--- 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: 0.26 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: 0.78 name: Maxsim Accuracy@10 - type: MaxSim_precision@1 value: 0.26 name: Maxsim Precision@1 - type: MaxSim_precision@3 value: 0.19333333333333333 name: Maxsim Precision@3 - type: MaxSim_precision@5 value: 0.16 name: Maxsim Precision@5 - type: MaxSim_precision@10 value: 0.1 name: Maxsim Precision@10 - type: MaxSim_recall@1 value: 0.1383333333333333 name: Maxsim Recall@1 - type: MaxSim_recall@3 value: 0.24999999999999997 name: Maxsim Recall@3 - type: MaxSim_recall@5 value: 0.32166666666666666 name: Maxsim Recall@5 - type: MaxSim_recall@10 value: 0.39066666666666655 name: Maxsim Recall@10 - type: MaxSim_ndcg@10 value: 0.32039147745578483 name: Maxsim Ndcg@10 - type: MaxSim_mrr@10 value: 0.42276984126984124 name: Maxsim Mrr@10 - type: MaxSim_map@100 value: 0.24935334206601034 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: 0.78 name: Maxsim Accuracy@1 - type: MaxSim_accuracy@3 value: 0.9 name: Maxsim Accuracy@3 - type: MaxSim_accuracy@5 value: 0.9 name: Maxsim Accuracy@5 - type: MaxSim_accuracy@10 value: 0.94 name: Maxsim Accuracy@10 - type: MaxSim_precision@1 value: 0.78 name: Maxsim Precision@1 - type: MaxSim_precision@3 value: 0.6599999999999998 name: Maxsim Precision@3 - type: MaxSim_precision@5 value: 0.616 name: Maxsim Precision@5 - type: MaxSim_precision@10 value: 0.55 name: Maxsim Precision@10 - type: MaxSim_recall@1 value: 0.09075272085277744 name: Maxsim Recall@1 - type: MaxSim_recall@3 value: 0.16895043381209857 name: Maxsim Recall@3 - type: MaxSim_recall@5 value: 0.24051424266181912 name: Maxsim Recall@5 - type: MaxSim_recall@10 value: 0.36868865362502956 name: Maxsim Recall@10 - type: MaxSim_ndcg@10 value: 0.66624662933317 name: Maxsim Ndcg@10 - type: MaxSim_mrr@10 value: 0.8415238095238096 name: Maxsim Mrr@10 - type: MaxSim_map@100 value: 0.5145725477836222 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: 0.98 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: 0.34666666666666657 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: 0.9433333333333332 name: Maxsim Recall@3 - type: MaxSim_recall@5 value: 0.9633333333333333 name: Maxsim Recall@5 - type: MaxSim_recall@10 value: 0.97 name: Maxsim Recall@10 - type: MaxSim_ndcg@10 value: 0.925157785716936 name: Maxsim Ndcg@10 - type: MaxSim_mrr@10 value: 0.935 name: Maxsim Mrr@10 - type: MaxSim_map@100 value: 0.900428388746803 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: 0.5 name: Maxsim Accuracy@1 - type: MaxSim_accuracy@3 value: 0.7 name: Maxsim Accuracy@3 - type: MaxSim_accuracy@5 value: 0.74 name: Maxsim Accuracy@5 - type: MaxSim_accuracy@10 value: 0.8 name: Maxsim Accuracy@10 - type: MaxSim_precision@1 value: 0.5 name: Maxsim Precision@1 - type: MaxSim_precision@3 value: 0.31999999999999995 name: Maxsim Precision@3 - type: MaxSim_precision@5 value: 0.24 name: Maxsim Precision@5 - type: MaxSim_precision@10 value: 0.142 name: Maxsim Precision@10 - type: MaxSim_recall@1 value: 0.3094126984126984 name: Maxsim Recall@1 - type: MaxSim_recall@3 value: 0.474515873015873 name: Maxsim Recall@3 - type: MaxSim_recall@5 value: 0.5476190476190476 name: Maxsim Recall@5 - type: MaxSim_recall@10 value: 0.6147857142857143 name: Maxsim Recall@10 - type: MaxSim_ndcg@10 value: 0.5449947187566443 name: Maxsim Ndcg@10 - type: MaxSim_mrr@10 value: 0.6068888888888889 name: Maxsim Mrr@10 - type: MaxSim_map@100 value: 0.47848630223690586 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: 0.92 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: 0.92 name: Maxsim Precision@1 - type: MaxSim_precision@3 value: 0.5199999999999999 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: 0.46 name: Maxsim Recall@1 - type: MaxSim_recall@3 value: 0.78 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: 0.8390423470478856 name: Maxsim Ndcg@10 - type: MaxSim_mrr@10 value: 0.9506666666666667 name: Maxsim Mrr@10 - type: MaxSim_map@100 value: 0.7749759887824803 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: 0.56 name: Maxsim Accuracy@1 - type: MaxSim_accuracy@3 value: 0.72 name: Maxsim Accuracy@3 - type: MaxSim_accuracy@5 value: 0.76 name: Maxsim Accuracy@5 - type: MaxSim_accuracy@10 value: 0.88 name: Maxsim Accuracy@10 - type: MaxSim_precision@1 value: 0.56 name: Maxsim Precision@1 - type: MaxSim_precision@3 value: 0.24 name: Maxsim Precision@3 - type: MaxSim_precision@5 value: 0.15200000000000002 name: Maxsim Precision@5 - type: MaxSim_precision@10 value: 0.088 name: Maxsim Precision@10 - type: MaxSim_recall@1 value: 0.56 name: Maxsim Recall@1 - type: MaxSim_recall@3 value: 0.72 name: Maxsim Recall@3 - type: MaxSim_recall@5 value: 0.76 name: Maxsim Recall@5 - type: MaxSim_recall@10 value: 0.88 name: Maxsim Recall@10 - type: MaxSim_ndcg@10 value: 0.7161567165508727 name: Maxsim Ndcg@10 - type: MaxSim_mrr@10 value: 0.6650476190476189 name: Maxsim Mrr@10 - type: MaxSim_map@100 value: 0.672465263965264 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: 0.46 name: Maxsim Accuracy@1 - type: MaxSim_accuracy@3 value: 0.58 name: Maxsim Accuracy@3 - type: MaxSim_accuracy@5 value: 0.6 name: Maxsim Accuracy@5 - type: MaxSim_accuracy@10 value: 0.66 name: Maxsim Accuracy@10 - type: MaxSim_precision@1 value: 0.46 name: Maxsim Precision@1 - type: MaxSim_precision@3 value: 0.38 name: Maxsim Precision@3 - type: MaxSim_precision@5 value: 0.32 name: Maxsim Precision@5 - type: MaxSim_precision@10 value: 0.272 name: Maxsim Precision@10 - type: MaxSim_recall@1 value: 0.04317667470348151 name: Maxsim Recall@1 - type: MaxSim_recall@3 value: 0.07996223003774396 name: Maxsim Recall@3 - type: MaxSim_recall@5 value: 0.09447327378743205 name: Maxsim Recall@5 - type: MaxSim_recall@10 value: 0.12091153813606693 name: Maxsim Recall@10 - type: MaxSim_ndcg@10 value: 0.33473796463548466 name: Maxsim Ndcg@10 - type: MaxSim_mrr@10 value: 0.5260238095238096 name: Maxsim Mrr@10 - type: MaxSim_map@100 value: 0.14684740975296695 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: 0.48 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: 0.9 name: Maxsim Accuracy@10 - type: MaxSim_precision@1 value: 0.48 name: Maxsim Precision@1 - type: MaxSim_precision@3 value: 0.24666666666666667 name: Maxsim Precision@3 - type: MaxSim_precision@5 value: 0.16799999999999998 name: Maxsim Precision@5 - type: MaxSim_precision@10 value: 0.09399999999999999 name: Maxsim Precision@10 - type: MaxSim_recall@1 value: 0.46 name: Maxsim Recall@1 - type: MaxSim_recall@3 value: 0.68 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: 0.6686040003007178 name: Maxsim Ndcg@10 - type: MaxSim_mrr@10 value: 0.6210714285714285 name: Maxsim Mrr@10 - type: MaxSim_map@100 value: 0.6099890727147909 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: 0.92 name: Maxsim Accuracy@1 - type: MaxSim_accuracy@3 value: 1.0 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: 0.92 name: Maxsim Precision@1 - type: MaxSim_precision@3 value: 0.40666666666666657 name: Maxsim Precision@3 - type: MaxSim_precision@5 value: 0.26 name: Maxsim Precision@5 - type: MaxSim_precision@10 value: 0.13599999999999998 name: Maxsim Precision@10 - type: MaxSim_recall@1 value: 0.8073333333333333 name: Maxsim Recall@1 - type: MaxSim_recall@3 value: 0.9586666666666668 name: Maxsim Recall@3 - type: MaxSim_recall@5 value: 0.9826666666666667 name: Maxsim Recall@5 - type: MaxSim_recall@10 value: 0.9933333333333334 name: Maxsim Recall@10 - type: MaxSim_ndcg@10 value: 0.9578930498899669 name: Maxsim Ndcg@10 - type: MaxSim_mrr@10 value: 0.96 name: Maxsim Mrr@10 - type: MaxSim_map@100 value: 0.9378103896103898 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: 0.46 name: Maxsim Accuracy@1 - type: MaxSim_accuracy@3 value: 0.66 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: 0.46 name: Maxsim Precision@1 - type: MaxSim_precision@3 value: 0.34 name: Maxsim Precision@3 - type: MaxSim_precision@5 value: 0.256 name: Maxsim Precision@5 - type: MaxSim_precision@10 value: 0.19 name: Maxsim Precision@10 - type: MaxSim_recall@1 value: 0.09666666666666668 name: Maxsim Recall@1 - type: MaxSim_recall@3 value: 0.21066666666666664 name: Maxsim Recall@3 - type: MaxSim_recall@5 value: 0.26266666666666666 name: Maxsim Recall@5 - type: MaxSim_recall@10 value: 0.38766666666666666 name: Maxsim Recall@10 - type: MaxSim_ndcg@10 value: 0.3716553413359221 name: Maxsim Ndcg@10 - type: MaxSim_mrr@10 value: 0.5760555555555554 name: Maxsim Mrr@10 - type: MaxSim_map@100 value: 0.27745676706388667 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: 0.2 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: 0.82 name: Maxsim Accuracy@10 - type: MaxSim_precision@1 value: 0.2 name: Maxsim Precision@1 - type: MaxSim_precision@3 value: 0.18666666666666668 name: Maxsim Precision@3 - type: MaxSim_precision@5 value: 0.128 name: Maxsim Precision@5 - type: MaxSim_precision@10 value: 0.08199999999999999 name: Maxsim Precision@10 - type: MaxSim_recall@1 value: 0.2 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: 0.82 name: Maxsim Recall@10 - type: MaxSim_ndcg@10 value: 0.49503741719510885 name: Maxsim Ndcg@10 - type: MaxSim_mrr@10 value: 0.3925793650793651 name: Maxsim Mrr@10 - type: MaxSim_map@100 value: 0.3970842977571503 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: 0.78 name: Maxsim Accuracy@3 - type: MaxSim_accuracy@5 value: 0.8 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: 0.27999999999999997 name: Maxsim Precision@3 - type: MaxSim_precision@5 value: 0.18 name: Maxsim Precision@5 - type: MaxSim_precision@10 value: 0.09799999999999999 name: Maxsim Precision@10 - type: MaxSim_recall@1 value: 0.675 name: Maxsim Recall@1 - type: MaxSim_recall@3 value: 0.765 name: Maxsim Recall@3 - type: MaxSim_recall@5 value: 0.8 name: Maxsim Recall@5 - type: MaxSim_recall@10 value: 0.87 name: Maxsim Recall@10 - type: MaxSim_ndcg@10 value: 0.7788958916951562 name: Maxsim Ndcg@10 - type: MaxSim_mrr@10 value: 0.7513571428571428 name: Maxsim Mrr@10 - type: MaxSim_map@100 value: 0.7534500915750916 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: 0.8163265306122449 name: Maxsim Accuracy@1 - type: MaxSim_accuracy@3 value: 0.9591836734693877 name: Maxsim Accuracy@3 - type: MaxSim_accuracy@5 value: 0.9591836734693877 name: Maxsim Accuracy@5 - type: MaxSim_accuracy@10 value: 0.9795918367346939 name: Maxsim Accuracy@10 - type: MaxSim_precision@1 value: 0.8163265306122449 name: Maxsim Precision@1 - type: MaxSim_precision@3 value: 0.7074829931972788 name: Maxsim Precision@3 - type: MaxSim_precision@5 value: 0.6204081632653061 name: Maxsim Precision@5 - type: MaxSim_precision@10 value: 0.5102040816326531 name: Maxsim Precision@10 - type: MaxSim_recall@1 value: 0.05518453156908425 name: Maxsim Recall@1 - type: MaxSim_recall@3 value: 0.1473987812718667 name: Maxsim Recall@3 - type: MaxSim_recall@5 value: 0.21441836348902682 name: Maxsim Recall@5 - type: MaxSim_recall@10 value: 0.33183454535355095 name: Maxsim Recall@10 - type: MaxSim_ndcg@10 value: 0.5945921894543182 name: Maxsim Ndcg@10 - type: MaxSim_mrr@10 value: 0.8877551020408163 name: Maxsim Mrr@10 - type: MaxSim_map@100 value: 0.4401324508472191 name: Maxsim Map@100 - task: type: nano-beir name: Nano BEIR dataset: name: NanoBEIR mean type: NanoBEIR_mean metrics: - type: MaxSim_accuracy@1 value: 0.6104866562009419 name: Maxsim Accuracy@1 - type: MaxSim_accuracy@3 value: 0.7768602825745682 name: Maxsim Accuracy@3 - type: MaxSim_accuracy@5 value: 0.815321821036107 name: Maxsim Accuracy@5 - type: MaxSim_accuracy@10 value: 0.8845839874411303 name: Maxsim Accuracy@10 - type: MaxSim_precision@1 value: 0.6104866562009419 name: Maxsim Precision@1 - type: MaxSim_precision@3 value: 0.37134484563055986 name: Maxsim Precision@3 - type: MaxSim_precision@5 value: 0.28095447409733126 name: Maxsim Precision@5 - type: MaxSim_precision@10 value: 0.19570800627943483 name: Maxsim Precision@10 - type: MaxSim_recall@1 value: 0.36250204811831094 name: Maxsim Recall@1 - type: MaxSim_recall@3 value: 0.5183456911387884 name: Maxsim Recall@3 - type: MaxSim_recall@5 value: 0.5728737123762044 name: Maxsim Recall@5 - type: MaxSim_recall@10 value: 0.6513759321590022 name: Maxsim Recall@10 - type: MaxSim_ndcg@10 value: 0.6318004253359976 name: Maxsim Ndcg@10 - type: MaxSim_mrr@10 value: 0.7028260945403803 name: Maxsim Mrr@10 - type: MaxSim_map@100 value: 0.5502347933001986 name: Maxsim Map@100 --- # PyLate This is a [PyLate](https://github.com/lightonai/pylate) model trained on the [train](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 ### 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 | 0.26 | 0.78 | 0.88 | 0.5 | 0.92 | 0.56 | 0.46 | 0.48 | 0.92 | 0.46 | 0.2 | 0.7 | 0.8163 | | MaxSim_accuracy@3 | 0.56 | 0.9 | 0.98 | 0.7 | 0.98 | 0.72 | 0.58 | 0.72 | 1.0 | 0.66 | 0.56 | 0.78 | 0.9592 | | MaxSim_accuracy@5 | 0.64 | 0.9 | 1.0 | 0.74 | 1.0 | 0.76 | 0.6 | 0.8 | 1.0 | 0.76 | 0.64 | 0.8 | 0.9592 | | MaxSim_accuracy@10 | 0.78 | 0.94 | 1.0 | 0.8 | 1.0 | 0.88 | 0.66 | 0.9 | 1.0 | 0.86 | 0.82 | 0.88 | 0.9796 | | MaxSim_precision@1 | 0.26 | 0.78 | 0.88 | 0.5 | 0.92 | 0.56 | 0.46 | 0.48 | 0.92 | 0.46 | 0.2 | 0.7 | 0.8163 | | MaxSim_precision@3 | 0.1933 | 0.66 | 0.3467 | 0.32 | 0.52 | 0.24 | 0.38 | 0.2467 | 0.4067 | 0.34 | 0.1867 | 0.28 | 0.7075 | | MaxSim_precision@5 | 0.16 | 0.616 | 0.212 | 0.24 | 0.34 | 0.152 | 0.32 | 0.168 | 0.26 | 0.256 | 0.128 | 0.18 | 0.6204 | | MaxSim_precision@10 | 0.1 | 0.55 | 0.108 | 0.142 | 0.174 | 0.088 | 0.272 | 0.094 | 0.136 | 0.19 | 0.082 | 0.098 | 0.5102 | | MaxSim_recall@1 | 0.1383 | 0.0908 | 0.8167 | 0.3094 | 0.46 | 0.56 | 0.0432 | 0.46 | 0.8073 | 0.0967 | 0.2 | 0.675 | 0.0552 | | MaxSim_recall@3 | 0.25 | 0.169 | 0.9433 | 0.4745 | 0.78 | 0.72 | 0.08 | 0.68 | 0.9587 | 0.2107 | 0.56 | 0.765 | 0.1474 | | MaxSim_recall@5 | 0.3217 | 0.2405 | 0.9633 | 0.5476 | 0.85 | 0.76 | 0.0945 | 0.77 | 0.9827 | 0.2627 | 0.64 | 0.8 | 0.2144 | | MaxSim_recall@10 | 0.3907 | 0.3687 | 0.97 | 0.6148 | 0.87 | 0.88 | 0.1209 | 0.85 | 0.9933 | 0.3877 | 0.82 | 0.87 | 0.3318 | | **MaxSim_ndcg@10** | **0.3204** | **0.6662** | **0.9252** | **0.545** | **0.839** | **0.7162** | **0.3347** | **0.6686** | **0.9579** | **0.3717** | **0.495** | **0.7789** | **0.5946** | | MaxSim_mrr@10 | 0.4228 | 0.8415 | 0.935 | 0.6069 | 0.9507 | 0.665 | 0.526 | 0.6211 | 0.96 | 0.5761 | 0.3926 | 0.7514 | 0.8878 | | MaxSim_map@100 | 0.2494 | 0.5146 | 0.9004 | 0.4785 | 0.775 | 0.6725 | 0.1468 | 0.61 | 0.9378 | 0.2775 | 0.3971 | 0.7535 | 0.4401 | #### Nano BEIR * Dataset: `NanoBEIR_mean` * Evaluated with pylate.evaluation.nano_beir_evaluator.NanoBEIREvaluator | Metric | Value | |:--------------------|:-----------| | MaxSim_accuracy@1 | 0.6105 | | MaxSim_accuracy@3 | 0.7769 | | MaxSim_accuracy@5 | 0.8153 | | MaxSim_accuracy@10 | 0.8846 | | MaxSim_precision@1 | 0.6105 | | MaxSim_precision@3 | 0.3713 | | MaxSim_precision@5 | 0.281 | | MaxSim_precision@10 | 0.1957 | | MaxSim_recall@1 | 0.3625 | | MaxSim_recall@3 | 0.5183 | | MaxSim_recall@5 | 0.5729 | | MaxSim_recall@10 | 0.6514 | | **MaxSim_ndcg@10** | **0.6318** | | MaxSim_mrr@10 | 0.7028 | | MaxSim_map@100 | 0.5502 | ## 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 | | | | * Samples: | query_id | document_ids | scores | |:--------------------|:----------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------| | 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
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: True - `per_device_train_batch_size`: 16 - `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`: 4e-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`: 3.0 - `max_steps`: 20000 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.0 - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: True - `save_on_each_node`: False - `save_only_model`: False - `restore_callback_states_from_checkpoint`: False - `no_cuda`: False - `use_cpu`: False - `use_mps_device`: False - `seed`: 42 - `data_seed`: None - `jit_mode_eval`: False - `use_ipex`: False - `bf16`: 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`: True - `dataloader_num_workers`: 8 - `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 - `optim_args`: None - `adafactor`: False - `group_by_length`: False - `length_column_name`: length - `ddp_find_unused_parameters`: False - `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`: True - `torch_compile_backend`: inductor - `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`: True - `use_liger_kernel`: False - `liger_kernel_config`: None - `eval_use_gather_object`: False - `average_tokens_across_devices`: False - `prompts`: None - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: proportional - `router_mapping`: {} - `learning_rate_mapping`: {}