 | 0.6242 | 0.9164 | 0.2933 | 0.3743 | 0.7801 | 0.4447 |
#### Nano BEIR
* Dataset: `NanoBEIR_mean`
* Evaluated with pylate.evaluation.nano_beir_evaluator.NanoBEIREvaluator
| Metric | Value |
|:--------------------|:-----------|
| MaxSim_accuracy@1 | 0.6074 |
| MaxSim_accuracy@3 | 0.7815 |
| MaxSim_accuracy@5 | 0.8323 |
| MaxSim_accuracy@10 | 0.8862 |
| MaxSim_precision@1 | 0.6074 |
| MaxSim_precision@3 | 0.3755 |
| MaxSim_precision@5 | 0.2912 |
| MaxSim_precision@10 | 0.1967 |
| MaxSim_recall@1 | 0.3601 |
| MaxSim_recall@3 | 0.5192 |
| MaxSim_recall@5 | 0.582 |
| MaxSim_recall@10 | 0.6523 |
| **MaxSim_ndcg@10** | **0.6331** |
| MaxSim_mrr@10 | 0.7033 |
| MaxSim_map@100 | 0.551 |
## Training Details
### Training Dataset
#### train
* Dataset: [train](https://huggingface.co/datasets/lightonai/ms-marco-en-bge-gemma) at [1a1ffe7](https://huggingface.co/datasets/lightonai/ms-marco-en-bge-gemma/tree/1a1ffe7cde403016be12ae532b249965b2293114)
* Size: 640,000 training samples
* Columns: query_id, document_ids, and scores
* Approximate statistics based on the first 1000 samples:
| | query_id | document_ids | scores |
|:--------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------|:------------------------------------|
| type | int | list | list |
| details |
685613 | [7546874, 1176459, 197677, 2306318, 8541504, ...] | [0.9999999992804947, 0.24845418756716053, 0.7594154013647826, 0.26644182105618575, 0.390668914839766, ...] |
| 237784 | [6366584, 4034101, 2325374, 6914618, 6042146, ...] | [0.9999999991784339, 0.42233632827946693, 0.5956354295491569, 0.12644415907455164, 0.6636713730105909, ...] |
| 904294 | [448408, 8743975, 49600, 7339401, 2714261, ...] | [0.9999999991841937, 0.877629062381539, 0.8330146583389045, 0.3116634796692611, 0.4633524534142185, ...] |
* Loss: pylate.losses.distillation.Distillation
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 16
- `learning_rate`: 4e-06
- `max_steps`: 20000
- `fp16`: True
- `dataloader_drop_last`: True
- `dataloader_num_workers`: 8
- `ddp_find_unused_parameters`: False
- `torch_compile`: True
- `torch_compile_backend`: inductor
- `eval_on_start`: True
#### All Hyperparameters