|
|
--- |
|
|
language: |
|
|
- en |
|
|
tags: |
|
|
- ColBERT |
|
|
- PyLate |
|
|
- sentence-transformers |
|
|
- sentence-similarity |
|
|
- feature-extraction |
|
|
- generated_from_trainer |
|
|
- dataset_size:640000 |
|
|
- loss:Distillation |
|
|
base_model: NeuML/bert-hash-nano |
|
|
datasets: |
|
|
- lightonai/ms-marco-en-bge-gemma |
|
|
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 Nano |
|
|
results: |
|
|
- task: |
|
|
type: py-late-information-retrieval |
|
|
name: Py Late Information Retrieval |
|
|
dataset: |
|
|
name: NanoClimateFEVER |
|
|
type: NanoClimateFEVER |
|
|
metrics: |
|
|
- type: MaxSim_accuracy@1 |
|
|
value: 0.3 |
|
|
name: Maxsim Accuracy@1 |
|
|
- type: MaxSim_accuracy@3 |
|
|
value: 0.4 |
|
|
name: Maxsim Accuracy@3 |
|
|
- type: MaxSim_accuracy@5 |
|
|
value: 0.48 |
|
|
name: Maxsim Accuracy@5 |
|
|
- type: MaxSim_accuracy@10 |
|
|
value: 0.54 |
|
|
name: Maxsim Accuracy@10 |
|
|
- type: MaxSim_precision@1 |
|
|
value: 0.3 |
|
|
name: Maxsim Precision@1 |
|
|
- type: MaxSim_precision@3 |
|
|
value: 0.14666666666666664 |
|
|
name: Maxsim Precision@3 |
|
|
- type: MaxSim_precision@5 |
|
|
value: 0.10800000000000001 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.07200000000000001 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.12999999999999998 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.19833333333333333 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.24 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.295 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.25693689476232956 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.3689126984126984 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.20238579189860822 |
|
|
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: 0.66 |
|
|
name: Maxsim Accuracy@1 |
|
|
- type: MaxSim_accuracy@3 |
|
|
value: 0.82 |
|
|
name: Maxsim Accuracy@3 |
|
|
- type: MaxSim_accuracy@5 |
|
|
value: 0.9 |
|
|
name: Maxsim Accuracy@5 |
|
|
- type: MaxSim_accuracy@10 |
|
|
value: 0.92 |
|
|
name: Maxsim Accuracy@10 |
|
|
- type: MaxSim_precision@1 |
|
|
value: 0.66 |
|
|
name: Maxsim Precision@1 |
|
|
- type: MaxSim_precision@3 |
|
|
value: 0.5666666666666665 |
|
|
name: Maxsim Precision@3 |
|
|
- type: MaxSim_precision@5 |
|
|
value: 0.524 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.48200000000000004 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.05242687651506869 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.13921550887445522 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.19747421384152156 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.3240079111162478 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.5626087795584744 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.7505 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.43170467867134016 |
|
|
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: 0.8 |
|
|
name: Maxsim Accuracy@1 |
|
|
- type: MaxSim_accuracy@3 |
|
|
value: 0.84 |
|
|
name: Maxsim Accuracy@3 |
|
|
- type: MaxSim_accuracy@5 |
|
|
value: 0.86 |
|
|
name: Maxsim Accuracy@5 |
|
|
- type: MaxSim_accuracy@10 |
|
|
value: 0.92 |
|
|
name: Maxsim Accuracy@10 |
|
|
- type: MaxSim_precision@1 |
|
|
value: 0.8 |
|
|
name: Maxsim Precision@1 |
|
|
- type: MaxSim_precision@3 |
|
|
value: 0.29333333333333333 |
|
|
name: Maxsim Precision@3 |
|
|
- type: MaxSim_precision@5 |
|
|
value: 0.184 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.09999999999999998 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.7566666666666667 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.8133333333333332 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.84 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.89 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.8297799319515553 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.8250476190476193 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.8113438403701564 |
|
|
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: 0.4 |
|
|
name: Maxsim Accuracy@1 |
|
|
- type: MaxSim_accuracy@3 |
|
|
value: 0.52 |
|
|
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: 0.4 |
|
|
name: Maxsim Precision@1 |
|
|
- type: MaxSim_precision@3 |
|
|
value: 0.22666666666666668 |
|
|
name: Maxsim Precision@3 |
|
|
- type: MaxSim_precision@5 |
|
|
value: 0.18799999999999997 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.11199999999999999 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.2461904761904762 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.3277936507936508 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.4542380952380952 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.5184047619047619 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.4359941442854233 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.5049126984126984 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.36500352221028065 |
|
|
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: 0.8 |
|
|
name: Maxsim Accuracy@1 |
|
|
- type: MaxSim_accuracy@3 |
|
|
value: 0.94 |
|
|
name: Maxsim Accuracy@3 |
|
|
- type: MaxSim_accuracy@5 |
|
|
value: 0.96 |
|
|
name: Maxsim Accuracy@5 |
|
|
- type: MaxSim_accuracy@10 |
|
|
value: 1.0 |
|
|
name: Maxsim Accuracy@10 |
|
|
- type: MaxSim_precision@1 |
|
|
value: 0.8 |
|
|
name: Maxsim Precision@1 |
|
|
- type: MaxSim_precision@3 |
|
|
value: 0.4599999999999999 |
|
|
name: Maxsim Precision@3 |
|
|
- type: MaxSim_precision@5 |
|
|
value: 0.30799999999999994 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.16999999999999996 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.4 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.69 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.77 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.85 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.7791724226460205 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.8793333333333332 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.7004123402170076 |
|
|
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: 0.44 |
|
|
name: Maxsim Accuracy@1 |
|
|
- type: MaxSim_accuracy@3 |
|
|
value: 0.64 |
|
|
name: Maxsim Accuracy@3 |
|
|
- type: MaxSim_accuracy@5 |
|
|
value: 0.72 |
|
|
name: Maxsim Accuracy@5 |
|
|
- type: MaxSim_accuracy@10 |
|
|
value: 0.78 |
|
|
name: Maxsim Accuracy@10 |
|
|
- type: MaxSim_precision@1 |
|
|
value: 0.44 |
|
|
name: Maxsim Precision@1 |
|
|
- type: MaxSim_precision@3 |
|
|
value: 0.21333333333333332 |
|
|
name: Maxsim Precision@3 |
|
|
- type: MaxSim_precision@5 |
|
|
value: 0.14400000000000002 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.07800000000000001 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.44 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.64 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.72 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.78 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.6037947687284007 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.5473333333333332 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.5593945067344082 |
|
|
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: 0.66 |
|
|
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: 0.33199999999999996 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.26 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.042699664136408834 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.07806895769271134 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.09327844593663599 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.11679808931654996 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.32747074296711476 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.5297222222222222 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.14001894101433573 |
|
|
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: 0.36 |
|
|
name: Maxsim Accuracy@1 |
|
|
- type: MaxSim_accuracy@3 |
|
|
value: 0.58 |
|
|
name: Maxsim Accuracy@3 |
|
|
- type: MaxSim_accuracy@5 |
|
|
value: 0.72 |
|
|
name: Maxsim Accuracy@5 |
|
|
- type: MaxSim_accuracy@10 |
|
|
value: 0.8 |
|
|
name: Maxsim Accuracy@10 |
|
|
- type: MaxSim_precision@1 |
|
|
value: 0.36 |
|
|
name: Maxsim Precision@1 |
|
|
- type: MaxSim_precision@3 |
|
|
value: 0.19333333333333333 |
|
|
name: Maxsim Precision@3 |
|
|
- type: MaxSim_precision@5 |
|
|
value: 0.14800000000000002 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.08199999999999999 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.35 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.56 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.69 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.77 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.5666668175637105 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.5109365079365079 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.5060753330396947 |
|
|
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: 0.9 |
|
|
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: 0.86 |
|
|
name: Maxsim Precision@1 |
|
|
- type: MaxSim_precision@3 |
|
|
value: 0.32666666666666666 |
|
|
name: Maxsim Precision@3 |
|
|
- type: MaxSim_precision@5 |
|
|
value: 0.21599999999999997 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.11599999999999998 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.784 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.8313333333333333 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.8713333333333333 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.898 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.8685515910259487 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.8838888888888888 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.8518536903500825 |
|
|
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: 0.38 |
|
|
name: Maxsim Accuracy@1 |
|
|
- type: MaxSim_accuracy@3 |
|
|
value: 0.5 |
|
|
name: Maxsim Accuracy@3 |
|
|
- type: MaxSim_accuracy@5 |
|
|
value: 0.62 |
|
|
name: Maxsim Accuracy@5 |
|
|
- type: MaxSim_accuracy@10 |
|
|
value: 0.76 |
|
|
name: Maxsim Accuracy@10 |
|
|
- type: MaxSim_precision@1 |
|
|
value: 0.38 |
|
|
name: Maxsim Precision@1 |
|
|
- type: MaxSim_precision@3 |
|
|
value: 0.2333333333333333 |
|
|
name: Maxsim Precision@3 |
|
|
- type: MaxSim_precision@5 |
|
|
value: 0.18799999999999997 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.128 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.08066666666666666 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.14566666666666667 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.19466666666666668 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.26366666666666666 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.26913925437260855 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.4848809523809524 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.19279409328239955 |
|
|
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: 0.14 |
|
|
name: Maxsim Accuracy@1 |
|
|
- type: MaxSim_accuracy@3 |
|
|
value: 0.32 |
|
|
name: Maxsim Accuracy@3 |
|
|
- type: MaxSim_accuracy@5 |
|
|
value: 0.42 |
|
|
name: Maxsim Accuracy@5 |
|
|
- type: MaxSim_accuracy@10 |
|
|
value: 0.56 |
|
|
name: Maxsim Accuracy@10 |
|
|
- type: MaxSim_precision@1 |
|
|
value: 0.14 |
|
|
name: Maxsim Precision@1 |
|
|
- type: MaxSim_precision@3 |
|
|
value: 0.10666666666666666 |
|
|
name: Maxsim Precision@3 |
|
|
- type: MaxSim_precision@5 |
|
|
value: 0.08400000000000002 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.056000000000000015 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.14 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.32 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.42 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.56 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.3381955845251465 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.2689920634920634 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.27812414648450906 |
|
|
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: 0.6 |
|
|
name: Maxsim Accuracy@1 |
|
|
- type: MaxSim_accuracy@3 |
|
|
value: 0.72 |
|
|
name: Maxsim Accuracy@3 |
|
|
- type: MaxSim_accuracy@5 |
|
|
value: 0.8 |
|
|
name: Maxsim Accuracy@5 |
|
|
- type: MaxSim_accuracy@10 |
|
|
value: 0.82 |
|
|
name: Maxsim Accuracy@10 |
|
|
- type: MaxSim_precision@1 |
|
|
value: 0.6 |
|
|
name: Maxsim Precision@1 |
|
|
- type: MaxSim_precision@3 |
|
|
value: 0.2533333333333333 |
|
|
name: Maxsim Precision@3 |
|
|
- type: MaxSim_precision@5 |
|
|
value: 0.17600000000000002 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.092 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.565 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.7 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.785 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.81 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.6965110171594289 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.6668888888888889 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.659209595959596 |
|
|
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: 0.9591836734693877 |
|
|
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: 0.673469387755102 |
|
|
name: Maxsim Precision@1 |
|
|
- type: MaxSim_precision@3 |
|
|
value: 0.7074829931972788 |
|
|
name: Maxsim Precision@3 |
|
|
- type: MaxSim_precision@5 |
|
|
value: 0.6612244897959185 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.5204081632653061 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.04513010438618095 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.14053118239478446 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.21284594516135155 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.3318018815073785 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.5876998904974655 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.826530612244898 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.41690806080588444 |
|
|
name: Maxsim Map@100 |
|
|
- task: |
|
|
type: nano-beir |
|
|
name: Nano BEIR |
|
|
dataset: |
|
|
name: NanoBEIR mean |
|
|
type: NanoBEIR_mean |
|
|
metrics: |
|
|
- type: MaxSim_accuracy@1 |
|
|
value: 0.5271899529042385 |
|
|
name: Maxsim Accuracy@1 |
|
|
- type: MaxSim_accuracy@3 |
|
|
value: 0.6722448979591836 |
|
|
name: Maxsim Accuracy@3 |
|
|
- type: MaxSim_accuracy@5 |
|
|
value: 0.7446153846153846 |
|
|
name: Maxsim Accuracy@5 |
|
|
- type: MaxSim_accuracy@10 |
|
|
value: 0.8046153846153847 |
|
|
name: Maxsim Accuracy@10 |
|
|
- type: MaxSim_precision@1 |
|
|
value: 0.5271899529042385 |
|
|
name: Maxsim Precision@1 |
|
|
- type: MaxSim_precision@3 |
|
|
value: 0.3169858712715855 |
|
|
name: Maxsim Precision@3 |
|
|
- type: MaxSim_precision@5 |
|
|
value: 0.25086342229199377 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.17449293563579277 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.31021388112011294 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.4295596897247899 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.49914128462904644 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.5698214854239696 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.5478862953879712 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.6190676783533925 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.47040219546448486 |
|
|
name: Maxsim Map@100 |
|
|
--- |
|
|
|
|
|
# ColBERT MUVERA Nano |
|
|
|
|
|
This is a [PyLate](https://github.com/lightonai/pylate) model finetuned from [neuml/bert-hash-nano](https://huggingface.co/neuml/bert-hash-nano) on the [msmarco-en-bge-gemma unnormalized split](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. |
|
|
|
|
|
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-nano", |
|
|
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-nano", 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-nano", |
|
|
) |
|
|
|
|
|
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: BertHashModel |
|
|
(1): Dense({'in_features': 128, '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 | NFCorpus | SciDocs | SciFact | Average | |
|
|
|:------------------|:-----------|:---------|:---------|:--------|:--------| |
|
|
| [ColBERT v2](https://huggingface.co/colbert-ir/colbertv2.0) | 110M | 0.3165 | 0.1497 | 0.6456 | 0.3706 | |
|
|
| [ColBERT MUVERA Femto](https://huggingface.co/neuml/colbert-muvera-femto) | 0.2M | 0.2513 | 0.0870 | 0.4710 | 0.2698 | |
|
|
| [ColBERT MUVERA Pico](https://huggingface.co/neuml/colbert-muvera-pico) | 0.4M | 0.3005 | 0.1117 | 0.6452 | 0.3525 | |
|
|
| [**ColBERT MUVERA Nano**](https://huggingface.co/neuml/colbert-muvera-nano) | **0.9M** | **0.3180** | **0.1262** | **0.6576** | **0.3673** | |
|
|
| [ColBERT MUVERA Micro](https://huggingface.co/neuml/colbert-muvera-micro) | 4M | 0.3235 | 0.1244 | 0.6676 | 0.3718 | |
|
|
|
|
|
#### MUVERA encoding + maxsim re-ranking of the top 100 results per MUVERA paper |
|
|
|
|
|
| Model | Parameters | NFCorpus | SciDocs | SciFact | Average | |
|
|
|:------------------|:-----------|:---------|:---------|:--------|:--------| |
|
|
| [ColBERT v2](https://huggingface.co/colbert-ir/colbertv2.0) | 110M | 0.3025 | 0.1538 | 0.6278 | 0.3614 | |
|
|
| [ColBERT MUVERA Femto](https://huggingface.co/neuml/colbert-muvera-femto) | 0.2M | 0.2316 | 0.0858 | 0.4641 | 0.2605 | |
|
|
| [ColBERT MUVERA Pico](https://huggingface.co/neuml/colbert-muvera-pico) | 0.4M | 0.2821 | 0.1004 | 0.6090 | 0.3305 | |
|
|
| [**ColBERT MUVERA Nano**](https://huggingface.co/neuml/colbert-muvera-nano) | **0.9M** | **0.2996** | **0.1201** | **0.6249** | **0.3482** | |
|
|
| [ColBERT MUVERA Micro](https://huggingface.co/neuml/colbert-muvera-micro) | 4M | 0.3095 | 0.1228 | 0.6464 | 0.3596 | |
|
|
|
|
|
#### MUVERA encoding only |
|
|
|
|
|
| Model | Parameters | NFCorpus | SciDocs | SciFact | Average | |
|
|
|:------------------|:-----------|:---------|:---------|:--------|:--------| |
|
|
| [ColBERT v2](https://huggingface.co/colbert-ir/colbertv2.0) | 110M | 0.2356 | 0.1229 | 0.5002 | 0.2862 | |
|
|
| [ColBERT MUVERA Femto](https://huggingface.co/neuml/colbert-muvera-femto) | 0.2M | 0.1851 | 0.0411 | 0.3518 | 0.1927 | |
|
|
| [ColBERT MUVERA Pico](https://huggingface.co/neuml/colbert-muvera-pico) | 0.4M | 0.1926 | 0.0564 | 0.4424 | 0.2305 | |
|
|
| [**ColBERT MUVERA Nano**](https://huggingface.co/neuml/colbert-muvera-nano) | **0.9M** | **0.2355** | **0.0807** | **0.4904** | **0.2689** | |
|
|
| [ColBERT MUVERA Micro](https://huggingface.co/neuml/colbert-muvera-micro) | 4M | 0.2348 | 0.0882 | 0.4875 | 0.2702 | |
|
|
|
|
|
_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. |
|
|
|
|
|
**This model packs a punch into 950K parameters. It's the same architecture as the 4M parameter model with the modified embeddings layer taking the parameter county down. It even beats the original ColBERT v2 model on a couple of the benchmarks.** |
|
|
|
|
|
### Nano BEIR |
|
|
* Dataset: `NanoBEIR_mean` |
|
|
* Evaluated with <code>pylate.evaluation.nano_beir_evaluator.NanoBEIREvaluator</code> |
|
|
|
|
|
| Metric | Value | |
|
|
|:--------------------|:-----------| |
|
|
| MaxSim_accuracy@1 | 0.5272 | |
|
|
| MaxSim_accuracy@3 | 0.6722 | |
|
|
| MaxSim_accuracy@5 | 0.7446 | |
|
|
| MaxSim_accuracy@10 | 0.8046 | |
|
|
| MaxSim_precision@1 | 0.5272 | |
|
|
| MaxSim_precision@3 | 0.317 | |
|
|
| MaxSim_precision@5 | 0.2509 | |
|
|
| MaxSim_precision@10 | 0.1745 | |
|
|
| MaxSim_recall@1 | 0.3102 | |
|
|
| MaxSim_recall@3 | 0.4296 | |
|
|
| MaxSim_recall@5 | 0.4991 | |
|
|
| MaxSim_recall@10 | 0.5698 | |
|
|
| **MaxSim_ndcg@10** | **0.5479** | |
|
|
| MaxSim_mrr@10 | 0.6191 | |
|
|
| MaxSim_map@100 | 0.4704 | |
|
|
|
|
|
## Training Details |
|
|
|
|
|
### Training Hyperparameters |
|
|
|
|
|
#### Non-Default Hyperparameters |
|
|
|
|
|
- `eval_strategy`: steps |
|
|
- `per_device_train_batch_size`: 32 |
|
|
- `learning_rate`: 0.0003 |
|
|
- `num_train_epochs`: 1 |
|
|
- `warmup_ratio`: 0.05 |
|
|
- `fp16`: 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`: 32 |
|
|
- `per_device_eval_batch_size`: 8 |
|
|
- `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`: 0.0003 |
|
|
- `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 |
|
|
- `bf16`: False |
|
|
- `fp16`: True |
|
|
- `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} |
|
|
- `parallelism_config`: None |
|
|
- `deepspeed`: None |
|
|
- `label_smoothing_factor`: 0.0 |
|
|
- `optim`: adamw_torch_fused |
|
|
- `optim_args`: None |
|
|
- `adafactor`: False |
|
|
- `group_by_length`: False |
|
|
- `length_column_name`: length |
|
|
- `project`: huggingface |
|
|
- `trackio_space_id`: trackio |
|
|
- `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 |
|
|
- `hub_revision`: None |
|
|
- `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`: no |
|
|
- `neftune_noise_alpha`: None |
|
|
- `optim_target_modules`: None |
|
|
- `batch_eval_metrics`: False |
|
|
- `eval_on_start`: False |
|
|
- `use_liger_kernel`: False |
|
|
- `liger_kernel_config`: None |
|
|
- `eval_use_gather_object`: False |
|
|
- `average_tokens_across_devices`: True |
|
|
- `prompts`: None |
|
|
- `batch_sampler`: batch_sampler |
|
|
- `multi_dataset_batch_sampler`: proportional |
|
|
|
|
|
</details> |
|
|
|
|
|
### Framework Versions |
|
|
- Python: 3.10.18 |
|
|
- Sentence Transformers: 4.0.2 |
|
|
- PyLate: 1.3.2 |
|
|
- Transformers: 4.57.0 |
|
|
- PyTorch: 2.8.0+cu128 |
|
|
- Accelerate: 1.10.1 |
|
|
- Datasets: 4.1.1 |
|
|
- Tokenizers: 0.22.1 |
|
|
|
|
|
## 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} |
|
|
} |
|
|
``` |
|
|
|
