Nomic Embed Text v1.5

--- library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - feature-extraction - sentence-similarity - mteb - transformers - transformers.js model-index: - name: epoch_0_model results: - task: type: Classification dataset: type: mteb/amazon_counterfactual name: MTEB AmazonCounterfactualClassification (en) config: en split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 75.20895522388058 - type: ap value: 38.57605549557802 - type: f1 value: 69.35586565857854 - task: type: Classification dataset: type: mteb/amazon_polarity name: MTEB AmazonPolarityClassification config: default split: test revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy value: 91.8144 - type: ap value: 88.65222882032363 - type: f1 value: 91.80426301643274 - task: type: Classification dataset: type: mteb/amazon_reviews_multi name: MTEB AmazonReviewsClassification (en) config: en split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 47.162000000000006 - type: f1 value: 46.59329642263158 - task: type: Retrieval dataset: type: arguana name: MTEB ArguAna config: default split: test revision: None metrics: - type: map_at_1 value: 24.253 - type: map_at_10 value: 38.962 - type: map_at_100 value: 40.081 - type: map_at_1000 value: 40.089000000000006 - type: map_at_3 value: 33.499 - type: map_at_5 value: 36.351 - type: mrr_at_1 value: 24.609 - type: mrr_at_10 value: 39.099000000000004 - type: mrr_at_100 value: 40.211000000000006 - type: mrr_at_1000 value: 40.219 - type: mrr_at_3 value: 33.677 - type: mrr_at_5 value: 36.469 - type: ndcg_at_1 value: 24.253 - type: ndcg_at_10 value: 48.010999999999996 - type: ndcg_at_100 value: 52.756 - type: ndcg_at_1000 value: 52.964999999999996 - type: ndcg_at_3 value: 36.564 - type: ndcg_at_5 value: 41.711999999999996 - type: precision_at_1 value: 24.253 - type: precision_at_10 value: 7.738 - type: precision_at_100 value: 0.98 - type: precision_at_1000 value: 0.1 - type: precision_at_3 value: 15.149000000000001 - type: precision_at_5 value: 11.593 - type: recall_at_1 value: 24.253 - type: recall_at_10 value: 77.383 - type: recall_at_100 value: 98.009 - type: recall_at_1000 value: 99.644 - type: recall_at_3 value: 45.448 - type: recall_at_5 value: 57.965999999999994 - task: type: Clustering dataset: type: mteb/arxiv-clustering-p2p name: MTEB ArxivClusteringP2P config: default split: test revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: v_measure value: 45.69069567851087 - task: type: Clustering dataset: type: mteb/arxiv-clustering-s2s name: MTEB ArxivClusteringS2S config: default split: test revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: v_measure value: 36.35185490976283 - task: type: Reranking dataset: type: mteb/askubuntudupquestions-reranking name: MTEB AskUbuntuDupQuestions config: default split: test revision: 2000358ca161889fa9c082cb41daa8dcfb161a54 metrics: - type: map value: 61.71274951450321 - type: mrr value: 76.06032625423207 - task: type: STS dataset: type: mteb/biosses-sts name: MTEB BIOSSES config: default split: test revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: cos_sim_pearson value: 86.73980520022269 - type: cos_sim_spearman value: 84.24649792685918 - type: euclidean_pearson value: 85.85197641158186 - type: euclidean_spearman value: 84.24649792685918 - type: manhattan_pearson value: 86.26809552711346 - type: manhattan_spearman value: 84.56397504030865 - task: type: Classification dataset: type: mteb/banking77 name: MTEB Banking77Classification config: default split: test revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy value: 84.25324675324674 - type: f1 value: 84.17872280892557 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-p2p name: MTEB BiorxivClusteringP2P config: default split: test revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: v_measure value: 38.770253446400886 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-s2s name: MTEB BiorxivClusteringS2S config: default split: test revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: v_measure value: 32.94307095497281 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackAndroidRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 32.164 - type: map_at_10 value: 42.641 - type: map_at_100 value: 43.947 - type: map_at_1000 value: 44.074999999999996 - type: map_at_3 value: 39.592 - type: map_at_5 value: 41.204 - type: mrr_at_1 value: 39.628 - type: mrr_at_10 value: 48.625 - type: mrr_at_100 value: 49.368 - type: mrr_at_1000 value: 49.413000000000004 - type: mrr_at_3 value: 46.400000000000006 - type: mrr_at_5 value: 47.68 - type: ndcg_at_1 value: 39.628 - type: ndcg_at_10 value: 48.564 - type: ndcg_at_100 value: 53.507000000000005 - type: ndcg_at_1000 value: 55.635999999999996 - type: ndcg_at_3 value: 44.471 - type: ndcg_at_5 value: 46.137 - type: precision_at_1 value: 39.628 - type: precision_at_10 value: 8.856 - type: precision_at_100 value: 1.429 - type: precision_at_1000 value: 0.191 - type: precision_at_3 value: 21.268 - type: precision_at_5 value: 14.649000000000001 - type: recall_at_1 value: 32.164 - type: recall_at_10 value: 59.609 - type: recall_at_100 value: 80.521 - type: recall_at_1000 value: 94.245 - type: recall_at_3 value: 46.521 - type: recall_at_5 value: 52.083999999999996 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackEnglishRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 31.526 - type: map_at_10 value: 41.581 - type: map_at_100 value: 42.815999999999995 - type: map_at_1000 value: 42.936 - type: map_at_3 value: 38.605000000000004 - type: map_at_5 value: 40.351 - type: mrr_at_1 value: 39.489999999999995 - type: mrr_at_10 value: 47.829 - type: mrr_at_100 value: 48.512 - type: mrr_at_1000 value: 48.552 - type: mrr_at_3 value: 45.754 - type: mrr_at_5 value: 46.986 - type: ndcg_at_1 value: 39.489999999999995 - type: ndcg_at_10 value: 47.269 - type: ndcg_at_100 value: 51.564 - type: ndcg_at_1000 value: 53.53099999999999 - type: ndcg_at_3 value: 43.301 - type: ndcg_at_5 value: 45.239000000000004 - type: precision_at_1 value: 39.489999999999995 - type: precision_at_10 value: 8.93 - type: precision_at_100 value: 1.415 - type: precision_at_1000 value: 0.188 - type: precision_at_3 value: 20.892 - type: precision_at_5 value: 14.865999999999998 - type: recall_at_1 value: 31.526 - type: recall_at_10 value: 56.76 - type: recall_at_100 value: 75.029 - type: recall_at_1000 value: 87.491 - type: recall_at_3 value: 44.786 - type: recall_at_5 value: 50.254 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGamingRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 40.987 - type: map_at_10 value: 52.827 - type: map_at_100 value: 53.751000000000005 - type: map_at_1000 value: 53.81 - type: map_at_3 value: 49.844 - type: map_at_5 value: 51.473 - type: mrr_at_1 value: 46.833999999999996 - type: mrr_at_10 value: 56.389 - type: mrr_at_100 value: 57.003 - type: mrr_at_1000 value: 57.034 - type: mrr_at_3 value: 54.17999999999999 - type: mrr_at_5 value: 55.486999999999995 - type: ndcg_at_1 value: 46.833999999999996 - type: ndcg_at_10 value: 58.372 - type: ndcg_at_100 value: 62.068 - type: ndcg_at_1000 value: 63.288 - type: ndcg_at_3 value: 53.400000000000006 - type: ndcg_at_5 value: 55.766000000000005 - type: precision_at_1 value: 46.833999999999996 - type: precision_at_10 value: 9.191 - type: precision_at_100 value: 1.192 - type: precision_at_1000 value: 0.134 - type: precision_at_3 value: 23.448 - type: precision_at_5 value: 15.862000000000002 - type: recall_at_1 value: 40.987 - type: recall_at_10 value: 71.146 - type: recall_at_100 value: 87.035 - type: recall_at_1000 value: 95.633 - type: recall_at_3 value: 58.025999999999996 - type: recall_at_5 value: 63.815999999999995 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGisRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 24.587 - type: map_at_10 value: 33.114 - type: map_at_100 value: 34.043 - type: map_at_1000 value: 34.123999999999995 - type: map_at_3 value: 30.45 - type: map_at_5 value: 31.813999999999997 - type: mrr_at_1 value: 26.554 - type: mrr_at_10 value: 35.148 - type: mrr_at_100 value: 35.926 - type: mrr_at_1000 value: 35.991 - type: mrr_at_3 value: 32.599000000000004 - type: mrr_at_5 value: 33.893 - type: ndcg_at_1 value: 26.554 - type: ndcg_at_10 value: 38.132 - type: ndcg_at_100 value: 42.78 - type: ndcg_at_1000 value: 44.919 - type: ndcg_at_3 value: 32.833 - type: ndcg_at_5 value: 35.168 - type: precision_at_1 value: 26.554 - type: precision_at_10 value: 5.921 - type: precision_at_100 value: 0.8659999999999999 - type: precision_at_1000 value: 0.109 - type: precision_at_3 value: 13.861 - type: precision_at_5 value: 9.605 - type: recall_at_1 value: 24.587 - type: recall_at_10 value: 51.690000000000005 - type: recall_at_100 value: 73.428 - type: recall_at_1000 value: 89.551 - type: recall_at_3 value: 37.336999999999996 - type: recall_at_5 value: 43.047000000000004 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackMathematicaRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 16.715 - type: map_at_10 value: 24.251 - type: map_at_100 value: 25.326999999999998 - type: map_at_1000 value: 25.455 - type: map_at_3 value: 21.912000000000003 - type: map_at_5 value: 23.257 - type: mrr_at_1 value: 20.274 - type: mrr_at_10 value: 28.552 - type: mrr_at_100 value: 29.42 - type: mrr_at_1000 value: 29.497 - type: mrr_at_3 value: 26.14 - type: mrr_at_5 value: 27.502 - type: ndcg_at_1 value: 20.274 - type: ndcg_at_10 value: 29.088 - type: ndcg_at_100 value: 34.293 - type: ndcg_at_1000 value: 37.271 - type: ndcg_at_3 value: 24.708 - type: ndcg_at_5 value: 26.809 - type: precision_at_1 value: 20.274 - type: precision_at_10 value: 5.361 - type: precision_at_100 value: 0.915 - type: precision_at_1000 value: 0.13 - type: precision_at_3 value: 11.733 - type: precision_at_5 value: 8.556999999999999 - type: recall_at_1 value: 16.715 - type: recall_at_10 value: 39.587 - type: recall_at_100 value: 62.336000000000006 - type: recall_at_1000 value: 83.453 - type: recall_at_3 value: 27.839999999999996 - type: recall_at_5 value: 32.952999999999996 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackPhysicsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 28.793000000000003 - type: map_at_10 value: 38.582 - type: map_at_100 value: 39.881 - type: map_at_1000 value: 39.987 - type: map_at_3 value: 35.851 - type: map_at_5 value: 37.289 - type: mrr_at_1 value: 34.455999999999996 - type: mrr_at_10 value: 43.909 - type: mrr_at_100 value: 44.74 - type: mrr_at_1000 value: 44.786 - type: mrr_at_3 value: 41.659 - type: mrr_at_5 value: 43.010999999999996 - type: ndcg_at_1 value: 34.455999999999996 - type: ndcg_at_10 value: 44.266 - type: ndcg_at_100 value: 49.639 - type: ndcg_at_1000 value: 51.644 - type: ndcg_at_3 value: 39.865 - type: ndcg_at_5 value: 41.887 - type: precision_at_1 value: 34.455999999999996 - type: precision_at_10 value: 7.843999999999999 - type: precision_at_100 value: 1.243 - type: precision_at_1000 value: 0.158 - type: precision_at_3 value: 18.831999999999997 - type: precision_at_5 value: 13.147 - type: recall_at_1 value: 28.793000000000003 - type: recall_at_10 value: 55.68300000000001 - type: recall_at_100 value: 77.99000000000001 - type: recall_at_1000 value: 91.183 - type: recall_at_3 value: 43.293 - type: recall_at_5 value: 48.618 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackProgrammersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 25.907000000000004 - type:...