Datasets:
Euanyu
/
Task_models_BioNLP_results_GPT

Dataset card Data Studio Files Community
1
id
stringlengths
6
113
author
stringlengths
2
36
task_category
stringclasses
39 values
tags
sequencelengths
1
4.05k
created_time
int64
1,646B
1,742B
last_modified
timestamp[s]date
2020-05-14 13:13:12
2025-03-18 10:01:09
downloads
int64
0
118M
likes
int64
0
4.86k
README
stringlengths
30
1.01M
matched_task
sequencelengths
1
10
is_bionlp
stringclasses
3 values
benayad7/concat-e5-small-bge-small-01
benayad7
null
[ "mteb", "model-index", "region:us" ]
1,728,551,241,000
2024-10-14T09:37:01
0
0
--- tags: - mteb model-index: - name: no_model_name_available results: - task: type: Classification dataset: name: MTEB AmazonCounterfactualClassification (en-ext) type: mteb/amazon_counterfactual config: en-ext split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 75.58470764617691 - type: ap value: 24.719701151617723 - type: ap_weighted value: 24.719701151617723 - type: f1 value: 63.00164246074738 - type: f1_weighted value: 80.03796552199202 - type: main_score value: 75.58470764617691 - task: type: Classification dataset: name: MTEB AmazonCounterfactualClassification (en) type: mteb/amazon_counterfactual config: en split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 74.34328358208955 - type: ap value: 37.50929758783498 - type: ap_weighted value: 37.50929758783498 - type: f1 value: 68.47468266207234 - type: f1_weighted value: 76.71536156910686 - type: main_score value: 74.34328358208955 - task: type: Classification dataset: name: MTEB AmazonCounterfactualClassification (en-ext) type: mteb/amazon_counterfactual config: en-ext split: validation revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 73.10810810810811 - type: ap value: 21.095894998268182 - type: ap_weighted value: 21.095894998268182 - type: f1 value: 59.88562259265849 - type: f1_weighted value: 78.24218318628027 - type: main_score value: 73.10810810810811 - task: type: Classification dataset: name: MTEB AmazonCounterfactualClassification (en) type: mteb/amazon_counterfactual config: en split: validation revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 73.76119402985076 - type: ap value: 33.462242773250075 - type: ap_weighted value: 33.462242773250075 - type: f1 value: 66.50228790953409 - type: f1_weighted value: 76.66423272035549 - type: main_score value: 73.76119402985076 - task: type: Classification dataset: name: MTEB AmazonPolarityClassification (default) type: mteb/amazon_polarity config: default split: test revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy value: 92.99744999999999 - type: ap value: 89.7770669227447 - type: ap_weighted value: 89.7770669227447 - type: f1 value: 92.98870898689393 - type: f1_weighted value: 92.98870898689394 - type: main_score value: 92.99744999999999 - task: type: Classification dataset: name: MTEB AmazonReviewsClassification (en) type: mteb/amazon_reviews_multi config: en split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 49.364000000000004 - type: f1 value: 48.09686892529694 - type: f1_weighted value: 48.09686892529693 - type: main_score value: 49.364000000000004 - task: type: Classification dataset: name: MTEB AmazonReviewsClassification (en) type: mteb/amazon_reviews_multi config: en split: validation revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 48.797999999999995 - type: f1 value: 47.572308082658886 - type: f1_weighted value: 47.572308082658886 - type: main_score value: 48.797999999999995 - task: type: Retrieval dataset: name: MTEB ArguAna (default) type: mteb/arguana config: default split: test revision: c22ab2a51041ffd869aaddef7af8d8215647e41a metrics: - type: main_score value: 59.345000000000006 - type: map_at_1 value: 34.993 - type: map_at_10 value: 50.93299999999999 - type: map_at_100 value: 51.653999999999996 - type: map_at_1000 value: 51.659 - type: map_at_20 value: 51.503 - type: map_at_3 value: 46.539 - type: map_at_5 value: 49.078 - type: mrr_at_1 value: 35.34850640113798 - type: mrr_at_10 value: 51.08029081713292 - type: mrr_at_100 value: 51.79453395523629 - type: mrr_at_1000 value: 51.79922640990794 - type: mrr_at_20 value: 51.64015533841996 - type: mrr_at_3 value: 46.68089141773353 - type: mrr_at_5 value: 49.20578473210052 - type: nauc_map_at_1000_diff1 value: 10.777019519798255 - type: nauc_map_at_1000_max value: -7.407917463470924 - type: nauc_map_at_1000_std value: -7.563268405241759 - type: nauc_map_at_100_diff1 value: 10.779545140640199 - type: nauc_map_at_100_max value: -7.401298063310178 - type: nauc_map_at_100_std value: -7.556601235531485 - type: nauc_map_at_10_diff1 value: 10.721539302065686 - type: nauc_map_at_10_max value: -7.166136768327753 - type: nauc_map_at_10_std value: -7.293662115267615 - type: nauc_map_at_1_diff1 value: 14.156914156584854 - type: nauc_map_at_1_max value: -9.498793111705812 - type: nauc_map_at_1_std value: -9.726351399489474 - type: nauc_map_at_20_diff1 value: 10.761980363958246 - type: nauc_map_at_20_max value: -7.3011716552322445 - type: nauc_map_at_20_std value: -7.474633798851565 - type: nauc_map_at_3_diff1 value: 10.32402309373244 - type: nauc_map_at_3_max value: -7.789968158157112 - type: nauc_map_at_3_std value: -8.459911202243127 - type: nauc_map_at_5_diff1 value: 9.950359837131687 - type: nauc_map_at_5_max value: -7.54700058691015 - type: nauc_map_at_5_std value: -7.4852438758641515 - type: nauc_mrr_at_1000_diff1 value: 9.545661892556165 - type: nauc_mrr_at_1000_max value: -8.17995767306064 - type: nauc_mrr_at_1000_std value: -7.690544153747644 - type: nauc_mrr_at_100_diff1 value: 9.54837560401051 - type: nauc_mrr_at_100_max value: -8.173227861584765 - type: nauc_mrr_at_100_std value: -7.683867106566364 - type: nauc_mrr_at_10_diff1 value: 9.522795074409384 - type: nauc_mrr_at_10_max value: -7.9063165040486645 - type: nauc_mrr_at_10_std value: -7.431873185012491 - type: nauc_mrr_at_1_diff1 value: 13.130099478615803 - type: nauc_mrr_at_1_max value: -9.992669947319378 - type: nauc_mrr_at_1_std value: -10.051618087478493 - type: nauc_mrr_at_20_diff1 value: 9.541270804874118 - type: nauc_mrr_at_20_max value: -8.058828250931276 - type: nauc_mrr_at_20_std value: -7.598979599209439 - type: nauc_mrr_at_3_diff1 value: 9.116533214412966 - type: nauc_mrr_at_3_max value: -8.540266568222016 - type: nauc_mrr_at_3_std value: -8.693222832504544 - type: nauc_mrr_at_5_diff1 value: 8.694955232599785 - type: nauc_mrr_at_5_max value: -8.34107055995193 - type: nauc_mrr_at_5_std value: -7.6629161714950484 - type: nauc_ndcg_at_1000_diff1 value: 10.526533346595262 - type: nauc_ndcg_at_1000_max value: -6.703732662610731 - type: nauc_ndcg_at_1000_std value: -6.603623582089393 - type: nauc_ndcg_at_100_diff1 value: 10.561172146895252 - type: nauc_ndcg_at_100_max value: -6.514791218416639 - type: nauc_ndcg_at_100_std value: -6.354781956088969 - type: nauc_ndcg_at_10_diff1 value: 10.361381171866082 - type: nauc_ndcg_at_10_max value: -5.2230158943462985 - type: nauc_ndcg_at_10_std value: -5.007524284028199 - type: nauc_ndcg_at_1_diff1 value: 14.156914156584854 - type: nauc_ndcg_at_1_max value: -9.498793111705812 - type: nauc_ndcg_at_1_std value: -9.726351399489474 - type: nauc_ndcg_at_20_diff1 value: 10.517676064474847 - type: nauc_ndcg_at_20_max value: -5.711765067868173 - type: nauc_ndcg_at_20_std value: -5.605824861630572 - type: nauc_ndcg_at_3_diff1 value: 9.186600380601536 - type: nauc_ndcg_at_3_max value: -7.056576818596352 - type: nauc_ndcg_at_3_std value: -7.812761606548313 - type: nauc_ndcg_at_5_diff1 value: 8.432418101937406 - type: nauc_ndcg_at_5_max value: -6.480411547015269 - type: nauc_ndcg_at_5_std value: -5.777975379414998 - type: nauc_precision_at_1000_diff1 value: 13.955746514246906 - type: nauc_precision_at_1000_max value: 28.8840202640091 - type: nauc_precision_at_1000_std value: 65.36756825837523 - type: nauc_precision_at_100_diff1 value: 14.686199038527814 - type: nauc_precision_at_100_max value: 31.31632878025447 - type: nauc_precision_at_100_std value: 54.07113844512418 - type: nauc_precision_at_10_diff1 value: 9.662188427513989 - type: nauc_precision_at_10_max value: 9.22345326975617 - type: nauc_precision_at_10_std value: 11.831872077040245 - type: nauc_precision_at_1_diff1 value: 14.156914156584854 - type: nauc_precision_at_1_max value: -9.498793111705812 - type: nauc_precision_at_1_std value: -9.726351399489474 - type: nauc_precision_at_20_diff1 value: 11.432148213771988 - type: nauc_precision_at_20_max value: 18.514764981962074 - type: nauc_precision_at_20_std value: 22.78510644336147 - type: nauc_precision_at_3_diff1 value: 5.6317217760949685 - type: nauc_precision_at_3_max value: -4.676598241685319 - type: nauc_precision_at_3_std value: -5.684836764145716 - type: nauc_precision_at_5_diff1 value: 2.5659150784472753 - type: nauc_precision_at_5_max value: -2.1551693896958524 - type: nauc_precision_at_5_std value: 1.384881159297645 - type: nauc_recall_at_1000_diff1 value: 13.955746514247625 - type: nauc_recall_at_1000_max value: 28.884020264002835 - type: nauc_recall_at_1000_std value: 65.36756825836953 - type: nauc_recall_at_100_diff1 value: 14.686199038527365 - type: nauc_recall_at_100_max value: 31.31632878025263 - type: nauc_recall_at_100_std value: 54.071138445123225 - type: nauc_recall_at_10_diff1 value: 9.662188427513836 - type: nauc_recall_at_10_max value: 9.22345326975619 - type: nauc_recall_at_10_std value: 11.83187207704014 - type: nauc_recall_at_1_diff1 value: 14.156914156584854 - type: nauc_recall_at_1_max value: -9.498793111705812 - type: nauc_recall_at_1_std value: -9.726351399489474 - type: nauc_recall_at_20_diff1 value: 11.432148213772072 - type: nauc_recall_at_20_max value: 18.514764981961978 - type: nauc_recall_at_20_std value: 22.785106443361688 - type: nauc_recall_at_3_diff1 value: 5.63172177609501 - type: nauc_recall_at_3_max value: -4.676598241685221 - type: nauc_recall_at_3_std value: -5.684836764145642 - type: nauc_recall_at_5_diff1 value: 2.5659150784473406 - type: nauc_recall_at_5_max value: -2.1551693896959048 - type: nauc_recall_at_5_std value: 1.3848811592975896 - type: ndcg_at_1 value: 34.993 - type: ndcg_at_10 value: 59.345000000000006 - type: ndcg_at_100 value: 62.324999999999996 - type: ndcg_at_1000 value: 62.437 - type: ndcg_at_20 value: 61.36899999999999 - type: ndcg_at_3 value: 50.381 - type: ndcg_at_5 value: 54.923 - type: precision_at_1 value: 34.993 - type: precision_at_10 value: 8.599 - type: precision_at_100 value: 0.988 - type: precision_at_1000 value: 0.1 - type: precision_at_20 value: 4.694 - type: precision_at_3 value: 20.507 - type: precision_at_5 value: 14.495 - type: recall_at_1 value: 34.993 - type: recall_at_10 value: 85.989 - type: recall_at_100 value: 98.791 - type: recall_at_1000 value: 99.644 - type: recall_at_20 value: 93.88300000000001 - type: recall_at_3 value: 61.522 - type: recall_at_5 value: 72.475 - task: type: Clustering dataset: name: MTEB ArxivClusteringP2P (default) type: mteb/arxiv-clustering-p2p config: default split: test revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: main_score value: 47.552697319955676 - type: v_measure value: 47.552697319955676 - type: v_measure_std value: 13.808952106577216 - task: type: Clustering dataset: name: MTEB ArxivClusteringS2S (default) type: mteb/arxiv-clustering-s2s config: default split: test revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: main_score value: 40.03337707775063 - type: v_measure value: 40.03337707775063 - type: v_measure_std value: 14.249888078941146 - task: type: Reranking dataset: name: MTEB AskUbuntuDupQuestions (default) type: mteb/askubuntudupquestions-reranking config: default split: test revision: 2000358ca161889fa9c082cb41daa8dcfb161a54 metrics: - type: main_score value: 61.8126291529566 - type: map value: 61.8126291529566 - type: mrr value: 74.36705799586686 - type: nAUC_map_diff1 value: 8.967467836084921 - type: nAUC_map_max value: 26.579764001539115 - type: nAUC_map_std value: 17.40600362828969 - type: nAUC_mrr_diff1 value: 17.598155509582792 - type: nAUC_mrr_max value: 39.897111892695534 - type: nAUC_mrr_std value: 22.494399933018467 - task: type: STS dataset: name: MTEB BIOSSES (default) type: mteb/biosses-sts config: default split: test revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: cosine_pearson value: 86.08936662443202 - type: cosine_spearman value: 84.89832000798314 - type: euclidean_pearson value: 84.81392595158542 - type: euclidean_spearman value: 84.89832000798314 - type: main_score value: 84.89832000798314 - type: manhattan_pearson value: 85.13291943945366 - type: manhattan_spearman value: 85.16820567558344 - type: pearson value: 86.08936662443202 - type: spearman value: 84.89832000798314 - task: type: Classification dataset: name: MTEB Banking77Classification (default) type: mteb/banking77 config: default split: test revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy value: 82.18831168831169 - type: f1 value: 81.5323786025089 - type: f1_weighted value: 81.5323786025089 - type: main_score value: 82.18831168831169 - task: type: Clustering dataset: name: MTEB BiorxivClusteringP2P (default) type: mteb/biorxiv-clustering-p2p config: default split: test revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: main_score value: 38.67384534802573 - type: v_measure value: 38.67384534802573 - type: v_measure_std value: 0.7568897383721817 - task: type: Clustering dataset: name: MTEB BiorxivClusteringS2S (default) type: mteb/biorxiv-clustering-s2s config: default split: test revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: main_score value: 34.355519780975385 - type: v_measure value: 34.355519780975385 - type: v_measure_std value: 1.110838684148089 - task: type: Retrieval dataset: name: MTEB CQADupstackAndroidRetrieval (default) type: mteb/cqadupstack-android config: default split: test revision: f46a197baaae43b4f621051089b82a364682dfeb metrics: - type: main_score value: 49.34 - type: map_at_1 value: 31.978 - type: map_at_10 value: 42.963 - type: map_at_100 value: 44.446999999999996 - type: map_at_1000 value: 44.584 - type: map_at_20 value: 43.804 - type: map_at_3 value: 39.422000000000004 - type: map_at_5 value: 41.504000000000005 - type: mrr_at_1 value: 39.77110157367668 - type: mrr_at_10 value: 49.26595817153757 - type: mrr_at_100 value: 49.978002791230615 - type: mrr_at_1000 value: 50.02634861972985 - type: mrr_at_20 value: 49.71356312876928 - type: mrr_at_3 value: 46.49499284692418 - type: mrr_at_5 value: 48.22603719599428 - type: nauc_map_at_1000_diff1 value: 47.79618096338393 - type: nauc_map_at_1000_max value: 41.176156568022584 - type: nauc_map_at_1000_std value: -2.896933596181026 - type: nauc_map_at_100_diff1 value: 47.809435131565934 - type: nauc_map_at_100_max value: 41.16647280007524 - type: nauc_map_at_100_std value: -2.8831579711166193 - type: nauc_map_at_10_diff1 value: 48.10973144108661 - type: nauc_map_at_10_max value: 40.664863006508625 - type: nauc_map_at_10_std value: -3.578886025167837 - type: nauc_map_at_1_diff1 value: 51.708891898356256 - type: nauc_map_at_1_max value: 36.28682951162398 - type: nauc_map_at_1_std value: -7.4668723971868065 - type: nauc_map_at_20_diff1 value: 47.9555643209195 - type: nauc_map_at_20_max value: 40.916180069472304 - type: nauc_map_at_20_std value: -3.0932267113062433 - type: nauc_map_at_3_diff1 value: 48.98794466901641 - type: nauc_map_at_3_max value: 39.681057169237455 - type: nauc_map_at_3_std value: -5.066827772334784 - type: nauc_map_at_5_diff1 value: 48.646328680462275 - type: nauc_map_at_5_max value: 40.477824460870764 - type: nauc_map_at_5_std value: -4.491443351489804 - type: nauc_mrr_at_1000_diff1 value: 45.616911771663744 - type: nauc_mrr_at_1000_max value: 41.74404269617856 - type: nauc_mrr_at_1000_std value: -4.559184319493835 - type: nauc_mrr_at_100_diff1 value: 45.59611866833938 - type: nauc_mrr_at_100_max value: 41.72604055232334 - type: nauc_mrr_at_100_std value: -4.558345700839123 - type: nauc_mrr_at_10_diff1 value: 45.55894061838237 - type: nauc_mrr_at_10_max value: 41.77360038611892 - type: nauc_mrr_at_10_std value: -4.618036976051173 - type: nauc_mrr_at_1_diff1 value: 48.15582854302911 - type: nauc_mrr_at_1_max value: 39.82659893618731 - type: nauc_mrr_at_1_std value: -8.183852381071691 - type: nauc_mrr_at_20_diff1 value: 45.57723701387737 - type: nauc_mrr_at_20_max value: 41.6914875419549 - type: nauc_mrr_at_20_std value: -4.4669938868552865 - type: nauc_mrr_at_3_diff1 value: 46.254550893686755 - type: nauc_mrr_at_3_max value: 41.4719065274011 - type: nauc_mrr_at_3_std value: -5.655174401673945 - type: nauc_mrr_at_5_diff1 value: 46.042457649709675 - type: nauc_mrr_at_5_max value: 42.03643705756859 - type: nauc_mrr_at_5_std value: -4.958139821587032 - type: nauc_ndcg_at_1000_diff1 value: 45.81204094950804 - type: nauc_ndcg_at_1000_max value: 42.73689566776186 - type: nauc_ndcg_at_1000_std value: -0.7066382518858306 - type: nauc_ndcg_at_100_diff1 value: 45.28640379554905 - type: nauc_ndcg_at_100_max value: 42.681083144594815 - type: nauc_ndcg_at_100_std value: -0.09688585685774474 - type: nauc_ndcg_at_10_diff1 value: 45.71414379972128 - type: nauc_ndcg_at_10_max value: 41.53626843173395 - type: nauc_ndcg_at_10_std value: -1.8507612518474037 - type: nauc_ndcg_at_1_diff1 value: 48.15582854302911 - type: nauc_ndcg_at_1_max value: 39.82659893618731 - type: nauc_ndcg_at_1_std value: -8.183852381071691 - type: nauc_ndcg_at_20_diff1 value: 45.39833040860289 - type: nauc_ndcg_at_20_max value: 41.55849686342755 - type: nauc_ndcg_at_20_std value: -1.0215221134520232 - type: nauc_ndcg_at_3_diff1 value: 46.87312912585575 - type: nauc_ndcg_at_3_max value: 41.057497209218255 - type: nauc_ndcg_at_3_std value: -3.9052157576939535 - type: nauc_ndcg_at_5_diff1 value: 46.52903875914039 - type: nauc_ndcg_at_5_max value: 41.793701014010786 - type: nauc_ndcg_at_5_std value: -2.9870402822330866 - type: nauc_precision_at_1000_diff1 value: -19.737292446155067 - type: nauc_precision_at_1000_max value: -10.181883018676627 - type: nauc_precision_at_1000_std value: -3.068587468550703 - type: nauc_precision_at_100_diff1 value: -11.377068363169922 - type: nauc_precision_at_100_max value: 6.3871026306788705 - type: nauc_precision_at_100_std value: 8.872198838850938 - type: nauc_precision_at_10_diff1 value: 9.599810544198046 - type: nauc_precision_at_10_max value: 26.62316097540815 - type: nauc_precision_at_10_std value: 8.686741005293698 - type: nauc_precision_at_1_diff1 value: 48.15582854302911 - type: nauc_precision_at_1_max value: 39.82659893618731 - type: nauc_precision_at_1_std value: -8.183852381071691 - type: nauc_precision_at_20_diff1 value: 0.25496998553714123 - type: nauc_precision_at_20_max value: 18.471523812532052 - type: nauc_precision_at_20_std value: 10.351704374808387 - type: nauc_precision_at_3_diff1 value: 30.617775870803055 - type: nauc_precision_at_3_max value: 38.01125065426583 - type: nauc_precision_at_3_std value: -0.7623574434648546 - type: nauc_precision_at_5_diff1 value: 20.450147138491545 - type: nauc_precision_at_5_max value: 33.18114326263472 - type: nauc_precision_at_5_std value: 2.998578407482621 - type: nauc_recall_at_1000_diff1 value: 22.91280255517604 - type: nauc_recall_at_1000_max value: 64.0102572612793 - type: nauc_recall_at_1000_std value: 51.549096370979406 - type: nauc_recall_at_100_diff1 value: 28.635647358302503 - type: nauc_recall_at_100_max value: 44.00473186289832 - type: nauc_recall_at_100_std value: 19.912314783541138 - type: nauc_recall_at_10_diff1 value: 37.808472531928786 - type: nauc_recall_at_10_max value: 38.67030494361658 - type: nauc_recall_at_10_std value: 4.063425477456253 - type: nauc_recall_at_1_diff1 value: 51.708891898356256 - type: nauc_recall_at_1_max value: 36.28682951162398 - type: nauc_recall_at_1_std value: -7.4668723971868065 - type: nauc_recall_at_20_diff1 value: 34.51072533447235 - type: nauc_recall_at_20_max value: 37.73082104160229 - type: nauc_recall_at_20_std value: 8.219053762621884 - type: nauc_recall_at_3_diff1 value: 44.99432786987943 - type: nauc_recall_at_3_max value: 39.55995143135335 - type: nauc_recall_at_3_std value: -2.4914190692599165 - type: nauc_recall_at_5_diff1 value: 42.547651108851106 - type: nauc_recall_at_5_max value: 40.85551908930608 - type: nauc_recall_at_5_std value: 0.4962059846390094 - type: ndcg_at_1 value: 39.771 - type: ndcg_at_10 value: 49.34 - type: ndcg_at_100 value: 54.595000000000006 - type: ndcg_at_1000 value: 56.666000000000004 - type: ndcg_at_20 value: 51.492000000000004 - type: ndcg_at_3 value: 44.308 - type: ndcg_at_5 value: 46.838 - type: precision_at_1 value: 39.771 - type: precision_at_10 value: 9.442 - type: precision_at_100 value: 1.5010000000000001 - type: precision_at_1000 value: 0.2 - type: precision_at_20 value: 5.651 - type: precision_at_3 value: 21.125 - type: precision_at_5 value: 15.479000000000001 - type: recall_at_1 value: 31.978 - type: recall_at_10 value: 61.129 - type: recall_at_100 value: 83.052 - type: recall_at_1000 value: 96.378 - type: recall_at_20 value: 68.72500000000001 - type: recall_at_3 value: 46.518 - type: recall_at_5 value: 53.59 - task: type: Retrieval dataset: name: MTEB CQADupstackEnglishRetrieval (default) type: mteb/cqadupstack-english config: default split: test revision: ad9991cb51e31e31e430383c75ffb2885547b5f0 metrics: - type: main_score value: 45.286 - type: map_at_1 value: 30.169 - type: map_at_10 value: 39.711999999999996 - type: map_at_100 value: 40.898 - type: map_at_1000 value: 41.038999999999994 - type: map_at_20 value: 40.357 - type: map_at_3 value: 36.949 - type: map_at_5 value: 38.473 - type: mrr_at_1 value: 37.57961783439491 - type: mrr_at_10 value: 46.031847133757964 - type: mrr_at_100 value: 46.65912851493955 - type: mrr_at_1000 value: 46.707042666709604 - type: mrr_at_20 value: 46.40068681036863 - type: mrr_at_3 value: 43.7791932059448 - type: mrr_at_5 value: 45.10084925690022 - type: nauc_map_at_1000_diff1 value: 50.85056542222115 - type: nauc_map_at_1000_max value: 31.05651616405919 - type: nauc_map_at_1000_std value: -2.2368126065205987 - type: nauc_map_at_100_diff1 value: 50.89417988965435 - type: nauc_map_at_100_max value: 30.997137971767142 - type: nauc_map_at_100_std value: -2.3409324916593492 - type: nauc_map_at_10_diff1 value: 51.142437175292955 - type: nauc_map_at_10_max value: 30.227559741209287 - type: nauc_map_at_10_std value: -3.7930421273349264 - type: nauc_map_at_1_diff1 value: 55.941637622487214 - type: nauc_map_at_1_max value: 25.080533324385613 - type: nauc_map_at_1_std value: -8.864138917095795 - type: nauc_map_at_20_diff1 value: 50.96714330539312 - type: nauc_map_at_20_max value: 30.56073364246607 - type: nauc_map_at_20_std value: -3.1109111786530703 - type: nauc_map_at_3_diff1 value: 51.56324965582417 - type: nauc_map_at_3_max value: 28.83764240000901 - type: nauc_map_at_3_std value: -5.496574943583724 - type: nauc_map_at_5_diff1 value: 51.2643900871776 - type: nauc_map_at_5_max value: 29.42492887150313 - type: nauc_map_at_5_std value: -4.7906573624880675 - type: nauc_mrr_at_1000_diff1 value: 49.81188202883573 - type: nauc_mrr_at_1000_max value: 32.758906990991626 - type: nauc_mrr_at_1000_std value: 1.5051321484514517 - type: nauc_mrr_at_100_diff1 value: 49.808094282032876 - type: nauc_mrr_at_100_max value: 32.75870267430557 - type: nauc_mrr_at_100_std value: 1.5117004894545576 - type: nauc_mrr_at_10_diff1 value: 49.86964428608597 - type: nauc_mrr_at_10_max value: 32.75447791816241 - type: nauc_mrr_at_10_std value: 1.0472130007711005 - type: nauc_mrr_at_1_diff1 value: 54.63093984058127 - type: nauc_mrr_at_1_max value: 31.486608661031973 - type: nauc_mrr_at_1_std value: -1.3741363436543739 - type: nauc_mrr_at_20_diff1 value: 49.790685542152005 - type: nauc_mrr_at_20_max value: 32.75477912841072 - type: nauc_mrr_at_20_std value: 1.338641256922409 - type: nauc_mrr_at_3_diff1 value: 50.17281274015403 - type: nauc_mrr_at_3_max value: 32.55859057277966 - type: nauc_mrr_at_3_std value: 0.6635403402684905 - type: nauc_mrr_at_5_diff1 value: 49.99493486356793 - type: nauc_mrr_at_5_max value: 32.61428342888774 - type: nauc_mrr_at_5_std value: 0.7430591391457354 - type: nauc_ndcg_at_1000_diff1 value: 48.22576941926604 - type: nauc_ndcg_at_1000_max value: 32.93511771089829 - type: nauc_ndcg_at_1000_std value: 3.129856319572661 - type: nauc_ndcg_at_100_diff1 value: 48.62921110376326 - type: nauc_ndcg_at_100_max value: 32.991588269891764 - type: nauc_ndcg_at_100_std value: 3.0722970856766 - type: nauc_ndcg_at_10_diff1 value: 49.18605872592804 - type: nauc_ndcg_at_10_max value: 32.24106173386995 - type: nauc_ndcg_at_10_std value: -0.2906781273981978 - type: nauc_ndcg_at_1_diff1 value: 54.63093984058127 - type: nauc_ndcg_at_1_max value: 31.486608661031973 - type: nauc_ndcg_at_1_std value: -1.3741363436543739 - type: nauc_ndcg_at_20_diff1 value: 48.67444292759105 - type: nauc_ndcg_at_20_max value: 32.38356642801882 - type: nauc_ndcg_at_20_std value: 1.0417910616522417 - type: nauc_ndcg_at_3_diff1 value: 49.64405616341687 - type: nauc_ndcg_at_3_max value: 31.851912727510662 - type: nauc_ndcg_at_3_std value: -1.3378234982644532 - type: nauc_ndcg_at_5_diff1 value: 49.41698121410308 - type: nauc_ndcg_at_5_max value: 31.796598394828706 - type: nauc_ndcg_at_5_std value: -1.356552455719212 - type: nauc_precision_at_1000_diff1 value: -16.185681544062707 - type: nauc_precision_at_1000_max value: 15.06181269349989 - type: nauc_precision_at_1000_std value: 29.16661769411087 - type: nauc_precision_at_100_diff1 value: -4.50092289449142 - type: nauc_precision_at_100_max value: 26.889499343262663 - type: nauc_precision_at_100_std value: 34.61625224772955 - type: nauc_precision_at_10_diff1 value: 16.845250924167054 - type: nauc_precision_at_10_max value: 33.18165476286763 - type: nauc_precision_at_10_std value: 20.01633509478702 - type: nauc_precision_at_1_diff1 value: 54.63093984058127 - type: nauc_precision_at_1_max value: 31.486608661031973 - type: nauc_precision_at_1_std value: -1.3741363436543739 - type: nauc_precision_at_20_diff1 value: 7.904987701430007 - type: nauc_precision_at_20_max value: 31.66538848828912 - type: nauc_precision_at_20_std value: 27.373203146189333 - type: nauc_precision_at_3_diff1 value: 32.98074210677402 - type: nauc_precision_at_3_max value: 35.70551590699247 - type: nauc_precision_at_3_std value: 9.64957518804935 - type: nauc_precision_at_5_diff1 value: 25.68789006898062 - type: nauc_precision_at_5_max value: 34.528632431840606 - type: nauc_precision_at_5_std value: 13.758348844848392 - type: nauc_recall_at_1000_diff1 value: 27.292499993748585 - type: nauc_recall_at_1000_max value: 33.50856923877545 - type: nauc_recall_at_1000_std value: 32.219345025751586 - type: nauc_recall_at_100_diff1 value: 37.33505162034011 - type: nauc_recall_at_100_max value: 33.97748076845698 - type: nauc_recall_at_100_std value: 21.716723075947385 - type: nauc_recall_at_10_diff1 value: 42.67650896437499 - type: nauc_recall_at_10_max value: 30.930396085103517 - type: nauc_recall_at_10_std value: 2.5045964341943163 - type: nauc_recall_at_1_diff1 value: 55.941637622487214 - type: nauc_recall_at_1_max value: 25.080533324385613 - type: nauc_recall_at_1_std value: -8.864138917095795 - type: nauc_recall_at_20_diff1 value: 39.97433575808996 - type: nauc_recall_at_20_max value: 31.44609230387655 - type: nauc_recall_at_20_std value: 7.736221159385454 - type: nauc_recall_at_3_diff1 value: 46.21571868804605 - type: nauc_recall_at_3_max value: 28.893654020460204 - type: nauc_recall_at_3_std value: -3.6376291909998493 - type: nauc_recall_at_5_diff1 value: 44.64111423499069 - type: nauc_recall_at_5_max value: 29.065352256728865 - type: nauc_recall_at_5_std value: -2.0155177145574905 - type: ndcg_at_1 value: 37.580000000000005 - type: ndcg_at_10 value: 45.286 - type: ndcg_at_100 value: 49.518 - type: ndcg_at_1000 value: 51.778999999999996 - type: ndcg_at_20 value: 46.921 - type: ndcg_at_3 value: 41.237 - type: ndcg_at_5 value: 43.085 - type: precision_at_1 value: 37.580000000000005 - type: precision_at_10 value: 8.452 - type: precision_at_100 value: 1.358 - type: precision_at_1000 value: 0.186 - type: precision_at_20 value: 4.987 - type: precision_at_3 value: 19.66 - type: precision_at_5 value: 13.936000000000002 - type: recall_at_1 value: 30.169 - type: recall_at_10 value: 54.657999999999994 - type: recall_at_100 value: 72.631 - type: recall_at_1000 value: 86.99799999999999 - type: recall_at_20 value: 60.549 - type: recall_at_3 value: 42.703 - type: recall_at_5 value: 47.871 - task: type: Retrieval dataset: name: MTEB CQADupstackGamingRetrieval (default) type: mteb/cqadupstack-gaming config: default split: test revision: 4885aa143210c98657558c04aaf3dc47cfb54340 metrics: - type: main_score value: 57.935 - type: map_at_1 value: 39.459 - type: map_at_10 value: 52.041000000000004 - type: map_at_100 value: 53.123 - type: map_at_1000 value: 53.174 - type: map_at_20 value: 52.715999999999994 - type: map_at_3 value: 48.652 - type: map_at_5 value: 50.526 - type: mrr_at_1 value: 45.141065830721004 - type: mrr_at_10 value: 55.4189680051749 - type: mrr_at_100 value: 56.12734090607992 - type: mrr_at_1000 value: 56.15035665102205 - type: mrr_at_20 value: 55.870980474719914 - type: mrr_at_3 value: 52.92580982236154 - type: mrr_at_5 value: 54.380355276907 - type: nauc_map_at_1000_diff1 value: 49.350343037507805 - type: nauc_map_at_1000_max value: 39.98281162376331 - type: nauc_map_at_1000_std value: -3.6565717425989255 - type: nauc_map_at_100_diff1 value: 49.342545452256 - type: nauc_map_at_100_max value: 39.98916109913233 - type: nauc_map_at_100_std value: -3.643010722158061 - type: nauc_map_at_10_diff1 value: 49.45960781144599 - type: nauc_map_at_10_max value: 39.68189953288183 - type: nauc_map_at_10_std value: -4.405767261039445 - type: nauc_map_at_1_diff1 value: 52.089101330688045 - type: nauc_map_at_1_max value: 33.85881212484232 - type: nauc_map_at_1_std value: -8.418190685614235 - type: nauc_map_at_20_diff1 value: 49.32978868149478 - type: nauc_map_at_20_max value: 39.75645643846 - type: nauc_map_at_20_std value: -3.9860531109091193 - type: nauc_map_at_3_diff1 value: 50.04151871930599 - type: nauc_map_at_3_max value: 37.79961474082032 - type: nauc_map_at_3_std value: -6.670028333711345 - type: nauc_map_at_5_diff1 value: 49.71975459031514 - type: nauc_map_at_5_max value: 38.817567597269466 - type: nauc_map_at_5_std value: -5.434776325022176 - type: nauc_mrr_at_1000_diff1 value: 48.947499409111096 - type: nauc_mrr_at_1000_max value: 40.93741059921989 - type: nauc_mrr_at_1000_std value: -3.1825006442699553 - type: nauc_mrr_at_100_diff1 value: 48.942343488274815 - type: nauc_mrr_at_100_max value: 40.95031134407549 - type: nauc_mrr_at_100_std value: -3.160377489400296 - type: nauc_mrr_at_10_diff1 value: 48.840125595383455 - type: nauc_mrr_at_10_max value: 41.02170174858195 - type: nauc_mrr_at_10_std value: -3.197031134091893 - type: nauc_mrr_at_1_diff1 value: 52.064927865645075 - type: nauc_mrr_at_1_max value: 38.44984483881011 - type: nauc_mrr_at_1_std value: -6.416298888465512 - type: nauc_mrr_at_20_diff1 value: 48.906114080185866 - type: nauc_mrr_at_20_max value: 40.87883825337818 - type: nauc_mrr_at_20_std value: -3.255032101669121 - type: nauc_mrr_at_3_diff1 value: 49.32815249648534 - type: nauc_mrr_at_3_max value: 40.432904378326384 - type: nauc_mrr_at_3_std value: -4.370615209045244 - type: nauc_mrr_at_5_diff1 value: 48.83993033552693 - type: nauc_mrr_at_5_max value: 40.71824702891057 - type: nauc_mrr_at_5_std value: -3.655659400980567 - type: nauc_ndcg_at_1000_diff1 value: 48.474352967441945 - type: nauc_ndcg_at_1000_max value: 41.96481325646208 - type: nauc_ndcg_at_1000_std value: -0.6346960977825105 - type: nauc_ndcg_at_100_diff1 value: 48.3009196475395 - type: nauc_ndcg_at_100_max value: 42.349365306663664 - type: nauc_ndcg_at_100_std value: 0.16696421606061568 - type: nauc_ndcg_at_10_diff1 value: 48.22259923512447 - type: nauc_ndcg_at_10_max value: 41.81263561142292 - type: nauc_ndcg_at_10_std value: -1.6113767450068854 - type: nauc_ndcg_at_1_diff1 value: 52.064927865645075 - type: nauc_ndcg_at_1_max value: 38.44984483881011 - type: nauc_ndcg_at_1_std value: -6.416298888465512 - type: nauc_ndcg_at_20_diff1 value: 48.07530674920143 - type: nauc_ndcg_at_20_max value: 41.481398876880355 - type: nauc_ndcg_at_20_std value: -1.1959186932073145 - type: nauc_ndcg_at_3_diff1 value: 48.97047357315626 - type: nauc_ndcg_at_3_max value: 39.3764554710483 - type: nauc_ndcg_at_3_std value: -4.737405650853368 - type: nauc_ndcg_at_5_diff1 value: 48.465073616087444 - type: nauc_ndcg_at_5_max value: 40.48611129423828 - type: nauc_ndcg_at_5_std value: -3.2733514958040946 - type: nauc_precision_at_1000_diff1 value: -9.539304087056678 - type: nauc_precision_at_1000_max value: 15.041788011496934 - type: nauc_precision_at_1000_std value: 22.84867087898786 - type: nauc_precision_at_100_diff1 value: -5.179075253413082 - type: nauc_precision_at_100_max value: 22.968148583194907 - type: nauc_precision_at_100_std value: 28.16118112550293 - type: nauc_precision_at_10_diff1 value: 12.68864903314593 - type: nauc_precision_at_10_max value: 33.402306007402416 - type: nauc_precision_at_10_std value: 15.954788657247748 - type: nauc_precision_at_1_diff1 value: 52.064927865645075 - type: nauc_precision_at_1_max value: 38.44984483881011 - type: nauc_precision_at_1_std value: -6.416298888465512 - type: nauc_precision_at_20_diff1 value: 4.086070276980883 - type: nauc_precision_at_20_max value: 28.466186216262646 - type: nauc_precision_at_20_std value: 21.548953975789946 - type: nauc_precision_at_3_diff1 value: 31.827793894919836 - type: nauc_precision_at_3_max value: 38.13215690903121 - type: nauc_precision_at_3_std value: 2.3490498723729787 - type: nauc_precision_at_5_diff1 value: 23.36248316835303 - type: nauc_precision_at_5_max value: 36.6085689865106 - type: nauc_precision_at_5_std value: 8.730583249465882 - type: nauc_recall_at_1000_diff1 value: 35.58748183758336 - type: nauc_recall_at_1000_max value: 63.481971018253866 - type: nauc_recall_at_1000_std value: 50.255552349121324 - type: nauc_recall_at_100_diff1 value: 38.30162180279426 - type: nauc_recall_at_100_max value: 55.32704556841503 - type: nauc_recall_at_100_std value: 33.05803540444057 - type: nauc_recall_at_10_diff1 value: 42.88255606095961 - type: nauc_recall_at_10_max value: 45.08979716365479 - type: nauc_recall_at_10_std value: 6.080592095781171 - type: nauc_recall_at_1_diff1 value: 52.089101330688045 - type: nauc_recall_at_1_max value: 33.85881212484232 - type: nauc_recall_at_1_std value: -8.418190685614235 - type: nauc_recall_at_20_diff1 value: 40.717620176248104 - type: nauc_recall_at_20_max value: 43.889494702908635 - type: nauc_recall_at_20_std value: 9.674760090258394 - type: nauc_recall_at_3_diff1 value: 46.97768558746882 - type: nauc_recall_at_3_max value: 38.285091697616465 - type: nauc_recall_at_3_std value: -4.852209401420014 - type: nauc_recall_at_5_diff1 value: 44.54361378218751 - type: nauc_recall_at_5_max value: 40.49656738354392 - type: nauc_recall_at_5_std value: -0.39210246739263926 - type: ndcg_at_1 value: 45.141 - type: ndcg_at_10 value: 57.935 - type: ndcg_at_100 value: 62.121 - type: ndcg_at_1000 value: 63.086 - type: ndcg_at_20 value: 59.907999999999994 - type: ndcg_at_3 value: 52.358000000000004 - type: ndcg_at_5 value: 55.027 - type: precision_at_1 value: 45.141 - type: precision_at_10 value: 9.347999999999999 - type: precision_at_100 value: 1.232 - type: precision_at_1000 value: 0.136 - type: precision_at_20 value: 5.251 - type: precision_at_3 value: 23.344 - type: precision_at_5 value: 16.05 - type: recall_at_1 value: 39.459 - type: recall_at_10 value: 71.968 - type: recall_at_100 value: 89.81 - type: recall_at_1000 value: 96.55 - type: recall_at_20 value: 79.33099999999999 - type: recall_at_3 value: 57.099999999999994 - type: recall_at_5 value: 63.637 - task: type: Retrieval dataset: name: MTEB CQADupstackGisRetrieval (default) type: mteb/cqadupstack-gis config: default split: test revision: 5003b3064772da1887988e05400cf3806fe491f2 metrics: - type: main_score value: 39.839999999999996 - type: map_at_1 value: 26.821 - type: map_at_10 value: 34.993 - type: map_at_100 value: 36.009 - type: map_at_1000 value: 36.083 - type: map_at_20 value: 35.554 - type: map_at_3 value: 32.228 - type: map_at_5 value: 33.904 - type: mrr_at_1 value: 28.926553672316384 - type: mrr_at_10 value: 36.986368935521476 - type: mrr_at_100 value: 37.895698883680886 - type: mrr_at_1000 value: 37.95031449676498 - type: mrr_at_20 value: 37.48535917350526 - type: mrr_at_3 value: 34.293785310734464 - type: mrr_at_5 value: 35.983050847457626 - type: nauc_map_at_1000_diff1 value: 43.31690408477667 - type: nauc_map_at_1000_max value: 30.862014860762795 - type: nauc_map_at_1000_std value: -0.8551391908390162 - type: nauc_map_at_100_diff1 value: 43.312902470408524 - type: nauc_map_at_100_max value: 30.862986571062383 - type: nauc_map_at_100_std value: -0.8637722733314122 - type: nauc_map_at_10_diff1 value: 43.385672679389984 - type: nauc_map_at_10_max value: 30.714784436737087 - type: nauc_map_at_10_std value: -1.2522744939678505 - type: nauc_map_at_1_diff1 value: 47.86681025046955 - type: nauc_map_at_1_max value: 29.132194162422586 - type: nauc_map_at_1_std value: -5.002201483950293 - type: nauc_map_at_20_diff1 value: 43.37717003110337 - type: nauc_map_at_20_max value: 30.78438235738698 - type: nauc_map_at_20_std value: -0.8953950024164806 - type: nauc_map_at_3_diff1 value: 44.38299520601522 - type: nauc_map_at_3_max value: 29.83366218086086 - type: nauc_map_at_3_std value: -2.5693730585913297 - type: nauc_map_at_5_diff1 value: 43.51921405125155 - type: nauc_map_at_5_max value: 30.22504627106614 - type: nauc_map_at_5_std value: -1.5972020248683592 - type: nauc_mrr_at_1000_diff1 value: 42.49108453787739 - type: nauc_mrr_at_1000_max value: 31.972602761246655 - type: nauc_mrr_at_1000_std value: 1.0231286981944512 - type: nauc_mrr_at_100_diff1 value: 42.479172722773896 - type: nauc_mrr_at_100_max value: 31.987222969415342 - type: nauc_mrr_at_100_std value: 1.0274146182701183 - type: nauc_mrr_at_10_diff1 value: 42.526290626365196 - type: nauc_mrr_at_10_max value: 32.01830237899739 - type: nauc_mrr_at_10_std value: 0.9161077778836639 - type: nauc_mrr_at_1_diff1 value: 46.621348392565736 - type: nauc_mrr_at_1_max value: 31.470289340095604 - type: nauc_mrr_at_1_std value: -2.4591738933621867 - type: nauc_mrr_at_20_diff1 value: 42.534853876861575 - type: nauc_mrr_at_20_max value: 31.996618075721905 - type: nauc_mrr_at_20_std value: 1.1174044583485392 - type: nauc_mrr_at_3_diff1 value: 43.24815151493605 - type: nauc_mrr_at_3_max value: 31.282640177477422 - type: nauc_mrr_at_3_std value: -0.2891247404070639 - type: nauc_mrr_at_5_diff1 value: 42.730970720344594 - type: nauc_mrr_at_5_max value: 31.60546178005326 - type: nauc_mrr_at_5_std value: 0.5275202736677842 - type: nauc_ndcg_at_1000_diff1 value: 41.11037892060558 - type: nauc_ndcg_at_1000_max value: 31.981322365939096 - type: nauc_ndcg_at_1000_std value: 2.5104274168043115 - type: nauc_ndcg_at_100_diff1 value: 40.72420815298269 - type: nauc_ndcg_at_100_max value: 32.12478900255941 - type: nauc_ndcg_at_100_std value: 2.823745879247313 - type: nauc_ndcg_at_10_diff1 value: 41.248176699595774 - type: nauc_ndcg_at_10_max value: 31.76223462957885 - type: nauc_ndcg_at_10_std value: 1.325254903938574 - type: nauc_ndcg_at_1_diff1 value: 46.621348392565736 - type: nauc_ndcg_at_1_max value: 31.470289340095604 - type: nauc_ndcg_at_1_std value: -2.4591738933621867 - type: nauc_ndcg_at_20_diff1 value: 41.2264296695926 - type: nauc_ndcg_at_20_max value: 31.880018569087127 - type: nauc_ndcg_at_20_std value: 2.5771307591404953 - type: nauc_ndcg_at_3_diff1 value: 43.14220610066874 - type: nauc_ndcg_at_3_max value: 30.506711094581906 - type: nauc_ndcg_at_3_std value: -1.32756254984396 - type: nauc_ndcg_at_5_diff1 value: 41.766023996364815 - type: nauc_ndcg_at_5_max value: 30.89844409312977 - type: nauc_ndcg_at_5_std value: 0.3788803778583815 - type: nauc_precision_at_1000_diff1 value: -1.6666285719678695 - type: nauc_precision_at_1000_max value: 16.874851634956954 - type: nauc_precision_at_1000_std value: 13.467634314792958 - type: nauc_precision_at_100_diff1 value: 12.127904836990574 - type: nauc_precision_at_100_max value: 29.832469022456742 - type: nauc_precision_at_100_std value: 17.83171142960893 - type: nauc_precision_at_10_diff1 value: 28.629632098778924 - type: nauc_precision_at_10_max value: 36.382552111288504 - type: nauc_precision_at_10_std value: 10.527329328113375 - type: nauc_precision_at_1_diff1 value: 46.621348392565736 - type: nauc_precision_at_1_max value: 31.470289340095604 - type: nauc_precision_at_1_std value: -2.4591738933621867 - type: nauc_precision_at_20_diff1 value: 26.30904506190692 - type: nauc_precision_at_20_max value: 35.806707688621934 - type: nauc_precision_at_20_std value: 15.568878952628618 - type: nauc_precision_at_3_diff1 value: 37.18723505833023 - type: nauc_precision_at_3_max value: 33.61785834920449 - type: nauc_precision_at_3_std value: 2.9164041375719263 - type: nauc_precision_at_5_diff1 value: 32.815958974052634 - type: nauc_precision_at_5_max value: 34.22763811245109 - type: nauc_precision_at_5_std value: 6.903458965358602 - type: nauc_recall_at_1000_diff1 value: 19.113079964836775 - type: nauc_recall_at_1000_max value: 34.179678630291214 - type: nauc_recall_at_1000_std value: 32.767248399630766 - type: nauc_recall_at_100_diff1 value: 25.8811372897862 - type: nauc_recall_at_100_max value: 34.080364921744646 - type: nauc_recall_at_100_std value: 19.89467893613937 - type: nauc_recall_at_10_diff1 value: 33.89551559779046 - type: nauc_recall_at_10_max value: 32.010002950841205 - type: nauc_recall_at_10_std value: 6.940984864057547 - type: nauc_recall_at_1_diff1 value: 47.86681025046955 - type: nauc_recall_at_1_max value: 29.132194162422586 - type: nauc_recall_at_1_std value: -5.002201483950293 - type: nauc_recall_at_20_diff1 value: 33.23701340255753 - type: nauc_recall_at_20_max value: 32.4122108288123 - type: nauc_recall_at_20_std value: 12.716938752356722 - type: nauc_recall_at_3_diff1 value: 40.13928334370612 - type: nauc_recall_at_3_max value: 29.763781596658056 - type: nauc_recall_at_3_std value: 0.34341106017726875 - type: nauc_recall_at_5_diff1 value: 36.11418609771827 - type: nauc_recall_at_5_max value: 30.444939213226345 - type: nauc_recall_at_5_std value: 4.2497080620670244 - type: ndcg_at_1 value: 28.927000000000003 - type: ndcg_at_10 value: 39.839999999999996 - type: ndcg_at_100 value: 45.044000000000004 - type: ndcg_at_1000 value: 46.937 - type: ndcg_at_20 value: 41.821999999999996 - type: ndcg_at_3 value: 34.455000000000005 - type: ndcg_at_5 value: 37.37 - type: precision_at_1 value: 28.927000000000003 - type: precision_at_10 value: 6.045 - type: precision_at_100 value: 0.914 - type: precision_at_1000 value: 0.11199999999999999 - type: precision_at_20 value: 3.4799999999999995 - type: precision_at_3 value: 14.313 - type: precision_at_5 value: 10.26 - type: recall_at_1 value: 26.821 - type: recall_at_10 value: 52.917 - type: recall_at_100 value: 77.093 - type: recall_at_1000 value: 91.316 - type: recall_at_20 value: 60.56700000000001 - type: recall_at_3 value: 38.51 - type: recall_at_5 value: 45.536 - task: type: Retrieval dataset: name: MTEB CQADupstackMathematicaRetrieval (default) type: mteb/cqadupstack-mathematica config: default split: test revision: 90fceea13679c63fe563ded68f3b6f06e50061de metrics: - type: main_score value: 29.98 - type: map_at_1 value: 16.006999999999998 - type: map_at_10 value: 24.477 - type: map_at_100 value: 25.668000000000003 - type: map_at_1000 value: 25.788 - type: map_at_20 value: 25.048 - type: map_at_3 value: 21.656 - type: map_at_5 value: 23.34 - type: mrr_at_1 value: 20.024875621890548 - type: mrr_at_10 value: 29.197020848140255 - type: mrr_at_100 value: 30.11227723049729 - type: mrr_at_1000 value: 30.18189915906596 - type: mrr_at_20 value: 29.656175097568173 - type: mrr_at_3 value: 26.409618573797676 - type: mrr_at_5 value: 28.094941956882252 - type: nauc_map_at_1000_diff1 value: 29.373123176645237 - type: nauc_map_at_1000_max value: 21.445648024191712 - type: nauc_map_at_1000_std value: 4.405281916537104 - type: nauc_map_at_100_diff1 value: 29.35310092597499 - type: nauc_map_at_100_max value: 21.40489526072531 - type: nauc_map_at_100_std value: 4.380387058523312 - type: nauc_map_at_10_diff1 value: 29.141697351596253 - type: nauc_map_at_10_max value: 21.03434833947413 - type: nauc_map_at_10_std value: 4.144922514001805 - type: nauc_map_at_1_diff1 value: 38.13496031071367 - type: nauc_map_at_1_max value: 21.901814324794117 - type: nauc_map_at_1_std value: 0.4814120186616989 - type: nauc_map_at_20_diff1 value: 29.32299833637584 - type: nauc_map_at_20_max value: 21.306214454816754 - type: nauc_map_at_20_std value: 4.300356249155504 - type: nauc_map_at_3_diff1 value: 29.06177418598614 - type: nauc_map_at_3_max value: 20.811300750566513 - type: nauc_map_at_3_std value: 3.4414335533909166 - type: nauc_map_at_5_diff1 value: 29.338077175083153 - type: nauc_map_at_5_max value: 20.905802602838854 - type: nauc_map_at_5_std value: 3.718624565651613 - type: nauc_mrr_at_1000_diff1 value: 30.008651430755055 - type: nauc_mrr_at_1000_max value: 22.107612668457936 - type: nauc_mrr_at_1000_std value: 2.722385123849279 - type: nauc_mrr_at_100_diff1 value: 29.99004753126145 - type: nauc_mrr_at_100_max value: 22.094848691097166 - type: nauc_mrr_at_100_std value: 2.732788863788039 - type: nauc_mrr_at_10_diff1 value: 29.88442282413889 - type: nauc_mrr_at_10_max value: 22.02646483854745 - type: nauc_mrr_at_10_std value: 2.6648957296233644 - type: nauc_mrr_at_1_diff1 value: 37.967956104647755 - type: nauc_mrr_at_1_max value: 21.44460113476502 - type: nauc_mrr_at_1_std value: -1.7530679840582375 - type: nauc_mrr_at_20_diff1 value: 29.927851260160853 - type: nauc_mrr_at_20_max value: 22.01880502582662 - type: nauc_mrr_at_20_std value: 2.708224642328409 - type: nauc_mrr_at_3_diff1 value: 30.266105364910807 - type: nauc_mrr_at_3_max value: 21.89072561010228 - type: nauc_mrr_at_3_std value: 2.1435490321496875 - type: nauc_mrr_at_5_diff1 value: 30.15575881656933 - type: nauc_mrr_at_5_max value: 22.16515882306906 - type: nauc_mrr_at_5_std value: 2.577739748796098 - type: nauc_ndcg_at_1000_diff1 value: 27.90510789867005 - type: nauc_ndcg_at_1000_max value: 22.530968354985028 - type: nauc_ndcg_at_1000_std value: 6.781805354595171 - type: nauc_ndcg_at_100_diff1 value: 27.380292435540532 - type: nauc_ndcg_at_100_max value: 21.809545194883373 - type: nauc_ndcg_at_100_std value: 6.466454400897538 - type: nauc_ndcg_at_10_diff1 value: 26.787786754146648 - type: nauc_ndcg_at_10_max value: 21.1259284562756 - type: nauc_ndcg_at_10_std value: 5.5137140693199065 - type: nauc_ndcg_at_1_diff1 value: 37.967956104647755 - type: nauc_ndcg_at_1_max value: 21.44460113476502 - type: nauc_ndcg_at_1_std value: -1.7530679840582375 - type: nauc_ndcg_at_20_diff1 value: 27.263083511878065 - type: nauc_ndcg_at_20_max value: 21.679228236914504 - type: nauc_ndcg_at_20_std value: 6.089674507905745 - type: nauc_ndcg_at_3_diff1 value: 27.146357683499524 - type: nauc_ndcg_at_3_max value: 21.104681584239923 - type: nauc_ndcg_at_3_std value: 3.7675309462600217 - type: nauc_ndcg_at_5_diff1 value: 27.331511358161997 - type: nauc_ndcg_at_5_max value: 21.18337870362178 - type: nauc_ndcg_at_5_std value: 4.57529049323361 - type: nauc_precision_at_1000_diff1 value: 3.239653820602742 - type: nauc_precision_at_1000_max value: 7.26961590562058 - type: nauc_precision_at_1000_std value: 2.2025825300071125 - type: nauc_precision_at_100_diff1 value: 10.44430363394719 - type: nauc_precision_at_100_max value: 14.264783558128372 - type: nauc_precision_at_100_std value: 7.062602811028171 - type: nauc_precision_at_10_diff1 value: 18.25356714400902 - type: nauc_precision_at_10_max value: 19.640874340636955 - type: nauc_precision_at_10_std value: 7.720476038645774 - type: nauc_precision_at_1_diff1 value: 37.967956104647755 - type: nauc_precision_at_1_max value: 21.44460113476502 - type: nauc_precision_at_1_std value: -1.7530679840582375 - type: nauc_precision_at_20_diff1 value: 18.054556815828192 - type: nauc_precision_at_20_max value: 20.132496075135354 - type: nauc_precision_at_20_std value: 8.992246975170467 - type: nauc_precision_at_3_diff1 value: 20.99569005515048 - type: nauc_precision_at_3_max value: 20.986073606132656 - type: nauc_precision_at_3_std value: 4.447517886269654 - type: nauc_precision_at_5_diff1 value: 20.501261498730983 - type: nauc_precision_at_5_max value: 20.506697758500973 - type: nauc_precision_at_5_std value: 6.836691174582398 - type: nauc_recall_at_1000_diff1 value: 17.117021891023526 - type: nauc_recall_at_1000_max value: 28.098336442218425 - type: nauc_recall_at_1000_std value: 32.03347662796732 - type: nauc_recall_at_100_diff1 value: 17.981711126081034 - type: nauc_recall_at_100_max value: 18.60340216104814 - type: nauc_recall_at_100_std value: 14.313017781949211 - type: nauc_recall_at_10_diff1 value: 18.464197753039507 - type: nauc_recall_at_10_max value: 18.474261038624018 - type: nauc_recall_at_10_std value: 9.090322373993915 - type: nauc_recall_at_1_diff1 value: 38.13496031071367 - type: nauc_recall_at_1_max value: 21.901814324794117 - type: nauc_recall_at_1_std value: 0.4814120186616989 - type: nauc_recall_at_20_diff1 value: 19.45317881386327 - type: nauc_recall_at_20_max value: 19.791890415922335 - type: nauc_recall_at_20_std value: 11.195653035396559 - type: nauc_recall_at_3_diff1 value: 19.58052222735834 - type: nauc_recall_at_3_max value: 18.390514209031757 - type: nauc_recall_at_3_std value: 6.285979231354349 - type: nauc_recall_at_5_diff1 value: 19.957569014017217 - type: nauc_recall_at_5_max value: 18.605256807993243 - type: nauc_recall_at_5_std value: 6.7220712737663755 - type: ndcg_at_1 value: 20.025000000000002 - type: ndcg_at_10 value: 29.98 - type: ndcg_at_100 value: 35.69 - type: ndcg_at_1000 value: 38.568000000000005 - type: ndcg_at_20 value: 31.820999999999998 - type: ndcg_at_3 value: 24.891 - type: ndcg_at_5 value: 27.46 - type: precision_at_1 value: 20.025000000000002 - type: precision_at_10 value: 5.759 - type: precision_at_100 value: 0.984 - type: precision_at_1000 value: 0.136 - type: precision_at_20 value: 3.3640000000000003 - type: precision_at_3 value: 12.106 - type: precision_at_5 value: 9.179 - type: recall_at_1 value: 16.006999999999998 - type: recall_at_10 value: 42.081 - type: recall_at_100 value: 67.305 - type: recall_at_1000 value: 87.957 - type: recall_at_20 value: 48.704 - type: recall_at_3 value: 28.354000000000003 - type: recall_at_5 value: 34.605000000000004 - task: type: Retrieval dataset: name: MTEB CQADupstackPhysicsRetrieval (default) type: mteb/cqadupstack-physics config: default split: test revision: 79531abbd1fb92d06c6d6315a0cbbbf5bb247ea4 metrics: - type: main_score value: 45.073 - type: map_at_1 value: 28.136 - type: map_at_10 value: 38.868 - type: map_at_100 value: 40.108 - type: map_at_1000 value: 40.221000000000004 - type: map_at_20 value: 39.564 - type: map_at_3 value: 35.449000000000005 - type: map_at_5 value: 37.385000000000005 - type: mrr_at_1 value: 34.93743984600577 - type: mrr_at_10 value: 44.622385688314466 - type: mrr_at_100 value: 45.34143739001397 - type: mrr_at_1000 value: 45.39414063155817 - type: mrr_at_20 value: 45.00770434975747 - type: mrr_at_3 value: 41.88322104587745 - type: mrr_at_5 value: 43.50016041065127 - type: nauc_map_at_1000_diff1 value: 52.26823337938297 - type: nauc_map_at_1000_max value: 37.37245329468808 - type: nauc_map_at_1000_std value: 4.72166664574236 - type: nauc_map_at_100_diff1 value: 52.24616463751152 - type: nauc_map_at_100_max value: 37.33426712740629 - type: nauc_map_at_100_std value: 4.681771946538098 - type: nauc_map_at_10_diff1 value: 52.161361569838085 - type: nauc_map_at_10_max value: 36.73617207301781 - type: nauc_map_at_10_std value: 3.8276263103624397 - type: nauc_map_at_1_diff1 value: 58.609107153987026 - type: nauc_map_at_1_max value: 35.02757021351409 - type: nauc_map_at_1_std value: -0.6936621804258922 - type: nauc_map_at_20_diff1 value: 52.20038315316372 - type: nauc_map_at_20_max value: 37.24718279507634 - type: nauc_map_at_20_std value: 4.433483954204022 - type: nauc_map_at_3_diff1 value: 52.98890960683455 - type: nauc_map_at_3_max value: 36.627227662545636 - type: nauc_map_at_3_std value: 2.1473003055776303 - type: nauc_map_at_5_diff1 value: 52.138722935493796 - type: nauc_map_at_5_max value: 36.57267129483463 - type: nauc_map_at_5_std value: 2.9487505674940846 - type: nauc_mrr_at_1000_diff1 value: 52.727499174808976 - type: nauc_mrr_at_1000_max value: 39.660587784745125 - type: nauc_mrr_at_1000_std value: 7.215620440931916 - type: nauc_mrr_at_100_diff1 value: 52.71227861389539 - type: nauc_mrr_at_100_max value: 39.65944541613258 - type: nauc_mrr_at_100_std value: 7.232920570021006 - type: nauc_mrr_at_10_diff1 value: 52.605293878188306 - type: nauc_mrr_at_10_max value: 39.39789652621602 - type: nauc_mrr_at_10_std value: 6.994445305721646 - type: nauc_mrr_at_1_diff1 value: 58.87987158821745 - type: nauc_mrr_at_1_max value: 39.883000294981386 - type: nauc_mrr_at_1_std value: 4.525740385718022 - type: nauc_mrr_at_20_diff1 value: 52.709991373902476 - type: nauc_mrr_at_20_max value: 39.63900552236034 - type: nauc_mrr_at_20_std value: 7.180374629477749 - type: nauc_mrr_at_3_diff1 value: 52.87253562158551 - type: nauc_mrr_at_3_max value: 39.8526236943088 - type: nauc_mrr_at_3_std value: 6.312802069469314 - type: nauc_mrr_at_5_diff1 value: 52.4218392724399 - type: nauc_mrr_at_5_max value: 39.31643340619565 - type: nauc_mrr_at_5_std value: 6.497151104380261 - type: nauc_ndcg_at_1000_diff1 value: 50.896715084702 - type: nauc_ndcg_at_1000_max value: 39.03137903719933 - type: nauc_ndcg_at_1000_std value: 9.120093464579284 - type: nauc_ndcg_at_100_diff1 value: 50.57128970408371 - type: nauc_ndcg_at_100_max value: 38.57734282233673 - type: nauc_ndcg_at_100_std value: 8.948100860484162 - type: nauc_ndcg_at_10_diff1 value: 50.10362861621041 - type: nauc_ndcg_at_10_max value: 36.81788741482043 - type: nauc_ndcg_at_10_std value: 6.248168006196132 - type: nauc_ndcg_at_1_diff1 value: 58.87987158821745 - type: nauc_ndcg_at_1_max value: 39.883000294981386 - type: nauc_ndcg_at_1_std value: 4.525740385718022 - type: nauc_ndcg_at_20_diff1 value: 50.226356261645435 - type: nauc_ndcg_at_20_max value: 38.11050217929487 - type: nauc_ndcg_at_20_std value: 7.486965774997671 - type: nauc_ndcg_at_3_diff1 value: 51.11099202906786 - type: nauc_ndcg_at_3_max value: 37.9283909559886 - type: nauc_ndcg_at_3_std value: 4.702254100554942 - type: nauc_ndcg_at_5_diff1 value: 50.09568890455949 - type: nauc_ndcg_at_5_max value: 36.9698296373855 - type: nauc_ndcg_at_5_std value: 5.188587998085958 - type: nauc_precision_at_1000_diff1 value: -5.397384708148253 - type: nauc_precision_at_1000_max value: 7.658538116479907 - type: nauc_precision_at_1000_std value: 19.419371334393016 - type: nauc_precision_at_100_diff1 value: 4.13777630264156 - type: nauc_precision_at_100_max value: 18.076564064280507 - type: nauc_precision_at_100_std value: 24.333555979164466 - type: nauc_precision_at_10_diff1 value: 20.55388046991252 - type: nauc_precision_at_10_max value: 29.41800073419997 - type: nauc_precision_at_10_std value: 18.580366767122076 - type: nauc_precision_at_1_diff1 value: 58.87987158821745 - type: nauc_precision_at_1_max value: 39.883000294981386 - type: nauc_precision_at_1_std value: 4.525740385718022 - type: nauc_precision_at_20_diff1 value: 14.242304182638074 - type: nauc_precision_at_20_max value: 28.10797068496045 - type: nauc_precision_at_20_std value: 21.90112335945266 - type: nauc_precision_at_3_diff1 value: 37.46947895260127 - type: nauc_precision_at_3_max value: 38.006705277755955 - type: nauc_precision_at_3_std value: 12.158729151102953 - type: nauc_precision_at_5_diff1 value: 28.328393033049203 - type: nauc_precision_at_5_max value: 33.15639175834532 - type: nauc_precision_at_5_std value: 14.406771010005597 - type: nauc_recall_at_1000_diff1 value: 34.31859222623266 - type: nauc_recall_at_1000_max value: 45.13722035429492 - type: nauc_recall_at_1000_std value: 53.791310222471886 - type: nauc_recall_at_100_diff1 value: 38.78662480990974 - type: nauc_recall_at_100_max value: 36.173587813938305 - type: nauc_recall_at_100_std value: 26.619442060940923 - type: nauc_recall_at_10_diff1 value: 40.329036336117454 - type: nauc_recall_at_10_max value: 30.912126881840678 - type: nauc_recall_at_10_std value: 9.814880445182029 - type: nauc_recall_at_1_diff1 value: 58.609107153987026 - type: nauc_recall_at_1_max value: 35.02757021351409 - type: nauc_recall_at_1_std value: -0.6936621804258922 - type: nauc_recall_at_20_diff1 value: 40.18277885997754 - type: nauc_recall_at_20_max value: 34.8149234226211 - type: nauc_recall_at_20_std value: 14.12527070299619 - type: nauc_recall_at_3_diff1 value: 45.40990517015726 - type: nauc_recall_at_3_max value: 34.69882134310449 - type: nauc_recall_at_3_std value: 3.732266451734092 - type: nauc_recall_at_5_diff1 value: 41.766916839112206 - type: nauc_recall_at_5_max value: 32.129792239721716 - type: nauc_recall_at_5_std value: 5.6211961779763415 - type: ndcg_at_1 value: 34.937000000000005 - type: ndcg_at_10 value: 45.073 - type: ndcg_at_100 value: 50.182 - type: ndcg_at_1000 value: 52.276 - type: ndcg_at_20 value: 47.010000000000005 - type: ndcg_at_3 value: 39.612 - type: ndcg_at_5 value: 42.266999999999996 - type: precision_at_1 value: 34.937000000000005 - type: precision_at_10 value: 8.286999999999999 - type: precision_at_100 value: 1.268 - type: precision_at_1000 value: 0.163 - type: precision_at_20 value: 4.832 - type: precision_at_3 value: 18.704 - type: precision_at_5 value: 13.474 - type: recall_at_1 value: 28.136 - type: recall_at_10 value: 57.791000000000004 - type: recall_at_100 value: 79.521 - type: recall_at_1000 value: 93.176 - type: recall_at_20 value: 64.48700000000001 - type: recall_at_3 value: 42.427 - type: recall_at_5 value: 49.39 - task: type: Retrieval dataset: name: MTEB CQADupstackProgrammersRetrieval (default) type: mteb/cqadupstack-programmers config: default split: test revision: 6184bc1440d2dbc7612be22b50686b8826d22b32 metrics: - type: main_score value: 40.65 - type: map_at_1 value: 24.381 - type: map_at_10 value: 34.522000000000006 - type: map_at_100 value: 35.823 - type: map_at_1000 value: 35.939 - type: map_at_20 value: 35.153 - type: map_at_3 value: 31.079 - type: map_at_5 value: 33.167 - type: mrr_at_1 value: 30.47945205479452 - type: mrr_at_10 value: 40.03556026672465 - type: mrr_at_100 value: 40.859486284310805 - type: mrr_at_1000 value: 40.91385465888402 - type: mrr_at_20 value: 40.44289694965349 - type: mrr_at_3 value: 37.29071537290716 - type: mrr_at_5 value: 38.86605783866057 - type: nauc_map_at_1000_diff1 value: 45.08645907290653 - type: nauc_map_at_1000_max value: 37.93984277049077 - type: nauc_map_at_1000_std value: 4.348018171635654 - type: nauc_map_at_100_diff1 value: 45.103728679899895 - type: nauc_map_at_100_max value: 37.99535887007234 - type: nauc_map_at_100_std value: 4.357619716783864 - type: nauc_map_at_10_diff1 value: 45.00658982142447 - type: nauc_map_at_10_max value: 37.31815420707169 - type: nauc_map_at_10_std value: 3.3382278188396106 - type: nauc_map_at_1_diff1 value: 52.252891830215134 - type: nauc_map_at_1_max value: 32.77061213394142 - type: nauc_map_at_1_std value: -2.8010640035289143 - type: nauc_map_at_20_diff1 value: 45.091235458676685 - type: nauc_map_at_20_max value: 37.61754711974 - type: nauc_map_at_20_std value: 3.980483359486563 - type: nauc_map_at_3_diff1 value: 45.96759132853502 - type: nauc_map_at_3_max value: 35.70107657784562 - type: nauc_map_at_3_std value: 0.5893514980003082 - type: nauc_map_at_5_diff1 value: 44.76256760745472 - type: nauc_map_at_5_max value: 36.837428148742184 - type: nauc_map_at_5_std value: 2.739539166736263 - type: nauc_mrr_at_1000_diff1 value: 42.92232217227843 - type: nauc_mrr_at_1000_max value: 40.17925571552386 - type: nauc_mrr_at_1000_std value: 8.148960526298065 - type: nauc_mrr_at_100_diff1 value: 42.91455614925039 - type: nauc_mrr_at_100_max value: 40.20045379839933 - type: nauc_mrr_at_100_std value: 8.18118615824958 - type: nauc_mrr_at_10_diff1 value: 42.813559222481004 - type: nauc_mrr_at_10_max value: 40.22809168556719 - type: nauc_mrr_at_10_std value: 7.862450240887059 - type: nauc_mrr_at_1_diff1 value: 49.85954283512805 - type: nauc_mrr_at_1_max value: 39.100124047592615 - type: nauc_mrr_at_1_std value: 4.308285447853536 - type: nauc_mrr_at_20_diff1 value: 42.916739579172855 - type: nauc_mrr_at_20_max value: 40.18884672645215 - type: nauc_mrr_at_20_std value: 8.070953502233257 - type: nauc_mrr_at_3_diff1 value: 43.33588918249767 - type: nauc_mrr_at_3_max value: 40.02185259938533 - type: nauc_mrr_at_3_std value: 6.611771804932232 - type: nauc_mrr_at_5_diff1 value: 42.31798087627212 - type: nauc_mrr_at_5_max value: 39.95836322628087 - type: nauc_mrr_at_5_std value: 7.8252604777639565 - type: nauc_ndcg_at_1000_diff1 value: 42.58508571989192 - type: nauc_ndcg_at_1000_max value: 39.911165427637954 - type: nauc_ndcg_at_1000_std value: 9.035223072322985 - type: nauc_ndcg_at_100_diff1 value: 42.85331157305972 - type: nauc_ndcg_at_100_max value: 40.901343091681056 - type: nauc_ndcg_at_100_std value: 10.085512946952077 - type: nauc_ndcg_at_10_diff1 value: 42.40611041378945 - type: nauc_ndcg_at_10_max value: 39.0395878685548 - type: nauc_ndcg_at_10_std value: 6.603225480063732 - type: nauc_ndcg_at_1_diff1 value: 49.85954283512805 - type: nauc_ndcg_at_1_max value: 39.100124047592615 - type: nauc_ndcg_at_1_std value: 4.308285447853536 - type: nauc_ndcg_at_20_diff1 value: 42.77709403486501 - type: nauc_ndcg_at_20_max value: 39.45047866326879 - type: nauc_ndcg_at_20_std value: 8.324410425742744 - type: nauc_ndcg_at_3_diff1 value: 43.358589542818706 - type: nauc_ndcg_at_3_max value: 37.91671645220353 - type: nauc_ndcg_at_3_std value: 3.548176766967823 - type: nauc_ndcg_at_5_diff1 value: 41.56594514959379 - type: nauc_ndcg_at_5_max value: 38.42086968355651 - type: nauc_ndcg_at_5_std value: 6.066217005485217 - type: nauc_precision_at_1000_diff1 value: -4.792438397619244 - type: nauc_precision_at_1000_max value: 2.7129923853733118 - type: nauc_precision_at_1000_std value: 11.67095620060032 - type: nauc_precision_at_100_diff1 value: 4.188981090197261 - type: nauc_precision_at_100_max value: 24.721360175955237 - type: nauc_precision_at_100_std value: 25.081372551205 - type: nauc_precision_at_10_diff1 value: 18.811203609613973 - type: nauc_precision_at_10_max value: 38.14203413304164 - type: nauc_precision_at_10_std value: 21.933474701361284 - type: nauc_precision_at_1_diff1 value: 49.85954283512805 - type: nauc_precision_at_1_max value: 39.100124047592615 - type: nauc_precision_at_1_std value: 4.308285447853536 - type: nauc_precision_at_20_diff1 value: 14.825255525788132 - type: nauc_precision_at_20_max value: 33.96942297730217 - type: nauc_precision_at_20_std value: 24.843048642950983 - type: nauc_precision_at_3_diff1 value: 31.399689348786293 - type: nauc_precision_at_3_max value: 42.36936733454805 - type: nauc_precision_at_3_std value: 13.606543019531983 - type: nauc_precision_at_5_diff1 value: 22.95129561216099 - type: nauc_precision_at_5_max value: 40.15375346390098 - type: nauc_precision_at_5_std value: 19.844337655067264 - type: nauc_recall_at_1000_diff1 value: 18.250357722466067 - type: nauc_recall_at_1000_max value: 46.49889896497268 - type: nauc_recall_at_1000_std value: 49.015133298216114 - type: nauc_recall_at_100_diff1 value: 34.14073541913647 - type: nauc_recall_at_100_max value: 47.880871182499654 - type: nauc_recall_at_100_std value: 33.394450460167654 - type: nauc_recall_at_10_diff1 value: 34.10055202985094 - type: nauc_recall_at_10_max value: 37.29000268460915 - type: nauc_recall_at_10_std value: 10.719966977592444 - type: nauc_recall_at_1_diff1 value: 52.252891830215134 - type: nauc_recall_at_1_max value: 32.77061213394142 - type: nauc_recall_at_1_std value: -2.8010640035289143 - type: nauc_recall_at_20_diff1 value: 34.77711534255729 - type: nauc_recall_at_20_max value: 37.8830564545796 - type: nauc_recall_at_20_std value: 17.204302583685262 - type: nauc_recall_at_3_diff1 value: 37.38919386647721 - type: nauc_recall_at_3_max value: 34.570111627131695 - type: nauc_recall_at_3_std value: 2.2380100020283096 - type: nauc_recall_at_5_diff1 value: 32.187904365676324 - type: nauc_recall_at_5_max value: 35.77757062335063 - type: nauc_recall_at_5_std value: 8.796247583408153 - type: ndcg_at_1 value: 30.479 - type: ndcg_at_10 value: 40.65 - type: ndcg_at_100 value: 46.366 - type: ndcg_at_1000 value: 48.689 - type: ndcg_at_20 value: 42.576 - type: ndcg_at_3 value: 35.116 - type: ndcg_at_5 value: 37.909 - type: precision_at_1 value: 30.479 - type: precision_at_10 value: 7.603 - type: precision_at_100 value: 1.226 - type: precision_at_1000 value: 0.16 - type: precision_at_20 value: 4.458 - type: precision_at_3 value: 17.122999999999998 - type: precision_at_5 value: 12.58 - type: recall_at_1 value: 24.381 - type: recall_at_10 value: 53.591 - type: recall_at_100 value: 78.31 - type: recall_at_1000 value: 93.952 - type: recall_at_20 value: 60.465999999999994 - type: recall_at_3 value: 38.189 - type: recall_at_5 value: 45.425 - task: type: Retrieval dataset: name: MTEB CQADupstackRetrieval (default) type: CQADupstackRetrieval_is_a_combined_dataset config: default split: test revision: CQADupstackRetrieval_is_a_combined_dataset metrics: - type: main_score value: 40.268750000000004 - type: ndcg_at_10 value: 40.268750000000004 - task: type: Retrieval dataset: name: MTEB CQADupstackStatsRetrieval (default) type: mteb/cqadupstack-stats config: default split: test revision: 65ac3a16b8e91f9cee4c9828cc7c335575432a2a metrics: - type: main_score value: 34.89 - type: map_at_1 value: 24.343 - type: map_at_10 value: 31.064999999999998 - type: map_at_100 value: 32.013000000000005 - type: map_at_1000 value: 32.11 - type: map_at_20 value: 31.584 - type: map_at_3 value: 29.287999999999997 - type: map_at_5 value: 30.262 - type: mrr_at_1 value: 27.453987730061353 - type: mrr_at_10 value: 33.89503603077223 - type: mrr_at_100 value: 34.76452500547403 - type: mrr_at_1000 value: 34.831641998976096 - type: mrr_at_20 value: 34.39433378717007 - type: mrr_at_3 value: 32.20858895705521 - type: mrr_at_5 value: 33.09049079754601 - type: nauc_map_at_1000_diff1 value: 52.16433709147209 - type: nauc_map_at_1000_max value: 41.895031426126124 - type: nauc_map_at_1000_std value: 7.981597857750285 - type: nauc_map_at_100_diff1 value: 52.151218712376554 - type: nauc_map_at_100_max value: 41.845879262079926 - type: nauc_map_at_100_std value: 7.961900934081761 - type: nauc_map_at_10_diff1 value: 52.402838490484406 - type: nauc_map_at_10_max value: 41.77705031749437 - type: nauc_map_at_10_std value: 7.46409351133074 - type: nauc_map_at_1_diff1 value: 58.5759193069631 - type: nauc_map_at_1_max value: 40.228075475738066 - type: nauc_map_at_1_std value: -0.331391740789906 - type: nauc_map_at_20_diff1 value: 52.24118427663996 - type: nauc_map_at_20_max value: 41.717633721989124 - type: nauc_map_at_20_std value: 7.713122213513287 - type: nauc_map_at_3_diff1 value: 53.00130785485122 - type: nauc_map_at_3_max value: 41.257807025801554 - type: nauc_map_at_3_std value: 5.77564250625532 - type: nauc_map_at_5_diff1 value: 52.765771056206034 - type: nauc_map_at_5_max value: 41.17385278218844 - type: nauc_map_at_5_std value: 6.267751055469911 - type: nauc_mrr_at_1000_diff1 value: 50.542579627409346 - type: nauc_mrr_at_1000_max value: 43.84384933961597 - type: nauc_mrr_at_1000_std value: 8.9290783799145 - type: nauc_mrr_at_100_diff1 value: 50.52367459214615 - type: nauc_mrr_at_100_max value: 43.83317399067154 - type: nauc_mrr_at_100_std value: 8.93848179915739 - type: nauc_mrr_at_10_diff1 value: 50.592180069200076 - type: nauc_mrr_at_10_max value: 43.86512615662472 - type: nauc_mrr_at_10_std value: 8.648594684024122 - type: nauc_mrr_at_1_diff1 value: 56.64925132242809 - type: nauc_mrr_at_1_max value: 44.302509524664245 - type: nauc_mrr_at_1_std value: 2.8736722205582566 - type: nauc_mrr_at_20_diff1 value: 50.621524856832025 - type: nauc_mrr_at_20_max value: 43.85010163029952 - type: nauc_mrr_at_20_std value: 8.767065605432117 - type: nauc_mrr_at_3_diff1 value: 51.38022486401255 - type: nauc_mrr_at_3_max value: 43.690091517144886 - type: nauc_mrr_at_3_std value: 7.583000007208131 - type: nauc_mrr_at_5_diff1 value: 51.026555577484345 - type: nauc_mrr_at_5_max value: 43.40937882095473 - type: nauc_mrr_at_5_std value: 7.870192951985875 - type: nauc_ndcg_at_1000_diff1 value: 48.946807624632214 - type: nauc_ndcg_at_1000_max value: 43.63846016728263 - type: nauc_ndcg_at_1000_std value: 13.07112902361304 - type: nauc_ndcg_at_100_diff1 value: 48.46009023670086 - type: nauc_ndcg_at_100_max value: 42.84578351440459 - type: nauc_ndcg_at_100_std value: 13.048673429979113 - type: nauc_ndcg_at_10_diff1 value: 49.80098562249132 - type: nauc_ndcg_at_10_max value: 42.46231067480857 - type: nauc_ndcg_at_10_std value: 10.5896193945906 - type: nauc_ndcg_at_1_diff1 value: 56.64925132242809 - type: nauc_ndcg_at_1_max value: 44.302509524664245 - type: nauc_ndcg_at_1_std value: 2.8736722205582566 - type: nauc_ndcg_at_20_diff1 value: 49.32237998567543 - type: nauc_ndcg_at_20_max value: 42.23892720118917 - type: nauc_ndcg_at_20_std value: 11.311668576433599 - type: nauc_ndcg_at_3_diff1 value: 51.01125725288161 - type: nauc_ndcg_at_3_max value: 42.12827055031322 - type: nauc_ndcg_at_3_std value: 7.952435809082195 - type: nauc_ndcg_at_5_diff1 value: 50.88410133484621 - type: nauc_ndcg_at_5_max value: 41.565359240466975 - type: nauc_ndcg_at_5_std value: 8.314306379070254 - type: nauc_precision_at_1000_diff1 value: 4.413508451597973 - type: nauc_precision_at_1000_max value: 33.762398288256094 - type: nauc_precision_at_1000_std value: 25.98231326304456 - type: nauc_precision_at_100_diff1 value: 17.203842054243655 - type: nauc_precision_at_100_max value: 41.105989573268204 - type: nauc_precision_at_100_std value: 31.631978351351798 - type: nauc_precision_at_10_diff1 value: 34.696132889148664 - type: nauc_precision_at_10_max value: 45.80034445639316 - type: nauc_precision_at_10_std value: 25.084569022460418 - type: nauc_precision_at_1_diff1 value: 56.64925132242809 - type: nauc_precision_at_1_max value: 44.302509524664245 - type: nauc_precision_at_1_std value: 2.8736722205582566 - type: nauc_precision_at_20_diff1 value: 29.865679363368436 - type: nauc_precision_at_20_max value: 43.51573363065152 - type: nauc_precision_at_20_std value: 26.69033832110468 - type: nauc_precision_at_3_diff1 value: 41.389196232922316 - type: nauc_precision_at_3_max value: 46.28755529729629 - type: nauc_precision_at_3_std value: 16.909849769292716 - type: nauc_precision_at_5_diff1 value: 39.087938584206306 - type: nauc_precision_at_5_max value: 43.92003534457625 - type: nauc_precision_at_5_std value: 18.560228476365946 - type: nauc_recall_at_1000_diff1 value: 26.669464596984678 - type: nauc_recall_at_1000_max value: 46.54456322772547 - type: nauc_recall_at_1000_std value: 44.24504504678441 - type: nauc_recall_at_100_diff1 value: 31.188372051167907 - type: nauc_recall_at_100_max value: 39.33606079794924 - type: nauc_recall_at_100_std value: 31.351107197440655 - type: nauc_recall_at_10_diff1 value: 42.00542257322957 - type: nauc_recall_at_10_max value: 40.557783865813306 - type: nauc_recall_at_10_std value: 17.578789968761935 - type: nauc_recall_at_1_diff1 value: 58.5759193069631 - type: nauc_recall_at_1_max value: 40.228075475738066 - type: nauc_recall_at_1_std value: -0.331391740789906 - type: nauc_recall_at_20_diff1 value: 39.65715933448972 - type: nauc_recall_at_20_max value: 38.93829722046506 - type: nauc_recall_at_20_std value: 20.20996021737043 - type: nauc_recall_at_3_diff1 value: 46.87588712984084 - type: nauc_recall_at_3_max value: 39.797140704347825 - type: nauc_recall_at_3_std value: 10.153636337649985 - type: nauc_recall_at_5_diff1 value: 46.08928170734386 - type: nauc_recall_at_5_max value: 39.01544586906766 - type: nauc_recall_at_5_std value: 11.453087165740614 - type: ndcg_at_1 value: 27.454 - type: ndcg_at_10 value: 34.89 - type: ndcg_at_100 value: 39.612 - type: ndcg_at_1000 value: 42.045 - type: ndcg_at_20 value: 36.738 - type: ndcg_at_3 value: 31.630000000000003 - type: ndcg_at_5 value: 33.056000000000004 - type: precision_at_1 value: 27.454 - type: precision_at_10 value: 5.383 - type: precision_at_100 value: 0.8330000000000001 - type: precision_at_1000 value: 0.11199999999999999 - type: precision_at_20 value: 3.152 - type: precision_at_3 value: 13.65 - type: precision_at_5 value: 9.232999999999999 - type: recall_at_1 value: 24.343 - type: recall_at_10 value: 43.836999999999996 - type: recall_at_100 value: 65.202 - type: recall_at_1000 value: 83.206 - type: recall_at_20 value: 50.829 - type: recall_at_3 value: 34.695 - type: recall_at_5 value: 38.33 - task: type: Retrieval dataset: name: MTEB CQADupstackTexRetrieval (default) type: mteb/cqadupstack-tex config: default split: test revision: 46989137a86843e03a6195de44b09deda022eec7 metrics: - type: main_score value: 28.595 - type: map_at_1 value: 17.134 - type: map_at_10 value: 24.104 - type: map_at_100 value: 25.238 - type: map_at_1000 value: 25.368000000000002 - type: map_at_20 value: 24.691 - type: map_at_3 value: 21.803 - type: map_at_5 value: 23.066 - type: mrr_at_1 value: 20.750172057811426 - type: mrr_at_10 value: 27.87088017129311 - type: mrr_at_100 value: 28.81791033306077 - type: mrr_at_1000 value: 28.899375497257516 - type: mrr_at_20 value: 28.378447148229803 - type: mrr_at_3 value: 25.699701766460198 - type: mrr_at_5 value: 26.892062399632945 - type: nauc_map_at_1000_diff1 value: 36.89782887137058 - type: nauc_map_at_1000_max value: 33.08016929719372 - type: nauc_map_at_1000_std value: 3.3099635444764735 - type: nauc_map_at_100_diff1 value: 36.8780819112453 - type: nauc_map_at_100_max value: 33.050931677418774 - type: nauc_map_at_100_std value: 3.2972109847369 - type: nauc_map_at_10_diff1 value: 37.08595684018923 - type: nauc_map_at_10_max value: 32.816323824163476 - type: nauc_map_at_10_std value: 2.552386021070936 - type: nauc_map_at_1_diff1 value: 43.51132829968084 - type: nauc_map_at_1_max value: 32.3415757101499 - type: nauc_map_at_1_std value: 1.1401002178840585 - type: nauc_map_at_20_diff1 value: 36.94143359488415 - type: nauc_map_at_20_max value: 32.982623511734424 - type: nauc_map_at_20_std value: 2.948810693672891 - type: nauc_map_at_3_diff1 value: 38.71612128344212 - type: nauc_map_at_3_max value: 32.637048522654034 - type: nauc_map_at_3_std value: 1.156009064619756 - type: nauc_map_at_5_diff1 value: 37.78942760585617 - type: nauc_map_at_5_max value: 32.75604432178518 - type: nauc_map_at_5_std value: 2.0173303861590925 - type: nauc_mrr_at_1000_diff1 value: 36.135612852709095 - type: nauc_mrr_at_1000_max value: 34.12476601616417 - type: nauc_mrr_at_1000_std value: 3.845954153422737 - type: nauc_mrr_at_100_diff1 value: 36.12068139187418 - type: nauc_mrr_at_100_max value: 34.119358854394214 - type: nauc_mrr_at_100_std value: 3.849886746617628 - type: nauc_mrr_at_10_diff1 value: 36.21596271906166 - type: nauc_mrr_at_10_max value: 34.0449176526415 - type: nauc_mrr_at_10_std value: 3.392757560646604 - type: nauc_mrr_at_1_diff1 value: 42.4688892662091 - type: nauc_mrr_at_1_max value: 34.61638632573713 - type: nauc_mrr_at_1_std value: 1.842575033698782 - type: nauc_mrr_at_20_diff1 value: 36.100856934569805 - type: nauc_mrr_at_20_max value: 34.09556229697657 - type: nauc_mrr_at_20_std value: 3.6620323814000684 - type: nauc_mrr_at_3_diff1 value: 37.47429125012118 - type: nauc_mrr_at_3_max value: 34.16045576255616 - type: nauc_mrr_at_3_std value: 2.2755120232411903 - type: nauc_mrr_at_5_diff1 value: 36.65972061354651 - type: nauc_mrr_at_5_max value: 33.96708531025307 - type: nauc_mrr_at_5_std value: 2.8464790894241885 - type: nauc_ndcg_at_1000_diff1 value: 33.78518836462285 - type: nauc_ndcg_at_1000_max value: 33.63185976032734 - type: nauc_ndcg_at_1000_std value: 6.989447169026228 - type: nauc_ndcg_at_100_diff1 value: 33.39381937519511 - type: nauc_ndcg_at_100_max value: 33.27132063948536 - type: nauc_ndcg_at_100_std value: 6.813560048322648 - type: nauc_ndcg_at_10_diff1 value: 34.231562121939554 - type: nauc_ndcg_at_10_max value: 32.957787193957664 - type: nauc_ndcg_at_10_std value: 3.9141441526477867 - type: nauc_ndcg_at_1_diff1 value: 42.4688892662091 - type: nauc_ndcg_at_1_max value: 34.61638632573713 - type: nauc_ndcg_at_1_std value: 1.842575033698782 - type: nauc_ndcg_at_20_diff1 value: 33.73777473522033 - type: nauc_ndcg_at_20_max value: 33.210514059183375 - type: nauc_ndcg_at_20_std value: 5.073301185091096 - type: nauc_ndcg_at_3_diff1 value: 36.878575344351624 - type: nauc_ndcg_at_3_max value: 33.32312056613959 - type: nauc_ndcg_at_3_std value: 1.4148329239930337 - type: nauc_ndcg_at_5_diff1 value: 35.53121227641059 - type: nauc_ndcg_at_5_max value: 32.97583732206957 - type: nauc_ndcg_at_5_std value: 2.7296938204105046 - type: nauc_precision_at_1000_diff1 value: 5.048094785844507 - type: nauc_precision_at_1000_max value: 20.72305226491182 - type: nauc_precision_at_1000_std value: 13.166659843282705 - type: nauc_precision_at_100_diff1 value: 11.403111213178537 - type: nauc_precision_at_100_max value: 25.876626218425784 - type: nauc_precision_at_100_std value: 15.750263914866009 - type: nauc_precision_at_10_diff1 value: 21.812128842605574 - type: nauc_precision_at_10_max value: 32.36024330484034 - type: nauc_precision_at_10_std value: 8.30153625256048 - type: nauc_precision_at_1_diff1 value: 42.4688892662091 - type: nauc_precision_at_1_max value: 34.61638632573713 - type: nauc_precision_at_1_std value: 1.842575033698782 - type: nauc_precision_at_20_diff1 value: 18.126781090521444 - type: nauc_precision_at_20_max value: 30.879595883417306 - type: nauc_precision_at_20_std value: 10.9632189477538 - type: nauc_precision_at_3_diff1 value: 30.857088332242842 - type: nauc_precision_at_3_max value: 34.435211511210596 - type: nauc_precision_at_3_std value: 2.1743174606141897 - type: nauc_precision_at_5_diff1 value: 26.70684474302077 - type: nauc_precision_at_5_max value: 33.881041843033714 - type: nauc_precision_at_5_std value: 4.964700828623661 - type: nauc_recall_at_1000_diff1 value: 15.179090310075448 - type: nauc_recall_at_1000_max value: 31.177239498655414 - type: nauc_recall_at_1000_std value: 32.817986166465225 - type: nauc_recall_at_100_diff1 value: 19.791440992074865 - type: nauc_recall_at_100_max value: 29.00647998704242 - type: nauc_recall_at_100_std value: 19.00290442690933 - type: nauc_recall_at_10_diff1 value: 25.400689588358937 - type: nauc_recall_at_10_max value: 29.67225586682777 - type: nauc_recall_at_10_std value: 6.326653531699302 - type: nauc_recall_at_1_diff1 value: 43.51132829968084 - type: nauc_recall_at_1_max value: 32.3415757101499 - type: nauc_recall_at_1_std value: 1.1401002178840585 - type: nauc_recall_at_20_diff1 value: 23.158667708575777 - type: nauc_recall_at_20_max value: 29.65979097031932 - type: nauc_recall_at_20_std value: 10.004891834963093 - type: nauc_recall_at_3_diff1 value: 32.631467317064406 - type: nauc_recall_at_3_max value: 30.531285335243492 - type: nauc_recall_at_3_std value: 0.9187457345239257 - type: nauc_recall_at_5_diff1 value: 29.18624452088816 - type: nauc_recall_at_5_max value: 29.708509257799818 - type: nauc_recall_at_5_std value: 3.6369154905030765 - type: ndcg_at_1 value: 20.75 - type: ndcg_at_10 value: 28.595 - type: ndcg_at_100 value: 34.047 - type: ndcg_at_1000 value: 37.039 - type: ndcg_at_20 value: 30.526999999999997 - type: ndcg_at_3 value: 24.46 - type: ndcg_at_5 value: 26.339000000000002 - type: precision_at_1 value: 20.75 - type: precision_at_10 value: 5.231 - type: precision_at_100 value: 0.9400000000000001 - type: precision_at_1000 value: 0.13699999999999998 - type: precision_at_20 value: 3.1919999999999997 - type: precision_at_3 value: 11.482000000000001 - type: precision_at_5 value: 8.369 - type: recall_at_1 value: 17.134 - type: recall_at_10 value: 38.316 - type: recall_at_100 value: 62.913 - type: recall_at_1000 value: 84.233 - type: recall_at_20 value: 45.465 - type: recall_at_3 value: 26.840000000000003 - type: recall_at_5 value: 31.616 - task: type: Retrieval dataset: name: MTEB CQADupstackUnixRetrieval (default) type: mteb/cqadupstack-unix config: default split: test revision: 6c6430d3a6d36f8d2a829195bc5dc94d7e063e53 metrics: - type: main_score value: 39.89 - type: map_at_1 value: 25.712000000000003 - type: map_at_10 value: 34.615 - type: map_at_100 value: 35.846000000000004 - type: map_at_1000 value: 35.953 - type: map_at_20 value: 35.321999999999996 - type: map_at_3 value: 32.056000000000004 - type: map_at_5 value: 33.315 - type: mrr_at_1 value: 29.850746268656714 - type: mrr_at_10 value: 38.71860933428097 - type: mrr_at_100 value: 39.61660285528755 - type: mrr_at_1000 value: 39.676734545015016 - type: mrr_at_20 value: 39.20100616633673 - type: mrr_at_3 value: 36.53606965174129 - type: mrr_at_5 value: 37.604166666666664 - type: nauc_map_at_1000_diff1 value: 44.53604492112556 - type: nauc_map_at_1000_max value: 39.23951280655509 - type: nauc_map_at_1000_std value: -0.5395031277467611 - type: nauc_map_at_100_diff1 value: 44.51770266447437 - type: nauc_map_at_100_max value: 39.24922673974566 - type: nauc_map_at_100_std value: -0.5418148801230667 - type: nauc_map_at_10_diff1 value: 44.65794786125487 - type: nauc_map_at_10_max value: 38.73649462647244 - type: nauc_map_at_10_std value: -1.2439485316781116 - type: nauc_map_at_1_diff1 value: 51.3015448718258 - type: nauc_map_at_1_max value: 37.68162132042243 - type: nauc_map_at_1_std value: -4.942523398750195 - type: nauc_map_at_20_diff1 value: 44.56752919145453 - type: nauc_map_at_20_max value: 39.15671461993185 - type: nauc_map_at_20_std value: -0.69839546492355 - type: nauc_map_at_3_diff1 value: 45.85932349411764 - type: nauc_map_at_3_max value: 38.36052842023208 - type: nauc_map_at_3_std value: -2.2972931157260588 - type: nauc_map_at_5_diff1 value: 45.05340840012778 - type: nauc_map_at_5_max value: 38.498629564114125 - type: nauc_map_at_5_std value: -1.5490287999131676 - type: nauc_mrr_at_1000_diff1 value: 43.86315579499585 - type: nauc_mrr_at_1000_max value: 41.22972681259589 - type: nauc_mrr_at_1000_std value: 0.2312354368485346 - type: nauc_mrr_at_100_diff1 value: 43.82688559618802 - type: nauc_mrr_at_100_max value: 41.228924353114486 - type: nauc_mrr_at_100_std value: 0.23800385006789107 - type: nauc_mrr_at_10_diff1 value: 43.83189862351878 - type: nauc_mrr_at_10_max value: 41.10756388047098 - type: nauc_mrr_at_10_std value: -0.21685246034735925 - type: nauc_mrr_at_1_diff1 value: 51.230432406020476 - type: nauc_mrr_at_1_max value: 41.48741446620127 - type: nauc_mrr_at_1_std value: -2.7496538177528658 - type: nauc_mrr_at_20_diff1 value: 43.83356230557604 - type: nauc_mrr_at_20_max value: 41.22449434055463 - type: nauc_mrr_at_20_std value: 0.1017557136662017 - type: nauc_mrr_at_3_diff1 value: 44.642204252525374 - type: nauc_mrr_at_3_max value: 41.394135395117 - type: nauc_mrr_at_3_std value: -0.3102479679512395 - type: nauc_mrr_at_5_diff1 value: 44.03177178118225 - type: nauc_mrr_at_5_max value: 41.14617895311199 - type: nauc_mrr_at_5_std value: -0.15778767756702847 - type: nauc_ndcg_at_1000_diff1 value: 41.931781429588355 - type: nauc_ndcg_at_1000_max value: 40.19130298587713 - type: nauc_ndcg_at_1000_std value: 2.4213241669516314 - type: nauc_ndcg_at_100_diff1 value: 41.47736552910553 - type: nauc_ndcg_at_100_max value: 40.35512795681438 - type: nauc_ndcg_at_100_std value: 2.797704103101513 - type: nauc_ndcg_at_10_diff1 value: 41.89774080166355 - type: nauc_ndcg_at_10_max value: 39.068973811839285 - type: nauc_ndcg_at_10_std value: 0.1409703112345929 - type: nauc_ndcg_at_1_diff1 value: 51.230432406020476 - type: nauc_ndcg_at_1_max value: 41.48741446620127 - type: nauc_ndcg_at_1_std value: -2.7496538177528658 - type: nauc_ndcg_at_20_diff1 value: 41.654873436264864 - type: nauc_ndcg_at_20_max value: 40.02385895251709 - type: nauc_ndcg_at_20_std value: 1.6616675841903024 - type: nauc_ndcg_at_3_diff1 value: 43.677208022052135 - type: nauc_ndcg_at_3_max value: 39.355842345181706 - type: nauc_ndcg_at_3_std value: -0.9994914032687997 - type: nauc_ndcg_at_5_diff1 value: 42.63394828100176 - type: nauc_ndcg_at_5_max value: 38.78287388555721 - type: nauc_ndcg_at_5_std value: -0.40383353126040594 - type: nauc_precision_at_1000_diff1 value: -12.720363964831158 - type: nauc_precision_at_1000_max value: 1.780615695736265 - type: nauc_precision_at_1000_std value: 6.9259933939590015 - type: nauc_precision_at_100_diff1 value: 1.5494816839626728 - type: nauc_precision_at_100_max value: 21.16486694935512 - type: nauc_precision_at_100_std value: 13.63358160875128 - type: nauc_precision_at_10_diff1 value: 21.022460223564163 - type: nauc_precision_at_10_max value: 33.517939417026845 - type: nauc_precision_at_10_std value: 6.777527986277892 - type: nauc_precision_at_1_diff1 value: 51.230432406020476 - type: nauc_precision_at_1_max value: 41.48741446620127 - type: nauc_precision_at_1_std value: -2.7496538177528658 - type: nauc_precision_at_20_diff1 value: 14.686385148466163 - type: nauc_precision_at_20_max value: 31.18430505462782 - type: nauc_precision_at_20_std value: 12.077548081645366 - type: nauc_precision_at_3_diff1 value: 33.70051545579217 - type: nauc_precision_at_3_max value: 39.60907345133216 - type: nauc_precision_at_3_std value: 4.2539653363781476 - type: nauc_precision_at_5_diff1 value: 27.941480760698635 - type: nauc_precision_at_5_max value: 37.31639952677206 - type: nauc_precision_at_5_std value: 6.219978856190591 - type: nauc_recall_at_1000_diff1 value: 20.47974719909093 - type: nauc_recall_at_1000_max value: 40.904077508578574 - type: nauc_recall_at_1000_std value: 36.68929060623499 - type: nauc_recall_at_100_diff1 value: 26.82928665193226 - type: nauc_recall_at_100_max value: 39.0725275666681 - type: nauc_recall_at_100_std value: 18.856939694213875 - type: nauc_recall_at_10_diff1 value: 32.48097141976132 - type: nauc_recall_at_10_max value: 34.921002737123445 - type: nauc_recall_at_10_std value: 2.8847239359758596 - type: nauc_recall_at_1_diff1 value: 51.3015448718258 - type: nauc_recall_at_1_max value: 37.68162132042243 - type: nauc_recall_at_1_std value: -4.942523398750195 - type: nauc_recall_at_20_diff1 value: 31.155212544928517 - type: nauc_recall_at_20_max value: 37.903451497060075 - type: nauc_recall_at_20_std value: 8.052860930292049 - type: nauc_recall_at_3_diff1 value: 38.338624569740745 - type: nauc_recall_at_3_max value: 36.16696793299773 - type: nauc_recall_at_3_std value: -0.5499014670399716 - type: nauc_recall_at_5_diff1 value: 35.47491917247829 - type: nauc_recall_at_5_max value: 34.98125952824827 - type: nauc_recall_at_5_std value: 1.18095697584272 - type: ndcg_at_1 value: 29.851 - type: ndcg_at_10 value: 39.89 - type: ndcg_at_100 value: 45.327 - type: ndcg_at_1000 value: 47.772999999999996 - type: ndcg_at_20 value: 42.022999999999996 - type: ndcg_at_3 value: 35.284 - type: ndcg_at_5 value: 37.062 - type: precision_at_1 value: 29.851 - type: precision_at_10 value: 6.707000000000001 - type: precision_at_100 value: 1.054 - type: precision_at_1000 value: 0.13699999999999998 - type: precision_at_20 value: 3.9690000000000003 - type: precision_at_3 value: 16.107 - type: precision_at_5 value: 10.97 - type: recall_at_1 value: 25.712000000000003 - type: recall_at_10 value: 51.754 - type: recall_at_100 value: 75.229 - type: recall_at_1000 value: 92.352 - type: recall_at_20 value: 59.224 - type: recall_at_3 value: 38.942 - type: recall_at_5 value: 43.608000000000004 - task: type: Retrieval dataset: name: MTEB CQADupstackWebmastersRetrieval (default) type: mteb/cqadupstack-webmasters config: default split: test revision: 160c094312a0e1facb97e55eeddb698c0abe3571 metrics: - type: main_score value: 39.275 - type: map_at_1 value: 25.207 - type: map_at_10 value: 33.73 - type: map_at_100 value: 35.314 - type: map_at_1000 value: 35.539 - type: map_at_20 value: 34.485 - type: map_at_3 value: 30.751 - type: map_at_5 value: 32.458 - type: mrr_at_1 value: 30.237154150197625 - type: mrr_at_10 value: 38.160330008156095 - type: mrr_at_100 value: 39.19604519073853 - type: mrr_at_1000 value: 39.25828944824003 - type: mrr_at_20 value: 38.76011256052923 - type: mrr_at_3 value: 35.573122529644266 - type: mrr_at_5 value: 37.02569169960474 - type: nauc_map_at_1000_diff1 value: 43.30050536386893 - type: nauc_map_at_1000_max value: 34.49322247549182 - type: nauc_map_at_1000_std value: 11.480704685860331 - type: nauc_map_at_100_diff1 value: 43.23374152493401 - type: nauc_map_at_100_max value: 34.63190473420833 - type: nauc_map_at_100_std value: 11.327553372568829 - type: nauc_map_at_10_diff1 value: 43.30961094445623 - type: nauc_map_at_10_max value: 34.03516491801115 - type: nauc_map_at_10_std value: 9.930448779277498 - type: nauc_map_at_1_diff1 value: 48.52093859650541 - type: nauc_map_at_1_max value: 31.75748436789384 - type: nauc_map_at_1_std value: 6.295511700792233 - type: nauc_map_at_20_diff1 value: 43.20196516265475 - type: nauc_map_at_20_max value: 34.40279536967664 - type: nauc_map_at_20_std value: 10.502521746353215 - type: nauc_map_at_3_diff1 value: 44.95075655761481 - type: nauc_map_at_3_max value: 34.26130085326597 - type: nauc_map_at_3_std value: 8.112284718354838 - type: nauc_map_at_5_diff1 value: 44.07530466847515 - type: nauc_map_at_5_max value: 34.29301885967441 - type: nauc_map_at_5_std value: 9.578236763789624 - type: nauc_mrr_at_1000_diff1 value: 43.74672886274306 - type: nauc_mrr_at_1000_max value: 34.91906226000147 - type: nauc_mrr_at_1000_std value: 11.902601352714218 - type: nauc_mrr_at_100_diff1 value: 43.723509090577245 - type: nauc_mrr_at_100_max value: 34.90821615383906 - type: nauc_mrr_at_100_std value: 11.929277924338157 - type: nauc_mrr_at_10_diff1 value: 43.79863834518147 - type: nauc_mrr_at_10_max value: 34.77481237076968 - type: nauc_mrr_at_10_std value: 11.621191309978766 - type: nauc_mrr_at_1_diff1 value: 47.691221572943014 - type: nauc_mrr_at_1_max value: 33.83642419108169 - type: nauc_mrr_at_1_std value: 9.150897325122848 - type: nauc_mrr_at_20_diff1 value: 43.72762657840614 - type: nauc_mrr_at_20_max value: 34.93505549897513 - type: nauc_mrr_at_20_std value: 11.77349360531995 - type: nauc_mrr_at_3_diff1 value: 44.801537918309464 - type: nauc_mrr_at_3_max value: 35.19185952684632 - type: nauc_mrr_at_3_std value: 10.129116464250496 - type: nauc_mrr_at_5_diff1 value: 44.002923041903024 - type: nauc_mrr_at_5_max value: 35.04910165721431 - type: nauc_mrr_at_5_std value: 11.398743784126784 - type: nauc_ndcg_at_1000_diff1 value: 42.1442239971562 - type: nauc_ndcg_at_1000_max value: 35.56548085015422 - type: nauc_ndcg_at_1000_std value: 14.555455012386773 - type: nauc_ndcg_at_100_diff1 value: 41.050980420258334 - type: nauc_ndcg_at_100_max value: 35.2027650239632 - type: nauc_ndcg_at_100_std value: 15.344655139587024 - type: nauc_ndcg_at_10_diff1 value: 41.471409940051366 - type: nauc_ndcg_at_10_max value: 34.09128642447279 - type: nauc_ndcg_at_10_std value: 12.90078883047037 - type: nauc_ndcg_at_1_diff1 value: 47.691221572943014 - type: nauc_ndcg_at_1_max value: 33.83642419108169 - type: nauc_ndcg_at_1_std value: 9.150897325122848 - type: nauc_ndcg_at_20_diff1 value: 41.1905793713784 - type: nauc_ndcg_at_20_max value: 34.647479344052016 - type: nauc_ndcg_at_20_std value: 13.402886235852945 - type: nauc_ndcg_at_3_diff1 value: 44.297355376548786 - type: nauc_ndcg_at_3_max value: 35.81339314801316 - type: nauc_ndcg_at_3_std value: 10.823231337841902 - type: nauc_ndcg_at_5_diff1 value: 42.800976621550305 - type: nauc_ndcg_at_5_max value: 35.31553747718296 - type: nauc_ndcg_at_5_std value: 12.999770768672233 - type: nauc_precision_at_1000_diff1 value: 1.3287822595564707 - type: nauc_precision_at_1000_max value: -7.831380419769612 - type: nauc_precision_at_1000_std value: 22.16155818707822 - type: nauc_precision_at_100_diff1 value: 7.9573230301645275 - type: nauc_precision_at_100_max value: 8.250711189680114 - type: nauc_precision_at_100_std value: 27.281502698532794 - type: nauc_precision_at_10_diff1 value: 20.32301793773069 - type: nauc_precision_at_10_max value: 26.292089297975213 - type: nauc_precision_at_10_std value: 22.04086433136549 - type: nauc_precision_at_1_diff1 value: 47.691221572943014 - type: nauc_precision_at_1_max value: 33.83642419108169 - type: nauc_precision_at_1_std value: 9.150897325122848 - type: nauc_precision_at_20_diff1 value: 15.599818198246682 - type: nauc_precision_at_20_max value: 22.892539838177527 - type: nauc_precision_at_20_std value: 25.01036353128196 - type: nauc_precision_at_3_diff1 value: 34.886829985942896 - type: nauc_precision_at_3_max value: 35.42710937207887 - type: nauc_precision_at_3_std value: 15.365089091648043 - type: nauc_precision_at_5_diff1 value: 28.15586527983956 - type: nauc_precision_at_5_max value: 32.56389381889207 - type: nauc_precision_at_5_std value: 21.509648911296196 - type: nauc_recall_at_1000_diff1 value: 26.26755669559851 - type: nauc_recall_at_1000_max value: 47.26359554231266 - type: nauc_recall_at_1000_std value: 49.17271507988052 - type: nauc_recall_at_100_diff1 value: 24.907171416372044 - type: nauc_recall_at_100_max value: 31.73666795365669 - type: nauc_recall_at_100_std value: 34.72430395157542 - type: nauc_recall_at_10_diff1 value: 31.950390817058445 - type: nauc_recall_at_10_max value: 30.2098918820224 - type: nauc_recall_at_10_std value: 14.899223627845695 - type: nauc_recall_at_1_diff1 value: 48.52093859650541 - type: nauc_recall_at_1_max value: 31.75748436789384 - type: nauc_recall_at_1_std value: 6.295511700792233 - type: nauc_recall_at_20_diff1 value: 30.085789421997823 - type: nauc_recall_at_20_max value: 31.331626697063587 - type: nauc_recall_at_20_std value: 17.995054512768437 - type: nauc_recall_at_3_diff1 value: 40.13064450428089 - type: nauc_recall_at_3_max value: 34.31621377237918 - type: nauc_recall_at_3_std value: 8.678472209664326 - type: nauc_recall_at_5_diff1 value: 36.077286485853236 - type: nauc_recall_at_5_max value: 33.299301282489374 - type: nauc_recall_at_5_std value: 13.612662967959412 - type: ndcg_at_1 value: 30.237000000000002 - type: ndcg_at_10 value: 39.275 - type: ndcg_at_100 value: 45.333 - type: ndcg_at_1000 value: 48.037 - type: ndcg_at_20 value: 41.370000000000005 - type: ndcg_at_3 value: 34.64 - type: ndcg_at_5 value: 36.909 - type: precision_at_1 value: 30.237000000000002 - type: precision_at_10 value: 7.371999999999999 - type: precision_at_100 value: 1.528 - type: precision_at_1000 value: 0.241 - type: precision_at_20 value: 4.733 - type: precision_at_3 value: 16.073999999999998 - type: precision_at_5 value: 11.700000000000001 - type: recall_at_1 value: 25.207 - type: recall_at_10 value: 49.727 - type: recall_at_100 value: 76.936 - type: recall_at_1000 value: 94.299 - type: recall_at_20 value: 57.589 - type: recall_at_3 value: 35.994 - type: recall_at_5 value: 42.406 - task: type: Retrieval dataset: name: MTEB CQADupstackWordpressRetrieval (default) type: mteb/cqadupstack-wordpress config: default split: test revision: 4ffe81d471b1924886b33c7567bfb200e9eec5c4 metrics: - type: main_score value: 32.471 - type: map_at_1 value: 19.356 - type: map_at_10 value: 27.230999999999998 - type: map_at_100 value: 28.081 - type: map_at_1000 value: 28.181 - type: map_at_20 value: 27.559 - type: map_at_3 value: 24.171 - type: map_at_5 value: 26.057999999999996 - type: mrr_at_1 value: 21.072088724584106 - type: mrr_at_10 value: 29.30647243493824 - type: mrr_at_100 value: 30.00869418929891 - type: mrr_at_1000 value: 30.080405060029037 - type: mrr_at_20 value: 29.578807931610335 - type: mrr_at_3 value: 26.247689463955638 - type: mrr_at_5 value: 28.188539741219966 - type: nauc_map_at_1000_diff1 value: 36.02401315504141 - type: nauc_map_at_1000_max value: 31.376220748052575 - type: nauc_map_at_1000_std value: 0.1346247536534226 - type: nauc_map_at_100_diff1 value: 35.97288988366299 - type: nauc_map_at_100_max value: 31.37343097714007 - type: nauc_map_at_100_std value: 0.0958351635147478 - type: nauc_map_at_10_diff1 value: 36.15899620024802 - type: nauc_map_at_10_max value: 31.361037177575795 - type: nauc_map_at_10_std value: -0.4041283486899738 - type: nauc_map_at_1_diff1 value: 45.43410283777835 - type: nauc_map_at_1_max value: 32.58678422458408 - type: nauc_map_at_1_std value: -2.6851172017575133 - type: nauc_map_at_20_diff1 value: 35.934404619775286 - type: nauc_map_at_20_max value: 31.31030383249301 - type: nauc_map_at_20_std value: -0.14717896898491972 - type: nauc_map_at_3_diff1 value: 37.86423915954705 - type: nauc_map_at_3_max value: 32.2809012047829 - type: nauc_map_at_3_std value: -2.1708148155059592 - type: nauc_map_at_5_diff1 value: 36.84265522390141 - type: nauc_map_at_5_max value: 31.37157808476922 - type: nauc_map_at_5_std value: -0.29963826158644064 - type: nauc_mrr_at_1000_diff1 value: 36.20544738283434 - type: nauc_mrr_at_1000_max value: 32.30208954588085 - type: nauc_mrr_at_1000_std value: 1.2838715864936316 - type: nauc_mrr_at_100_diff1 value: 36.15904411259169 - type: nauc_mrr_at_100_max value: 32.327938256466766 - type: nauc_mrr_at_100_std value: 1.2657067250082925 - type: nauc_mrr_at_10_diff1 value: 36.2543779320316 - type: nauc_mrr_at_10_max value: 32.24904810717847 - type: nauc_mrr_at_10_std value: 0.9726935050696278 - type: nauc_mrr_at_1_diff1 value: 45.20429144833244 - type: nauc_mrr_at_1_max value: 33.82767894871078 - type: nauc_mrr_at_1_std value: -1.8704335003125725 - type: nauc_mrr_at_20_diff1 value: 36.113279457295576 - type: nauc_mrr_at_20_max value: 32.21594845332526 - type: nauc_mrr_at_20_std value: 1.2095516871175558 - type: nauc_mrr_at_3_diff1 value: 38.20188328518054 - type: nauc_mrr_at_3_max value: 33.4670227017699 - type: nauc_mrr_at_3_std value: -0.9236814295925724 - type: nauc_mrr_at_5_diff1 value: 36.931570063812494 - type: nauc_mrr_at_5_max value: 32.13489737875822 - type: nauc_mrr_at_5_std value: 1.2076368928061894 - type: nauc_ndcg_at_1000_diff1 value: 33.10609773784356 - type: nauc_ndcg_at_1000_max value: 31.453190993700264 - type: nauc_ndcg_at_1000_std value: 4.163506021728012 - type: nauc_ndcg_at_100_diff1 value: 32.17682816382762 - type: nauc_ndcg_at_100_max value: 31.138666275698608 - type: nauc_ndcg_at_100_std value: 3.479378119538843 - type: nauc_ndcg_at_10_diff1 value: 32.36757537451326 - type: nauc_ndcg_at_10_max value: 30.337414154328656 - type: nauc_ndcg_at_10_std value: 1.2414375322956122 - type: nauc_ndcg_at_1_diff1 value: 45.20429144833244 - type: nauc_ndcg_at_1_max value: 33.82767894871078 - type: nauc_ndcg_at_1_std value: -1.8704335003125725 - type: nauc_ndcg_at_20_diff1 value: 31.63077246604112 - type: nauc_ndcg_at_20_max value: 30.145549351574726 - type: nauc_ndcg_at_20_std value: 2.2258665508440916 - type: nauc_ndcg_at_3_diff1 value: 35.7601957137602 - type: nauc_ndcg_at_3_max value: 32.14158639451499 - type: nauc_ndcg_at_3_std value: -1.5690858449662577 - type: nauc_ndcg_at_5_diff1 value: 33.96138687625853 - type: nauc_ndcg_at_5_max value: 30.334046334206526 - type: nauc_ndcg_at_5_std value: 1.6084690034355629 - type: nauc_precision_at_1000_diff1 value: 0.9129162358156773 - type: nauc_precision_at_1000_max value: 0.31132302385509963 - type: nauc_precision_at_1000_std value: 13.514346244208935 - type: nauc_precision_at_100_diff1 value: 9.48976640458681 - type: nauc_precision_at_100_max value: 20.18267841145738 - type: nauc_precision_at_100_std value: 19.747863553039213 - type: nauc_precision_at_10_diff1 value: 20.33134020850462 - type: nauc_precision_at_10_max value: 27.91758448136032 - type: nauc_precision_at_10_std value: 8.727850582611723 - type: nauc_precision_at_1_diff1 value: 45.20429144833244 - type: nauc_precision_at_1_max value: 33.82767894871078 - type: nauc_precision_at_1_std value: -1.8704335003125725 - type: nauc_precision_at_20_diff1 value: 15.896166469695693 - type: nauc_precision_at_20_max value: 25.364993587711677 - type: nauc_precision_at_20_std value: 13.114218169676196 - type: nauc_precision_at_3_diff1 value: 29.003771079583746 - type: nauc_precision_at_3_max value: 32.65304146225246 - type: nauc_precision_at_3_std value: 1.1340423196142706 - type: nauc_precision_at_5_diff1 value: 25.57516378319094 - type: nauc_precision_at_5_max value: 28.99827810579553 - type: nauc_precision_at_5_std value: 7.945608340859795 - type: nauc_recall_at_1000_diff1 value: 17.592328574711598 - type: nauc_recall_at_1000_max value: 36.04732369555508 - type: nauc_recall_at_1000_std value: 37.39190072119301 - type: nauc_recall_at_100_diff1 value: 17.82377173461608 - type: nauc_recall_at_100_max value: 28.7134171033536 - type: nauc_recall_at_100_std value: 14.674088397323942 - type: nauc_recall_at_10_diff1 value: 20.986778993947823 - type: nauc_recall_at_10_max value: 25.73837718906844 - type: nauc_recall_at_10_std value: 4.164768619671828 - type: nauc_recall_at_1_diff1 value: 45.43410283777835 - type: nauc_recall_at_1_max value: 32.58678422458408 - type: nauc_recall_at_1_std value: -2.6851172017575133 - type: nauc_recall_at_20_diff1 value: 17.951879051749504 - type: nauc_recall_at_20_max value: 24.485751903899704 - type: nauc_recall_at_20_std value: 7.330820639157978 - type: nauc_recall_at_3_diff1 value: 29.347120526930233 - type: nauc_recall_at_3_max value: 30.40588230331169 - type: nauc_recall_at_3_std value: -0.8229385769060911 - type: nauc_recall_at_5_diff1 value: 25.655758092986265 - type: nauc_recall_at_5_max value: 26.529657553507846 - type: nauc_recall_at_5_std value: 5.6563620697950405 - type: ndcg_at_1 value: 21.072 - type: ndcg_at_10 value: 32.471 - type: ndcg_at_100 value: 37.183 - type: ndcg_at_1000 value: 39.644 - type: ndcg_at_20 value: 33.559 - type: ndcg_at_3 value: 26.52 - type: ndcg_at_5 value: 29.773 - type: precision_at_1 value: 21.072 - type: precision_at_10 value: 5.396999999999999 - type: precision_at_100 value: 0.856 - type: precision_at_1000 value: 0.11800000000000001 - type: precision_at_20 value: 2.976 - type: precision_at_3 value: 11.522 - type: precision_at_5 value: 8.799 - type: recall_at_1 value: 19.356 - type: recall_at_10 value: 46.636 - type: recall_at_100 value: 69.663 - type: recall_at_1000 value: 87.789 - type: recall_at_20 value: 50.819 - type: recall_at_3 value: 30.745 - type: recall_at_5 value: 38.558 - task: type: Retrieval dataset: name: MTEB ClimateFEVER (default) type: mteb/climate-fever config: default split: test revision: 47f2ac6acb640fc46020b02a5b59fdda04d39380 metrics: - type: main_score value: 28.83 - type: map_at_1 value: 11.912 - type: map_at_10 value: 20.47 - type: map_at_100 value: 22.519 - type: map_at_1000 value: 22.723 - type: map_at_20 value: 21.597 - type: map_at_3 value: 17.14 - type: map_at_5 value: 18.784 - type: mrr_at_1 value: 26.97068403908795 - type: mrr_at_10 value: 38.490486531203146 - type: mrr_at_100 value: 39.53396099832615 - type: mrr_at_1000 value: 39.57210684594996 - type: mrr_at_20 value: 39.15425856866292 - type: mrr_at_3 value: 35.11400651465798 - type: mrr_at_5 value: 37.045602605863195 - type: nauc_map_at_1000_diff1 value: 24.76538935736538 - type: nauc_map_at_1000_max value: 33.971343734250524 - type: nauc_map_at_1000_std value: 15.514286902461812 - type: nauc_map_at_100_diff1 value: 24.779729311279336 - type: nauc_map_at_100_max value: 33.919396423104644 - type: nauc_map_at_100_std value: 15.447044791174381 - type: nauc_map_at_10_diff1 value: 24.846700880282587 - type: nauc_map_at_10_max value: 33.009555706514895 - type: nauc_map_at_10_std value: 13.466161448314931 - type: nauc_map_at_1_diff1 value: 30.77619025618349 - type: nauc_map_at_1_max value: 29.34711506798961 - type: nauc_map_at_1_std value: 5.370506534257179 - type: nauc_map_at_20_diff1 value: 24.887170838281627 - type: nauc_map_at_20_max value: 33.417660516280556 - type: nauc_map_at_20_std value: 14.573987916991893 - type: nauc_map_at_3_diff1 value: 26.268565940718595 - type: nauc_map_at_3_max value: 31.393759098190273 - type: nauc_map_at_3_std value: 9.903530484775908 - type: nauc_map_at_5_diff1 value: 25.92807753940896 - type: nauc_map_at_5_max value: 31.75547205926257 - type: nauc_map_at_5_std value: 11.144523593563873 - type: nauc_mrr_at_1000_diff1 value: 21.169799923106503 - type: nauc_mrr_at_1000_max value: 30.197960966240423 - type: nauc_mrr_at_1000_std value: 14.9456013284975 - type: nauc_mrr_at_100_diff1 value: 21.163213044565072 - type: nauc_mrr_at_100_max value: 30.203598251460463 - type: nauc_mrr_at_100_std value: 14.965088745621394 - type: nauc_mrr_at_10_diff1 value: 21.288223958797573 - type: nauc_mrr_at_10_max value: 30.216972741035725 - type: nauc_mrr_at_10_std value: 14.843389003635199 - type: nauc_mrr_at_1_diff1 value: 23.727724539614726 - type: nauc_mrr_at_1_max value: 25.48232837843042 - type: nauc_mrr_at_1_std value: 7.3658686447303365 - type: nauc_mrr_at_20_diff1 value: 21.169422189267745 - type: nauc_mrr_at_20_max value: 30.301266953756706 - type: nauc_mrr_at_20_std value: 15.075334986433173 - type: nauc_mrr_at_3_diff1 value: 21.196573573020927 - type: nauc_mrr_at_3_max value: 28.977465265081033 - type: nauc_mrr_at_3_std value: 13.332883636713632 - type: nauc_mrr_at_5_diff1 value: 21.357024988142246 - type: nauc_mrr_at_5_max value: 29.813915226240674 - type: nauc_mrr_at_5_std value: 14.24321875462318 - type: nauc_ndcg_at_1000_diff1 value: 21.61770986869092 - type: nauc_ndcg_at_1000_max value: 36.60187844333304 - type: nauc_ndcg_at_1000_std value: 22.795099112621724 - type: nauc_ndcg_at_100_diff1 value: 21.776142474396803 - type: nauc_ndcg_at_100_max value: 36.2414089305107 - type: nauc_ndcg_at_100_std value: 22.4799584915147 - type: nauc_ndcg_at_10_diff1 value: 22.481037341715847 - type: nauc_ndcg_at_10_max value: 34.06739169204709 - type: nauc_ndcg_at_10_std value: 17.57021576387562 - type: nauc_ndcg_at_1_diff1 value: 23.727724539614726 - type: nauc_ndcg_at_1_max value: 25.48232837843042 - type: nauc_ndcg_at_1_std value: 7.3658686447303365 - type: nauc_ndcg_at_20_diff1 value: 22.498496087588748 - type: nauc_ndcg_at_20_max value: 34.892054494351775 - type: nauc_ndcg_at_20_std value: 19.86842474039087 - type: nauc_ndcg_at_3_diff1 value: 23.227651070229673 - type: nauc_ndcg_at_3_max value: 30.75938173648469 - type: nauc_ndcg_at_3_std value: 12.463565273811932 - type: nauc_ndcg_at_5_diff1 value: 23.799000279668764 - type: nauc_ndcg_at_5_max value: 32.0660491516285 - type: nauc_ndcg_at_5_std value: 13.990017306982494 - type: nauc_precision_at_1000_diff1 value: -6.21355360115824 - type: nauc_precision_at_1000_max value: 14.235538664122721 - type: nauc_precision_at_1000_std value: 25.265885010833472 - type: nauc_precision_at_100_diff1 value: 0.562403756165029 - type: nauc_precision_at_100_max value: 23.924206050764756 - type: nauc_precision_at_100_std value: 31.338663218741008 - type: nauc_precision_at_10_diff1 value: 10.354652757659355 - type: nauc_precision_at_10_max value: 30.758798212425408 - type: nauc_precision_at_10_std value: 26.7031344564241 - type: nauc_precision_at_1_diff1 value: 23.727724539614726 - type: nauc_precision_at_1_max value: 25.48232837843042 - type: nauc_precision_at_1_std value: 7.3658686447303365 - type: nauc_precision_at_20_diff1 value: 7.953520958455318 - type: nauc_precision_at_20_max value: 27.65892195364336 - type: nauc_precision_at_20_std value: 29.388872379134785 - type: nauc_precision_at_3_diff1 value: 16.808332567181218 - type: nauc_precision_at_3_max value: 29.936324350885325 - type: nauc_precision_at_3_std value: 17.73176704168099 - type: nauc_precision_at_5_diff1 value: 14.763444123101097 - type: nauc_precision_at_5_max value: 29.010028453553105 - type: nauc_precision_at_5_std value: 20.023906594546354 - type: nauc_recall_at_1000_diff1 value: 7.556266790051787 - type: nauc_recall_at_1000_max value: 39.68519315547223 - type: nauc_recall_at_1000_std value: 42.629307490289136 - type: nauc_recall_at_100_diff1 value: 11.82811136427535 - type: nauc_recall_at_100_max value: 34.385603696492915 - type: nauc_recall_at_100_std value: 32.712899819080086 - type: nauc_recall_at_10_diff1 value: 16.862688054209933 - type: nauc_recall_at_10_max value: 32.3375156464964 - type: nauc_recall_at_10_std value: 20.728901631388972 - type: nauc_recall_at_1_diff1 value: 30.77619025618349 - type: nauc_recall_at_1_max value: 29.34711506798961 - type: nauc_recall_at_1_std value: 5.370506534257179 - type: nauc_recall_at_20_diff1 value: 16.155103050272285 - type: nauc_recall_at_20_max value: 32.5683721009582 - type: nauc_recall_at_20_std value: 24.833541877340508 - type: nauc_recall_at_3_diff1 value: 21.31158530879841 - type: nauc_recall_at_3_max value: 30.2555482302795 - type: nauc_recall_at_3_std value: 12.723641578903559 - type: nauc_recall_at_5_diff1 value: 20.646276690604772 - type: nauc_recall_at_5_max value: 30.46478603020548 - type: nauc_recall_at_5_std value: 14.74543343019217 - type: ndcg_at_1 value: 26.971 - type: ndcg_at_10 value: 28.83 - type: ndcg_at_100 value: 36.742000000000004 - type: ndcg_at_1000 value: 40.228 - type: ndcg_at_20 value: 31.983 - type: ndcg_at_3 value: 23.546 - type: ndcg_at_5 value: 25.291999999999998 - type: precision_at_1 value: 26.971 - type: precision_at_10 value: 9.075 - type: precision_at_100 value: 1.7500000000000002 - type: precision_at_1000 value: 0.24 - type: precision_at_20 value: 5.912 - type: precision_at_3 value: 17.59 - type: precision_at_5 value: 13.485 - type: recall_at_1 value: 11.912 - type: recall_at_10 value: 34.746 - type: recall_at_100 value: 61.869 - type: recall_at_1000 value: 81.178 - type: recall_at_20 value: 43.575 - type: recall_at_3 value: 21.706 - type: recall_at_5 value: 26.826 - task: type: Retrieval dataset: name: MTEB DBPedia (default) type: mteb/dbpedia config: default split: dev revision: c0f706b76e590d620bd6618b3ca8efdd34e2d659 metrics: - type: main_score value: 46.941 - type: map_at_1 value: 11.128 - type: map_at_10 value: 21.468 - type: map_at_100 value: 31.257 - type: map_at_1000 value: 32.994 - type: map_at_20 value: 25.85 - type: map_at_3 value: 15.384999999999998 - type: map_at_5 value: 17.918 - type: mrr_at_1 value: 74.6268656716418 - type: mrr_at_10 value: 82.71736555318644 - type: mrr_at_100 value: 82.86968222071188 - type: mrr_at_1000 value: 82.87289889595635 - type: mrr_at_20 value: 82.81686804074863 - type: mrr_at_3 value: 82.33830845771143 - type: mrr_at_5 value: 82.33830845771143 - type: nauc_map_at_1000_diff1 value: 28.205873220137107 - type: nauc_map_at_1000_max value: 32.58677206955515 - type: nauc_map_at_1000_std value: 5.320112182691084 - type: nauc_map_at_100_diff1 value: 30.2072705535807 - type: nauc_map_at_100_max value: 31.398441843394203 - type: nauc_map_at_100_std value: 0.3721987672572358 - type: nauc_map_at_10_diff1 value: 43.658171592848966 - type: nauc_map_at_10_max value: 20.163715859146205 - type: nauc_map_at_10_std value: -27.377423723665643 - type: nauc_map_at_1_diff1 value: 53.67643301898103 - type: nauc_map_at_1_max value: 9.619896030610045 - type: nauc_map_at_1_std value: -39.90622904765458 - type: nauc_map_at_20_diff1 value: 37.89256707694639 - type: nauc_map_at_20_max value: 23.572362119543783 - type: nauc_map_at_20_std value: -17.725673906501697 - type: nauc_map_at_3_diff1 value: 44.79713521587412 - type: nauc_map_at_3_max value: 11.458612145657254 - type: nauc_map_at_3_std value: -38.4860514263039 - type: nauc_map_at_5_diff1 value: 44.27015282190561 - type: nauc_map_at_5_max value: 16.420591916821895 - type: nauc_map_at_5_std value: -32.85173443465263 - type: nauc_mrr_at_1000_diff1 value: 40.68406246743924 - type: nauc_mrr_at_1000_max value: 54.557403984682374 - type: nauc_mrr_at_1000_std value: 40.971924667245645 - type: nauc_mrr_at_100_diff1 value: 40.68710053046815 - type: nauc_mrr_at_100_max value: 54.561036423251075 - type: nauc_mrr_at_100_std value: 40.97834383095643 - type: nauc_mrr_at_10_diff1 value: 41.01499432410833 - type: nauc_mrr_at_10_max value: 54.97000112752338 - type: nauc_mrr_at_10_std value: 41.318724395876444 - type: nauc_mrr_at_1_diff1 value: 38.93343855503621 - type: nauc_mrr_at_1_max value: 44.716366048532024 - type: nauc_mrr_at_1_std value: 31.486396303111274 - type: nauc_mrr_at_20_diff1 value: 40.64197845924939 - type: nauc_mrr_at_20_max value: 54.6852354691744 - type: nauc_mrr_at_20_std value: 41.1230179065546 - type: nauc_mrr_at_3_diff1 value: 40.82958545456673 - type: nauc_mrr_at_3_max value: 55.153817526702355 - type: nauc_mrr_at_3_std value: 41.650161545663664 - type: nauc_mrr_at_5_diff1 value: 40.82958545456673 - type: nauc_mrr_at_5_max value: 55.153817526702355 - type: nauc_mrr_at_5_std value: 41.650161545663664 - type: nauc_ndcg_at_1000_diff1 value: 23.929983013223506 - type: nauc_ndcg_at_1000_max value: 44.75276524735193 - type: nauc_ndcg_at_1000_std value: 29.517675569258962 - type: nauc_ndcg_at_100_diff1 value: 29.624406725667374 - type: nauc_ndcg_at_100_max value: 41.6779897397469 - type: nauc_ndcg_at_100_std value: 13.705531184382655 - type: nauc_ndcg_at_10_diff1 value: 31.416257175446887 - type: nauc_ndcg_at_10_max value: 38.589902876894975 - type: nauc_ndcg_at_10_std value: 11.728256480525854 - type: nauc_ndcg_at_1_diff1 value: 28.46337552050302 - type: nauc_ndcg_at_1_max value: 38.225886384997445 - type: nauc_ndcg_at_1_std value: 21.338500059461598 - type: nauc_ndcg_at_20_diff1 value: 33.256723866450166 - type: nauc_ndcg_at_20_max value: 33.537144781805374 - type: nauc_ndcg_at_20_std value: -0.33743018664631347 - type: nauc_ndcg_at_3_diff1 value: 13.969404562448364 - type: nauc_ndcg_at_3_max value: 30.565751196256763 - type: nauc_ndcg_at_3_std value: 17.30174026819281 - type: nauc_ndcg_at_5_diff1 value: 18.872272865937877 - type: nauc_ndcg_at_5_max value: 35.263519230922064 - type: nauc_ndcg_at_5_std value: 19.33016308269416 - type: nauc_precision_at_1000_diff1 value: -33.04092483049479 - type: nauc_precision_at_1000_max value: 11.49095198021317 - type: nauc_precision_at_1000_std value: 60.12678457700677 - type: nauc_precision_at_100_diff1 value: -31.078345270653546 - type: nauc_precision_at_100_max value: 24.725068437496166 - type: nauc_precision_at_100_std value: 67.57419232501738 - type: nauc_precision_at_10_diff1 value: -22.292617190022344 - type: nauc_precision_at_10_max value: 24.54113659577851 - type: nauc_precision_at_10_std value: 50.62947534355667 - type: nauc_precision_at_1_diff1 value: 38.93343855503621 - type: nauc_precision_at_1_max value: 44.716366048532024 - type: nauc_precision_at_1_std value: 31.486396303111274 - type: nauc_precision_at_20_diff1 value: -25.92502457178481 - type: nauc_precision_at_20_max value: 23.621039548137382 - type: nauc_precision_at_20_std value: 52.21318384886264 - type: nauc_precision_at_3_diff1 value: -15.971548173967095 - type: nauc_precision_at_3_max value: 24.699430304690164 - type: nauc_precision_at_3_std value: 35.799215461434265 - type: nauc_precision_at_5_diff1 value: -19.615035551746058 - type: nauc_precision_at_5_max value: 30.732478067399917 - type: nauc_precision_at_5_std value: 49.57700533096512 - type: nauc_recall_at_1000_diff1 value: 2.3453680689225975 - type: nauc_recall_at_1000_max value: 41.49529473708931 - type: nauc_recall_at_1000_std value: 41.33189951068062 - type: nauc_recall_at_100_diff1 value: 20.244471165146653 - type: nauc_recall_at_100_max value: 37.4543481569782 - type: nauc_recall_at_100_std value: 7.801110449891264 - type: nauc_recall_at_10_diff1 value: 46.105545914294964 - type: nauc_recall_at_10_max value: 21.930607285926236 - type: nauc_recall_at_10_std value: -29.972280971809862 - type: nauc_recall_at_1_diff1 value: 53.67643301898103 - type: nauc_recall_at_1_max value: 9.619896030610045 - type: nauc_recall_at_1_std value: -39.90622904765458 - type: nauc_recall_at_20_diff1 value: 31.224305541777962 - type: nauc_recall_at_20_max value: 18.835055220233627 - type: nauc_recall_at_20_std value: -23.34247163762115 - type: nauc_recall_at_3_diff1 value: 42.73205224851371 - type: nauc_recall_at_3_max value: 9.89768785740234 - type: nauc_recall_at_3_std value: -40.04768970629589 - type: nauc_recall_at_5_diff1 value: 43.48392547485277 - type: nauc_recall_at_5_max value: 16.208422216255546 - type: nauc_recall_at_5_std value: -33.79681691846111 - type: ndcg_at_1 value: 64.925 - type: ndcg_at_10 value: 46.941 - type: ndcg_at_100 value: 53.242999999999995 - type: ndcg_at_1000 value: 60.87200000000001 - type: ndcg_at_20 value: 47.138999999999996 - type: ndcg_at_3 value: 54.533 - type: ndcg_at_5 value: 50.536 - type: precision_at_1 value: 74.627 - type: precision_at_10 value: 34.477999999999994 - type: precision_at_100 value: 10.776 - type: precision_at_1000 value: 1.737 - type: precision_at_20 value: 26.939999999999998 - type: precision_at_3 value: 53.234 - type: precision_at_5 value: 45.074999999999996 - type: recall_at_1 value: 11.128 - type: recall_at_10 value: 27.354 - type: recall_at_100 value: 60.211999999999996 - type: recall_at_1000 value: 84.485 - type: recall_at_20 value: 38.645 - type: recall_at_3 value: 16.72 - type: recall_at_5 value: 20.648 - task: type: Retrieval dataset: name: MTEB DBPedia (default) type: mteb/dbpedia config: default split: test revision: c0f706b76e590d620bd6618b3ca8efdd34e2d659 metrics: - type: main_score value: 40.463 - type: map_at_1 value: 9.029 - type: map_at_10 value: 19.262999999999998 - type: map_at_100 value: 27.32 - type: map_at_1000 value: 28.898000000000003 - type: map_at_20 value: 22.285 - type: map_at_3 value: 13.741999999999999 - type: map_at_5 value: 16.184 - type: mrr_at_1 value: 66.5 - type: mrr_at_10 value: 74.58015873015873 - type: mrr_at_100 value: 74.90889577505533 - type: mrr_at_1000 value: 74.91723981152577 - type: mrr_at_20 value: 74.81400519415226 - type: mrr_at_3 value: 72.75 - type: mrr_at_5 value: 74.0125 - type: nauc_map_at_1000_diff1 value: 18.09558210846325 - type: nauc_map_at_1000_max value: 23.2203289549629 - type: nauc_map_at_1000_std value: 26.956962795986172 - type: nauc_map_at_100_diff1 value: 19.26318278180542 - type: nauc_map_at_100_max value: 21.385042416697452 - type: nauc_map_at_100_std value: 24.102985219136333 - type: nauc_map_at_10_diff1 value: 23.01034372544496 - type: nauc_map_at_10_max value: 10.878304152216096 - type: nauc_map_at_10_std value: 2.362436293740753 - type: nauc_map_at_1_diff1 value: 37.366256622356744 - type: nauc_map_at_1_max value: 3.3385920525541053 - type: nauc_map_at_1_std value: -13.380038032859368 - type: nauc_map_at_20_diff1 value: 21.282079555449165 - type: nauc_map_at_20_max value: 14.770333252524978 - type: nauc_map_at_20_std value: 10.07082791626879 - type: nauc_map_at_3_diff1 value: 27.510938193340262 - type: nauc_map_at_3_max value: 4.965379678339785 - type: nauc_map_at_3_std value: -8.210306316829763 - type: nauc_map_at_5_diff1 value: 25.261898710191527 - type: nauc_map_at_5_max value: 6.767168819826101 - type: nauc_map_at_5_std value: -4.755049267878645 - type: nauc_mrr_at_1000_diff1 value: 43.97215491866585 - type: nauc_mrr_at_1000_max value: 57.2564604463254 - type: nauc_mrr_at_1000_std value: 37.52158604598497 - type: nauc_mrr_at_100_diff1 value: 43.9520395412017 - type: nauc_mrr_at_100_max value: 57.25472510851986 - type: nauc_mrr_at_100_std value: 37.512313370242985 - type: nauc_mrr_at_10_diff1 value: 44.149055538533176 - type: nauc_mrr_at_10_max value: 57.33498205903583 - type: nauc_mrr_at_10_std value: 37.47474466090973 - type: nauc_mrr_at_1_diff1 value: 47.2190330933805 - type: nauc_mrr_at_1_max value: 54.17417392251676 - type: nauc_mrr_at_1_std value: 32.26038934374714 - type: nauc_mrr_at_20_diff1 value: 43.968230171527594 - type: nauc_mrr_at_20_max value: 57.29041263736231 - type: nauc_mrr_at_20_std value: 37.544977698244445 - type: nauc_mrr_at_3_diff1 value: 43.34027046577654 - type: nauc_mrr_at_3_max value: 56.66557913521474 - type: nauc_mrr_at_3_std value: 38.76901326294043 - type: nauc_mrr_at_5_diff1 value: 44.12604461577999 - type: nauc_mrr_at_5_max value: 57.612606984606195 - type: nauc_mrr_at_5_std value: 37.82836737434154 - type: nauc_ndcg_at_1000_diff1 value: 17.44988479317236 - type: nauc_ndcg_at_1000_max value: 37.7482696046901 - type: nauc_ndcg_at_1000_std value: 38.65638419071411 - type: nauc_ndcg_at_100_diff1 value: 19.507315827241328 - type: nauc_ndcg_at_100_max value: 30.400138333090588 - type: nauc_ndcg_at_100_std value: 31.113058945606742 - type: nauc_ndcg_at_10_diff1 value: 20.815636696375392 - type: nauc_ndcg_at_10_max value: 33.68288613631258 - type: nauc_ndcg_at_10_std value: 29.671362930314803 - type: nauc_ndcg_at_1_diff1 value: 38.11376341528132 - type: nauc_ndcg_at_1_max value: 44.403414549347204 - type: nauc_ndcg_at_1_std value: 25.52384786407678 - type: nauc_ndcg_at_20_diff1 value: 20.918758451069003 - type: nauc_ndcg_at_20_max value: 30.06195313262468 - type: nauc_ndcg_at_20_std value: 26.54741096206399 - type: nauc_ndcg_at_3_diff1 value: 24.372445814427298 - type: nauc_ndcg_at_3_max value: 37.527105863035004 - type: nauc_ndcg_at_3_std value: 29.627357113821652 - type: nauc_ndcg_at_5_diff1 value: 22.24317304883715 - type: nauc_ndcg_at_5_max value: 36.01451546088971 - type: nauc_ndcg_at_5_std value: 29.681491475278758 - type: nauc_precision_at_1000_diff1 value: -16.787088918126038 - type: nauc_precision_at_1000_max value: 7.469815188782062 - type: nauc_precision_at_1000_std value: 20.347279526863016 - type: nauc_precision_at_100_diff1 value: -7.767846738327802 - type: nauc_precision_at_100_max value: 29.03244278470077 - type: nauc_precision_at_100_std value: 46.382880462091606 - type: nauc_precision_at_10_diff1 value: -0.5232913303652262 - type: nauc_precision_at_10_max value: 38.64476507974731 - type: nauc_precision_at_10_std value: 47.74014794238241 - type: nauc_precision_at_1_diff1 value: 47.2190330933805 - type: nauc_precision_at_1_max value: 54.17417392251676 - type: nauc_precision_at_1_std value: 32.26038934374714 - type: nauc_precision_at_20_diff1 value: -2.1834578501338147 - type: nauc_precision_at_20_max value: 35.998198621553904 - type: nauc_precision_at_20_std value: 48.111771749288465 - type: nauc_precision_at_3_diff1 value: 10.263223401237676 - type: nauc_precision_at_3_max value: 38.014854436938116 - type: nauc_precision_at_3_std value: 38.4358555773606 - type: nauc_precision_at_5_diff1 value: 4.413009169159884 - type: nauc_precision_at_5_max value: 39.10496606345797 - type: nauc_precision_at_5_std value: 42.78105363038704 - type: nauc_recall_at_1000_diff1 value: 5.614459025569145 - type: nauc_recall_at_1000_max value: 30.609110099594243 - type: nauc_recall_at_1000_std value: 41.7665129006611 - type: nauc_recall_at_100_diff1 value: 11.30144179728448 - type: nauc_recall_at_100_max value: 16.59742852717951 - type: nauc_recall_at_100_std value: 24.50296358615415 - type: nauc_recall_at_10_diff1 value: 16.490149625173352 - type: nauc_recall_at_10_max value: 3.832770249980029 - type: nauc_recall_at_10_std value: -2.374496776149457 - type: nauc_recall_at_1_diff1 value: 37.366256622356744 - type: nauc_recall_at_1_max value: 3.3385920525541053 - type: nauc_recall_at_1_std value: -13.380038032859368 - type: nauc_recall_at_20_diff1 value: 15.292191881271883 - type: nauc_recall_at_20_max value: 8.415679565455628 - type: nauc_recall_at_20_std value: 5.074936206972553 - type: nauc_recall_at_3_diff1 value: 24.152242185735222 - type: nauc_recall_at_3_max value: 1.506727274505061 - type: nauc_recall_at_3_std value: -10.019411125629754 - type: nauc_recall_at_5_diff1 value: 21.7463835872855 - type: nauc_recall_at_5_max value: 2.645640036075683 - type: nauc_recall_at_5_std value: -7.864417712754525 - type: ndcg_at_1 value: 54.625 - type: ndcg_at_10 value: 40.463 - type: ndcg_at_100 value: 45.693 - type: ndcg_at_1000 value: 53.21900000000001 - type: ndcg_at_20 value: 39.948 - type: ndcg_at_3 value: 44.546 - type: ndcg_at_5 value: 42.370000000000005 - type: precision_at_1 value: 66.5 - type: precision_at_10 value: 31.724999999999998 - type: precision_at_100 value: 10.308 - type: precision_at_1000 value: 2.015 - type: precision_at_20 value: 24.013 - type: precision_at_3 value: 47.5 - type: precision_at_5 value: 40.8 - type: recall_at_1 value: 9.029 - type: recall_at_10 value: 25.064999999999998 - type: recall_at_100 value: 52.578 - type: recall_at_1000 value: 76.43100000000001 - type: recall_at_20 value: 32.012 - type: recall_at_3 value: 15.046000000000001 - type: recall_at_5 value: 19.012 - task: type: Classification dataset: name: MTEB EmotionClassification (default) type: mteb/emotion config: default split: test revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy value: 50.815 - type: f1 value: 44.094634894021816 - type: f1_weighted value: 52.60818465807737 - type: main_score value: 50.815 - task: type: Classification dataset: name: MTEB EmotionClassification (default) type: mteb/emotion config: default split: validation revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy value: 50.25999999999999 - type: f1 value: 44.29688695357058 - type: f1_weighted value: 51.782894585455274 - type: main_score value: 50.25999999999999 - task: type: Retrieval dataset: name: MTEB FEVER (default) type: mteb/fever config: default split: dev revision: bea83ef9e8fb933d90a2f1d5515737465d613e12 metrics: - type: main_score value: 86.581 - type: map_at_1 value: 74.727 - type: map_at_10 value: 82.856 - type: map_at_100 value: 83.08 - type: map_at_1000 value: 83.095 - type: map_at_20 value: 82.98 - type: map_at_3 value: 81.874 - type: map_at_5 value: 82.528 - type: mrr_at_1 value: 81.11311131113112 - type: mrr_at_10 value: 88.08008777068184 - type: mrr_at_100 value: 88.15267896396102 - type: mrr_at_1000 value: 88.15440036957291 - type: mrr_at_20 value: 88.12826180824881 - type: mrr_at_3 value: 87.42624262426241 - type: mrr_at_5 value: 87.90179017901791 - type: nauc_map_at_1000_diff1 value: 50.36356059540196 - type: nauc_map_at_1000_max value: 23.9992915254945 - type: nauc_map_at_1000_std value: -5.351570096789122 - type: nauc_map_at_100_diff1 value: 50.32379212854651 - type: nauc_map_at_100_max value: 23.98098961038551 - type: nauc_map_at_100_std value: -5.348874939403815 - type: nauc_map_at_10_diff1 value: 49.99523888098324 - type: nauc_map_at_10_max value: 23.709118817821636 - type: nauc_map_at_10_std value: -5.655330318910658 - type: nauc_map_at_1_diff1 value: 54.8096391515275 - type: nauc_map_at_1_max value: 20.61234382722085 - type: nauc_map_at_1_std value: -7.831309271791796 - type: nauc_map_at_20_diff1 value: 50.19276270347539 - type: nauc_map_at_20_max value: 23.8325417359291 - type: nauc_map_at_20_std value: -5.4936298430989 - type: nauc_map_at_3_diff1 value: 50.28796474395995 - type: nauc_map_at_3_max value: 23.45783355551859 - type: nauc_map_at_3_std value: -6.885753631015993 - type: nauc_map_at_5_diff1 value: 49.96283216222825 - type: nauc_map_at_5_max value: 23.555049015922823 - type: nauc_map_at_5_std value: -6.090659860215219 - type: nauc_mrr_at_1000_diff1 value: 69.17421533744194 - type: nauc_mrr_at_1000_max value: 33.02158730991583 - type: nauc_mrr_at_1000_std value: -8.948358014186812 - type: nauc_mrr_at_100_diff1 value: 69.17553004498271 - type: nauc_mrr_at_100_max value: 33.028331950038684 - type: nauc_mrr_at_100_std value: -8.942802854470754 - type: nauc_mrr_at_10_diff1 value: 69.13328163893561 - type: nauc_mrr_at_10_max value: 33.18335904223495 - type: nauc_mrr_at_10_std value: -8.89478907359742 - type: nauc_mrr_at_1_diff1 value: 69.59435273515031 - type: nauc_mrr_at_1_max value: 28.41439149035527 - type: nauc_mrr_at_1_std value: -9.895055694379428 - type: nauc_mrr_at_20_diff1 value: 69.19362398254414 - type: nauc_mrr_at_20_max value: 33.09302969870915 - type: nauc_mrr_at_20_std value: -8.903618952902336 - type: nauc_mrr_at_3_diff1 value: 69.03641198083353 - type: nauc_mrr_at_3_max value: 33.689976336215125 - type: nauc_mrr_at_3_std value: -9.53929739319604 - type: nauc_mrr_at_5_diff1 value: 69.03744477223476 - type: nauc_mrr_at_5_max value: 33.343224412356946 - type: nauc_mrr_at_5_std value: -9.107354899986388 - type: nauc_ndcg_at_1000_diff1 value: 52.37043460910987 - type: nauc_ndcg_at_1000_max value: 26.868515910590585 - type: nauc_ndcg_at_1000_std value: -3.8173698040799926 - type: nauc_ndcg_at_100_diff1 value: 51.59304592952214 - type: nauc_ndcg_at_100_max value: 26.582916315809957 - type: nauc_ndcg_at_100_std value: -3.507246327999668 - type: nauc_ndcg_at_10_diff1 value: 50.56748641091843 - type: nauc_ndcg_at_10_max value: 25.937839511946397 - type: nauc_ndcg_at_10_std value: -4.317117533070399 - type: nauc_ndcg_at_1_diff1 value: 69.59435273515031 - type: nauc_ndcg_at_1_max value: 28.41439149035527 - type: nauc_ndcg_at_1_std value: -9.895055694379428 - type: nauc_ndcg_at_20_diff1 value: 51.07942544100161 - type: nauc_ndcg_at_20_max value: 26.079691268086176 - type: nauc_ndcg_at_20_std value: -3.9867583589809534 - type: nauc_ndcg_at_3_diff1 value: 52.08099666063276 - type: nauc_ndcg_at_3_max value: 26.743415311234692 - type: nauc_ndcg_at_3_std value: -6.45797306431994 - type: nauc_ndcg_at_5_diff1 value: 50.763723596631735 - type: nauc_ndcg_at_5_max value: 26.016889338180306 - type: nauc_ndcg_at_5_std value: -5.248574264404534 - type: nauc_precision_at_1000_diff1 value: -5.387965863532961 - type: nauc_precision_at_1000_max value: 10.372523367921854 - type: nauc_precision_at_1000_std value: 13.415209647969087 - type: nauc_precision_at_100_diff1 value: -5.685856344844705 - type: nauc_precision_at_100_max value: 13.882370685075996 - type: nauc_precision_at_100_std value: 17.947725196159116 - type: nauc_precision_at_10_diff1 value: 1.4713194150281539 - type: nauc_precision_at_10_max value: 20.264317861307276 - type: nauc_precision_at_10_std value: 12.524533346684677 - type: nauc_precision_at_1_diff1 value: 69.59435273515031 - type: nauc_precision_at_1_max value: 28.41439149035527 - type: nauc_precision_at_1_std value: -9.895055694379428 - type: nauc_precision_at_20_diff1 value: -1.040212171206397 - type: nauc_precision_at_20_max value: 17.76967921210208 - type: nauc_precision_at_20_std value: 15.86703101590195 - type: nauc_precision_at_3_diff1 value: 27.397567762305414 - type: nauc_precision_at_3_max value: 29.983353547368306 - type: nauc_precision_at_3_std value: -2.024560146034635 - type: nauc_precision_at_5_diff1 value: 11.978185255474472 - type: nauc_precision_at_5_max value: 25.336475474417213 - type: nauc_precision_at_5_std value: 6.079864267936165 - type: nauc_recall_at_1000_diff1 value: 5.978402010181869 - type: nauc_recall_at_1000_max value: 26.578352090329005 - type: nauc_recall_at_1000_std value: 31.804174323172713 - type: nauc_recall_at_100_diff1 value: 9.67678765671401 - type: nauc_recall_at_100_max value: 21.918365367812797 - type: nauc_recall_at_100_std value: 24.820139168438597 - type: nauc_recall_at_10_diff1 value: 21.60125165788751 - type: nauc_recall_at_10_max value: 21.565110839293144 - type: nauc_recall_at_10_std value: 8.449173954921543 - type: nauc_recall_at_1_diff1 value: 54.8096391515275 - type: nauc_recall_at_1_max value: 20.61234382722085 - type: nauc_recall_at_1_std value: -7.831309271791796 - type: nauc_recall_at_20_diff1 value: 19.681237121526223 - type: nauc_recall_at_20_max value: 20.77874943741462 - type: nauc_recall_at_20_std value: 12.46872212646974 - type: nauc_recall_at_3_diff1 value: 35.25648317456749 - type: nauc_recall_at_3_max value: 24.513936377413255 - type: nauc_recall_at_3_std value: -3.46424213085049 - type: nauc_recall_at_5_diff1 value: 27.636657051463775 - type: nauc_recall_at_5_max value: 22.76892845457896 - type: nauc_recall_at_5_std value: 1.819321132167595 - type: ndcg_at_1 value: 81.113 - type: ndcg_at_10 value: 86.581 - type: ndcg_at_100 value: 87.37700000000001 - type: ndcg_at_1000 value: 87.634 - type: ndcg_at_20 value: 86.90299999999999 - type: ndcg_at_3 value: 85.126 - type: ndcg_at_5 value: 85.992 - type: precision_at_1 value: 81.113 - type: precision_at_10 value: 10.35 - type: precision_at_100 value: 1.102 - type: precision_at_1000 value: 0.11399999999999999 - type: precision_at_20 value: 5.281000000000001 - type: precision_at_3 value: 32.543 - type: precision_at_5 value: 20.150000000000002 - type: recall_at_1 value: 74.727 - type: recall_at_10 value: 92.93 - type: recall_at_100 value: 96.122 - type: recall_at_1000 value: 97.722 - type: recall_at_20 value: 94.038 - type: recall_at_3 value: 88.785 - type: recall_at_5 value: 91.143 - task: type: Retrieval dataset: name: MTEB FEVER (default) type: mteb/fever config: default split: test revision: bea83ef9e8fb933d90a2f1d5515737465d613e12 metrics: - type: main_score value: 85.319 - type: map_at_1 value: 72.161 - type: map_at_10 value: 81.238 - type: map_at_100 value: 81.46 - type: map_at_1000 value: 81.473 - type: map_at_20 value: 81.365 - type: map_at_3 value: 80.01599999999999 - type: map_at_5 value: 80.857 - type: mrr_at_1 value: 77.93279327932792 - type: mrr_at_10 value: 85.94110601536343 - type: mrr_at_100 value: 86.02247464267394 - type: mrr_at_1000 value: 86.02424083776694 - type: mrr_at_20 value: 85.99713844897458 - type: mrr_at_3 value: 85.10351035103511 - type: mrr_at_5 value: 85.74182418241824 - type: nauc_map_at_1000_diff1 value: 48.87942532850865 - type: nauc_map_at_1000_max value: 19.207999873933872 - type: nauc_map_at_1000_std value: -6.426739011393975 - type: nauc_map_at_100_diff1 value: 48.844165528106586 - type: nauc_map_at_100_max value: 19.19923211737889 - type: nauc_map_at_100_std value: -6.413953838280856 - type: nauc_map_at_10_diff1 value: 48.66909865150514 - type: nauc_map_at_10_max value: 19.08422286721995 - type: nauc_map_at_10_std value: -6.550612019706119 - type: nauc_map_at_1_diff1 value: 52.38347452384079 - type: nauc_map_at_1_max value: 15.321152180069644 - type: nauc_map_at_1_std value: -9.404483536334594 - type: nauc_map_at_20_diff1 value: 48.75447470976026 - type: nauc_map_at_20_max value: 19.146566952856375 - type: nauc_map_at_20_std value: -6.433993868501403 - type: nauc_map_at_3_diff1 value: 48.848389883387796 - type: nauc_map_at_3_max value: 18.375903836766348 - type: nauc_map_at_3_std value: -8.115547043380014 - type: nauc_map_at_5_diff1 value: 48.45908591701036 - type: nauc_map_at_5_max value: 18.91547083095089 - type: nauc_map_at_5_std value: -7.0216129648180345 - type: nauc_mrr_at_1000_diff1 value: 61.86764697591185 - type: nauc_mrr_at_1000_max value: 23.37259724729802 - type: nauc_mrr_at_1000_std value: -11.240785012446858 - type: nauc_mrr_at_100_diff1 value: 61.86299894038223 - type: nauc_mrr_at_100_max value: 23.377993723874425 - type: nauc_mrr_at_100_std value: -11.234547507145425 - type: nauc_mrr_at_10_diff1 value: 61.89745030747914 - type: nauc_mrr_at_10_max value: 23.51179181879897 - type: nauc_mrr_at_10_std value: -11.21542754410092 - type: nauc_mrr_at_1_diff1 value: 62.87718289404487 - type: nauc_mrr_at_1_max value: 20.036585845650016 - type: nauc_mrr_at_1_std value: -11.824468808796672 - type: nauc_mrr_at_20_diff1 value: 61.87965159241426 - type: nauc_mrr_at_20_max value: 23.46555093254262 - type: nauc_mrr_at_20_std value: -11.184929381359039 - type: nauc_mrr_at_3_diff1 value: 61.96154941592062 - type: nauc_mrr_at_3_max value: 23.30622207138397 - type: nauc_mrr_at_3_std value: -12.526039371134765 - type: nauc_mrr_at_5_diff1 value: 61.71707334295513 - type: nauc_mrr_at_5_max value: 23.5270336630759 - type: nauc_mrr_at_5_std value: -11.623135779913035 - type: nauc_ndcg_at_1000_diff1 value: 50.409731512636114 - type: nauc_ndcg_at_1000_max value: 21.65102021635264 - type: nauc_ndcg_at_1000_std value: -4.92217385213998 - type: nauc_ndcg_at_100_diff1 value: 49.61567352404278 - type: nauc_ndcg_at_100_max value: 21.66920626618109 - type: nauc_ndcg_at_100_std value: -4.449124212637381 - type: nauc_ndcg_at_10_diff1 value: 48.92696345322944 - type: nauc_ndcg_at_10_max value: 21.43134916536533 - type: nauc_ndcg_at_10_std value: -4.875245880370844 - type: nauc_ndcg_at_1_diff1 value: 62.87718289404487 - type: nauc_ndcg_at_1_max value: 20.036585845650016 - type: nauc_ndcg_at_1_std value: -11.824468808796672 - type: nauc_ndcg_at_20_diff1 value: 49.11732939114983 - type: nauc_ndcg_at_20_max value: 21.599262409124997 - type: nauc_ndcg_at_20_std value: -4.420171263096915 - type: nauc_ndcg_at_3_diff1 value: 50.45116917733788 - type: nauc_ndcg_at_3_max value: 20.80003117781856 - type: nauc_ndcg_at_3_std value: -8.452770588263899 - type: nauc_ndcg_at_5_diff1 value: 48.748106275538724 - type: nauc_ndcg_at_5_max value: 21.211994383559222 - type: nauc_ndcg_at_5_std value: -6.225634212256297 - type: nauc_precision_at_1000_diff1 value: -2.65994713494688 - type: nauc_precision_at_1000_max value: 9.355224820997055 - type: nauc_precision_at_1000_std value: 6.93245511496358 - type: nauc_precision_at_100_diff1 value: -4.855736259082823 - type: nauc_precision_at_100_max value: 13.36331723677647 - type: nauc_precision_at_100_std value: 11.902586270338599 - type: nauc_precision_at_10_diff1 value: 3.216750400462425 - type: nauc_precision_at_10_max value: 21.25636976697531 - type: nauc_precision_at_10_std value: 12.137963028905675 - type: nauc_precision_at_1_diff1 value: 62.87718289404487 - type: nauc_precision_at_1_max value: 20.036585845650016 - type: nauc_precision_at_1_std value: -11.824468808796672 - type: nauc_precision_at_20_diff1 value: -1.4118811423454232 - type: nauc_precision_at_20_max value: 18.692537535200373 - type: nauc_precision_at_20_std value: 14.30532206890571 - type: nauc_precision_at_3_diff1 value: 30.339371349812698 - type: nauc_precision_at_3_max value: 26.408309865804767 - type: nauc_precision_at_3_std value: -4.0916660664063365 - type: nauc_precision_at_5_diff1 value: 12.879323748381793 - type: nauc_precision_at_5_max value: 25.69174163377847 - type: nauc_precision_at_5_std value: 6.093421699798719 - type: nauc_recall_at_1000_diff1 value: 12.273439585549289 - type: nauc_recall_at_1000_max value: 36.35356580077124 - type: nauc_recall_at_1000_std value: 48.56058221377234 - type: nauc_recall_at_100_diff1 value: 11.024787894935523 - type: nauc_recall_at_100_max value: 32.31032622508141 - type: nauc_recall_at_100_std value: 37.7793363899341 - type: nauc_recall_at_10_diff1 value: 23.70968015354158 - type: nauc_recall_at_10_max value: 26.928818056185793 - type: nauc_recall_at_10_std value: 15.603934216247126 - type: nauc_recall_at_1_diff1 value: 52.38347452384079 - type: nauc_recall_at_1_max value: 15.321152180069644 - type: nauc_recall_at_1_std value: -9.404483536334594 - type: nauc_recall_at_20_diff1 value: 19.803465715185133 - type: nauc_recall_at_20_max value: 29.156847915934563 - type: nauc_recall_at_20_std value: 23.60980197996787 - type: nauc_recall_at_3_diff1 value: 36.64320565102789 - type: nauc_recall_at_3_max value: 21.36937034204157 - type: nauc_recall_at_3_std value: -4.728003775515406 - type: nauc_recall_at_5_diff1 value: 27.617739447790917 - type: nauc_recall_at_5_max value: 24.241178855068966 - type: nauc_recall_at_5_std value: 4.7483438956009385 - type: ndcg_at_1 value: 77.93299999999999 - type: ndcg_at_10 value: 85.319 - type: ndcg_at_100 value: 86.13300000000001 - type: ndcg_at_1000 value: 86.378 - type: ndcg_at_20 value: 85.668 - type: ndcg_at_3 value: 83.41 - type: ndcg_at_5 value: 84.61999999999999 - type: precision_at_1 value: 77.93299999999999 - type: precision_at_10 value: 10.318 - type: precision_at_100 value: 1.095 - type: precision_at_1000 value: 0.11299999999999999 - type: precision_at_20 value: 5.2620000000000005 - type: precision_at_3 value: 32.063 - type: precision_at_5 value: 20.009 - type: recall_at_1 value: 72.161 - type: recall_at_10 value: 93.195 - type: recall_at_100 value: 96.455 - type: recall_at_1000 value: 97.98400000000001 - type: recall_at_20 value: 94.405 - type: recall_at_3 value: 88.061 - type: recall_at_5 value: 91.149 - task: type: Retrieval dataset: name: MTEB FEVER (default) type: mteb/fever config: default split: train revision: bea83ef9e8fb933d90a2f1d5515737465d613e12 metrics: - type: main_score value: 86.26899999999999 - type: map_at_1 value: 72.449 - type: map_at_10 value: 82.03 - type: map_at_100 value: 82.296 - type: map_at_1000 value: 82.314 - type: map_at_20 value: 82.186 - type: map_at_3 value: 80.83500000000001 - type: map_at_5 value: 81.623 - type: mrr_at_1 value: 80.61287678717785 - type: mrr_at_10 value: 88.20712760713671 - type: mrr_at_100 value: 88.2553288872469 - type: mrr_at_1000 value: 88.2557710463964 - type: mrr_at_20 value: 88.24322934725306 - type: mrr_at_3 value: 87.53498467049145 - type: mrr_at_5 value: 88.02728956075644 - type: nauc_map_at_1000_diff1 value: 39.95106411898475 - type: nauc_map_at_1000_max value: 9.654728508229924 - type: nauc_map_at_1000_std value: -12.151917182587324 - type: nauc_map_at_100_diff1 value: 39.90468852636486 - type: nauc_map_at_100_max value: 9.63167786931566 - type: nauc_map_at_100_std value: -12.13835017665434 - type: nauc_map_at_10_diff1 value: 39.46904405606303 - type: nauc_map_at_10_max value: 9.325543240387914 - type: nauc_map_at_10_std value: -12.262834163465582 - type: nauc_map_at_1_diff1 value: 45.26755146712848 - type: nauc_map_at_1_max value: 7.630523437842046 - type: nauc_map_at_1_std value: -13.605176488921838 - type: nauc_map_at_20_diff1 value: 39.66853756850951 - type: nauc_map_at_20_max value: 9.466678245833826 - type: nauc_map_at_20_std value: -12.1759657705622 - type: nauc_map_at_3_diff1 value: 39.50530889629205 - type: nauc_map_at_3_max value: 8.935845976271647 - type: nauc_map_at_3_std value: -13.490923397297127 - type: nauc_map_at_5_diff1 value: 39.30464767323601 - type: nauc_map_at_5_max value: 9.171957030191257 - type: nauc_map_at_5_std value: -12.606276076261402 - type: nauc_mrr_at_1000_diff1 value: 61.318394082054084 - type: nauc_mrr_at_1000_max value: 13.942830061515366 - type: nauc_mrr_at_1000_std value: -23.553800119123004 - type: nauc_mrr_at_100_diff1 value: 61.31872034357897 - type: nauc_mrr_at_100_max value: 13.94419608612362 - type: nauc_mrr_at_100_std value: -23.553055204470468 - type: nauc_mrr_at_10_diff1 value: 61.31278822068778 - type: nauc_mrr_at_10_max value: 14.031207581756833 - type: nauc_mrr_at_10_std value: -23.584266855456125 - type: nauc_mrr_at_1_diff1 value: 62.02492634987989 - type: nauc_mrr_at_1_max value: 12.426103478237204 - type: nauc_mrr_at_1_std value: -21.462128885638194 - type: nauc_mrr_at_20_diff1 value: 61.315947046589194 - type: nauc_mrr_at_20_max value: 13.974382096839708 - type: nauc_mrr_at_20_std value: -23.54265969965065 - type: nauc_mrr_at_3_diff1 value: 61.15068247478852 - type: nauc_mrr_at_3_max value: 14.166286324555182 - type: nauc_mrr_at_3_std value: -24.539638368220956 - type: nauc_mrr_at_5_diff1 value: 61.27021769164674 - type: nauc_mrr_at_5_max value: 14.18154187157247 - type: nauc_mrr_at_5_std value: -23.86452902597003 - type: nauc_ndcg_at_1000_diff1 value: 42.33233119047479 - type: nauc_ndcg_at_1000_max value: 11.565331883315682 - type: nauc_ndcg_at_1000_std value: -12.178748604304223 - type: nauc_ndcg_at_100_diff1 value: 41.37693942834703 - type: nauc_ndcg_at_100_max value: 11.328077098906448 - type: nauc_ndcg_at_100_std value: -11.65003452480089 - type: nauc_ndcg_at_10_diff1 value: 39.766907902897806 - type: nauc_ndcg_at_10_max value: 10.419530131217563 - type: nauc_ndcg_at_10_std value: -12.020911860422277 - type: nauc_ndcg_at_1_diff1 value: 62.02492634987989 - type: nauc_ndcg_at_1_max value: 12.426103478237204 - type: nauc_ndcg_at_1_std value: -21.462128885638194 - type: nauc_ndcg_at_20_diff1 value: 40.21705035603188 - type: nauc_ndcg_at_20_max value: 10.683814012195125 - type: nauc_ndcg_at_20_std value: -11.69979166757856 - type: nauc_ndcg_at_3_diff1 value: 41.841810239951 - type: nauc_ndcg_at_3_max value: 11.064226884457492 - type: nauc_ndcg_at_3_std value: -14.913305538472887 - type: nauc_ndcg_at_5_diff1 value: 40.04853934119725 - type: nauc_ndcg_at_5_max value: 10.57426706775158 - type: nauc_ndcg_at_5_std value: -13.00820458664088 - type: nauc_precision_at_1000_diff1 value: 0.3851195665415394 - type: nauc_precision_at_1000_max value: 10.719664087222139 - type: nauc_precision_at_1000_std value: 4.060546631755005 - type: nauc_precision_at_100_diff1 value: -1.1672675937708246 - type: nauc_precision_at_100_max value: 11.76706994923555 - type: nauc_precision_at_100_std value: 6.682502752333491 - type: nauc_precision_at_10_diff1 value: -2.442502050324997 - type: nauc_precision_at_10_max value: 9.982032022937407 - type: nauc_precision_at_10_std value: 2.253707666893988 - type: nauc_precision_at_1_diff1 value: 62.02492634987989 - type: nauc_precision_at_1_max value: 12.426103478237204 - type: nauc_precision_at_1_std value: -21.462128885638194 - type: nauc_precision_at_20_diff1 value: -2.8909153065947506 - type: nauc_precision_at_20_max value: 10.381422532792685 - type: nauc_precision_at_20_std value: 4.880699672256141 - type: nauc_precision_at_3_diff1 value: 13.983067176933947 - type: nauc_precision_at_3_max value: 11.941084260114476 - type: nauc_precision_at_3_std value: -12.615897998044437 - type: nauc_precision_at_5_diff1 value: 2.6828558906895688 - type: nauc_precision_at_5_max value: 10.78931350518598 - type: nauc_precision_at_5_std value: -3.6318676409745203 - type: nauc_recall_at_1000_diff1 value: -8.672439956073752 - type: nauc_recall_at_1000_max value: 23.244662839438533 - type: nauc_recall_at_1000_std value: 40.18478080701204 - type: nauc_recall_at_100_diff1 value: -4.465450402228265 - type: nauc_recall_at_100_max value: 15.424894718754112 - type: nauc_recall_at_100_std value: 28.33923562045188 - type: nauc_recall_at_10_diff1 value: 5.824940232374557 - type: nauc_recall_at_10_max value: 9.55369331654998 - type: nauc_recall_at_10_std value: 8.705857917052512 - type: nauc_recall_at_1_diff1 value: 45.26755146712848 - type: nauc_recall_at_1_max value: 7.630523437842046 - type: nauc_recall_at_1_std value: -13.605176488921838 - type: nauc_recall_at_20_diff1 value: 1.1759544592030455 - type: nauc_recall_at_20_max value: 10.197822183591066 - type: nauc_recall_at_20_std value: 15.269883968698228 - type: nauc_recall_at_3_diff1 value: 21.902162866702668 - type: nauc_recall_at_3_max value: 9.183669197010431 - type: nauc_recall_at_3_std value: -8.694680120818228 - type: nauc_recall_at_5_diff1 value: 13.653229973783526 - type: nauc_recall_at_5_max value: 9.716681689699136 - type: nauc_recall_at_5_std value: -0.2880989596678906 - type: ndcg_at_1 value: 80.613 - type: ndcg_at_10 value: 86.26899999999999 - type: ndcg_at_100 value: 87.12100000000001 - type: ndcg_at_1000 value: 87.40299999999999 - type: ndcg_at_20 value: 86.651 - type: ndcg_at_3 value: 84.64500000000001 - type: ndcg_at_5 value: 85.59 - type: precision_at_1 value: 80.613 - type: precision_at_10 value: 10.763 - type: precision_at_100 value: 1.16 - type: precision_at_1000 value: 0.121 - type: precision_at_20 value: 5.525 - type: precision_at_3 value: 33.415 - type: precision_at_5 value: 20.808 - type: recall_at_1 value: 72.449 - type: recall_at_10 value: 93.29899999999999 - type: recall_at_100 value: 96.421 - type: recall_at_1000 value: 98.053 - type: recall_at_20 value: 94.53200000000001 - type: recall_at_3 value: 88.594 - type: recall_at_5 value: 91.268 - task: type: Retrieval dataset: name: MTEB FiQA2018 (default) type: mteb/fiqa config: default split: dev revision: 27a168819829fe9bcd655c2df245fb19452e8e06 metrics: - type: main_score value: 42.362 - type: map_at_1 value: 22.462 - type: map_at_10 value: 34.717999999999996 - type: map_at_100 value: 36.561 - type: map_at_1000 value: 36.716 - type: map_at_20 value: 35.716 - type: map_at_3 value: 30.692000000000004 - type: map_at_5 value: 32.553 - type: mrr_at_1 value: 40.400000000000006 - type: mrr_at_10 value: 49.666428571428575 - type: mrr_at_100 value: 50.487418944361295 - type: mrr_at_1000 value: 50.51970264235359 - type: mrr_at_20 value: 50.13681738969665 - type: mrr_at_3 value: 47.56666666666667 - type: mrr_at_5 value: 48.85666666666666 - type: nauc_map_at_1000_diff1 value: 48.907747941693266 - type: nauc_map_at_1000_max value: 33.36065026293396 - type: nauc_map_at_1000_std value: 3.721763378995018 - type: nauc_map_at_100_diff1 value: 48.84727756808333 - type: nauc_map_at_100_max value: 33.24694910436772 - type: nauc_map_at_100_std value: 3.697147651138032 - type: nauc_map_at_10_diff1 value: 49.12331607215452 - type: nauc_map_at_10_max value: 32.834495636560405 - type: nauc_map_at_10_std value: 1.842046947246096 - type: nauc_map_at_1_diff1 value: 55.677889443633454 - type: nauc_map_at_1_max value: 29.14429236432774 - type: nauc_map_at_1_std value: -6.340931692625591 - type: nauc_map_at_20_diff1 value: 48.94402984571876 - type: nauc_map_at_20_max value: 32.97842670695263 - type: nauc_map_at_20_std value: 2.719721699786715 - type: nauc_map_at_3_diff1 value: 50.345833937052284 - type: nauc_map_at_3_max value: 30.884637973451046 - type: nauc_map_at_3_std value: -1.7032612225578052 - type: nauc_map_at_5_diff1 value: 49.4967472092422 - type: nauc_map_at_5_max value: 32.04823415779001 - type: nauc_map_at_5_std value: 0.11348259159930259 - type: nauc_mrr_at_1000_diff1 value: 53.4664833188161 - type: nauc_mrr_at_1000_max value: 43.94130528629785 - type: nauc_mrr_at_1000_std value: 6.3073911252297625 - type: nauc_mrr_at_100_diff1 value: 53.45784380239337 - type: nauc_mrr_at_100_max value: 43.93103386484263 - type: nauc_mrr_at_100_std value: 6.326857176825003 - type: nauc_mrr_at_10_diff1 value: 53.16999005935199 - type: nauc_mrr_at_10_max value: 43.96148608534777 - type: nauc_mrr_at_10_std value: 6.060709004613991 - type: nauc_mrr_at_1_diff1 value: 60.454425921819976 - type: nauc_mrr_at_1_max value: 44.854772426097114 - type: nauc_mrr_at_1_std value: 1.7461856169787138 - type: nauc_mrr_at_20_diff1 value: 53.4253064364276 - type: nauc_mrr_at_20_max value: 43.93067697716607 - type: nauc_mrr_at_20_std value: 6.132078452692403 - type: nauc_mrr_at_3_diff1 value: 53.75537772130037 - type: nauc_mrr_at_3_max value: 43.612665358637784 - type: nauc_mrr_at_3_std value: 5.3924645903759165 - type: nauc_mrr_at_5_diff1 value: 53.23878310443892 - type: nauc_mrr_at_5_max value: 44.154494509820275 - type: nauc_mrr_at_5_std value: 6.128619405551008 - type: nauc_ndcg_at_1000_diff1 value: 48.74084938103878 - type: nauc_ndcg_at_1000_max value: 38.28143671294916 - type: nauc_ndcg_at_1000_std value: 9.48205302587039 - type: nauc_ndcg_at_100_diff1 value: 47.86688156492628 - type: nauc_ndcg_at_100_max value: 36.73585329637074 - type: nauc_ndcg_at_100_std value: 9.886842243260414 - type: nauc_ndcg_at_10_diff1 value: 47.874511239978354 - type: nauc_ndcg_at_10_max value: 35.7706902177999 - type: nauc_ndcg_at_10_std value: 5.509978475259395 - type: nauc_ndcg_at_1_diff1 value: 60.454425921819976 - type: nauc_ndcg_at_1_max value: 44.854772426097114 - type: nauc_ndcg_at_1_std value: 1.7461856169787138 - type: nauc_ndcg_at_20_diff1 value: 47.98814179482003 - type: nauc_ndcg_at_20_max value: 35.80004813629657 - type: nauc_ndcg_at_20_std value: 6.632931898598267 - type: nauc_ndcg_at_3_diff1 value: 48.153795894304174 - type: nauc_ndcg_at_3_max value: 36.28196005109544 - type: nauc_ndcg_at_3_std value: 2.793405120536969 - type: nauc_ndcg_at_5_diff1 value: 47.88157624782777 - type: nauc_ndcg_at_5_max value: 35.8935279838606 - type: nauc_ndcg_at_5_std value: 4.0533111045329955 - type: nauc_precision_at_1000_diff1 value: -2.8869159343467605 - type: nauc_precision_at_1000_max value: 21.13113140923961 - type: nauc_precision_at_1000_std value: 24.212722433897408 - type: nauc_precision_at_100_diff1 value: 1.1594774420038931 - type: nauc_precision_at_100_max value: 22.26831206413967 - type: nauc_precision_at_100_std value: 29.81314341287538 - type: nauc_precision_at_10_diff1 value: 16.05087694540557 - type: nauc_precision_at_10_max value: 29.809963401808616 - type: nauc_precision_at_10_std value: 19.84954878024915 - type: nauc_precision_at_1_diff1 value: 60.454425921819976 - type: nauc_precision_at_1_max value: 44.854772426097114 - type: nauc_precision_at_1_std value: 1.7461856169787138 - type: nauc_precision_at_20_diff1 value: 9.748587851192008 - type: nauc_precision_at_20_max value: 26.594687094795994 - type: nauc_precision_at_20_std value: 24.150090984390086 - type: nauc_precision_at_3_diff1 value: 32.12647129845763 - type: nauc_precision_at_3_max value: 38.608852867058395 - type: nauc_precision_at_3_std value: 10.859746017200495 - type: nauc_precision_at_5_diff1 value: 23.827901543995793 - type: nauc_precision_at_5_max value: 35.67460349135147 - type: nauc_precision_at_5_std value: 15.9392352657892 - type: nauc_recall_at_1000_diff1 value: 35.2270895294026 - type: nauc_recall_at_1000_max value: 42.19353048661261 - type: nauc_recall_at_1000_std value: 38.04743729975647 - type: nauc_recall_at_100_diff1 value: 30.40548686084564 - type: nauc_recall_at_100_max value: 25.92198350281053 - type: nauc_recall_at_100_std value: 26.42423804923528 - type: nauc_recall_at_10_diff1 value: 36.90410693124825 - type: nauc_recall_at_10_max value: 28.372843635416388 - type: nauc_recall_at_10_std value: 7.8175786831627905 - type: nauc_recall_at_1_diff1 value: 55.677889443633454 - type: nauc_recall_at_1_max value: 29.14429236432774 - type: nauc_recall_at_1_std value: -6.340931692625591 - type: nauc_recall_at_20_diff1 value: 35.99767274556454 - type: nauc_recall_at_20_max value: 27.04852589764223 - type: nauc_recall_at_20_std value: 11.072120738834073 - type: nauc_recall_at_3_diff1 value: 41.25393288041596 - type: nauc_recall_at_3_max value: 26.97488751275594 - type: nauc_recall_at_3_std value: 0.21950460796902102 - type: nauc_recall_at_5_diff1 value: 38.26235012673011 - type: nauc_recall_at_5_max value: 28.830247312497054 - type: nauc_recall_at_5_std value: 4.072132303371853 - type: ndcg_at_1 value: 40.400000000000006 - type: ndcg_at_10 value: 42.362 - type: ndcg_at_100 value: 48.982 - type: ndcg_at_1000 value: 51.581999999999994 - type: ndcg_at_20 value: 44.937 - type: ndcg_at_3 value: 38.922000000000004 - type: ndcg_at_5 value: 39.596 - type: precision_at_1 value: 40.400000000000006 - type: precision_at_10 value: 11.18 - type: precision_at_100 value: 1.796 - type: precision_at_1000 value: 0.22300000000000003 - type: precision_at_20 value: 6.710000000000001 - type: precision_at_3 value: 24.532999999999998 - type: precision_at_5 value: 17.52 - type: recall_at_1 value: 22.462 - type: recall_at_10 value: 49.382999999999996 - type: recall_at_100 value: 74.494 - type: recall_at_1000 value: 90.427 - type: recall_at_20 value: 57.524 - type: recall_at_3 value: 36.028999999999996 - type: recall_at_5 value: 41.089 - task: type: Retrieval dataset: name: MTEB FiQA2018 (default) type: mteb/fiqa config: default split: test revision: 27a168819829fe9bcd655c2df245fb19452e8e06 metrics: - type: main_score value: 40.558 - type: map_at_1 value: 20.451 - type: map_at_10 value: 33.041 - type: map_at_100 value: 34.945 - type: map_at_1000 value: 35.136 - type: map_at_20 value: 34.114 - type: map_at_3 value: 29.03 - type: map_at_5 value: 31.423000000000002 - type: mrr_at_1 value: 39.50617283950617 - type: mrr_at_10 value: 48.47491671565746 - type: mrr_at_100 value: 49.25528865170789 - type: mrr_at_1000 value: 49.30492546288068 - type: mrr_at_20 value: 48.90574296444466 - type: mrr_at_3 value: 46.16769547325103 - type: mrr_at_5 value: 47.47170781893004 - type: nauc_map_at_1000_diff1 value: 42.33223793532006 - type: nauc_map_at_1000_max value: 28.178269647825054 - type: nauc_map_at_1000_std value: 4.694684846288862 - type: nauc_map_at_100_diff1 value: 42.23585502790571 - type: nauc_map_at_100_max value: 28.09325262656699 - type: nauc_map_at_100_std value: 4.635779769876692 - type: nauc_map_at_10_diff1 value: 42.29892463032549 - type: nauc_map_at_10_max value: 26.885463946159042 - type: nauc_map_at_10_std value: 3.439834407388629 - type: nauc_map_at_1_diff1 value: 48.29160916418846 - type: nauc_map_at_1_max value: 20.558365030918516 - type: nauc_map_at_1_std value: -0.44854024391070973 - type: nauc_map_at_20_diff1 value: 42.1753422786911 - type: nauc_map_at_20_max value: 27.631926253435857 - type: nauc_map_at_20_std value: 4.002081405774815 - type: nauc_map_at_3_diff1 value: 44.56188133973965 - type: nauc_map_at_3_max value: 25.936921564225862 - type: nauc_map_at_3_std value: 2.3757170812866804 - type: nauc_map_at_5_diff1 value: 43.183022909231234 - type: nauc_map_at_5_max value: 26.115662732325145 - type: nauc_map_at_5_std value: 2.584799983984164 - type: nauc_mrr_at_1000_diff1 value: 49.90329578326087 - type: nauc_mrr_at_1000_max value: 35.86029877981383 - type: nauc_mrr_at_1000_std value: 6.305323054154965 - type: nauc_mrr_at_100_diff1 value: 49.86929948930004 - type: nauc_mrr_at_100_max value: 35.850698951924386 - type: nauc_mrr_at_100_std value: 6.3311346338729 - type: nauc_mrr_at_10_diff1 value: 49.943023388207195 - type: nauc_mrr_at_10_max value: 35.98541218521815 - type: nauc_mrr_at_10_std value: 6.0382083805515805 - type: nauc_mrr_at_1_diff1 value: 53.793790143858146 - type: nauc_mrr_at_1_max value: 33.46215151905759 - type: nauc_mrr_at_1_std value: 4.310648959342706 - type: nauc_mrr_at_20_diff1 value: 49.78255203343183 - type: nauc_mrr_at_20_max value: 35.67982988010112 - type: nauc_mrr_at_20_std value: 6.097005492945753 - type: nauc_mrr_at_3_diff1 value: 50.78094748778293 - type: nauc_mrr_at_3_max value: 36.31047156376032 - type: nauc_mrr_at_3_std value: 5.551964274549184 - type: nauc_mrr_at_5_diff1 value: 50.22070037219334 - type: nauc_mrr_at_5_max value: 35.82391876186752 - type: nauc_mrr_at_5_std value: 5.989440675787551 - type: nauc_ndcg_at_1000_diff1 value: 43.29067795693791 - type: nauc_ndcg_at_1000_max value: 32.770853091465156 - type: nauc_ndcg_at_1000_std value: 9.075882750305011 - type: nauc_ndcg_at_100_diff1 value: 41.92437892838288 - type: nauc_ndcg_at_100_max value: 31.977508922932984 - type: nauc_ndcg_at_100_std value: 9.345565382601217 - type: nauc_ndcg_at_10_diff1 value: 41.86314487224504 - type: nauc_ndcg_at_10_max value: 29.565216296817827 - type: nauc_ndcg_at_10_std value: 5.173875408923697 - type: nauc_ndcg_at_1_diff1 value: 53.793790143858146 - type: nauc_ndcg_at_1_max value: 33.46215151905759 - type: nauc_ndcg_at_1_std value: 4.310648959342706 - type: nauc_ndcg_at_20_diff1 value: 41.426074027410706 - type: nauc_ndcg_at_20_max value: 30.01328944145506 - type: nauc_ndcg_at_20_std value: 6.169601231532484 - type: nauc_ndcg_at_3_diff1 value: 44.27395561376024 - type: nauc_ndcg_at_3_max value: 31.503088046380313 - type: nauc_ndcg_at_3_std value: 5.208532778972112 - type: nauc_ndcg_at_5_diff1 value: 42.81322677405853 - type: nauc_ndcg_at_5_max value: 29.407079874158846 - type: nauc_ndcg_at_5_std value: 4.483826520898586 - type: nauc_precision_at_1000_diff1 value: 1.621703595454423 - type: nauc_precision_at_1000_max value: 23.880102194550204 - type: nauc_precision_at_1000_std value: 13.80100184324797 - type: nauc_precision_at_100_diff1 value: 6.575602396019008 - type: nauc_precision_at_100_max value: 28.264948074327478 - type: nauc_precision_at_100_std value: 17.684872532407283 - type: nauc_precision_at_10_diff1 value: 16.8328055869745 - type: nauc_precision_at_10_max value: 30.24323560145753 - type: nauc_precision_at_10_std value: 11.304688858560379 - type: nauc_precision_at_1_diff1 value: 53.793790143858146 - type: nauc_precision_at_1_max value: 33.46215151905759 - type: nauc_precision_at_1_std value: 4.310648959342706 - type: nauc_precision_at_20_diff1 value: 12.904056330326577 - type: nauc_precision_at_20_max value: 28.969423687460438 - type: nauc_precision_at_20_std value: 12.029389701897678 - type: nauc_precision_at_3_diff1 value: 31.1308248469768 - type: nauc_precision_at_3_max value: 33.86869420849858 - type: nauc_precision_at_3_std value: 8.474707630694647 - type: nauc_precision_at_5_diff1 value: 23.15042207925308 - type: nauc_precision_at_5_max value: 29.597450076869325 - type: nauc_precision_at_5_std value: 9.148285720232177 - type: nauc_recall_at_1000_diff1 value: 30.844750307544324 - type: nauc_recall_at_1000_max value: 30.58773950265899 - type: nauc_recall_at_1000_std value: 35.28925560349968 - type: nauc_recall_at_100_diff1 value: 24.148211328845242 - type: nauc_recall_at_100_max value: 26.79994369269315 - type: nauc_recall_at_100_std value: 24.218335174944343 - type: nauc_recall_at_10_diff1 value: 28.95261846685996 - type: nauc_recall_at_10_max value: 22.666727959324515 - type: nauc_recall_at_10_std value: 5.513769892416629 - type: nauc_recall_at_1_diff1 value: 48.29160916418846 - type: nauc_recall_at_1_max value: 20.558365030918516 - type: nauc_recall_at_1_std value: -0.44854024391070973 - type: nauc_recall_at_20_diff1 value: 26.837633000701228 - type: nauc_recall_at_20_max value: 22.535529588484504 - type: nauc_recall_at_20_std value: 8.42648285205937 - type: nauc_recall_at_3_diff1 value: 38.25026260610774 - type: nauc_recall_at_3_max value: 25.050690202547578 - type: nauc_recall_at_3_std value: 3.1080253121438766 - type: nauc_recall_at_5_diff1 value: 34.50423249642314 - type: nauc_recall_at_5_max value: 22.85592363545583 - type: nauc_recall_at_5_std value: 3.640758629683203 - type: ndcg_at_1 value: 39.506 - type: ndcg_at_10 value: 40.558 - type: ndcg_at_100 value: 47.247 - type: ndcg_at_1000 value: 50.437 - type: ndcg_at_20 value: 43.162 - type: ndcg_at_3 value: 37.261 - type: ndcg_at_5 value: 38.391999999999996 - type: precision_at_1 value: 39.506 - type: precision_at_10 value: 11.142000000000001 - type: precision_at_100 value: 1.813 - type: precision_at_1000 value: 0.23600000000000002 - type: precision_at_20 value: 6.7589999999999995 - type: precision_at_3 value: 25.051000000000002 - type: precision_at_5 value: 18.395 - type: recall_at_1 value: 20.451 - type: recall_at_10 value: 46.79 - type: recall_at_100 value: 71.353 - type: recall_at_1000 value: 90.536 - type: recall_at_20 value: 54.517 - type: recall_at_3 value: 33.672000000000004 - type: recall_at_5 value: 39.678999999999995 - task: type: Retrieval dataset: name: MTEB FiQA2018 (default) type: mteb/fiqa config: default split: train revision: 27a168819829fe9bcd655c2df245fb19452e8e06 metrics: - type: main_score value: 42.217 - type: map_at_1 value: 21.418 - type: map_at_10 value: 34.437 - type: map_at_100 value: 36.254999999999995 - type: map_at_1000 value: 36.424 - type: map_at_20 value: 35.449999999999996 - type: map_at_3 value: 30.122 - type: map_at_5 value: 32.46 - type: mrr_at_1 value: 40.21818181818182 - type: mrr_at_10 value: 49.078658008658 - type: mrr_at_100 value: 49.9159011457498 - type: mrr_at_1000 value: 49.956067513298244 - type: mrr_at_20 value: 49.59237755036657 - type: mrr_at_3 value: 46.62424242424243 - type: mrr_at_5 value: 48.02424242424242 - type: nauc_map_at_1000_diff1 value: 40.17457855495732 - type: nauc_map_at_1000_max value: 25.311659240262102 - type: nauc_map_at_1000_std value: 5.059430044056764 - type: nauc_map_at_100_diff1 value: 40.151268380342515 - type: nauc_map_at_100_max value: 25.21648990114121 - type: nauc_map_at_100_std value: 5.026493196551854 - type: nauc_map_at_10_diff1 value: 40.040465022431576 - type: nauc_map_at_10_max value: 24.355474347016965 - type: nauc_map_at_10_std value: 3.5640713532110886 - type: nauc_map_at_1_diff1 value: 44.23533684826564 - type: nauc_map_at_1_max value: 16.26051705102941 - type: nauc_map_at_1_std value: -0.9304514636140965 - type: nauc_map_at_20_diff1 value: 40.07253921544327 - type: nauc_map_at_20_max value: 24.840445695825426 - type: nauc_map_at_20_std value: 4.3692544013620225 - type: nauc_map_at_3_diff1 value: 40.802965930319765 - type: nauc_map_at_3_max value: 21.578173190568766 - type: nauc_map_at_3_std value: 0.6624363947378223 - type: nauc_map_at_5_diff1 value: 40.41105488775194 - type: nauc_map_at_5_max value: 22.962784936768788 - type: nauc_map_at_5_std value: 2.061146134529408 - type: nauc_mrr_at_1000_diff1 value: 45.39271593141525 - type: nauc_mrr_at_1000_max value: 32.71504880799005 - type: nauc_mrr_at_1000_std value: 7.416955987371169 - type: nauc_mrr_at_100_diff1 value: 45.37668004444169 - type: nauc_mrr_at_100_max value: 32.71589234567116 - type: nauc_mrr_at_100_std value: 7.429449409497287 - type: nauc_mrr_at_10_diff1 value: 45.296174959712616 - type: nauc_mrr_at_10_max value: 32.717197303838624 - type: nauc_mrr_at_10_std value: 7.283098786281713 - type: nauc_mrr_at_1_diff1 value: 49.480470078543185 - type: nauc_mrr_at_1_max value: 31.68605495492876 - type: nauc_mrr_at_1_std value: 4.5814903060120304 - type: nauc_mrr_at_20_diff1 value: 45.36317431590108 - type: nauc_mrr_at_20_max value: 32.706079440239364 - type: nauc_mrr_at_20_std value: 7.382450020586175 - type: nauc_mrr_at_3_diff1 value: 46.001809326251454 - type: nauc_mrr_at_3_max value: 32.46816837141833 - type: nauc_mrr_at_3_std value: 6.707194036403839 - type: nauc_mrr_at_5_diff1 value: 45.46057942438407 - type: nauc_mrr_at_5_max value: 32.408646791629394 - type: nauc_mrr_at_5_std value: 7.11971218876357 - type: nauc_ndcg_at_1000_diff1 value: 40.315538048774236 - type: nauc_ndcg_at_1000_max value: 29.577764682607636 - type: nauc_ndcg_at_1000_std value: 9.802905608930201 - type: nauc_ndcg_at_100_diff1 value: 39.69359815845272 - type: nauc_ndcg_at_100_max value: 28.64875657558225 - type: nauc_ndcg_at_100_std value: 10.074769927489001 - type: nauc_ndcg_at_10_diff1 value: 39.42499828447507 - type: nauc_ndcg_at_10_max value: 27.18259534858955 - type: nauc_ndcg_at_10_std value: 6.306777798983758 - type: nauc_ndcg_at_1_diff1 value: 49.480470078543185 - type: nauc_ndcg_at_1_max value: 31.68605495492876 - type: nauc_ndcg_at_1_std value: 4.5814903060120304 - type: nauc_ndcg_at_20_diff1 value: 39.51807220300204 - type: nauc_ndcg_at_20_max value: 27.62717063554887 - type: nauc_ndcg_at_20_std value: 7.612068802546053 - type: nauc_ndcg_at_3_diff1 value: 41.04629803524383 - type: nauc_ndcg_at_3_max value: 27.84818206495344 - type: nauc_ndcg_at_3_std value: 4.828135065879767 - type: nauc_ndcg_at_5_diff1 value: 40.01813972950631 - type: nauc_ndcg_at_5_max value: 26.524741885273233 - type: nauc_ndcg_at_5_std value: 5.068529272139508 - type: nauc_precision_at_1000_diff1 value: 0.5470497141171098 - type: nauc_precision_at_1000_max value: 24.170306355297317 - type: nauc_precision_at_1000_std value: 18.50896415433208 - type: nauc_precision_at_100_diff1 value: 7.241268035021293 - type: nauc_precision_at_100_max value: 28.939185497818976 - type: nauc_precision_at_100_std value: 24.22708062648789 - type: nauc_precision_at_10_diff1 value: 18.067403140646473 - type: nauc_precision_at_10_max value: 33.44992314337708 - type: nauc_precision_at_10_std value: 16.388600267880083 - type: nauc_precision_at_1_diff1 value: 49.480470078543185 - type: nauc_precision_at_1_max value: 31.68605495492876 - type: nauc_precision_at_1_std value: 4.5814903060120304 - type: nauc_precision_at_20_diff1 value: 14.651721506297456 - type: nauc_precision_at_20_max value: 32.54709281419177 - type: nauc_precision_at_20_std value: 20.017505605751566 - type: nauc_precision_at_3_diff1 value: 30.04485384205624 - type: nauc_precision_at_3_max value: 34.145525798671464 - type: nauc_precision_at_3_std value: 9.385558743613709 - type: nauc_precision_at_5_diff1 value: 24.483639848034873 - type: nauc_precision_at_5_max value: 33.41057528286542 - type: nauc_precision_at_5_std value: 12.384466658411828 - type: nauc_recall_at_1000_diff1 value: 21.123402730271586 - type: nauc_recall_at_1000_max value: 26.29127489133915 - type: nauc_recall_at_1000_std value: 41.48297645436926 - type: nauc_recall_at_100_diff1 value: 23.190745050134876 - type: nauc_recall_at_100_max value: 20.96730541491135 - type: nauc_recall_at_100_std value: 24.579783248787745 - type: nauc_recall_at_10_diff1 value: 28.523056048729163 - type: nauc_recall_at_10_max value: 21.334211258862197 - type: nauc_recall_at_10_std value: 7.805738098876508 - type: nauc_recall_at_1_diff1 value: 44.23533684826564 - type: nauc_recall_at_1_max value: 16.26051705102941 - type: nauc_recall_at_1_std value: -0.9304514636140965 - type: nauc_recall_at_20_diff1 value: 27.256571523147745 - type: nauc_recall_at_20_max value: 21.103408026023196 - type: nauc_recall_at_20_std value: 11.445449145769603 - type: nauc_recall_at_3_diff1 value: 34.31934638156186 - type: nauc_recall_at_3_max value: 18.78403262209476 - type: nauc_recall_at_3_std value: 1.4901630112302768 - type: nauc_recall_at_5_diff1 value: 31.63689568492167 - type: nauc_recall_at_5_max value: 19.123482920636295 - type: nauc_recall_at_5_std value: 3.880507575208801 - type: ndcg_at_1 value: 40.217999999999996 - type: ndcg_at_10 value: 42.217 - type: ndcg_at_100 value: 48.762 - type: ndcg_at_1000 value: 51.63100000000001 - type: ndcg_at_20 value: 44.767 - type: ndcg_at_3 value: 38.057 - type: ndcg_at_5 value: 39.427 - type: precision_at_1 value: 40.217999999999996 - type: precision_at_10 value: 11.376 - type: precision_at_100 value: 1.815 - type: precision_at_1000 value: 0.232 - type: precision_at_20 value: 6.775 - type: precision_at_3 value: 24.812 - type: precision_at_5 value: 18.185000000000002 - type: recall_at_1 value: 21.418 - type: recall_at_10 value: 49.854 - type: recall_at_100 value: 74.37700000000001 - type: recall_at_1000 value: 91.72200000000001 - type: recall_at_20 value: 57.857 - type: recall_at_3 value: 35.221999999999994 - type: recall_at_5 value: 41.404999999999994 - task: type: Retrieval dataset: name: MTEB HotpotQA (default) type: mteb/hotpotqa config: default split: dev revision: ab518f4d6fcca38d87c25209f94beba119d02014 metrics: - type: main_score value: 74.175 - type: map_at_1 value: 41.041 - type: map_at_10 value: 66.31099999999999 - type: map_at_100 value: 67.104 - type: map_at_1000 value: 67.161 - type: map_at_20 value: 66.782 - type: map_at_3 value: 62.925 - type: map_at_5 value: 65.134 - type: mrr_at_1 value: 82.08187993390858 - type: mrr_at_10 value: 87.22340242626639 - type: mrr_at_100 value: 87.36059128975714 - type: mrr_at_1000 value: 87.364851053774 - type: mrr_at_20 value: 87.31789909538858 - type: mrr_at_3 value: 86.40842053729882 - type: mrr_at_5 value: 86.97478734471574 - type: nauc_map_at_1000_diff1 value: 15.036034548647908 - type: nauc_map_at_1000_max value: 25.75085303993812 - type: nauc_map_at_1000_std value: 17.465887392707984 - type: nauc_map_at_100_diff1 value: 15.005143661829045 - type: nauc_map_at_100_max value: 25.745125861339808 - type: nauc_map_at_100_std value: 17.504053167240222 - type: nauc_map_at_10_diff1 value: 14.893496342739656 - type: nauc_map_at_10_max value: 25.56792154122193 - type: nauc_map_at_10_std value: 17.09812367943331 - type: nauc_map_at_1_diff1 value: 69.96236855623434 - type: nauc_map_at_1_max value: 49.448851447506925 - type: nauc_map_at_1_std value: 2.889004800052033 - type: nauc_map_at_20_diff1 value: 14.907169096850453 - type: nauc_map_at_20_max value: 25.664564175861543 - type: nauc_map_at_20_std value: 17.43387597817089 - type: nauc_map_at_3_diff1 value: 14.819429540966336 - type: nauc_map_at_3_max value: 24.63784431578106 - type: nauc_map_at_3_std value: 13.51698248320979 - type: nauc_map_at_5_diff1 value: 14.793999397375302 - type: nauc_map_at_5_max value: 25.273543691930023 - type: nauc_map_at_5_std value: 15.528475200820887 - type: nauc_mrr_at_1000_diff1 value: 69.09310778251964 - type: nauc_mrr_at_1000_max value: 51.91323689768607 - type: nauc_mrr_at_1000_std value: 5.0427302617514265 - type: nauc_mrr_at_100_diff1 value: 69.08774366986974 - type: nauc_mrr_at_100_max value: 51.91649892721352 - type: nauc_mrr_at_100_std value: 5.055693527150247 - type: nauc_mrr_at_10_diff1 value: 69.04162799026531 - type: nauc_mrr_at_10_max value: 51.94707923303371 - type: nauc_mrr_at_10_std value: 5.073028039967743 - type: nauc_mrr_at_1_diff1 value: 69.96236855623434 - type: nauc_mrr_at_1_max value: 49.448851447506925 - type: nauc_mrr_at_1_std value: 2.889004800052033 - type: nauc_mrr_at_20_diff1 value: 69.07119075448549 - type: nauc_mrr_at_20_max value: 51.945891610724935 - type: nauc_mrr_at_20_std value: 5.120139371969651 - type: nauc_mrr_at_3_diff1 value: 69.04728116249032 - type: nauc_mrr_at_3_max value: 52.19716746949592 - type: nauc_mrr_at_3_std value: 4.455467076969271 - type: nauc_mrr_at_5_diff1 value: 68.99508759550626 - type: nauc_mrr_at_5_max value: 52.00068611382036 - type: nauc_mrr_at_5_std value: 4.853875045723172 - type: nauc_ndcg_at_1000_diff1 value: 21.56019247861624 - type: nauc_ndcg_at_1000_max value: 29.992075228189385 - type: nauc_ndcg_at_1000_std value: 19.52149913625525 - type: nauc_ndcg_at_100_diff1 value: 20.57182767444212 - type: nauc_ndcg_at_100_max value: 29.671296370713957 - type: nauc_ndcg_at_100_std value: 20.459885577163732 - type: nauc_ndcg_at_10_diff1 value: 19.899707356785555 - type: nauc_ndcg_at_10_max value: 28.92080969944076 - type: nauc_ndcg_at_10_std value: 18.985520950121536 - type: nauc_ndcg_at_1_diff1 value: 69.96236855623434 - type: nauc_ndcg_at_1_max value: 49.448851447506925 - type: nauc_ndcg_at_1_std value: 2.889004800052033 - type: nauc_ndcg_at_20_diff1 value: 19.817147184816825 - type: nauc_ndcg_at_20_max value: 29.10607440644831 - type: nauc_ndcg_at_20_std value: 20.055386680932457 - type: nauc_ndcg_at_3_diff1 value: 20.563849560253576 - type: nauc_ndcg_at_3_max value: 28.040961943107828 - type: nauc_ndcg_at_3_std value: 13.092847825660659 - type: nauc_ndcg_at_5_diff1 value: 19.974303695690292 - type: nauc_ndcg_at_5_max value: 28.543507472783176 - type: nauc_ndcg_at_5_std value: 15.984138613333693 - type: nauc_precision_at_1000_diff1 value: -3.673616783114865 - type: nauc_precision_at_1000_max value: 23.053922175840807 - type: nauc_precision_at_1000_std value: 49.11991772792811 - type: nauc_precision_at_100_diff1 value: -1.216591429661993 - type: nauc_precision_at_100_max value: 22.391264965682506 - type: nauc_precision_at_100_std value: 42.72424514027106 - type: nauc_precision_at_10_diff1 value: 3.616065203597004 - type: nauc_precision_at_10_max value: 21.983666160174664 - type: nauc_precision_at_10_std value: 29.4059520720441 - type: nauc_precision_at_1_diff1 value: 69.96236855623434 - type: nauc_precision_at_1_max value: 49.448851447506925 - type: nauc_precision_at_1_std value: 2.889004800052033 - type: nauc_precision_at_20_diff1 value: 1.0139909003288345 - type: nauc_precision_at_20_max value: 21.586196202262293 - type: nauc_precision_at_20_std value: 34.67062542720318 - type: nauc_precision_at_3_diff1 value: 8.864530763513228 - type: nauc_precision_at_3_max value: 22.75139236955371 - type: nauc_precision_at_3_std value: 15.906499760044241 - type: nauc_precision_at_5_diff1 value: 6.115146064055562 - type: nauc_precision_at_5_max value: 22.511552769119312 - type: nauc_precision_at_5_std value: 21.404838493866283 - type: nauc_recall_at_1000_diff1 value: -3.673616783114743 - type: nauc_recall_at_1000_max value: 23.053922175841222 - type: nauc_recall_at_1000_std value: 49.11991772792807 - type: nauc_recall_at_100_diff1 value: -1.2165914296620488 - type: nauc_recall_at_100_max value: 22.391264965682254 - type: nauc_recall_at_100_std value: 42.72424514027085 - type: nauc_recall_at_10_diff1 value: 3.6160652035968592 - type: nauc_recall_at_10_max value: 21.983666160174625 - type: nauc_recall_at_10_std value: 29.405952072043952 - type: nauc_recall_at_1_diff1 value: 69.96236855623434 - type: nauc_recall_at_1_max value: 49.448851447506925 - type: nauc_recall_at_1_std value: 2.889004800052033 - type: nauc_recall_at_20_diff1 value: 1.0139909003285874 - type: nauc_recall_at_20_max value: 21.586196202262176 - type: nauc_recall_at_20_std value: 34.67062542720296 - type: nauc_recall_at_3_diff1 value: 8.864530763513235 - type: nauc_recall_at_3_max value: 22.75139236955375 - type: nauc_recall_at_3_std value: 15.906499760044227 - type: nauc_recall_at_5_diff1 value: 6.115146064055457 - type: nauc_recall_at_5_max value: 22.51155276911919 - type: nauc_recall_at_5_std value: 21.404838493866148 - type: ndcg_at_1 value: 82.082 - type: ndcg_at_10 value: 74.175 - type: ndcg_at_100 value: 76.818 - type: ndcg_at_1000 value: 77.86999999999999 - type: ndcg_at_20 value: 75.324 - type: ndcg_at_3 value: 69.505 - type: ndcg_at_5 value: 72.25399999999999 - type: precision_at_1 value: 82.082 - type: precision_at_10 value: 15.459999999999999 - type: precision_at_100 value: 1.7500000000000002 - type: precision_at_1000 value: 0.189 - type: precision_at_20 value: 8.099 - type: precision_at_3 value: 44.696999999999996 - type: precision_at_5 value: 28.992 - type: recall_at_1 value: 41.041 - type: recall_at_10 value: 77.29899999999999 - type: recall_at_100 value: 87.516 - type: recall_at_1000 value: 94.428 - type: recall_at_20 value: 80.99 - type: recall_at_3 value: 67.04599999999999 - type: recall_at_5 value: 72.48 - task: type: Retrieval dataset: name: MTEB HotpotQA (default) type: mteb/hotpotqa config: default split: test revision: ab518f4d6fcca38d87c25209f94beba119d02014 metrics: - type: main_score value: 72.099 - type: map_at_1 value: 39.993 - type: map_at_10 value: 63.906 - type: map_at_100 value: 64.768 - type: map_at_1000 value: 64.825 - type: map_at_20 value: 64.434 - type: map_at_3 value: 60.428000000000004 - type: map_at_5 value: 62.65500000000001 - type: mrr_at_1 value: 79.9864956110736 - type: mrr_at_10 value: 85.597317342422 - type: mrr_at_100 value: 85.75538451417644 - type: mrr_at_1000 value: 85.76054586395492 - type: mrr_at_20 value: 85.70043434608681 - type: mrr_at_3 value: 84.7085302723385 - type: mrr_at_5 value: 85.3006977267612 - type: nauc_map_at_1000_diff1 value: 14.879240191611792 - type: nauc_map_at_1000_max value: 17.352504404367227 - type: nauc_map_at_1000_std value: 12.058834112176255 - type: nauc_map_at_100_diff1 value: 14.849169805835471 - type: nauc_map_at_100_max value: 17.33232999123778 - type: nauc_map_at_100_std value: 12.077792740295559 - type: nauc_map_at_10_diff1 value: 14.739688896718311 - type: nauc_map_at_10_max value: 17.22236218684584 - type: nauc_map_at_10_std value: 11.601003434736638 - type: nauc_map_at_1_diff1 value: 65.4983976623848 - type: nauc_map_at_1_max value: 42.1548067294384 - type: nauc_map_at_1_std value: -0.664907685382726 - type: nauc_map_at_20_diff1 value: 14.775964716898365 - type: nauc_map_at_20_max value: 17.28407185806239 - type: nauc_map_at_20_std value: 11.938629322344202 - type: nauc_map_at_3_diff1 value: 15.187257332075571 - type: nauc_map_at_3_max value: 16.50469797840979 - type: nauc_map_at_3_std value: 8.427502806629832 - type: nauc_map_at_5_diff1 value: 14.734331855452067 - type: nauc_map_at_5_max value: 16.996649506768556 - type: nauc_map_at_5_std value: 10.675417416580272 - type: nauc_mrr_at_1000_diff1 value: 64.77314045859816 - type: nauc_mrr_at_1000_max value: 45.07640869774897 - type: nauc_mrr_at_1000_std value: 1.1223707370777345 - type: nauc_mrr_at_100_diff1 value: 64.7736064468281 - type: nauc_mrr_at_100_max value: 45.081668625794045 - type: nauc_mrr_at_100_std value: 1.1301861065543417 - type: nauc_mrr_at_10_diff1 value: 64.7436125478473 - type: nauc_mrr_at_10_max value: 45.17530304621016 - type: nauc_mrr_at_10_std value: 1.1574487279881827 - type: nauc_mrr_at_1_diff1 value: 65.4983976623848 - type: nauc_mrr_at_1_max value: 42.1548067294384 - type: nauc_mrr_at_1_std value: -0.664907685382726 - type: nauc_mrr_at_20_diff1 value: 64.74897914048353 - type: nauc_mrr_at_20_max value: 45.10718259984782 - type: nauc_mrr_at_20_std value: 1.1414090900637834 - type: nauc_mrr_at_3_diff1 value: 64.66047914937114 - type: nauc_mrr_at_3_max value: 45.240654624502135 - type: nauc_mrr_at_3_std value: 0.6018871726391307 - type: nauc_mrr_at_5_diff1 value: 64.62465365659278 - type: nauc_mrr_at_5_max value: 45.26782758375944 - type: nauc_mrr_at_5_std value: 0.9729934670795005 - type: nauc_ndcg_at_1000_diff1 value: 20.735117506723284 - type: nauc_ndcg_at_1000_max value: 21.973730279574237 - type: nauc_ndcg_at_1000_std value: 14.435511069333268 - type: nauc_ndcg_at_100_diff1 value: 19.92424972281059 - type: nauc_ndcg_at_100_max value: 21.46124911457025 - type: nauc_ndcg_at_100_std value: 14.997278102074985 - type: nauc_ndcg_at_10_diff1 value: 19.482173354148614 - type: nauc_ndcg_at_10_max value: 21.057780839586314 - type: nauc_ndcg_at_10_std value: 13.183889323902614 - type: nauc_ndcg_at_1_diff1 value: 65.4983976623848 - type: nauc_ndcg_at_1_max value: 42.1548067294384 - type: nauc_ndcg_at_1_std value: -0.664907685382726 - type: nauc_ndcg_at_20_diff1 value: 19.492746981314262 - type: nauc_ndcg_at_20_max value: 21.17506677843973 - type: nauc_ndcg_at_20_std value: 14.226350927505344 - type: nauc_ndcg_at_3_diff1 value: 20.783583144063783 - type: nauc_ndcg_at_3_max value: 20.412720533103773 - type: nauc_ndcg_at_3_std value: 8.1573992813502 - type: nauc_ndcg_at_5_diff1 value: 19.678652006506965 - type: nauc_ndcg_at_5_max value: 20.797671396298504 - type: nauc_ndcg_at_5_std value: 11.325414041574488 - type: nauc_precision_at_1000_diff1 value: -10.450656807230294 - type: nauc_precision_at_1000_max value: 13.984468023954232 - type: nauc_precision_at_1000_std value: 47.62472479785625 - type: nauc_precision_at_100_diff1 value: -4.196473742286918 - type: nauc_precision_at_100_max value: 12.121665049576427 - type: nauc_precision_at_100_std value: 37.19008451156229 - type: nauc_precision_at_10_diff1 value: 3.061787271972301 - type: nauc_precision_at_10_max value: 14.242591133970839 - type: nauc_precision_at_10_std value: 22.61377683902424 - type: nauc_precision_at_1_diff1 value: 65.4983976623848 - type: nauc_precision_at_1_max value: 42.1548067294384 - type: nauc_precision_at_1_std value: -0.664907685382726 - type: nauc_precision_at_20_diff1 value: 0.6113817731563579 - type: nauc_precision_at_20_max value: 13.40678529536442 - type: nauc_precision_at_20_std value: 27.36583188393757 - type: nauc_precision_at_3_diff1 value: 9.006850832399767 - type: nauc_precision_at_3_max value: 14.709279058037167 - type: nauc_precision_at_3_std value: 11.083943561368818 - type: nauc_precision_at_5_diff1 value: 5.4640694491525785 - type: nauc_precision_at_5_max value: 14.534695725481427 - type: nauc_precision_at_5_std value: 17.261328831180144 - type: nauc_recall_at_1000_diff1 value: -10.45065680723015 - type: nauc_recall_at_1000_max value: 13.984468023954296 - type: nauc_recall_at_1000_std value: 47.624724797856494 - type: nauc_recall_at_100_diff1 value: -4.1964737422872425 - type: nauc_recall_at_100_max value: 12.121665049576311 - type: nauc_recall_at_100_std value: 37.19008451156221 - type: nauc_recall_at_10_diff1 value: 3.061787271972265 - type: nauc_recall_at_10_max value: 14.242591133970848 - type: nauc_recall_at_10_std value: 22.613776839024126 - type: nauc_recall_at_1_diff1 value: 65.4983976623848 - type: nauc_recall_at_1_max value: 42.1548067294384 - type: nauc_recall_at_1_std value: -0.664907685382726 - type: nauc_recall_at_20_diff1 value: 0.6113817731563769 - type: nauc_recall_at_20_max value: 13.406785295364488 - type: nauc_recall_at_20_std value: 27.365831883937688 - type: nauc_recall_at_3_diff1 value: 9.006850832399833 - type: nauc_recall_at_3_max value: 14.709279058037176 - type: nauc_recall_at_3_std value: 11.083943561368827 - type: nauc_recall_at_5_diff1 value: 5.464069449152512 - type: nauc_recall_at_5_max value: 14.534695725481386 - type: nauc_recall_at_5_std value: 17.261328831180222 - type: ndcg_at_1 value: 79.986 - type: ndcg_at_10 value: 72.099 - type: ndcg_at_100 value: 75.01100000000001 - type: ndcg_at_1000 value: 76.062 - type: ndcg_at_20 value: 73.38799999999999 - type: ndcg_at_3 value: 67.252 - type: ndcg_at_5 value: 70.03399999999999 - type: precision_at_1 value: 79.986 - type: precision_at_10 value: 15.084 - type: precision_at_100 value: 1.735 - type: precision_at_1000 value: 0.187 - type: precision_at_20 value: 7.957 - type: precision_at_3 value: 43.165 - type: precision_at_5 value: 28.097 - type: recall_at_1 value: 39.993 - type: recall_at_10 value: 75.422 - type: recall_at_100 value: 86.739 - type: recall_at_1000 value: 93.633 - type: recall_at_20 value: 79.57499999999999 - type: recall_at_3 value: 64.747 - type: recall_at_5 value: 70.243 - task: type: Retrieval dataset: name: MTEB HotpotQA (default) type: mteb/hotpotqa config: default split: train revision: ab518f4d6fcca38d87c25209f94beba119d02014 metrics: - type: main_score value: 74.675 - type: map_at_1 value: 41.071999999999996 - type: map_at_10 value: 66.92 - type: map_at_100 value: 67.723 - type: map_at_1000 value: 67.774 - type: map_at_20 value: 67.408 - type: map_at_3 value: 63.55499999999999 - type: map_at_5 value: 65.704 - type: mrr_at_1 value: 82.14470588235294 - type: mrr_at_10 value: 87.27400186741363 - type: mrr_at_100 value: 87.4140081509131 - type: mrr_at_1000 value: 87.41798363724548 - type: mrr_at_20 value: 87.36842561587122 - type: mrr_at_3 value: 86.50941176470587 - type: mrr_at_5 value: 87.00347058823529 - type: nauc_map_at_1000_diff1 value: 15.173631052534247 - type: nauc_map_at_1000_max value: 26.068735945434245 - type: nauc_map_at_1000_std value: 16.679793876109372 - type: nauc_map_at_100_diff1 value: 15.145622681798832 - type: nauc_map_at_100_max value: 26.05989713486766 - type: nauc_map_at_100_std value: 16.707010441285338 - type: nauc_map_at_10_diff1 value: 14.914638256007287 - type: nauc_map_at_10_max value: 25.882443097244483 - type: nauc_map_at_10_std value: 16.268808050707122 - type: nauc_map_at_1_diff1 value: 68.99857028038306 - type: nauc_map_at_1_max value: 49.44823319018734 - type: nauc_map_at_1_std value: 3.95480041595882 - type: nauc_map_at_20_diff1 value: 15.024824474002042 - type: nauc_map_at_20_max value: 25.979156549532394 - type: nauc_map_at_20_std value: 16.58495990193771 - type: nauc_map_at_3_diff1 value: 14.82922429946727 - type: nauc_map_at_3_max value: 24.94644740438124 - type: nauc_map_at_3_std value: 13.163454771602703 - type: nauc_map_at_5_diff1 value: 14.786835699591697 - type: nauc_map_at_5_max value: 25.4952477897668 - type: nauc_map_at_5_std value: 15.132801238151277 - type: nauc_mrr_at_1000_diff1 value: 68.01504171335921 - type: nauc_mrr_at_1000_max value: 51.87765517862451 - type: nauc_mrr_at_1000_std value: 6.86223778975253 - type: nauc_mrr_at_100_diff1 value: 68.01399006752484 - type: nauc_mrr_at_100_max value: 51.88280954265237 - type: nauc_mrr_at_100_std value: 6.873608557329335 - type: nauc_mrr_at_10_diff1 value: 67.99091321438537 - type: nauc_mrr_at_10_max value: 51.969521221681624 - type: nauc_mrr_at_10_std value: 6.931166148442037 - type: nauc_mrr_at_1_diff1 value: 68.99857028038306 - type: nauc_mrr_at_1_max value: 49.44823319018734 - type: nauc_mrr_at_1_std value: 3.95480041595882 - type: nauc_mrr_at_20_diff1 value: 68.01259861100158 - type: nauc_mrr_at_20_max value: 51.92347187092682 - type: nauc_mrr_at_20_std value: 6.916000236458142 - type: nauc_mrr_at_3_diff1 value: 67.78455056859933 - type: nauc_mrr_at_3_max value: 51.871123397467976 - type: nauc_mrr_at_3_std value: 6.43509345435153 - type: nauc_mrr_at_5_diff1 value: 67.90240615066607 - type: nauc_mrr_at_5_max value: 52.0124881495014 - type: nauc_mrr_at_5_std value: 6.803350773425626 - type: nauc_ndcg_at_1000_diff1 value: 21.69891416034566 - type: nauc_ndcg_at_1000_max value: 30.461957789834806 - type: nauc_ndcg_at_1000_std value: 19.18877840309474 - type: nauc_ndcg_at_100_diff1 value: 20.7970186296764 - type: nauc_ndcg_at_100_max value: 30.15224012992887 - type: nauc_ndcg_at_100_std value: 19.943169128048474 - type: nauc_ndcg_at_10_diff1 value: 19.84268006275167 - type: nauc_ndcg_at_10_max value: 29.484945625149916 - type: nauc_ndcg_at_10_std value: 18.258410671819046 - type: nauc_ndcg_at_1_diff1 value: 68.99857028038306 - type: nauc_ndcg_at_1_max value: 49.44823319018734 - type: nauc_ndcg_at_1_std value: 3.95480041595882 - type: nauc_ndcg_at_20_diff1 value: 20.04561491289907 - type: nauc_ndcg_at_20_max value: 29.693953898939768 - type: nauc_ndcg_at_20_std value: 19.236240432268765 - type: nauc_ndcg_at_3_diff1 value: 20.257610313097572 - type: nauc_ndcg_at_3_max value: 28.337695262101402 - type: nauc_ndcg_at_3_std value: 13.27057009577805 - type: nauc_ndcg_at_5_diff1 value: 19.813917540582832 - type: nauc_ndcg_at_5_max value: 28.898934488412642 - type: nauc_ndcg_at_5_std value: 16.037376675812613 - type: nauc_precision_at_1000_diff1 value: -2.7630728745432833 - type: nauc_precision_at_1000_max value: 24.273957339049858 - type: nauc_precision_at_1000_std value: 51.174814670874234 - type: nauc_precision_at_100_diff1 value: -0.3693685702558231 - type: nauc_precision_at_100_max value: 23.540054418358388 - type: nauc_precision_at_100_std value: 42.86307596340895 - type: nauc_precision_at_10_diff1 value: 3.839420261166957 - type: nauc_precision_at_10_max value: 23.33220436834566 - type: nauc_precision_at_10_std value: 27.497642027822938 - type: nauc_precision_at_1_diff1 value: 68.99857028038306 - type: nauc_precision_at_1_max value: 49.44823319018734 - type: nauc_precision_at_1_std value: 3.95480041595882 - type: nauc_precision_at_20_diff1 value: 2.149278982050884 - type: nauc_precision_at_20_max value: 23.225228919773492 - type: nauc_precision_at_20_std value: 32.583030590092996 - type: nauc_precision_at_3_diff1 value: 8.414263763743502 - type: nauc_precision_at_3_max value: 23.266556039522364 - type: nauc_precision_at_3_std value: 16.166789635561578 - type: nauc_precision_at_5_diff1 value: 6.100362067031837 - type: nauc_precision_at_5_max value: 23.317092657737902 - type: nauc_precision_at_5_std value: 21.439743834724506 - type: nauc_recall_at_1000_diff1 value: -2.763072874542946 - type: nauc_recall_at_1000_max value: 24.273957339050046 - type: nauc_recall_at_1000_std value: 51.17481467087451 - type: nauc_recall_at_100_diff1 value: -0.36936857025585346 - type: nauc_recall_at_100_max value: 23.54005441835819 - type: nauc_recall_at_100_std value: 42.86307596340905 - type: nauc_recall_at_10_diff1 value: 3.8394202611669916 - type: nauc_recall_at_10_max value: 23.332204368345536 - type: nauc_recall_at_10_std value: 27.497642027822835 - type: nauc_recall_at_1_diff1 value: 68.99857028038306 - type: nauc_recall_at_1_max value: 49.44823319018734 - type: nauc_recall_at_1_std value: 3.95480041595882 - type: nauc_recall_at_20_diff1 value: 2.1492789820506943 - type: nauc_recall_at_20_max value: 23.22522891977323 - type: nauc_recall_at_20_std value: 32.58303059009287 - type: nauc_recall_at_3_diff1 value: 8.414263763743387 - type: nauc_recall_at_3_max value: 23.266556039522314 - type: nauc_recall_at_3_std value: 16.166789635561496 - type: nauc_recall_at_5_diff1 value: 6.100362067031725 - type: nauc_recall_at_5_max value: 23.317092657737877 - type: nauc_recall_at_5_std value: 21.43974383472456 - type: ndcg_at_1 value: 82.145 - type: ndcg_at_10 value: 74.675 - type: ndcg_at_100 value: 77.35499999999999 - type: ndcg_at_1000 value: 78.31099999999999 - type: ndcg_at_20 value: 75.859 - type: ndcg_at_3 value: 70.056 - type: ndcg_at_5 value: 72.68900000000001 - type: precision_at_1 value: 82.145 - type: precision_at_10 value: 15.594 - type: precision_at_100 value: 1.7670000000000001 - type: precision_at_1000 value: 0.189 - type: precision_at_20 value: 8.177 - type: precision_at_3 value: 45.207 - type: precision_at_5 value: 29.199 - type: recall_at_1 value: 41.071999999999996 - type: recall_at_10 value: 77.968 - type: recall_at_100 value: 88.342 - type: recall_at_1000 value: 94.636 - type: recall_at_20 value: 81.768 - type: recall_at_3 value: 67.81099999999999 - type: recall_at_5 value: 72.99799999999999 - task: type: Classification dataset: name: MTEB ImdbClassification (default) type: mteb/imdb config: default split: test revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7 metrics: - type: accuracy value: 91.6404 - type: ap value: 88.06069266911989 - type: ap_weighted value: 88.06069266911989 - type: f1 value: 91.63447508338969 - type: f1_weighted value: 91.63447508338966 - type: main_score value: 91.6404 - task: type: Retrieval dataset: name: MTEB MSMARCO (default) type: mteb/msmarco config: default split: dev revision: c5a29a104738b98a9e76336939199e264163d4a0 metrics: - type: main_score value: 41.881 - type: map_at_1 value: 22.467000000000002 - type: map_at_10 value: 34.910999999999994 - type: map_at_100 value: 36.061 - type: map_at_1000 value: 36.108000000000004 - type: map_at_20 value: 35.624 - type: map_at_3 value: 30.941999999999997 - type: map_at_5 value: 33.263999999999996 - type: mrr_at_1 value: 23.08022922636103 - type: mrr_at_10 value: 35.50051735116205 - type: mrr_at_100 value: 36.59446189817308 - type: mrr_at_1000 value: 36.635988914583265 - type: mrr_at_20 value: 36.18253329805409 - type: mrr_at_3 value: 31.609360076408787 - type: mrr_at_5 value: 33.90305635148042 - type: nauc_map_at_1000_diff1 value: 35.55451924480011 - type: nauc_map_at_1000_max value: 3.3973484820380984 - type: nauc_map_at_1000_std value: -15.313643259934148 - type: nauc_map_at_100_diff1 value: 35.550804246990495 - type: nauc_map_at_100_max value: 3.399807661520924 - type: nauc_map_at_100_std value: -15.275642266336313 - type: nauc_map_at_10_diff1 value: 35.5782836837628 - type: nauc_map_at_10_max value: 3.2528940284048993 - type: nauc_map_at_10_std value: -15.969363396756405 - type: nauc_map_at_1_diff1 value: 38.48673772459152 - type: nauc_map_at_1_max value: 3.058447908569679 - type: nauc_map_at_1_std value: -14.963393022102997 - type: nauc_map_at_20_diff1 value: 35.51677537885897 - type: nauc_map_at_20_max value: 3.3515639340449725 - type: nauc_map_at_20_std value: -15.515763931018828 - type: nauc_map_at_3_diff1 value: 35.92227750150707 - type: nauc_map_at_3_max value: 2.8055574560079064 - type: nauc_map_at_3_std value: -16.880504853072285 - type: nauc_map_at_5_diff1 value: 35.55198639506613 - type: nauc_map_at_5_max value: 2.9586919269467526 - type: nauc_map_at_5_std value: -16.54701954101431 - type: nauc_mrr_at_1000_diff1 value: 35.431696643964436 - type: nauc_mrr_at_1000_max value: 3.413854144953113 - type: nauc_mrr_at_1000_std value: -15.142803785812797 - type: nauc_mrr_at_100_diff1 value: 35.426786864620986 - type: nauc_mrr_at_100_max value: 3.4171950444493935 - type: nauc_mrr_at_100_std value: -15.103678118737987 - type: nauc_mrr_at_10_diff1 value: 35.420624727408644 - type: nauc_mrr_at_10_max value: 3.322578167282073 - type: nauc_mrr_at_10_std value: -15.720250181753793 - type: nauc_mrr_at_1_diff1 value: 38.282779286642096 - type: nauc_mrr_at_1_max value: 2.9904752802636327 - type: nauc_mrr_at_1_std value: -15.138960622677649 - type: nauc_mrr_at_20_diff1 value: 35.38506376339875 - type: nauc_mrr_at_20_max value: 3.394154792664457 - type: nauc_mrr_at_20_std value: -15.296898873665988 - type: nauc_mrr_at_3_diff1 value: 35.7803854971965 - type: nauc_mrr_at_3_max value: 2.7546109667567733 - type: nauc_mrr_at_3_std value: -16.7760243616548 - type: nauc_mrr_at_5_diff1 value: 35.40507525930076 - type: nauc_mrr_at_5_max value: 2.968967051093017 - type: nauc_mrr_at_5_std value: -16.322983362913682 - type: nauc_ndcg_at_1000_diff1 value: 34.61165703664126 - type: nauc_ndcg_at_1000_max value: 4.2633988477939315 - type: nauc_ndcg_at_1000_std value: -13.07846493573677 - type: nauc_ndcg_at_100_diff1 value: 34.496098679488654 - type: nauc_ndcg_at_100_max value: 4.35416012374578 - type: nauc_ndcg_at_100_std value: -11.701820911709307 - type: nauc_ndcg_at_10_diff1 value: 34.510499084561594 - type: nauc_ndcg_at_10_max value: 3.7195988744787765 - type: nauc_ndcg_at_10_std value: -15.20204882975027 - type: nauc_ndcg_at_1_diff1 value: 38.282779286642096 - type: nauc_ndcg_at_1_max value: 2.9904752802636327 - type: nauc_ndcg_at_1_std value: -15.138960622677649 - type: nauc_ndcg_at_20_diff1 value: 34.28895557191255 - type: nauc_ndcg_at_20_max value: 4.078634149451336 - type: nauc_ndcg_at_20_std value: -13.495634934731186 - type: nauc_ndcg_at_3_diff1 value: 35.1825890111415 - type: nauc_ndcg_at_3_max value: 2.6899697916041787 - type: nauc_ndcg_at_3_std value: -17.3200148795559 - type: nauc_ndcg_at_5_diff1 value: 34.50553625093832 - type: nauc_ndcg_at_5_max value: 2.9886919040366453 - type: nauc_ndcg_at_5_std value: -16.682910398462134 - type: nauc_precision_at_1000_diff1 value: -5.237411685181927 - type: nauc_precision_at_1000_max value: 12.33197477512628 - type: nauc_precision_at_1000_std value: 14.624993194631372 - type: nauc_precision_at_100_diff1 value: 12.929312931181103 - type: nauc_precision_at_100_max value: 11.682654496612322 - type: nauc_precision_at_100_std value: 22.44127157890021 - type: nauc_precision_at_10_diff1 value: 28.260532585949555 - type: nauc_precision_at_10_max value: 5.053591117400416 - type: nauc_precision_at_10_std value: -11.685872129702071 - type: nauc_precision_at_1_diff1 value: 38.282779286642096 - type: nauc_precision_at_1_max value: 2.9904752802636327 - type: nauc_precision_at_1_std value: -15.138960622677649 - type: nauc_precision_at_20_diff1 value: 24.082555406455477 - type: nauc_precision_at_20_max value: 7.220785769786994 - type: nauc_precision_at_20_std value: -2.3466420348408876 - type: nauc_precision_at_3_diff1 value: 32.2680340644695 - type: nauc_precision_at_3_max value: 2.195269827644658 - type: nauc_precision_at_3_std value: -18.77340802819126 - type: nauc_precision_at_5_diff1 value: 30.01850058048678 - type: nauc_precision_at_5_max value: 3.0452445562886243 - type: nauc_precision_at_5_std value: -16.787002738887892 - type: nauc_recall_at_1000_diff1 value: 7.940551548703448 - type: nauc_recall_at_1000_max value: 40.70493639275526 - type: nauc_recall_at_1000_std value: 66.21346351313893 - type: nauc_recall_at_100_diff1 value: 26.395513427993123 - type: nauc_recall_at_100_max value: 13.850278277490382 - type: nauc_recall_at_100_std value: 31.262749365543495 - type: nauc_recall_at_10_diff1 value: 30.810510902525202 - type: nauc_recall_at_10_max value: 5.342768575463394 - type: nauc_recall_at_10_std value: -12.041087579697969 - type: nauc_recall_at_1_diff1 value: 38.48673772459152 - type: nauc_recall_at_1_max value: 3.058447908569679 - type: nauc_recall_at_1_std value: -14.963393022102997 - type: nauc_recall_at_20_diff1 value: 28.97941173115346 - type: nauc_recall_at_20_max value: 7.387302922786026 - type: nauc_recall_at_20_std value: -2.9701154270124537 - type: nauc_recall_at_3_diff1 value: 33.11138786633106 - type: nauc_recall_at_3_max value: 2.3972198714504103 - type: nauc_recall_at_3_std value: -18.444370167091602 - type: nauc_recall_at_5_diff1 value: 31.354710954894315 - type: nauc_recall_at_5_max value: 3.0409753924683227 - type: nauc_recall_at_5_std value: -17.003889653830544 - type: ndcg_at_1 value: 23.080000000000002 - type: ndcg_at_10 value: 41.881 - type: ndcg_at_100 value: 47.384 - type: ndcg_at_1000 value: 48.563 - type: ndcg_at_20 value: 44.394 - type: ndcg_at_3 value: 33.819 - type: ndcg_at_5 value: 37.951 - type: precision_at_1 value: 23.080000000000002 - type: precision_at_10 value: 6.619 - type: precision_at_100 value: 0.9369999999999999 - type: precision_at_1000 value: 0.104 - type: precision_at_20 value: 3.836 - type: precision_at_3 value: 14.350999999999999 - type: precision_at_5 value: 10.705 - type: recall_at_1 value: 22.467000000000002 - type: recall_at_10 value: 63.363 - type: recall_at_100 value: 88.73 - type: recall_at_1000 value: 97.726 - type: recall_at_20 value: 73.072 - type: recall_at_3 value: 41.464 - type: recall_at_5 value: 51.367 - task: type: Retrieval dataset: name: MTEB MSMARCO (default) type: mteb/msmarco config: default split: test revision: c5a29a104738b98a9e76336939199e264163d4a0 metrics: - type: main_score value: 69.895 - type: map_at_1 value: 2.386 - type: map_at_10 value: 15.517 - type: map_at_100 value: 40.755 - type: map_at_1000 value: 48.650999999999996 - type: map_at_20 value: 23.866 - type: map_at_3 value: 6.593999999999999 - type: map_at_5 value: 9.733 - type: mrr_at_1 value: 90.69767441860465 - type: mrr_at_10 value: 94.26356589147287 - type: mrr_at_100 value: 94.26356589147287 - type: mrr_at_1000 value: 94.26356589147287 - type: mrr_at_20 value: 94.26356589147287 - type: mrr_at_3 value: 93.7984496124031 - type: mrr_at_5 value: 94.26356589147287 - type: nauc_map_at_1000_diff1 value: -17.43619926664674 - type: nauc_map_at_1000_max value: 33.6129902421304 - type: nauc_map_at_1000_std value: 46.534866437148445 - type: nauc_map_at_100_diff1 value: -3.4235524401190065 - type: nauc_map_at_100_max value: 20.249118581525174 - type: nauc_map_at_100_std value: 21.211678002623337 - type: nauc_map_at_10_diff1 value: 19.868551667849278 - type: nauc_map_at_10_max value: -7.049880879841646 - type: nauc_map_at_10_std value: -15.401797310529073 - type: nauc_map_at_1_diff1 value: 33.37422645090001 - type: nauc_map_at_1_max value: -26.28998419171722 - type: nauc_map_at_1_std value: -28.696833028930623 - type: nauc_map_at_20_diff1 value: 16.721532586974828 - type: nauc_map_at_20_max value: 5.488066416387458 - type: nauc_map_at_20_std value: -4.928338561410316 - type: nauc_map_at_3_diff1 value: 26.596230178724362 - type: nauc_map_at_3_max value: -21.091821185844502 - type: nauc_map_at_3_std value: -27.931616241692335 - type: nauc_map_at_5_diff1 value: 26.503416309451893 - type: nauc_map_at_5_max value: -14.966431698877205 - type: nauc_map_at_5_std value: -24.92953418435822 - type: nauc_mrr_at_1000_diff1 value: 37.25735469680115 - type: nauc_mrr_at_1000_max value: 58.86319796354405 - type: nauc_mrr_at_1000_std value: 91.72535591220716 - type: nauc_mrr_at_100_diff1 value: 37.25735469680115 - type: nauc_mrr_at_100_max value: 58.86319796354405 - type: nauc_mrr_at_100_std value: 91.72535591220716 - type: nauc_mrr_at_10_diff1 value: 37.25735469680115 - type: nauc_mrr_at_10_max value: 58.86319796354405 - type: nauc_mrr_at_10_std value: 91.72535591220716 - type: nauc_mrr_at_1_diff1 value: 34.671850640708776 - type: nauc_mrr_at_1_max value: 51.21031217917046 - type: nauc_mrr_at_1_std value: 89.79460562505535 - type: nauc_mrr_at_20_diff1 value: 37.25735469680115 - type: nauc_mrr_at_20_max value: 58.86319796354405 - type: nauc_mrr_at_20_std value: 91.72535591220716 - type: nauc_mrr_at_3_diff1 value: 38.60957957843779 - type: nauc_mrr_at_3_max value: 60.97560743754536 - type: nauc_mrr_at_3_std value: 92.34595421879162 - type: nauc_mrr_at_5_diff1 value: 37.25735469680115 - type: nauc_mrr_at_5_max value: 58.86319796354405 - type: nauc_mrr_at_5_std value: 91.72535591220716 - type: nauc_ndcg_at_1000_diff1 value: -16.225938948928025 - type: nauc_ndcg_at_1000_max value: 55.89533466517005 - type: nauc_ndcg_at_1000_std value: 55.40479015862836 - type: nauc_ndcg_at_100_diff1 value: -4.2505692685100485 - type: nauc_ndcg_at_100_max value: 41.08810853075458 - type: nauc_ndcg_at_100_std value: 51.72941963551418 - type: nauc_ndcg_at_10_diff1 value: 0.747121732650285 - type: nauc_ndcg_at_10_max value: 39.232823971742405 - type: nauc_ndcg_at_10_std value: 30.231095222965937 - type: nauc_ndcg_at_1_diff1 value: 50.70351721984524 - type: nauc_ndcg_at_1_max value: 22.223151480238055 - type: nauc_ndcg_at_1_std value: -1.6981049298345798 - type: nauc_ndcg_at_20_diff1 value: -5.964227909058437 - type: nauc_ndcg_at_20_max value: 41.04081240965169 - type: nauc_ndcg_at_20_std value: 38.124111046791164 - type: nauc_ndcg_at_3_diff1 value: 22.642365636430505 - type: nauc_ndcg_at_3_max value: 36.65277646275841 - type: nauc_ndcg_at_3_std value: 13.807981639504055 - type: nauc_ndcg_at_5_diff1 value: 13.228770870517279 - type: nauc_ndcg_at_5_max value: 39.26501372019075 - type: nauc_ndcg_at_5_std value: 18.117117619727306 - type: nauc_precision_at_1000_diff1 value: -34.34396146066081 - type: nauc_precision_at_1000_max value: 25.35157697994365 - type: nauc_precision_at_1000_std value: 52.692463751897535 - type: nauc_precision_at_100_diff1 value: -34.59882373262441 - type: nauc_precision_at_100_max value: 30.38585569564875 - type: nauc_precision_at_100_std value: 55.39043613247343 - type: nauc_precision_at_10_diff1 value: -34.84065479839732 - type: nauc_precision_at_10_max value: 52.453330287918234 - type: nauc_precision_at_10_std value: 65.94589958566101 - type: nauc_precision_at_1_diff1 value: 34.671850640708776 - type: nauc_precision_at_1_max value: 51.21031217917046 - type: nauc_precision_at_1_std value: 89.79460562505535 - type: nauc_precision_at_20_diff1 value: -34.405502025386006 - type: nauc_precision_at_20_max value: 47.22465715601537 - type: nauc_precision_at_20_std value: 60.3767447367751 - type: nauc_precision_at_3_diff1 value: -7.395035257468793 - type: nauc_precision_at_3_max value: 62.69785319929072 - type: nauc_precision_at_3_std value: 67.15720558808125 - type: nauc_precision_at_5_diff1 value: -19.659532277774154 - type: nauc_precision_at_5_max value: 65.88294876723467 - type: nauc_precision_at_5_std value: 65.5071257264847 - type: nauc_recall_at_1000_diff1 value: -32.13151178260713 - type: nauc_recall_at_1000_max value: 49.599798672364024 - type: nauc_recall_at_1000_std value: 53.416414623207245 - type: nauc_recall_at_100_diff1 value: 2.2830012629669367 - type: nauc_recall_at_100_max value: 20.72697656877468 - type: nauc_recall_at_100_std value: 15.090940745210233 - type: nauc_recall_at_10_diff1 value: 19.967019350754683 - type: nauc_recall_at_10_max value: -10.459789162236417 - type: nauc_recall_at_10_std value: -18.89446359106782 - type: nauc_recall_at_1_diff1 value: 33.37422645090001 - type: nauc_recall_at_1_max value: -26.28998419171722 - type: nauc_recall_at_1_std value: -28.696833028930623 - type: nauc_recall_at_20_diff1 value: 17.31230551930378 - type: nauc_recall_at_20_max value: 3.20695402833611 - type: nauc_recall_at_20_std value: -8.361923242107272 - type: nauc_recall_at_3_diff1 value: 26.874491125503315 - type: nauc_recall_at_3_max value: -22.372781558886633 - type: nauc_recall_at_3_std value: -30.08475617025354 - type: nauc_recall_at_5_diff1 value: 26.425992230237465 - type: nauc_recall_at_5_max value: -17.053828088435072 - type: nauc_recall_at_5_std value: -27.797398066593537 - type: ndcg_at_1 value: 74.806 - type: ndcg_at_10 value: 69.895 - type: ndcg_at_100 value: 64.736 - type: ndcg_at_1000 value: 71.563 - type: ndcg_at_20 value: 67.916 - type: ndcg_at_3 value: 72.72800000000001 - type: ndcg_at_5 value: 72.298 - type: precision_at_1 value: 90.69800000000001 - type: precision_at_10 value: 78.605 - type: precision_at_100 value: 38.256 - type: precision_at_1000 value: 6.914 - type: precision_at_20 value: 70.814 - type: precision_at_3 value: 86.047 - type: precision_at_5 value: 84.651 - type: recall_at_1 value: 2.386 - type: recall_at_10 value: 16.739 - type: recall_at_100 value: 52.782 - type: recall_at_1000 value: 77.948 - type: recall_at_20 value: 26.564 - type: recall_at_3 value: 6.789000000000001 - type: recall_at_5 value: 10.192 - task: type: Retrieval dataset: name: MTEB MSMARCO (default) type: mteb/msmarco config: default split: train revision: c5a29a104738b98a9e76336939199e264163d4a0 metrics: - type: main_score value: 39.287 - type: map_at_1 value: 20.312 - type: map_at_10 value: 32.37 - type: map_at_100 value: 33.617999999999995 - type: map_at_1000 value: 33.667 - type: map_at_20 value: 33.141999999999996 - type: map_at_3 value: 28.419 - type: map_at_5 value: 30.677 - type: mrr_at_1 value: 20.88106112272065 - type: mrr_at_10 value: 32.88347561288713 - type: mrr_at_100 value: 34.079369127830056 - type: mrr_at_1000 value: 34.12286416716751 - type: mrr_at_20 value: 33.6284955497779 - type: mrr_at_3 value: 29.00577074622038 - type: mrr_at_5 value: 31.230424233024944 - type: nauc_map_at_1000_diff1 value: 34.02708673784959 - type: nauc_map_at_1000_max value: -0.13774596315365284 - type: nauc_map_at_1000_std value: -14.811669105922384 - type: nauc_map_at_100_diff1 value: 34.01930820880688 - type: nauc_map_at_100_max value: -0.1347868034897845 - type: nauc_map_at_100_std value: -14.772649407858864 - type: nauc_map_at_10_diff1 value: 33.96158417816836 - type: nauc_map_at_10_max value: -0.3136135162999447 - type: nauc_map_at_10_std value: -15.444045950700714 - type: nauc_map_at_1_diff1 value: 37.58205211162927 - type: nauc_map_at_1_max value: -0.4822908400800713 - type: nauc_map_at_1_std value: -15.470046110078922 - type: nauc_map_at_20_diff1 value: 33.98271018950918 - type: nauc_map_at_20_max value: -0.21381571255200063 - type: nauc_map_at_20_std value: -15.007378462657424 - type: nauc_map_at_3_diff1 value: 34.289832746358385 - type: nauc_map_at_3_max value: -0.5002033864794293 - type: nauc_map_at_3_std value: -16.202034438595152 - type: nauc_map_at_5_diff1 value: 34.00117071654728 - type: nauc_map_at_5_max value: -0.45851793692290926 - type: nauc_map_at_5_std value: -16.006184527594332 - type: nauc_mrr_at_1000_diff1 value: 33.984976772028844 - type: nauc_mrr_at_1000_max value: -0.1529354207124242 - type: nauc_mrr_at_1000_std value: -14.857766881343624 - type: nauc_mrr_at_100_diff1 value: 33.97715243824301 - type: nauc_mrr_at_100_max value: -0.14868509934664242 - type: nauc_mrr_at_100_std value: -14.819185948867908 - type: nauc_mrr_at_10_diff1 value: 33.9073996451901 - type: nauc_mrr_at_10_max value: -0.3117834117567206 - type: nauc_mrr_at_10_std value: -15.447133275926591 - type: nauc_mrr_at_1_diff1 value: 37.569117720003305 - type: nauc_mrr_at_1_max value: -0.4402285765126485 - type: nauc_mrr_at_1_std value: -15.610329778824116 - type: nauc_mrr_at_20_diff1 value: 33.93531912336384 - type: nauc_mrr_at_20_max value: -0.21832751838659756 - type: nauc_mrr_at_20_std value: -15.02826142229628 - type: nauc_mrr_at_3_diff1 value: 34.233342147328905 - type: nauc_mrr_at_3_max value: -0.48966505992824105 - type: nauc_mrr_at_3_std value: -16.24404416215297 - type: nauc_mrr_at_5_diff1 value: 33.936224279069286 - type: nauc_mrr_at_5_max value: -0.4505343004388219 - type: nauc_mrr_at_5_std value: -16.009358996271995 - type: nauc_ndcg_at_1000_diff1 value: 33.15636942116579 - type: nauc_ndcg_at_1000_max value: 0.7421529032280344 - type: nauc_ndcg_at_1000_std value: -12.573458200734184 - type: nauc_ndcg_at_100_diff1 value: 32.93005052778217 - type: nauc_ndcg_at_100_max value: 0.9174493718835769 - type: nauc_ndcg_at_100_std value: -11.171269358523292 - type: nauc_ndcg_at_10_diff1 value: 32.702296942276526 - type: nauc_ndcg_at_10_max value: -0.09434815260748751 - type: nauc_ndcg_at_10_std value: -14.584325513499733 - type: nauc_ndcg_at_1_diff1 value: 37.58713933791024 - type: nauc_ndcg_at_1_max value: -0.4513949591167018 - type: nauc_ndcg_at_1_std value: -15.609650942411912 - type: nauc_ndcg_at_20_diff1 value: 32.73010631865281 - type: nauc_ndcg_at_20_max value: 0.28286295130856637 - type: nauc_ndcg_at_20_std value: -12.91199724170651 - type: nauc_ndcg_at_3_diff1 value: 33.376023670753284 - type: nauc_ndcg_at_3_max value: -0.5120382325774017 - type: nauc_ndcg_at_3_std value: -16.37620688280034 - type: nauc_ndcg_at_5_diff1 value: 32.84453673758015 - type: nauc_ndcg_at_5_max value: -0.4424535321329695 - type: nauc_ndcg_at_5_std value: -15.986073718543075 - type: nauc_precision_at_1000_diff1 value: -2.05172207477867 - type: nauc_precision_at_1000_max value: 11.420451556771813 - type: nauc_precision_at_1000_std value: 13.013500055223338 - type: nauc_precision_at_100_diff1 value: 14.09591129638288 - type: nauc_precision_at_100_max value: 10.301532890390265 - type: nauc_precision_at_100_std value: 21.262673040909597 - type: nauc_precision_at_10_diff1 value: 26.861179153662277 - type: nauc_precision_at_10_max value: 0.9328475133208457 - type: nauc_precision_at_10_std value: -10.923443610237937 - type: nauc_precision_at_1_diff1 value: 37.58713933791024 - type: nauc_precision_at_1_max value: -0.4513949591167018 - type: nauc_precision_at_1_std value: -15.609650942411912 - type: nauc_precision_at_20_diff1 value: 24.328515569316732 - type: nauc_precision_at_20_max value: 2.876122000952972 - type: nauc_precision_at_20_std value: -2.33467622450143 - type: nauc_precision_at_3_diff1 value: 30.578927129819753 - type: nauc_precision_at_3_max value: -0.42632757194706555 - type: nauc_precision_at_3_std value: -16.788412743765186 - type: nauc_precision_at_5_diff1 value: 28.78020642240962 - type: nauc_precision_at_5_max value: -0.2124025605546784 - type: nauc_precision_at_5_std value: -15.67344805195943 - type: nauc_recall_at_1000_diff1 value: 14.944369342374936 - type: nauc_recall_at_1000_max value: 46.83432685416887 - type: nauc_recall_at_1000_std value: 69.28042589318784 - type: nauc_recall_at_100_diff1 value: 24.745870493773193 - type: nauc_recall_at_100_max value: 13.558884583015281 - type: nauc_recall_at_100_std value: 31.59926593228638 - type: nauc_recall_at_10_diff1 value: 28.564011002637212 - type: nauc_recall_at_10_max value: 0.6794665651327308 - type: nauc_recall_at_10_std value: -11.184026264546878 - type: nauc_recall_at_1_diff1 value: 37.58205211162927 - type: nauc_recall_at_1_max value: -0.4822908400800713 - type: nauc_recall_at_1_std value: -15.470046110078922 - type: nauc_recall_at_20_diff1 value: 27.72144102460605 - type: nauc_recall_at_20_max value: 2.6132011820945884 - type: nauc_recall_at_20_std value: -2.461755722295994 - type: nauc_recall_at_3_diff1 value: 30.958109485805675 - type: nauc_recall_at_3_max value: -0.5576168684477084 - type: nauc_recall_at_3_std value: -16.72079877980838 - type: nauc_recall_at_5_diff1 value: 29.588704776525393 - type: nauc_recall_at_5_max value: -0.4055192968984154 - type: nauc_recall_at_5_std value: -15.750524291373111 - type: ndcg_at_1 value: 20.877000000000002 - type: ndcg_at_10 value: 39.287 - type: ndcg_at_100 value: 45.316 - type: ndcg_at_1000 value: 46.52 - type: ndcg_at_20 value: 42.028999999999996 - type: ndcg_at_3 value: 31.233 - type: ndcg_at_5 value: 35.259 - type: precision_at_1 value: 20.877000000000002 - type: precision_at_10 value: 6.327000000000001 - type: precision_at_100 value: 0.9329999999999999 - type: precision_at_1000 value: 0.104 - type: precision_at_20 value: 3.7310000000000003 - type: precision_at_3 value: 13.379 - type: precision_at_5 value: 10.065 - type: recall_at_1 value: 20.312 - type: recall_at_10 value: 60.748999999999995 - type: recall_at_100 value: 88.682 - type: recall_at_1000 value: 97.867 - type: recall_at_20 value: 71.411 - type: recall_at_3 value: 38.800000000000004 - type: recall_at_5 value: 48.483 - task: type: Classification dataset: name: MTEB MTOPDomainClassification (en) type: mteb/mtop_domain config: en split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 93.18741450068397 - type: f1 value: 93.0238595381845 - type: f1_weighted value: 93.17789324951269 - type: main_score value: 93.18741450068397 - task: type: Classification dataset: name: MTEB MTOPDomainClassification (en) type: mteb/mtop_domain config: en split: validation revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 93.05145413870247 - type: f1 value: 92.99732266407732 - type: f1_weighted value: 93.02588804838254 - type: main_score value: 93.05145413870247 - task: type: Classification dataset: name: MTEB MTOPIntentClassification (en) type: mteb/mtop_intent config: en split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 67.33470132238944 - type: f1 value: 48.97680766700152 - type: f1_weighted value: 69.63742750869805 - type: main_score value: 67.33470132238944 - task: type: Classification dataset: name: MTEB MTOPIntentClassification (en) type: mteb/mtop_intent config: en split: validation revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 67.76733780760627 - type: f1 value: 48.841507782489195 - type: f1_weighted value: 70.48620980474442 - type: main_score value: 67.76733780760627 - task: type: Classification dataset: name: MTEB MassiveIntentClassification (en) type: mteb/amazon_massive_intent config: en split: test revision: 4672e20407010da34463acc759c162ca9734bca6 metrics: - type: accuracy value: 72.4310692669805 - type: f1 value: 70.33600790276014 - type: f1_weighted value: 71.41893477886055 - type: main_score value: 72.4310692669805 - task: type: Classification dataset: name: MTEB MassiveIntentClassification (en) type: mteb/amazon_massive_intent config: en split: validation revision: 4672e20407010da34463acc759c162ca9734bca6 metrics: - type: accuracy value: 73.4284308903099 - type: f1 value: 69.55956726857646 - type: f1_weighted value: 72.15631882777167 - type: main_score value: 73.4284308903099 - task: type: Classification dataset: name: MTEB MassiveScenarioClassification (en) type: mteb/amazon_massive_scenario config: en split: test revision: fad2c6e8459f9e1c45d9315f4953d921437d70f8 metrics: - type: accuracy value: 76.78883658372561 - type: f1 value: 76.32136975183587 - type: f1_weighted value: 76.595264995014 - type: main_score value: 76.78883658372561 - task: type: Classification dataset: name: MTEB MassiveScenarioClassification (en) type: mteb/amazon_massive_scenario config: en split: validation revision: fad2c6e8459f9e1c45d9315f4953d921437d70f8 metrics: - type: accuracy value: 77.03885882931628 - type: f1 value: 76.31184523539754 - type: f1_weighted value: 76.88960030513515 - type: main_score value: 77.03885882931628 - task: type: Clustering dataset: name: MTEB MedrxivClusteringP2P (default) type: mteb/medrxiv-clustering-p2p config: default split: test revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73 metrics: - type: main_score value: 33.095522581541175 - type: v_measure value: 33.095522581541175 - type: v_measure_std value: 1.2733644358152183 - task: type: Clustering dataset: name: MTEB MedrxivClusteringS2S (default) type: mteb/medrxiv-clustering-s2s config: default split: test revision: 35191c8c0dca72d8ff3efcd72aa802307d469663 metrics: - type: main_score value: 31.06849440193581 - type: v_measure value: 31.06849440193581 - type: v_measure_std value: 1.6047314419984595 - task: type: Reranking dataset: name: MTEB MindSmallReranking (default) type: mteb/mind_small config: default split: test revision: 59042f120c80e8afa9cdbb224f67076cec0fc9a7 metrics: - type: main_score value: 31.29908728873086 - type: map value: 31.29908728873086 - type: mrr value: 32.39123019117521 - type: nAUC_map_diff1 value: 13.066848043751357 - type: nAUC_map_max value: -21.421847351002597 - type: nAUC_map_std value: -1.6918937775056007 - type: nAUC_mrr_diff1 value: 12.280185578076129 - type: nAUC_mrr_max value: -16.139433517987133 - type: nAUC_mrr_std value: -0.23907632474680363 - task: type: Retrieval dataset: name: MTEB NFCorpus (default) type: mteb/nfcorpus config: default split: test revision: ec0fa4fe99da2ff19ca1214b7966684033a58814 metrics: - type: main_score value: 35.509 - type: map_at_1 value: 5.508 - type: map_at_10 value: 13.014999999999999 - type: map_at_100 value: 16.342000000000002 - type: map_at_1000 value: 17.797 - type: map_at_20 value: 14.456 - type: map_at_3 value: 9.363000000000001 - type: map_at_5 value: 11.064 - type: mrr_at_1 value: 45.51083591331269 - type: mrr_at_10 value: 54.5795862204531 - type: mrr_at_100 value: 55.07630032637193 - type: mrr_at_1000 value: 55.127586714933805 - type: mrr_at_20 value: 54.90781971103837 - type: mrr_at_3 value: 52.32198142414861 - type: mrr_at_5 value: 53.74613003095975 - type: nauc_map_at_1000_diff1 value: 24.501330360153915 - type: nauc_map_at_1000_max value: 33.06045409371139 - type: nauc_map_at_1000_std value: 19.95230416435316 - type: nauc_map_at_100_diff1 value: 25.806053286220532 - type: nauc_map_at_100_max value: 31.933709402264153 - type: nauc_map_at_100_std value: 15.842452059972015 - type: nauc_map_at_10_diff1 value: 29.890503647724593 - type: nauc_map_at_10_max value: 25.92830734236527 - type: nauc_map_at_10_std value: 3.6250471128132804 - type: nauc_map_at_1_diff1 value: 50.389087879996865 - type: nauc_map_at_1_max value: 20.95986174718729 - type: nauc_map_at_1_std value: -5.41570803338871 - type: nauc_map_at_20_diff1 value: 27.444531905945162 - type: nauc_map_at_20_max value: 28.660078098188745 - type: nauc_map_at_20_std value: 8.44788718797198 - type: nauc_map_at_3_diff1 value: 37.92764614538618 - type: nauc_map_at_3_max value: 20.65857273684232 - type: nauc_map_at_3_std value: -6.143600629025448 - type: nauc_map_at_5_diff1 value: 34.81301402702416 - type: nauc_map_at_5_max value: 23.1193138262864 - type: nauc_map_at_5_std value: -1.7057107446005662 - type: nauc_mrr_at_1000_diff1 value: 28.19968199215303 - type: nauc_mrr_at_1000_max value: 46.82195714140159 - type: nauc_mrr_at_1000_std value: 31.68998255433254 - type: nauc_mrr_at_100_diff1 value: 28.23773638204092 - type: nauc_mrr_at_100_max value: 46.867704940087 - type: nauc_mrr_at_100_std value: 31.72723785491753 - type: nauc_mrr_at_10_diff1 value: 28.235449464678208 - type: nauc_mrr_at_10_max value: 46.757000930146255 - type: nauc_mrr_at_10_std value: 31.38607887979623 - type: nauc_mrr_at_1_diff1 value: 30.395863641073404 - type: nauc_mrr_at_1_max value: 39.14603700466295 - type: nauc_mrr_at_1_std value: 22.81299502437437 - type: nauc_mrr_at_20_diff1 value: 28.26836846663423 - type: nauc_mrr_at_20_max value: 46.71036119122077 - type: nauc_mrr_at_20_std value: 31.717717995472462 - type: nauc_mrr_at_3_diff1 value: 27.677977469638744 - type: nauc_mrr_at_3_max value: 46.281885617180905 - type: nauc_mrr_at_3_std value: 29.971954604398306 - type: nauc_mrr_at_5_diff1 value: 28.002295498470435 - type: nauc_mrr_at_5_max value: 46.24599903705559 - type: nauc_mrr_at_5_std value: 30.64406412426167 - type: nauc_ndcg_at_1000_diff1 value: 23.52189648298028 - type: nauc_ndcg_at_1000_max value: 48.84815340128893 - type: nauc_ndcg_at_1000_std value: 38.191275632053504 - type: nauc_ndcg_at_100_diff1 value: 24.241636067072005 - type: nauc_ndcg_at_100_max value: 44.044030318408616 - type: nauc_ndcg_at_100_std value: 33.08892120061157 - type: nauc_ndcg_at_10_diff1 value: 19.38875035508853 - type: nauc_ndcg_at_10_max value: 39.741010776186656 - type: nauc_ndcg_at_10_std value: 31.608748238315908 - type: nauc_ndcg_at_1_diff1 value: 31.62521740234213 - type: nauc_ndcg_at_1_max value: 37.777292135533955 - type: nauc_ndcg_at_1_std value: 23.13720120267271 - type: nauc_ndcg_at_20_diff1 value: 21.084936669355745 - type: nauc_ndcg_at_20_max value: 40.54909713178013 - type: nauc_ndcg_at_20_std value: 32.197062113529576 - type: nauc_ndcg_at_3_diff1 value: 24.011090519352297 - type: nauc_ndcg_at_3_max value: 41.390403583726155 - type: nauc_ndcg_at_3_std value: 25.970801370304663 - type: nauc_ndcg_at_5_diff1 value: 21.665450103655758 - type: nauc_ndcg_at_5_max value: 41.31692759970914 - type: nauc_ndcg_at_5_std value: 28.27222783671603 - type: nauc_precision_at_1000_diff1 value: -12.949662625593387 - type: nauc_precision_at_1000_max value: 9.813067200754695 - type: nauc_precision_at_1000_std value: 40.89419595054123 - type: nauc_precision_at_100_diff1 value: -8.788626197601692 - type: nauc_precision_at_100_max value: 24.009165542236552 - type: nauc_precision_at_100_std value: 52.03060008921234 - type: nauc_precision_at_10_diff1 value: -0.8821033318569177 - type: nauc_precision_at_10_max value: 36.63377864059687 - type: nauc_precision_at_10_std value: 41.728479740505605 - type: nauc_precision_at_1_diff1 value: 30.395863641073404 - type: nauc_precision_at_1_max value: 39.14603700466295 - type: nauc_precision_at_1_std value: 22.81299502437437 - type: nauc_precision_at_20_diff1 value: -4.247170694530449 - type: nauc_precision_at_20_max value: 34.1717839314797 - type: nauc_precision_at_20_std value: 46.95915867262384 - type: nauc_precision_at_3_diff1 value: 14.08549588334381 - type: nauc_precision_at_3_max value: 41.78305711419503 - type: nauc_precision_at_3_std value: 29.937750126808016 - type: nauc_precision_at_5_diff1 value: 6.795675986788425 - type: nauc_precision_at_5_max value: 41.1649623002547 - type: nauc_precision_at_5_std value: 35.10676757427974 - type: nauc_recall_at_1000_diff1 value: 9.323813197352594 - type: nauc_recall_at_1000_max value: 26.561710670307797 - type: nauc_recall_at_1000_std value: 27.567182664914775 - type: nauc_recall_at_100_diff1 value: 19.40746686768132 - type: nauc_recall_at_100_max value: 31.43872311644064 - type: nauc_recall_at_100_std value: 22.723757402094883 - type: nauc_recall_at_10_diff1 value: 25.54082922198322 - type: nauc_recall_at_10_max value: 22.018853511961083 - type: nauc_recall_at_10_std value: 4.299087738075515 - type: nauc_recall_at_1_diff1 value: 50.389087879996865 - type: nauc_recall_at_1_max value: 20.95986174718729 - type: nauc_recall_at_1_std value: -5.41570803338871 - type: nauc_recall_at_20_diff1 value: 23.338815663373357 - type: nauc_recall_at_20_max value: 23.350885868547458 - type: nauc_recall_at_20_std value: 8.049814823974602 - type: nauc_recall_at_3_diff1 value: 33.134066342544145 - type: nauc_recall_at_3_max value: 18.539807748844968 - type: nauc_recall_at_3_std value: -5.923909673276145 - type: nauc_recall_at_5_diff1 value: 29.55575014531457 - type: nauc_recall_at_5_max value: 19.067988699284534 - type: nauc_recall_at_5_std value: -0.8407775036491218 - type: ndcg_at_1 value: 43.808 - type: ndcg_at_10 value: 35.509 - type: ndcg_at_100 value: 31.676 - type: ndcg_at_1000 value: 40.543 - type: ndcg_at_20 value: 32.988 - type: ndcg_at_3 value: 40.376 - type: ndcg_at_5 value: 38.41 - type: precision_at_1 value: 45.511 - type: precision_at_10 value: 26.811 - type: precision_at_100 value: 8.056000000000001 - type: precision_at_1000 value: 2.098 - type: precision_at_20 value: 19.505 - type: precision_at_3 value: 38.080000000000005 - type: precision_at_5 value: 33.437 - type: recall_at_1 value: 5.508 - type: recall_at_10 value: 17.319000000000003 - type: recall_at_100 value: 31.294 - type: recall_at_1000 value: 63.275999999999996 - type: recall_at_20 value: 21.431 - type: recall_at_3 value: 10.473 - type: recall_at_5 value: 13.507 - task: type: Retrieval dataset: name: MTEB NQ (default) type: mteb/nq config: default split: test revision: b774495ed302d8c44a3a7ea25c90dbce03968f31 metrics: - type: main_score value: 49.393 - type: map_at_1 value: 26.849 - type: map_at_10 value: 41.499 - type: map_at_100 value: 42.653 - type: map_at_1000 value: 42.684 - type: map_at_20 value: 42.243 - type: map_at_3 value: 36.882999999999996 - type: map_at_5 value: 39.555 - type: mrr_at_1 value: 30.446118192352262 - type: mrr_at_10 value: 44.00585581857308 - type: mrr_at_100 value: 44.90568334013942 - type: mrr_at_1000 value: 44.927318173677044 - type: mrr_at_20 value: 44.606647073916015 - type: mrr_at_3 value: 40.02510621861723 - type: mrr_at_5 value: 42.41067979915025 - type: nauc_map_at_1000_diff1 value: 31.651453391622358 - type: nauc_map_at_1000_max value: 21.072274916232775 - type: nauc_map_at_1000_std value: -4.166680453231419 - type: nauc_map_at_100_diff1 value: 31.64962254039646 - type: nauc_map_at_100_max value: 21.098240383541132 - type: nauc_map_at_100_std value: -4.131604331386804 - type: nauc_map_at_10_diff1 value: 31.766862600658698 - type: nauc_map_at_10_max value: 21.010891364290753 - type: nauc_map_at_10_std value: -4.708084775930258 - type: nauc_map_at_1_diff1 value: 33.32708116835102 - type: nauc_map_at_1_max value: 16.533091238015647 - type: nauc_map_at_1_std value: -5.473056333831887 - type: nauc_map_at_20_diff1 value: 31.651686475476943 - type: nauc_map_at_20_max value: 21.118504172703588 - type: nauc_map_at_20_std value: -4.266813330654076 - type: nauc_map_at_3_diff1 value: 31.00533525886582 - type: nauc_map_at_3_max value: 19.147198618391343 - type: nauc_map_at_3_std value: -5.813774751421132 - type: nauc_map_at_5_diff1 value: 31.35355732909234 - type: nauc_map_at_5_max value: 20.164291644935563 - type: nauc_map_at_5_std value: -5.484865685870952 - type: nauc_mrr_at_1000_diff1 value: 31.2911953834966 - type: nauc_mrr_at_1000_max value: 20.98587622652489 - type: nauc_mrr_at_1000_std value: -2.899993822246 - type: nauc_mrr_at_100_diff1 value: 31.291944529588978 - type: nauc_mrr_at_100_max value: 21.005023374269047 - type: nauc_mrr_at_100_std value: -2.873367683133069 - type: nauc_mrr_at_10_diff1 value: 31.34953406118716 - type: nauc_mrr_at_10_max value: 21.090610712235293 - type: nauc_mrr_at_10_std value: -3.0680385450871865 - type: nauc_mrr_at_1_diff1 value: 33.28395799775457 - type: nauc_mrr_at_1_max value: 17.5779149107383 - type: nauc_mrr_at_1_std value: -4.09778735624495 - type: nauc_mrr_at_20_diff1 value: 31.26673427403389 - type: nauc_mrr_at_20_max value: 21.065827511367623 - type: nauc_mrr_at_20_std value: -2.9368911795293955 - type: nauc_mrr_at_3_diff1 value: 30.940055172744103 - type: nauc_mrr_at_3_max value: 19.798185385046573 - type: nauc_mrr_at_3_std value: -4.064157829412906 - type: nauc_mrr_at_5_diff1 value: 31.02626997196326 - type: nauc_mrr_at_5_max value: 20.619867130693375 - type: nauc_mrr_at_5_std value: -3.621718540966316 - type: nauc_ndcg_at_1000_diff1 value: 31.215275891803834 - type: nauc_ndcg_at_1000_max value: 23.038486093151146 - type: nauc_ndcg_at_1000_std value: -1.703062891132552 - type: nauc_ndcg_at_100_diff1 value: 31.222739143287704 - type: nauc_ndcg_at_100_max value: 23.73579897144862 - type: nauc_ndcg_at_100_std value: -0.7280084629042225 - type: nauc_ndcg_at_10_diff1 value: 31.552059739538358 - type: nauc_ndcg_at_10_max value: 23.663866950433963 - type: nauc_ndcg_at_10_std value: -2.8203583845097455 - type: nauc_ndcg_at_1_diff1 value: 33.28395799775457 - type: nauc_ndcg_at_1_max value: 17.5779149107383 - type: nauc_ndcg_at_1_std value: -4.09778735624495 - type: nauc_ndcg_at_20_diff1 value: 31.115573156536808 - type: nauc_ndcg_at_20_max value: 23.91556914404219 - type: nauc_ndcg_at_20_std value: -1.5512740313611486 - type: nauc_ndcg_at_3_diff1 value: 30.182801126285153 - type: nauc_ndcg_at_3_max value: 20.116992880379968 - type: nauc_ndcg_at_3_std value: -5.270323067103204 - type: nauc_ndcg_at_5_diff1 value: 30.55855867246541 - type: nauc_ndcg_at_5_max value: 21.854891798578514 - type: nauc_ndcg_at_5_std value: -4.621054609051083 - type: nauc_precision_at_1000_diff1 value: -1.2677610563440622 - type: nauc_precision_at_1000_max value: 10.306514334211938 - type: nauc_precision_at_1000_std value: 13.52311200877095 - type: nauc_precision_at_100_diff1 value: 4.584881683104716 - type: nauc_precision_at_100_max value: 19.05218376135677 - type: nauc_precision_at_100_std value: 19.53317534358223 - type: nauc_precision_at_10_diff1 value: 20.668826405226238 - type: nauc_precision_at_10_max value: 27.133486139333527 - type: nauc_precision_at_10_std value: 6.507236892401218 - type: nauc_precision_at_1_diff1 value: 33.28395799775457 - type: nauc_precision_at_1_max value: 17.5779149107383 - type: nauc_precision_at_1_std value: -4.09778735624495 - type: nauc_precision_at_20_diff1 value: 14.220253768827485 - type: nauc_precision_at_20_max value: 25.76903982782269 - type: nauc_precision_at_20_std value: 13.332493634341546 - type: nauc_precision_at_3_diff1 value: 25.11865756124606 - type: nauc_precision_at_3_max value: 22.659692088129788 - type: nauc_precision_at_3_std value: -2.4562156265188646 - type: nauc_precision_at_5_diff1 value: 23.14757206487534 - type: nauc_precision_at_5_max value: 24.626603388946382 - type: nauc_precision_at_5_std value: -0.3684391495744226 - type: nauc_recall_at_1000_diff1 value: 18.253568539360202 - type: nauc_recall_at_1000_max value: 69.97593556184775 - type: nauc_recall_at_1000_std value: 67.03053194965779 - type: nauc_recall_at_100_diff1 value: 27.49214266284193 - type: nauc_recall_at_100_max value: 52.8893274817214 - type: nauc_recall_at_100_std value: 41.90088287480938 - type: nauc_recall_at_10_diff1 value: 30.033274268188283 - type: nauc_recall_at_10_max value: 32.423763247028035 - type: nauc_recall_at_10_std value: 2.83469868226926 - type: nauc_recall_at_1_diff1 value: 33.32708116835102 - type: nauc_recall_at_1_max value: 16.533091238015647 - type: nauc_recall_at_1_std value: -5.473056333831887 - type: nauc_recall_at_20_diff1 value: 27.482504671207547 - type: nauc_recall_at_20_max value: 36.766903843277824 - type: nauc_recall_at_20_std value: 11.285869127910257 - type: nauc_recall_at_3_diff1 value: 26.871897458882167 - type: nauc_recall_at_3_max value: 21.40857537556137 - type: nauc_recall_at_3_std value: -5.177974131117242 - type: nauc_recall_at_5_diff1 value: 27.05417164774647 - type: nauc_recall_at_5_max value: 25.54051973421125 - type: nauc_recall_at_5_std value: -3.6239708422249772 - type: ndcg_at_1 value: 30.446 - type: ndcg_at_10 value: 49.393 - type: ndcg_at_100 value: 54.32900000000001 - type: ndcg_at_1000 value: 55.074999999999996 - type: ndcg_at_20 value: 51.837 - type: ndcg_at_3 value: 40.598 - type: ndcg_at_5 value: 45.129999999999995 - type: precision_at_1 value: 30.446 - type: precision_at_10 value: 8.456 - type: precision_at_100 value: 1.122 - type: precision_at_1000 value: 0.11900000000000001 - type: precision_at_20 value: 4.807 - type: precision_at_3 value: 18.694 - type: precision_at_5 value: 13.83 - type: recall_at_1 value: 26.849 - type: recall_at_10 value: 71.08 - type: recall_at_100 value: 92.528 - type: recall_at_1000 value: 98.124 - type: recall_at_20 value: 80.164 - type: recall_at_3 value: 48.211 - type: recall_at_5 value: 58.669000000000004 - task: type: Retrieval dataset: name: MTEB QuoraRetrieval (default) type: mteb/quora config: default split: dev revision: e4e08e0b7dbe3c8700f0daef558ff32256715259 metrics: - type: main_score value: 88.414 - type: map_at_1 value: 70.451 - type: map_at_10 value: 84.743 - type: map_at_100 value: 85.31800000000001 - type: map_at_1000 value: 85.334 - type: map_at_20 value: 85.139 - type: map_at_3 value: 81.852 - type: map_at_5 value: 83.692 - type: mrr_at_1 value: 81.10000000000001 - type: mrr_at_10 value: 87.573 - type: mrr_at_100 value: 87.6829088327801 - type: mrr_at_1000 value: 87.68388325928169 - type: mrr_at_20 value: 87.6581424881448 - type: mrr_at_3 value: 86.69333333333334 - type: mrr_at_5 value: 87.29333333333334 - type: nauc_map_at_1000_diff1 value: 75.72104615748786 - type: nauc_map_at_1000_max value: 31.609188396862343 - type: nauc_map_at_1000_std value: -46.52088683693813 - type: nauc_map_at_100_diff1 value: 75.72964444793845 - type: nauc_map_at_100_max value: 31.591912730669613 - type: nauc_map_at_100_std value: -46.60975557872442 - type: nauc_map_at_10_diff1 value: 75.94308571775802 - type: nauc_map_at_10_max value: 31.253563385398657 - type: nauc_map_at_10_std value: -48.181322538551086 - type: nauc_map_at_1_diff1 value: 79.79532882332838 - type: nauc_map_at_1_max value: 21.771809872442184 - type: nauc_map_at_1_std value: -42.77169105840692 - type: nauc_map_at_20_diff1 value: 75.81259077387881 - type: nauc_map_at_20_max value: 31.416579812982732 - type: nauc_map_at_20_std value: -47.20581632849992 - type: nauc_map_at_3_diff1 value: 76.20949767229638 - type: nauc_map_at_3_max value: 28.979538243065196 - type: nauc_map_at_3_std value: -49.54877638998648 - type: nauc_map_at_5_diff1 value: 76.00775678250743 - type: nauc_map_at_5_max value: 30.52865409003373 - type: nauc_map_at_5_std value: -49.12438963420192 - type: nauc_mrr_at_1000_diff1 value: 76.53323969103015 - type: nauc_mrr_at_1000_max value: 35.012128118744265 - type: nauc_mrr_at_1000_std value: -42.21934663675809 - type: nauc_mrr_at_100_diff1 value: 76.53433148138932 - type: nauc_mrr_at_100_max value: 35.01523464314866 - type: nauc_mrr_at_100_std value: -42.218206899281256 - type: nauc_mrr_at_10_diff1 value: 76.55659780959033 - type: nauc_mrr_at_10_max value: 35.12026307368733 - type: nauc_mrr_at_10_std value: -42.332025538861515 - type: nauc_mrr_at_1_diff1 value: 77.4819303112777 - type: nauc_mrr_at_1_max value: 33.87083528550898 - type: nauc_mrr_at_1_std value: -40.70273058923244 - type: nauc_mrr_at_20_diff1 value: 76.54181877814159 - type: nauc_mrr_at_20_max value: 35.029167402913025 - type: nauc_mrr_at_20_std value: -42.26416201560607 - type: nauc_mrr_at_3_diff1 value: 76.13878281984827 - type: nauc_mrr_at_3_max value: 34.95491780423885 - type: nauc_mrr_at_3_std value: -42.5669408971239 - type: nauc_mrr_at_5_diff1 value: 76.36492389659307 - type: nauc_mrr_at_5_max value: 35.26107283009812 - type: nauc_mrr_at_5_std value: -42.42173398101322 - type: nauc_ndcg_at_1000_diff1 value: 75.72692836343464 - type: nauc_ndcg_at_1000_max value: 33.247134568215095 - type: nauc_ndcg_at_1000_std value: -44.439309524493986 - type: nauc_ndcg_at_100_diff1 value: 75.76218437396709 - type: nauc_ndcg_at_100_max value: 33.213029188852076 - type: nauc_ndcg_at_100_std value: -44.86123377474948 - type: nauc_ndcg_at_10_diff1 value: 76.0418708659554 - type: nauc_ndcg_at_10_max value: 33.03535169276814 - type: nauc_ndcg_at_10_std value: -47.78769977393773 - type: nauc_ndcg_at_1_diff1 value: 77.5187067567312 - type: nauc_ndcg_at_1_max value: 33.752101025952825 - type: nauc_ndcg_at_1_std value: -40.74843856168861 - type: nauc_ndcg_at_20_diff1 value: 75.93559598948329 - type: nauc_ndcg_at_20_max value: 32.78328286896399 - type: nauc_ndcg_at_20_std value: -46.52407523302919 - type: nauc_ndcg_at_3_diff1 value: 74.79008589166301 - type: nauc_ndcg_at_3_max value: 31.808036331631794 - type: nauc_ndcg_at_3_std value: -47.52652861987724 - type: nauc_ndcg_at_5_diff1 value: 75.43287367533794 - type: nauc_ndcg_at_5_max value: 32.833203744407065 - type: nauc_ndcg_at_5_std value: -48.200904530310275 - type: nauc_precision_at_1000_diff1 value: -43.672762408765834 - type: nauc_precision_at_1000_max value: -2.214136208188294 - type: nauc_precision_at_1000_std value: 40.29144301611288 - type: nauc_precision_at_100_diff1 value: -43.12206249775465 - type: nauc_precision_at_100_max value: -1.6653962082743625 - type: nauc_precision_at_100_std value: 37.5746847458721 - type: nauc_precision_at_10_diff1 value: -37.22201537627446 - type: nauc_precision_at_10_max value: 2.313038479878318 - type: nauc_precision_at_10_std value: 24.85067899903987 - type: nauc_precision_at_1_diff1 value: 77.5187067567312 - type: nauc_precision_at_1_max value: 33.752101025952825 - type: nauc_precision_at_1_std value: -40.74843856168861 - type: nauc_precision_at_20_diff1 value: -40.88285707082065 - type: nauc_precision_at_20_max value: -0.4200418417967951 - type: nauc_precision_at_20_std value: 31.468438530634213 - type: nauc_precision_at_3_diff1 value: -19.411745749449427 - type: nauc_precision_at_3_max value: 10.67761072881965 - type: nauc_precision_at_3_std value: 6.696045978354165 - type: nauc_precision_at_5_diff1 value: -30.962882716609258 - type: nauc_precision_at_5_max value: 6.418634812410295 - type: nauc_precision_at_5_std value: 17.387821173608316 - type: nauc_recall_at_1000_diff1 value: 94.69386728069973 - type: nauc_recall_at_1000_max value: 84.28469880099311 - type: nauc_recall_at_1000_std value: 27.77863150403283 - type: nauc_recall_at_100_diff1 value: 75.67916531615204 - type: nauc_recall_at_100_max value: 38.167545891813184 - type: nauc_recall_at_100_std value: -64.10332561926879 - type: nauc_recall_at_10_diff1 value: 74.06200450248475 - type: nauc_recall_at_10_max value: 32.11315273973532 - type: nauc_recall_at_10_std value: -66.65395786324505 - type: nauc_recall_at_1_diff1 value: 79.79532882332838 - type: nauc_recall_at_1_max value: 21.771809872442184 - type: nauc_recall_at_1_std value: -42.77169105840692 - type: nauc_recall_at_20_diff1 value: 75.33902902721827 - type: nauc_recall_at_20_max value: 29.429302358270228 - type: nauc_recall_at_20_std value: -71.19429079945306 - type: nauc_recall_at_3_diff1 value: 71.53824579534546 - type: nauc_recall_at_3_max value: 27.06969939574833 - type: nauc_recall_at_3_std value: -56.11546620113172 - type: nauc_recall_at_5_diff1 value: 71.03056598232821 - type: nauc_recall_at_5_max value: 29.8357436692765 - type: nauc_recall_at_5_std value: -60.42704500308669 - type: ndcg_at_1 value: 81.08 - type: ndcg_at_10 value: 88.414 - type: ndcg_at_100 value: 89.586 - type: ndcg_at_1000 value: 89.68599999999999 - type: ndcg_at_20 value: 89.092 - type: ndcg_at_3 value: 85.697 - type: ndcg_at_5 value: 87.215 - type: precision_at_1 value: 81.08 - type: precision_at_10 value: 13.344000000000001 - type: precision_at_100 value: 1.489 - type: precision_at_1000 value: 0.152 - type: precision_at_20 value: 7.0440000000000005 - type: precision_at_3 value: 37.627 - type: precision_at_5 value: 24.668 - type: recall_at_1 value: 70.451 - type: recall_at_10 value: 95.588 - type: recall_at_100 value: 99.53 - type: recall_at_1000 value: 99.985 - type: recall_at_20 value: 97.723 - type: recall_at_3 value: 87.775 - type: recall_at_5 value: 92.134 - task: type: Retrieval dataset: name: MTEB QuoraRetrieval (default) type: mteb/quora config: default split: test revision: e4e08e0b7dbe3c8700f0daef558ff32256715259 metrics: - type: main_score value: 88.78 - type: map_at_1 value: 71.18100000000001 - type: map_at_10 value: 85.07900000000001 - type: map_at_100 value: 85.685 - type: map_at_1000 value: 85.702 - type: map_at_20 value: 85.476 - type: map_at_3 value: 82.15400000000001 - type: map_at_5 value: 83.99600000000001 - type: mrr_at_1 value: 81.94 - type: mrr_at_10 value: 88.03901984126983 - type: mrr_at_100 value: 88.12521550900104 - type: mrr_at_1000 value: 88.12597480807705 - type: mrr_at_20 value: 88.10112262221783 - type: mrr_at_3 value: 87.14833333333334 - type: mrr_at_5 value: 87.75433333333332 - type: nauc_map_at_1000_diff1 value: 76.35234622746741 - type: nauc_map_at_1000_max value: 34.98127835356811 - type: nauc_map_at_1000_std value: -48.412573733834584 - type: nauc_map_at_100_diff1 value: 76.360780142656 - type: nauc_map_at_100_max value: 34.95463862302956 - type: nauc_map_at_100_std value: -48.465125662089584 - type: nauc_map_at_10_diff1 value: 76.52051460855479 - type: nauc_map_at_10_max value: 34.52605693128301 - type: nauc_map_at_10_std value: -50.187292245995415 - type: nauc_map_at_1_diff1 value: 79.82094021507255 - type: nauc_map_at_1_max value: 26.775009943003003 - type: nauc_map_at_1_std value: -43.61817396485825 - type: nauc_map_at_20_diff1 value: 76.43954832866126 - type: nauc_map_at_20_max value: 34.90428946303489 - type: nauc_map_at_20_std value: -49.12609036782338 - type: nauc_map_at_3_diff1 value: 76.94334321778128 - type: nauc_map_at_3_max value: 32.622560188949166 - type: nauc_map_at_3_std value: -52.188893755275046 - type: nauc_map_at_5_diff1 value: 76.82067204509046 - type: nauc_map_at_5_max value: 33.69870062813589 - type: nauc_map_at_5_std value: -51.82728889112768 - type: nauc_mrr_at_1000_diff1 value: 76.95820451520244 - type: nauc_mrr_at_1000_max value: 37.55235025494403 - type: nauc_mrr_at_1000_std value: -44.920257644843616 - type: nauc_mrr_at_100_diff1 value: 76.9582899978155 - type: nauc_mrr_at_100_max value: 37.553463697088354 - type: nauc_mrr_at_100_std value: -44.91865155369245 - type: nauc_mrr_at_10_diff1 value: 76.9448254715384 - type: nauc_mrr_at_10_max value: 37.57592800822079 - type: nauc_mrr_at_10_std value: -44.99589549975646 - type: nauc_mrr_at_1_diff1 value: 77.9564573352381 - type: nauc_mrr_at_1_max value: 37.315703535659146 - type: nauc_mrr_at_1_std value: -42.14814981557996 - type: nauc_mrr_at_20_diff1 value: 76.96048519906928 - type: nauc_mrr_at_20_max value: 37.595921188645136 - type: nauc_mrr_at_20_std value: -44.95453191997584 - type: nauc_mrr_at_3_diff1 value: 76.75010647148396 - type: nauc_mrr_at_3_max value: 37.33157903176563 - type: nauc_mrr_at_3_std value: -45.76965088590701 - type: nauc_mrr_at_5_diff1 value: 76.91724094778046 - type: nauc_mrr_at_5_max value: 37.6961116255935 - type: nauc_mrr_at_5_std value: -45.315111572131336 - type: nauc_ndcg_at_1000_diff1 value: 76.17915741213382 - type: nauc_ndcg_at_1000_max value: 36.3994100974221 - type: nauc_ndcg_at_1000_std value: -46.52196285482035 - type: nauc_ndcg_at_100_diff1 value: 76.20633890208957 - type: nauc_ndcg_at_100_max value: 36.300160051636446 - type: nauc_ndcg_at_100_std value: -46.64640352852657 - type: nauc_ndcg_at_10_diff1 value: 76.15630905915566 - type: nauc_ndcg_at_10_max value: 35.60844948367385 - type: nauc_ndcg_at_10_std value: -49.545760942997966 - type: nauc_ndcg_at_1_diff1 value: 77.9374936485659 - type: nauc_ndcg_at_1_max value: 37.284222900318895 - type: nauc_ndcg_at_1_std value: -42.11990958304383 - type: nauc_ndcg_at_20_diff1 value: 76.27986532220213 - type: nauc_ndcg_at_20_max value: 36.21561434308417 - type: nauc_ndcg_at_20_std value: -48.37507535345429 - type: nauc_ndcg_at_3_diff1 value: 75.75636270427239 - type: nauc_ndcg_at_3_max value: 35.032989706721466 - type: nauc_ndcg_at_3_std value: -50.238571322181016 - type: nauc_ndcg_at_5_diff1 value: 76.196363901235 - type: nauc_ndcg_at_5_max value: 35.00688298015009 - type: nauc_ndcg_at_5_std value: -50.80538017477186 - type: nauc_precision_at_1000_diff1 value: -43.87939421459698 - type: nauc_precision_at_1000_max value: -6.616664050809342 - type: nauc_precision_at_1000_std value: 40.21658774987439 - type: nauc_precision_at_100_diff1 value: -43.38845573529132 - type: nauc_precision_at_100_max value: -6.459899067577796 - type: nauc_precision_at_100_std value: 38.97937099541361 - type: nauc_precision_at_10_diff1 value: -38.512616169714 - type: nauc_precision_at_10_max value: -2.0392553261530506 - type: nauc_precision_at_10_std value: 27.846561415195296 - type: nauc_precision_at_1_diff1 value: 77.9374936485659 - type: nauc_precision_at_1_max value: 37.284222900318895 - type: nauc_precision_at_1_std value: -42.11990958304383 - type: nauc_precision_at_20_diff1 value: -41.20993785338744 - type: nauc_precision_at_20_max value: -3.883205139317751 - type: nauc_precision_at_20_std value: 33.746465008755195 - type: nauc_precision_at_3_diff1 value: -18.925243780820253 - type: nauc_precision_at_3_max value: 7.636938829464144 - type: nauc_precision_at_3_std value: 5.1931719934549125 - type: nauc_precision_at_5_diff1 value: -30.993143706159508 - type: nauc_precision_at_5_max value: 1.6891759655648126 - type: nauc_precision_at_5_std value: 17.209212799329844 - type: nauc_recall_at_1000_diff1 value: 47.456878747204605 - type: nauc_recall_at_1000_max value: 23.807161723272337 - type: nauc_recall_at_1000_std value: -32.766355457141614 - type: nauc_recall_at_100_diff1 value: 72.34674588264632 - type: nauc_recall_at_100_max value: 33.99490510103659 - type: nauc_recall_at_100_std value: -36.46420217881495 - type: nauc_recall_at_10_diff1 value: 71.56272183904842 - type: nauc_recall_at_10_max value: 32.016038250938735 - type: nauc_recall_at_10_std value: -66.96989454392227 - type: nauc_recall_at_1_diff1 value: 79.82094021507255 - type: nauc_recall_at_1_max value: 26.775009943003003 - type: nauc_recall_at_1_std value: -43.61817396485825 - type: nauc_recall_at_20_diff1 value: 73.24474644767976 - type: nauc_recall_at_20_max value: 36.40934106083169 - type: nauc_recall_at_20_std value: -65.70195006740305 - type: nauc_recall_at_3_diff1 value: 72.78023437495966 - type: nauc_recall_at_3_max value: 29.643076465434625 - type: nauc_recall_at_3_std value: -60.40805827565894 - type: nauc_recall_at_5_diff1 value: 72.04421253222534 - type: nauc_recall_at_5_max value: 30.353847712973938 - type: nauc_recall_at_5_std value: -64.58955239875104 - type: ndcg_at_1 value: 81.95 - type: ndcg_at_10 value: 88.78 - type: ndcg_at_100 value: 89.90899999999999 - type: ndcg_at_1000 value: 90.011 - type: ndcg_at_20 value: 89.376 - type: ndcg_at_3 value: 86.027 - type: ndcg_at_5 value: 87.551 - type: precision_at_1 value: 81.95 - type: precision_at_10 value: 13.453999999999999 - type: precision_at_100 value: 1.528 - type: precision_at_1000 value: 0.157 - type: precision_at_20 value: 7.1209999999999996 - type: precision_at_3 value: 37.6 - type: precision_at_5 value: 24.712 - type: recall_at_1 value: 71.18100000000001 - type: recall_at_10 value: 95.75099999999999 - type: recall_at_100 value: 99.544 - type: recall_at_1000 value: 99.98899999999999 - type: recall_at_20 value: 97.629 - type: recall_at_3 value: 87.801 - type: recall_at_5 value: 92.14099999999999 - task: type: Clustering dataset: name: MTEB RedditClustering (default) type: mteb/reddit-clustering config: default split: test revision: 24640382cdbf8abc73003fb0fa6d111a705499eb metrics: - type: main_score value: 53.81557774708997 - type: v_measure value: 53.81557774708997 - type: v_measure_std value: 4.940724653585969 - task: type: Clustering dataset: name: MTEB RedditClusteringP2P (default) type: mteb/reddit-clustering-p2p config: default split: test revision: 385e3cb46b4cfa89021f56c4380204149d0efe33 metrics: - type: main_score value: 63.059340693644785 - type: v_measure value: 63.059340693644785 - type: v_measure_std value: 11.97353413900713 - task: type: Retrieval dataset: name: MTEB SCIDOCS (default) type: mteb/scidocs config: default split: test revision: f8c2fcf00f625baaa80f62ec5bd9e1fff3b8ae88 metrics: - type: main_score value: 20.441000000000003 - type: map_at_1 value: 4.508 - type: map_at_10 value: 12.141 - type: map_at_100 value: 14.316 - type: map_at_1000 value: 14.658 - type: map_at_20 value: 13.242 - type: map_at_3 value: 8.624 - type: map_at_5 value: 10.333 - type: mrr_at_1 value: 22.3 - type: mrr_at_10 value: 34.01488095238095 - type: mrr_at_100 value: 35.12947200540852 - type: mrr_at_1000 value: 35.18258200333811 - type: mrr_at_20 value: 34.72472937494222 - type: mrr_at_3 value: 30.51666666666667 - type: mrr_at_5 value: 32.471666666666664 - type: nauc_map_at_1000_diff1 value: 19.5295210919884 - type: nauc_map_at_1000_max value: 35.776154650551575 - type: nauc_map_at_1000_std value: 22.598989298641175 - type: nauc_map_at_100_diff1 value: 19.5575568280981 - type: nauc_map_at_100_max value: 35.764999407927924 - type: nauc_map_at_100_std value: 22.388928333977983 - type: nauc_map_at_10_diff1 value: 20.301784773079817 - type: nauc_map_at_10_max value: 33.90741195696659 - type: nauc_map_at_10_std value: 17.948501033988475 - type: nauc_map_at_1_diff1 value: 27.63795852560605 - type: nauc_map_at_1_max value: 28.677707624382226 - type: nauc_map_at_1_std value: 11.313097574744265 - type: nauc_map_at_20_diff1 value: 19.82097532850719 - type: nauc_map_at_20_max value: 35.10681865871605 - type: nauc_map_at_20_std value: 20.393280333290768 - type: nauc_map_at_3_diff1 value: 23.465265104601574 - type: nauc_map_at_3_max value: 31.90516362728403 - type: nauc_map_at_3_std value: 11.082550126615867 - type: nauc_map_at_5_diff1 value: 21.191560324800694 - type: nauc_map_at_5_max value: 32.349846169015365 - type: nauc_map_at_5_std value: 14.08086983687101 - type: nauc_mrr_at_1000_diff1 value: 22.43032918913008 - type: nauc_mrr_at_1000_max value: 30.264097065600065 - type: nauc_mrr_at_1000_std value: 17.16645379954286 - type: nauc_mrr_at_100_diff1 value: 22.431918077326362 - type: nauc_mrr_at_100_max value: 30.278656848582674 - type: nauc_mrr_at_100_std value: 17.205287864081686 - type: nauc_mrr_at_10_diff1 value: 22.399800621436718 - type: nauc_mrr_at_10_max value: 30.17231346566611 - type: nauc_mrr_at_10_std value: 17.12117352552421 - type: nauc_mrr_at_1_diff1 value: 27.338483005001855 - type: nauc_mrr_at_1_max value: 28.516706043782 - type: nauc_mrr_at_1_std value: 11.568218727642739 - type: nauc_mrr_at_20_diff1 value: 22.34527846970131 - type: nauc_mrr_at_20_max value: 30.293795035108754 - type: nauc_mrr_at_20_std value: 17.24818382223587 - type: nauc_mrr_at_3_diff1 value: 21.41347530740495 - type: nauc_mrr_at_3_max value: 29.49578215215621 - type: nauc_mrr_at_3_std value: 15.565310294336843 - type: nauc_mrr_at_5_diff1 value: 21.876219757110178 - type: nauc_mrr_at_5_max value: 29.579506797264944 - type: nauc_mrr_at_5_std value: 16.105358881703282 - type: nauc_ndcg_at_1000_diff1 value: 18.678582790233204 - type: nauc_ndcg_at_1000_max value: 36.955188341480266 - type: nauc_ndcg_at_1000_std value: 29.649172816911378 - type: nauc_ndcg_at_100_diff1 value: 18.52482522871902 - type: nauc_ndcg_at_100_max value: 37.130183155861445 - type: nauc_ndcg_at_100_std value: 29.52961271427892 - type: nauc_ndcg_at_10_diff1 value: 19.94175154982902 - type: nauc_ndcg_at_10_max value: 33.9452753797045 - type: nauc_ndcg_at_10_std value: 20.946470709263238 - type: nauc_ndcg_at_1_diff1 value: 27.338483005001855 - type: nauc_ndcg_at_1_max value: 28.516706043782 - type: nauc_ndcg_at_1_std value: 11.568218727642739 - type: nauc_ndcg_at_20_diff1 value: 19.293919910420897 - type: nauc_ndcg_at_20_max value: 35.76522367701567 - type: nauc_ndcg_at_20_std value: 24.376420891239388 - type: nauc_ndcg_at_3_diff1 value: 21.270066084825956 - type: nauc_ndcg_at_3_max value: 31.326650210409184 - type: nauc_ndcg_at_3_std value: 13.58976920494935 - type: nauc_ndcg_at_5_diff1 value: 20.02407289631927 - type: nauc_ndcg_at_5_max value: 31.684362011594843 - type: nauc_ndcg_at_5_std value: 16.249511700219692 - type: nauc_precision_at_1000_diff1 value: 6.234005186132995 - type: nauc_precision_at_1000_max value: 29.34471048327642 - type: nauc_precision_at_1000_std value: 39.64669468760326 - type: nauc_precision_at_100_diff1 value: 9.855106179885876 - type: nauc_precision_at_100_max value: 34.132120560020866 - type: nauc_precision_at_100_std value: 39.72164007339206 - type: nauc_precision_at_10_diff1 value: 15.90102642361928 - type: nauc_precision_at_10_max value: 33.65916770662614 - type: nauc_precision_at_10_std value: 25.390897965743548 - type: nauc_precision_at_1_diff1 value: 27.338483005001855 - type: nauc_precision_at_1_max value: 28.516706043782 - type: nauc_precision_at_1_std value: 11.568218727642739 - type: nauc_precision_at_20_diff1 value: 13.612513188408462 - type: nauc_precision_at_20_max value: 35.277982280608725 - type: nauc_precision_at_20_std value: 30.71930871320442 - type: nauc_precision_at_3_diff1 value: 18.807118007742872 - type: nauc_precision_at_3_max value: 31.816570276319002 - type: nauc_precision_at_3_std value: 14.449767808472858 - type: nauc_precision_at_5_diff1 value: 16.209744159726867 - type: nauc_precision_at_5_max value: 31.151946588732997 - type: nauc_precision_at_5_std value: 18.381161071520488 - type: nauc_recall_at_1000_diff1 value: 6.273647441536759 - type: nauc_recall_at_1000_max value: 29.1162229253121 - type: nauc_recall_at_1000_std value: 41.52051532378572 - type: nauc_recall_at_100_diff1 value: 10.065781985677573 - type: nauc_recall_at_100_max value: 33.83167291115486 - type: nauc_recall_at_100_std value: 40.006650979954934 - type: nauc_recall_at_10_diff1 value: 16.15411588223024 - type: nauc_recall_at_10_max value: 33.49396867499272 - type: nauc_recall_at_10_std value: 25.292996350892167 - type: nauc_recall_at_1_diff1 value: 27.63795852560605 - type: nauc_recall_at_1_max value: 28.677707624382226 - type: nauc_recall_at_1_std value: 11.313097574744265 - type: nauc_recall_at_20_diff1 value: 13.925034360460256 - type: nauc_recall_at_20_max value: 34.99803447287975 - type: nauc_recall_at_20_std value: 30.666854032413088 - type: nauc_recall_at_3_diff1 value: 18.998052423925802 - type: nauc_recall_at_3_max value: 31.62628665469099 - type: nauc_recall_at_3_std value: 14.239340647611009 - type: nauc_recall_at_5_diff1 value: 16.398224006899152 - type: nauc_recall_at_5_max value: 30.935454145918744 - type: nauc_recall_at_5_std value: 18.143468400300172 - type: ndcg_at_1 value: 22.3 - type: ndcg_at_10 value: 20.441000000000003 - type: ndcg_at_100 value: 28.836000000000002 - type: ndcg_at_1000 value: 34.705000000000005 - type: ndcg_at_20 value: 23.426 - type: ndcg_at_3 value: 19.205 - type: ndcg_at_5 value: 16.739 - type: precision_at_1 value: 22.3 - type: precision_at_10 value: 10.79 - type: precision_at_100 value: 2.2960000000000003 - type: precision_at_1000 value: 0.371 - type: precision_at_20 value: 7.115 - type: precision_at_3 value: 18.2 - type: precision_at_5 value: 14.84 - type: recall_at_1 value: 4.508 - type: recall_at_10 value: 21.853 - type: recall_at_100 value: 46.589999999999996 - type: recall_at_1000 value: 75.25 - type: recall_at_20 value: 28.853 - type: recall_at_3 value: 11.068 - type: recall_at_5 value: 15.033 - task: type: STS dataset: name: MTEB SICK-R (default) type: mteb/sickr-sts config: default split: test revision: 20a6d6f312dd54037fe07a32d58e5e168867909d metrics: - type: cosine_pearson value: 84.30788927270164 - type: cosine_spearman value: 80.07976019050732 - type: euclidean_pearson value: 81.27116301839057 - type: euclidean_spearman value: 80.07976519070897 - type: main_score value: 80.07976019050732 - type: manhattan_pearson value: 81.39470840383359 - type: manhattan_spearman value: 80.11309125271727 - type: pearson value: 84.30788927270164 - type: spearman value: 80.07976019050732 - task: type: STS dataset: name: MTEB STS12 (default) type: mteb/sts12-sts config: default split: test revision: a0d554a64d88156834ff5ae9920b964011b16384 metrics: - type: cosine_pearson value: 85.6494246715977 - type: cosine_spearman value: 77.21364859343417 - type: euclidean_pearson value: 82.16686843138514 - type: euclidean_spearman value: 77.2132269119475 - type: main_score value: 77.21364859343417 - type: manhattan_pearson value: 82.17288769644415 - type: manhattan_spearman value: 77.05682937722813 - type: pearson value: 85.6494246715977 - type: spearman value: 77.21364859343417 - task: type: STS dataset: name: MTEB STS13 (default) type: mteb/sts13-sts config: default split: test revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca metrics: - type: cosine_pearson value: 82.12583205748827 - type: cosine_spearman value: 83.55306391445943 - type: euclidean_pearson value: 82.81699442422787 - type: euclidean_spearman value: 83.55306391445943 - type: main_score value: 83.55306391445943 - type: manhattan_pearson value: 82.70032676616033 - type: manhattan_spearman value: 83.43696105973991 - type: pearson value: 82.12583205748827 - type: spearman value: 83.55306391445943 - task: type: STS dataset: name: MTEB STS14 (default) type: mteb/sts14-sts config: default split: test revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375 metrics: - type: cosine_pearson value: 82.8072878574002 - type: cosine_spearman value: 82.39917863256566 - type: euclidean_pearson value: 82.34142760248918 - type: euclidean_spearman value: 82.39918313271785 - type: main_score value: 82.39917863256566 - type: manhattan_pearson value: 82.35430476764317 - type: manhattan_spearman value: 82.38775090940842 - type: pearson value: 82.8072878574002 - type: spearman value: 82.39917863256566 - task: type: STS dataset: name: MTEB STS15 (default) type: mteb/sts15-sts config: default split: test revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3 metrics: - type: cosine_pearson value: 87.05873896779867 - type: cosine_spearman value: 88.08920102010087 - type: euclidean_pearson value: 87.43579028480816 - type: euclidean_spearman value: 88.08920593843715 - type: main_score value: 88.08920102010087 - type: manhattan_pearson value: 87.50258824179726 - type: manhattan_spearman value: 88.18943707030766 - type: pearson value: 87.05873896779867 - type: spearman value: 88.08920102010087 - task: type: STS dataset: name: MTEB STS16 (default) type: mteb/sts16-sts config: default split: test revision: 4d8694f8f0e0100860b497b999b3dbed754a0513 metrics: - type: cosine_pearson value: 83.18613820567626 - type: cosine_spearman value: 85.02812271380569 - type: euclidean_pearson value: 84.0552020752535 - type: euclidean_spearman value: 85.0281225608977 - type: main_score value: 85.02812271380569 - type: manhattan_pearson value: 83.79067016461165 - type: manhattan_spearman value: 84.75880971236536 - type: pearson value: 83.18613820567626 - type: spearman value: 85.02812271380569 - task: type: STS dataset: name: MTEB STS17 (fr-en) type: mteb/sts17-crosslingual-sts config: fr-en split: test revision: faeb762787bd10488a50c8b5be4a3b82e411949c metrics: - type: cosine_pearson value: 39.5876015348183 - type: cosine_spearman value: 38.2945838490163 - type: euclidean_pearson value: 39.79784346190561 - type: euclidean_spearman value: 38.2945838490163 - type: main_score value: 38.2945838490163 - type: manhattan_pearson value: 39.977833809923645 - type: manhattan_spearman value: 39.388422674752235 - type: pearson value: 39.5876015348183 - type: spearman value: 38.2945838490163 - task: type: STS dataset: name: MTEB STS17 (en-en) type: mteb/sts17-crosslingual-sts config: en-en split: test revision: faeb762787bd10488a50c8b5be4a3b82e411949c metrics: - type: cosine_pearson value: 88.51383096083804 - type: cosine_spearman value: 88.52537252266963 - type: euclidean_pearson value: 89.1117050087703 - type: euclidean_spearman value: 88.52537252266963 - type: main_score value: 88.52537252266963 - type: manhattan_pearson value: 89.31585295977288 - type: manhattan_spearman value: 88.78380232395662 - type: pearson value: 88.51383096083804 - type: spearman value: 88.52537252266963 - task: type: STS dataset: name: MTEB STS17 (nl-en) type: mteb/sts17-crosslingual-sts config: nl-en split: test revision: faeb762787bd10488a50c8b5be4a3b82e411949c metrics: - type: cosine_pearson value: 35.50474589697871 - type: cosine_spearman value: 30.812689378913603 - type: euclidean_pearson value: 36.25909794770876 - type: euclidean_spearman value: 30.812689378913603 - type: main_score value: 30.812689378913603 - type: manhattan_pearson value: 36.26828913763471 - type: manhattan_spearman value: 31.528781713909197 - type: pearson value: 35.50474589697871 - type: spearman value: 30.812689378913603 - task: type: STS dataset: name: MTEB STS17 (en-de) type: mteb/sts17-crosslingual-sts config: en-de split: test revision: faeb762787bd10488a50c8b5be4a3b82e411949c metrics: - type: cosine_pearson value: 32.652743251558654 - type: cosine_spearman value: 29.105392097318806 - type: euclidean_pearson value: 32.74903065824115 - type: euclidean_spearman value: 29.105392097318806 - type: main_score value: 29.105392097318806 - type: manhattan_pearson value: 33.540625008403524 - type: manhattan_spearman value: 29.355480493447494 - type: pearson value: 32.652743251558654 - type: spearman value: 29.105392097318806 - task: type: STS dataset: name: MTEB STS17 (en-tr) type: mteb/sts17-crosslingual-sts config: en-tr split: test revision: faeb762787bd10488a50c8b5be4a3b82e411949c metrics: - type: cosine_pearson value: 12.36849882661743 - type: cosine_spearman value: 7.611138217911713 - type: euclidean_pearson value: 12.77603971192848 - type: euclidean_spearman value: 7.611138217911713 - type: main_score value: 7.611138217911713 - type: manhattan_pearson value: 11.619163669702509 - type: manhattan_spearman value: 6.184520778812523 - type: pearson value: 12.36849882661743 - type: spearman value: 7.611138217911713 - task: type: STS dataset: name: MTEB STS17 (en-ar) type: mteb/sts17-crosslingual-sts config: en-ar split: test revision: faeb762787bd10488a50c8b5be4a3b82e411949c metrics: - type: cosine_pearson value: 6.59159885046766 - type: cosine_spearman value: 4.622204785531158 - type: euclidean_pearson value: 6.593149700947697 - type: euclidean_spearman value: 4.622204785531158 - type: main_score value: 4.622204785531158 - type: manhattan_pearson value: 5.566016374381194 - type: manhattan_spearman value: 3.8796229563749285 - type: pearson value: 6.59159885046766 - type: spearman value: 4.622204785531158 - task: type: STS dataset: name: MTEB STS17 (es-en) type: mteb/sts17-crosslingual-sts config: es-en split: test revision: faeb762787bd10488a50c8b5be4a3b82e411949c metrics: - type: cosine_pearson value: 30.35179238078445 - type: cosine_spearman value: 29.625068788447894 - type: euclidean_pearson value: 30.233806247338414 - type: euclidean_spearman value: 29.625068788447894 - type: main_score value: 29.625068788447894 - type: manhattan_pearson value: 29.936866734034933 - type: manhattan_spearman value: 28.57299479927884 - type: pearson value: 30.35179238078445 - type: spearman value: 29.625068788447894 - task: type: STS dataset: name: MTEB STS17 (it-en) type: mteb/sts17-crosslingual-sts config: it-en split: test revision: faeb762787bd10488a50c8b5be4a3b82e411949c metrics: - type: cosine_pearson value: 30.30232199857813 - type: cosine_spearman value: 27.219119781543988 - type: euclidean_pearson value: 30.225835856043272 - type: euclidean_spearman value: 27.219119781543988 - type: main_score value: 27.219119781543988 - type: manhattan_pearson value: 29.142315782629925 - type: manhattan_spearman value: 25.901216206187065 - type: pearson value: 30.30232199857813 - type: spearman value: 27.219119781543988 - task: type: STS dataset: name: MTEB STS22 (de-en) type: mteb/sts22-crosslingual-sts config: de-en split: test revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3 metrics: - type: cosine_pearson value: 43.22978323210299 - type: cosine_spearman value: 47.01518443724799 - type: euclidean_pearson value: 45.930506019807574 - type: euclidean_spearman value: 47.01518443724799 - type: main_score value: 47.01518443724799 - type: manhattan_pearson value: 47.44811320365125 - type: manhattan_spearman value: 47.73671354326406 - type: pearson value: 43.22978323210299 - type: spearman value: 47.01518443724799 - task: type: STS dataset: name: MTEB STS22 (en) type: mteb/sts22-crosslingual-sts config: en split: test revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3 metrics: - type: cosine_pearson value: 65.93329041695125 - type: cosine_spearman value: 65.95494400411647 - type: euclidean_pearson value: 67.77439530118112 - type: euclidean_spearman value: 65.95494400411647 - type: main_score value: 65.95494400411647 - type: manhattan_pearson value: 68.21709531505775 - type: manhattan_spearman value: 66.39646560258034 - type: pearson value: 65.93329041695125 - type: spearman value: 65.95494400411647 - task: type: STS dataset: name: MTEB STS22 (pl-en) type: mteb/sts22-crosslingual-sts config: pl-en split: test revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3 metrics: - type: cosine_pearson value: 46.929818903916804 - type: cosine_spearman value: 44.44075531175433 - type: euclidean_pearson value: 47.059078863657675 - type: euclidean_spearman value: 44.44075531175433 - type: main_score value: 44.44075531175433 - type: manhattan_pearson value: 46.04521740640152 - type: manhattan_spearman value: 44.576197773142866 - type: pearson value: 46.929818903916804 - type: spearman value: 44.44075531175433 - task: type: STS dataset: name: MTEB STS22 (es-en) type: mteb/sts22-crosslingual-sts config: es-en split: test revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3 metrics: - type: cosine_pearson value: 56.86304728923609 - type: cosine_spearman value: 63.05184294758852 - type: euclidean_pearson value: 58.177828253582206 - type: euclidean_spearman value: 63.05184294758852 - type: main_score value: 63.05184294758852 - type: manhattan_pearson value: 58.958715164135825 - type: manhattan_spearman value: 63.755348809781395 - type: pearson value: 56.86304728923609 - type: spearman value: 63.05184294758852 - task: type: STS dataset: name: MTEB STS22 (zh-en) type: mteb/sts22-crosslingual-sts config: zh-en split: test revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3 metrics: - type: cosine_pearson value: 45.6965322701485 - type: cosine_spearman value: 49.44860243126726 - type: euclidean_pearson value: 45.71922769223791 - type: euclidean_spearman value: 49.44860243126726 - type: main_score value: 49.44860243126726 - type: manhattan_pearson value: 45.78318374788422 - type: manhattan_spearman value: 49.521422718994984 - type: pearson value: 45.6965322701485 - type: spearman value: 49.44860243126726 - task: type: STS dataset: name: MTEB STSBenchmark (default) type: mteb/stsbenchmark-sts config: default split: test revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831 metrics: - type: cosine_pearson value: 85.0014615648556 - type: cosine_spearman value: 86.65686905435463 - type: euclidean_pearson value: 86.1451324543907 - type: euclidean_spearman value: 86.65685763157673 - type: main_score value: 86.65686905435463 - type: manhattan_pearson value: 86.0861598253851 - type: manhattan_spearman value: 86.61047820278552 - type: pearson value: 85.0014615648556 - type: spearman value: 86.65686905435463 - task: type: Reranking dataset: name: MTEB SciDocsRR (default) type: mteb/scidocs-reranking config: default split: test revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab metrics: - type: main_score value: 85.89651013746061 - type: map value: 85.89651013746061 - type: mrr value: 95.99524567661823 - type: nAUC_map_diff1 value: -0.0410803569069903 - type: nAUC_map_max value: 53.629827070614546 - type: nAUC_map_std value: 67.22768282404712 - type: nAUC_mrr_diff1 value: 40.687943307829606 - type: nAUC_mrr_max value: 85.09337269421229 - type: nAUC_mrr_std value: 79.32454109714799 - task: type: Retrieval dataset: name: MTEB SciFact (default) type: mteb/scifact config: default split: test revision: 0228b52cf27578f30900b9e5271d331663a030d7 metrics: - type: main_score value: 73.251 - type: map_at_1 value: 59.428000000000004 - type: map_at_10 value: 68.959 - type: map_at_100 value: 69.484 - type: map_at_1000 value: 69.511 - type: map_at_20 value: 69.30199999999999 - type: map_at_3 value: 66.083 - type: map_at_5 value: 67.683 - type: mrr_at_1 value: 62.33333333333333 - type: mrr_at_10 value: 69.96005291005292 - type: mrr_at_100 value: 70.37333611401961 - type: mrr_at_1000 value: 70.40109312065698 - type: mrr_at_20 value: 70.23336940836941 - type: mrr_at_3 value: 67.72222222222221 - type: mrr_at_5 value: 69.07222222222222 - type: nauc_map_at_1000_diff1 value: 70.13570749625822 - type: nauc_map_at_1000_max value: 52.65674632844235 - type: nauc_map_at_1000_std value: 10.132852161672638 - type: nauc_map_at_100_diff1 value: 70.13538095683808 - type: nauc_map_at_100_max value: 52.6884935329599 - type: nauc_map_at_100_std value: 10.14379381633777 - type: nauc_map_at_10_diff1 value: 70.36327918679356 - type: nauc_map_at_10_max value: 52.954942802961504 - type: nauc_map_at_10_std value: 10.02209736428799 - type: nauc_map_at_1_diff1 value: 73.49594650090174 - type: nauc_map_at_1_max value: 45.82858518993797 - type: nauc_map_at_1_std value: -0.40926083096917837 - type: nauc_map_at_20_diff1 value: 70.06837661473298 - type: nauc_map_at_20_max value: 52.76020878212071 - type: nauc_map_at_20_std value: 10.007600191187741 - type: nauc_map_at_3_diff1 value: 70.31817155099134 - type: nauc_map_at_3_max value: 48.641969098932314 - type: nauc_map_at_3_std value: 7.073005227799293 - type: nauc_map_at_5_diff1 value: 69.91715955939225 - type: nauc_map_at_5_max value: 50.08437399280585 - type: nauc_map_at_5_std value: 8.325142211837317 - type: nauc_mrr_at_1000_diff1 value: 70.89523822365368 - type: nauc_mrr_at_1000_max value: 54.566931991503175 - type: nauc_mrr_at_1000_std value: 13.068031822873314 - type: nauc_mrr_at_100_diff1 value: 70.89405457859479 - type: nauc_mrr_at_100_max value: 54.5971940226233 - type: nauc_mrr_at_100_std value: 13.075912428577213 - type: nauc_mrr_at_10_diff1 value: 71.03623671748012 - type: nauc_mrr_at_10_max value: 54.95069512409659 - type: nauc_mrr_at_10_std value: 13.363315852524071 - type: nauc_mrr_at_1_diff1 value: 73.44129679978948 - type: nauc_mrr_at_1_max value: 53.11585866037946 - type: nauc_mrr_at_1_std value: 8.225722407664433 - type: nauc_mrr_at_20_diff1 value: 70.83036037320228 - type: nauc_mrr_at_20_max value: 54.65143963366521 - type: nauc_mrr_at_20_std value: 13.136998458127792 - type: nauc_mrr_at_3_diff1 value: 71.153158657001 - type: nauc_mrr_at_3_max value: 53.205584683267084 - type: nauc_mrr_at_3_std value: 11.980916718299982 - type: nauc_mrr_at_5_diff1 value: 70.66319100789279 - type: nauc_mrr_at_5_max value: 53.64747705626284 - type: nauc_mrr_at_5_std value: 13.158118645048983 - type: nauc_ndcg_at_1000_diff1 value: 69.82895027282646 - type: nauc_ndcg_at_1000_max value: 54.52290390511955 - type: nauc_ndcg_at_1000_std value: 13.07433953652383 - type: nauc_ndcg_at_100_diff1 value: 69.66603141670811 - type: nauc_ndcg_at_100_max value: 55.33932851097095 - type: nauc_ndcg_at_100_std value: 13.531855815973309 - type: nauc_ndcg_at_10_diff1 value: 70.0672222067367 - type: nauc_ndcg_at_10_max value: 56.609848753019875 - type: nauc_ndcg_at_10_std value: 13.801015990958836 - type: nauc_ndcg_at_1_diff1 value: 73.44129679978948 - type: nauc_ndcg_at_1_max value: 53.11585866037946 - type: nauc_ndcg_at_1_std value: 8.225722407664433 - type: nauc_ndcg_at_20_diff1 value: 69.00029554032444 - type: nauc_ndcg_at_20_max value: 55.77587708778143 - type: nauc_ndcg_at_20_std value: 13.550535479714885 - type: nauc_ndcg_at_3_diff1 value: 69.35809356376409 - type: nauc_ndcg_at_3_max value: 50.88753511744564 - type: nauc_ndcg_at_3_std value: 10.376849196217488 - type: nauc_ndcg_at_5_diff1 value: 68.7557226824334 - type: nauc_ndcg_at_5_max value: 51.64039917399674 - type: nauc_ndcg_at_5_std value: 11.375060289968888 - type: nauc_precision_at_1000_diff1 value: -24.38184345232032 - type: nauc_precision_at_1000_max value: 25.3113664869997 - type: nauc_precision_at_1000_std value: 54.78151801755995 - type: nauc_precision_at_100_diff1 value: -10.585088484724002 - type: nauc_precision_at_100_max value: 34.58061719734689 - type: nauc_precision_at_100_std value: 51.08616923594603 - type: nauc_precision_at_10_diff1 value: 15.011059571897201 - type: nauc_precision_at_10_max value: 53.380534154853976 - type: nauc_precision_at_10_std value: 46.77574783177469 - type: nauc_precision_at_1_diff1 value: 73.44129679978948 - type: nauc_precision_at_1_max value: 53.11585866037946 - type: nauc_precision_at_1_std value: 8.225722407664433 - type: nauc_precision_at_20_diff1 value: 3.0375226465875627 - type: nauc_precision_at_20_max value: 46.96352459445593 - type: nauc_precision_at_20_std value: 47.8180732859282 - type: nauc_precision_at_3_diff1 value: 41.34820548287889 - type: nauc_precision_at_3_max value: 48.02988164084151 - type: nauc_precision_at_3_std value: 29.8325902163623 - type: nauc_precision_at_5_diff1 value: 28.292680467974172 - type: nauc_precision_at_5_max value: 48.2395519867733 - type: nauc_precision_at_5_std value: 36.77307484865436 - type: nauc_recall_at_1000_diff1 value: 86.92810457516407 - type: nauc_recall_at_1000_max value: 12.278244631182748 - type: nauc_recall_at_1000_std value: 86.92810457516407 - type: nauc_recall_at_100_diff1 value: 64.23902894491097 - type: nauc_recall_at_100_max value: 78.57809790582883 - type: nauc_recall_at_100_std value: 35.47085500866988 - type: nauc_recall_at_10_diff1 value: 67.63049621810325 - type: nauc_recall_at_10_max value: 71.99088366956788 - type: nauc_recall_at_10_std value: 25.694634100003483 - type: nauc_recall_at_1_diff1 value: 73.49594650090174 - type: nauc_recall_at_1_max value: 45.82858518993797 - type: nauc_recall_at_1_std value: -0.40926083096917837 - type: nauc_recall_at_20_diff1 value: 58.91757942656138 - type: nauc_recall_at_20_max value: 70.52947052947034 - type: nauc_recall_at_20_std value: 26.934442802706094 - type: nauc_recall_at_3_diff1 value: 66.06848071584821 - type: nauc_recall_at_3_max value: 47.58371405487635 - type: nauc_recall_at_3_std value: 10.115468870167247 - type: nauc_recall_at_5_diff1 value: 63.103805010550055 - type: nauc_recall_at_5_max value: 51.85255345215588 - type: nauc_recall_at_5_std value: 15.746356552783283 - type: ndcg_at_1 value: 62.333000000000006 - type: ndcg_at_10 value: 73.251 - type: ndcg_at_100 value: 75.471 - type: ndcg_at_1000 value: 76.058 - type: ndcg_at_20 value: 74.344 - type: ndcg_at_3 value: 68.314 - type: ndcg_at_5 value: 70.733 - type: precision_at_1 value: 62.333000000000006 - type: precision_at_10 value: 9.667 - type: precision_at_100 value: 1.083 - type: precision_at_1000 value: 0.11299999999999999 - type: precision_at_20 value: 5.067 - type: precision_at_3 value: 26.333000000000002 - type: precision_at_5 value: 17.4 - type: recall_at_1 value: 59.428000000000004 - type: recall_at_10 value: 85.422 - type: recall_at_100 value: 95.333 - type: recall_at_1000 value: 99.667 - type: recall_at_20 value: 89.533 - type: recall_at_3 value: 72.06099999999999 - type: recall_at_5 value: 78.261 - task: type: Retrieval dataset: name: MTEB SciFact (default) type: mteb/scifact config: default split: train revision: 0228b52cf27578f30900b9e5271d331663a030d7 metrics: - type: main_score value: 76.485 - type: map_at_1 value: 62.437 - type: map_at_10 value: 72.424 - type: map_at_100 value: 72.875 - type: map_at_1000 value: 72.894 - type: map_at_20 value: 72.699 - type: map_at_3 value: 69.929 - type: map_at_5 value: 71.41 - type: mrr_at_1 value: 65.389369592089 - type: mrr_at_10 value: 73.51874742480429 - type: mrr_at_100 value: 73.86149719584975 - type: mrr_at_1000 value: 73.87817655179401 - type: mrr_at_20 value: 73.69712246373606 - type: mrr_at_3 value: 72.10548001648127 - type: mrr_at_5 value: 72.83477544293366 - type: nauc_map_at_1000_diff1 value: 70.88987705012035 - type: nauc_map_at_1000_max value: 46.77717767104366 - type: nauc_map_at_1000_std value: 12.442652616829855 - type: nauc_map_at_100_diff1 value: 70.88170091037614 - type: nauc_map_at_100_max value: 46.78841410305628 - type: nauc_map_at_100_std value: 12.472496933804496 - type: nauc_map_at_10_diff1 value: 70.97977319347748 - type: nauc_map_at_10_max value: 46.84404169739291 - type: nauc_map_at_10_std value: 12.21031737700784 - type: nauc_map_at_1_diff1 value: 73.66858140737193 - type: nauc_map_at_1_max value: 37.72209378868329 - type: nauc_map_at_1_std value: 6.058877150429456 - type: nauc_map_at_20_diff1 value: 70.80507181778022 - type: nauc_map_at_20_max value: 46.819460847144114 - type: nauc_map_at_20_std value: 12.472103561158026 - type: nauc_map_at_3_diff1 value: 71.58242927801035 - type: nauc_map_at_3_max value: 43.60594750641507 - type: nauc_map_at_3_std value: 8.800606729897389 - type: nauc_map_at_5_diff1 value: 71.15709258217167 - type: nauc_map_at_5_max value: 45.724847576243924 - type: nauc_map_at_5_std value: 10.318911927965361 - type: nauc_mrr_at_1000_diff1 value: 71.04412576767227 - type: nauc_mrr_at_1000_max value: 48.49663895894284 - type: nauc_mrr_at_1000_std value: 15.61285718843641 - type: nauc_mrr_at_100_diff1 value: 71.03490861681165 - type: nauc_mrr_at_100_max value: 48.50439063635205 - type: nauc_mrr_at_100_std value: 15.640711217565325 - type: nauc_mrr_at_10_diff1 value: 71.03518493601177 - type: nauc_mrr_at_10_max value: 48.61941531114441 - type: nauc_mrr_at_10_std value: 15.706199493660014 - type: nauc_mrr_at_1_diff1 value: 73.60832695813949 - type: nauc_mrr_at_1_max value: 44.578750878677084 - type: nauc_mrr_at_1_std value: 11.890587471184963 - type: nauc_mrr_at_20_diff1 value: 70.97955641800446 - type: nauc_mrr_at_20_max value: 48.58739923848605 - type: nauc_mrr_at_20_std value: 15.664657516610061 - type: nauc_mrr_at_3_diff1 value: 71.27717189961885 - type: nauc_mrr_at_3_max value: 48.6513411916282 - type: nauc_mrr_at_3_std value: 15.310361808945489 - type: nauc_mrr_at_5_diff1 value: 71.20476915325136 - type: nauc_mrr_at_5_max value: 48.441764267472145 - type: nauc_mrr_at_5_std value: 15.365655626467209 - type: nauc_ndcg_at_1000_diff1 value: 70.08074385839639 - type: nauc_ndcg_at_1000_max value: 48.6611446591934 - type: nauc_ndcg_at_1000_std value: 15.430653624542611 - type: nauc_ndcg_at_100_diff1 value: 69.68550330145398 - type: nauc_ndcg_at_100_max value: 48.88307581467983 - type: nauc_ndcg_at_100_std value: 16.234260889596484 - type: nauc_ndcg_at_10_diff1 value: 69.84945527709709 - type: nauc_ndcg_at_10_max value: 49.4084894308013 - type: nauc_ndcg_at_10_std value: 15.695585904151896 - type: nauc_ndcg_at_1_diff1 value: 73.60832695813949 - type: nauc_ndcg_at_1_max value: 44.578750878677084 - type: nauc_ndcg_at_1_std value: 11.890587471184963 - type: nauc_ndcg_at_20_diff1 value: 69.33301377386857 - type: nauc_ndcg_at_20_max value: 49.35761408825228 - type: nauc_ndcg_at_20_std value: 16.3513166242212 - type: nauc_ndcg_at_3_diff1 value: 70.68084301272158 - type: nauc_ndcg_at_3_max value: 46.19757134168426 - type: nauc_ndcg_at_3_std value: 11.440557917517024 - type: nauc_ndcg_at_5_diff1 value: 70.22608752669124 - type: nauc_ndcg_at_5_max value: 47.715928046644144 - type: nauc_ndcg_at_5_std value: 12.927681872823138 - type: nauc_precision_at_1000_diff1 value: -30.771908331112545 - type: nauc_precision_at_1000_max value: 21.856638608356842 - type: nauc_precision_at_1000_std value: 35.14083908557948 - type: nauc_precision_at_100_diff1 value: -21.94474337380867 - type: nauc_precision_at_100_max value: 27.749326522576958 - type: nauc_precision_at_100_std value: 38.74941555088935 - type: nauc_precision_at_10_diff1 value: 4.1338368705214705 - type: nauc_precision_at_10_max value: 40.35268389940857 - type: nauc_precision_at_10_std value: 34.86150577835351 - type: nauc_precision_at_1_diff1 value: 73.60832695813949 - type: nauc_precision_at_1_max value: 44.578750878677084 - type: nauc_precision_at_1_std value: 11.890587471184963 - type: nauc_precision_at_20_diff1 value: -5.308128515414954 - type: nauc_precision_at_20_max value: 34.927193769639246 - type: nauc_precision_at_20_std value: 36.45210990375071 - type: nauc_precision_at_3_diff1 value: 38.801243070827766 - type: nauc_precision_at_3_max value: 50.15215786362873 - type: nauc_precision_at_3_std value: 22.902503553912712 - type: nauc_precision_at_5_diff1 value: 19.15608744207784 - type: nauc_precision_at_5_max value: 43.451044323440705 - type: nauc_precision_at_5_std value: 26.099168664730975 - type: nauc_recall_at_1000_diff1 value: 59.973000734681946 - type: nauc_recall_at_1000_max value: 90.19473173884923 - type: nauc_recall_at_1000_std value: 77.70012495920277 - type: nauc_recall_at_100_diff1 value: 49.520208174749534 - type: nauc_recall_at_100_max value: 62.658917735912844 - type: nauc_recall_at_100_std value: 57.59734216892526 - type: nauc_recall_at_10_diff1 value: 63.59382135270663 - type: nauc_recall_at_10_max value: 57.66910071241303 - type: nauc_recall_at_10_std value: 26.157501494756524 - type: nauc_recall_at_1_diff1 value: 73.66858140737193 - type: nauc_recall_at_1_max value: 37.72209378868329 - type: nauc_recall_at_1_std value: 6.058877150429456 - type: nauc_recall_at_20_diff1 value: 58.60290521588567 - type: nauc_recall_at_20_max value: 59.907374912367516 - type: nauc_recall_at_20_std value: 33.91543413688288 - type: nauc_recall_at_3_diff1 value: 68.02786476343704 - type: nauc_recall_at_3_max value: 45.954227249575986 - type: nauc_recall_at_3_std value: 10.821057815371045 - type: nauc_recall_at_5_diff1 value: 65.83241381992168 - type: nauc_recall_at_5_max value: 50.03082691375689 - type: nauc_recall_at_5_std value: 15.241601072308331 - type: ndcg_at_1 value: 65.389 - type: ndcg_at_10 value: 76.485 - type: ndcg_at_100 value: 78.47 - type: ndcg_at_1000 value: 78.875 - type: ndcg_at_20 value: 77.321 - type: ndcg_at_3 value: 72.51100000000001 - type: ndcg_at_5 value: 74.48 - type: precision_at_1 value: 65.389 - type: precision_at_10 value: 9.937999999999999 - type: precision_at_100 value: 1.098 - type: precision_at_1000 value: 0.11299999999999999 - type: precision_at_20 value: 5.167 - type: precision_at_3 value: 28.224 - type: precision_at_5 value: 18.368000000000002 - type: recall_at_1 value: 62.437 - type: recall_at_10 value: 87.50099999999999 - type: recall_at_100 value: 96.518 - type: recall_at_1000 value: 99.506 - type: recall_at_20 value: 90.606 - type: recall_at_3 value: 77.35300000000001 - type: recall_at_5 value: 81.811 - task: type: PairClassification dataset: name: MTEB SprintDuplicateQuestions (default) type: mteb/sprintduplicatequestions-pairclassification config: default split: test revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46 metrics: - type: cosine_accuracy value: 99.86534653465347 - type: cosine_accuracy_threshold value: 87.42109537124634 - type: cosine_ap value: 96.62589824590614 - type: cosine_f1 value: 93.1726907630522 - type: cosine_f1_threshold value: 87.26919889450073 - type: cosine_precision value: 93.54838709677419 - type: cosine_recall value: 92.80000000000001 - type: dot_accuracy value: 99.86534653465347 - type: dot_accuracy_threshold value: 174.84219074249268 - type: dot_ap value: 96.62589584517633 - type: dot_f1 value: 93.1726907630522 - type: dot_f1_threshold value: 174.53839778900146 - type: dot_precision value: 93.54838709677419 - type: dot_recall value: 92.80000000000001 - type: euclidean_accuracy value: 99.86534653465347 - type: euclidean_accuracy_threshold value: 70.93350887298584 - type: euclidean_ap value: 96.62589584517633 - type: euclidean_f1 value: 93.1726907630522 - type: euclidean_f1_threshold value: 71.36050462722778 - type: euclidean_precision value: 93.54838709677419 - type: euclidean_recall value: 92.80000000000001 - type: main_score value: 96.62589824590614 - type: manhattan_accuracy value: 99.86237623762376 - type: manhattan_accuracy_threshold value: 1510.8413696289062 - type: manhattan_ap value: 96.5990356446392 - type: manhattan_f1 value: 92.94057897409853 - type: manhattan_f1_threshold value: 1530.6350708007812 - type: manhattan_precision value: 94.42724458204334 - type: manhattan_recall value: 91.5 - type: max_accuracy value: 99.86534653465347 - type: max_ap value: 96.62589824590614 - type: max_f1 value: 93.1726907630522 - type: max_precision value: 94.42724458204334 - type: max_recall value: 92.80000000000001 - type: similarity_accuracy value: 99.86534653465347 - type: similarity_accuracy_threshold value: 87.42109537124634 - type: similarity_ap value: 96.62589824590614 - type: similarity_f1 value: 93.1726907630522 - type: similarity_f1_threshold value: 87.26919889450073 - type: similarity_precision value: 93.54838709677419 - type: similarity_recall value: 92.80000000000001 - task: type: PairClassification dataset: name: MTEB SprintDuplicateQuestions (default) type: mteb/sprintduplicatequestions-pairclassification config: default split: validation revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46 metrics: - type: cosine_accuracy value: 99.84059405940594 - type: cosine_accuracy_threshold value: 87.00189590454102 - type: cosine_ap value: 96.73329740037518 - type: cosine_f1 value: 92.0493827160494 - type: cosine_f1_threshold value: 86.32840514183044 - type: cosine_precision value: 90.92682926829269 - type: cosine_recall value: 93.2 - type: dot_accuracy value: 99.84059405940594 - type: dot_accuracy_threshold value: 174.00379180908203 - type: dot_ap value: 96.73329740037518 - type: dot_f1 value: 92.0493827160494 - type: dot_f1_threshold value: 172.65679836273193 - type: dot_precision value: 90.92682926829269 - type: dot_recall value: 93.2 - type: euclidean_accuracy value: 99.84059405940594 - type: euclidean_accuracy_threshold value: 72.1057653427124 - type: euclidean_ap value: 96.73329740037518 - type: euclidean_f1 value: 92.0493827160494 - type: euclidean_f1_threshold value: 73.95024299621582 - type: euclidean_precision value: 90.92682926829269 - type: euclidean_recall value: 93.2 - type: main_score value: 96.75632821046904 - type: manhattan_accuracy value: 99.84257425742574 - type: manhattan_accuracy_threshold value: 1568.2302474975586 - type: manhattan_ap value: 96.75632821046904 - type: manhattan_f1 value: 91.98229217904576 - type: manhattan_f1_threshold value: 1615.3419494628906 - type: manhattan_precision value: 90.51306873184899 - type: manhattan_recall value: 93.5 - type: max_accuracy value: 99.84257425742574 - type: max_ap value: 96.75632821046904 - type: max_f1 value: 92.0493827160494 - type: max_precision value: 90.92682926829269 - type: max_recall value: 93.5 - type: similarity_accuracy value: 99.84059405940594 - type: similarity_accuracy_threshold value: 87.00189590454102 - type: similarity_ap value: 96.73329740037518 - type: similarity_f1 value: 92.0493827160494 - type: similarity_f1_threshold value: 86.32840514183044 - type: similarity_precision value: 90.92682926829269 - type: similarity_recall value: 93.2 - task: type: Clustering dataset: name: MTEB StackExchangeClustering (default) type: mteb/stackexchange-clustering config: default split: test revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259 metrics: - type: main_score value: 62.86417213636288 - type: v_measure value: 62.86417213636288 - type: v_measure_std value: 4.26517499407962 - task: type: Clustering dataset: name: MTEB StackExchangeClusteringP2P (default) type: mteb/stackexchange-clustering-p2p config: default split: test revision: 815ca46b2622cec33ccafc3735d572c266efdb44 metrics: - type: main_score value: 34.49041102464247 - type: v_measure value: 34.49041102464247 - type: v_measure_std value: 1.5008009956624384 - task: type: Reranking dataset: name: MTEB StackOverflowDupQuestions (default) type: mteb/stackoverflowdupquestions-reranking config: default split: test revision: e185fbe320c72810689fc5848eb6114e1ef5ec69 metrics: - type: main_score value: 53.56080676583018 - type: map value: 53.56080676583018 - type: mrr value: 54.574155419743654 - type: nAUC_map_diff1 value: 38.68676474201522 - type: nAUC_map_max value: 13.538152012883021 - type: nAUC_map_std value: 8.406474170060411 - type: nAUC_mrr_diff1 value: 38.27738033427405 - type: nAUC_mrr_max value: 14.313023512543305 - type: nAUC_mrr_std value: 9.482773181023104 - task: type: Summarization dataset: name: MTEB SummEval (default) type: mteb/summeval config: default split: test revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c metrics: - type: cosine_pearson value: 30.78001838626019 - type: cosine_spearman value: 30.06796987185709 - type: dot_pearson value: 30.78001527942813 - type: dot_spearman value: 30.063748343894524 - type: main_score value: 30.06796987185709 - type: pearson value: 30.78001838626019 - type: spearman value: 30.06796987185709 - task: type: Retrieval dataset: name: MTEB TRECCOVID (default) type: mteb/trec-covid config: default split: test revision: bb9466bac8153a0349341eb1b22e06409e78ef4e metrics: - type: main_score value: 67.647 - type: map_at_1 value: 0.192 - type: map_at_10 value: 1.678 - type: map_at_100 value: 9.362 - type: map_at_1000 value: 23.655 - type: map_at_20 value: 2.9770000000000003 - type: map_at_3 value: 0.5559999999999999 - type: map_at_5 value: 0.91 - type: mrr_at_1 value: 74.0 - type: mrr_at_10 value: 84.07460317460317 - type: mrr_at_100 value: 84.07460317460317 - type: mrr_at_1000 value: 84.07460317460317 - type: mrr_at_20 value: 84.07460317460317 - type: mrr_at_3 value: 82.66666666666667 - type: mrr_at_5 value: 83.56666666666666 - type: nauc_map_at_1000_diff1 value: -1.1098863157023129 - type: nauc_map_at_1000_max value: 48.42614641797866 - type: nauc_map_at_1000_std value: 74.41245113222085 - type: nauc_map_at_100_diff1 value: 11.810610128543328 - type: nauc_map_at_100_max value: 45.54012493749073 - type: nauc_map_at_100_std value: 55.216633821552705 - type: nauc_map_at_10_diff1 value: 14.706640439003039 - type: nauc_map_at_10_max value: 27.009359341915196 - type: nauc_map_at_10_std value: 12.580248102741749 - type: nauc_map_at_1_diff1 value: 18.849085390343852 - type: nauc_map_at_1_max value: 22.147807794097968 - type: nauc_map_at_1_std value: 8.226943075643607 - type: nauc_map_at_20_diff1 value: 11.262073635376204 - type: nauc_map_at_20_max value: 29.788086926929736 - type: nauc_map_at_20_std value: 18.831720483995586 - type: nauc_map_at_3_diff1 value: 10.591785709689498 - type: nauc_map_at_3_max value: 19.999731080136282 - type: nauc_map_at_3_std value: 8.283426397720875 - type: nauc_map_at_5_diff1 value: 13.438781723934065 - type: nauc_map_at_5_max value: 23.771513155136258 - type: nauc_map_at_5_std value: 11.39274226111021 - type: nauc_mrr_at_1000_diff1 value: -7.700192607976083 - type: nauc_mrr_at_1000_max value: 58.06999088899807 - type: nauc_mrr_at_1000_std value: 55.498437292780146 - type: nauc_mrr_at_100_diff1 value: -7.700192607976083 - type: nauc_mrr_at_100_max value: 58.06999088899807 - type: nauc_mrr_at_100_std value: 55.498437292780146 - type: nauc_mrr_at_10_diff1 value: -7.700192607976083 - type: nauc_mrr_at_10_max value: 58.06999088899807 - type: nauc_mrr_at_10_std value: 55.498437292780146 - type: nauc_mrr_at_1_diff1 value: 5.8837841125663815 - type: nauc_mrr_at_1_max value: 57.15502209967149 - type: nauc_mrr_at_1_std value: 53.94752848627391 - type: nauc_mrr_at_20_diff1 value: -7.700192607976083 - type: nauc_mrr_at_20_max value: 58.06999088899807 - type: nauc_mrr_at_20_std value: 55.498437292780146 - type: nauc_mrr_at_3_diff1 value: -9.92939143073178 - type: nauc_mrr_at_3_max value: 59.45162969291663 - type: nauc_mrr_at_3_std value: 56.1706390124621 - type: nauc_mrr_at_5_diff1 value: -10.352998992145512 - type: nauc_mrr_at_5_max value: 57.75340046811098 - type: nauc_mrr_at_5_std value: 55.20409055698553 - type: nauc_ndcg_at_1000_diff1 value: 1.3886748577056562 - type: nauc_ndcg_at_1000_max value: 45.41548784147603 - type: nauc_ndcg_at_1000_std value: 69.30388009311415 - type: nauc_ndcg_at_100_diff1 value: 0.4312493032685509 - type: nauc_ndcg_at_100_max value: 45.2714318986444 - type: nauc_ndcg_at_100_std value: 73.00621559010233 - type: nauc_ndcg_at_10_diff1 value: -8.161869949696207 - type: nauc_ndcg_at_10_max value: 44.11896916629053 - type: nauc_ndcg_at_10_std value: 56.814234959093845 - type: nauc_ndcg_at_1_diff1 value: 6.616052060737538 - type: nauc_ndcg_at_1_max value: 36.42502274158562 - type: nauc_ndcg_at_1_std value: 50.542299349240814 - type: nauc_ndcg_at_20_diff1 value: -10.435311528666439 - type: nauc_ndcg_at_20_max value: 40.17434792292328 - type: nauc_ndcg_at_20_std value: 58.15224379743095 - type: nauc_ndcg_at_3_diff1 value: -8.681207709572954 - type: nauc_ndcg_at_3_max value: 42.74075328162171 - type: nauc_ndcg_at_3_std value: 52.252671273049266 - type: nauc_ndcg_at_5_diff1 value: -10.760752447599076 - type: nauc_ndcg_at_5_max value: 45.30740412496431 - type: nauc_ndcg_at_5_std value: 58.2580376338619 - type: nauc_precision_at_1000_diff1 value: -17.63226899483217 - type: nauc_precision_at_1000_max value: 34.52005297813093 - type: nauc_precision_at_1000_std value: 58.08147588022084 - type: nauc_precision_at_100_diff1 value: -1.6026030210260822 - type: nauc_precision_at_100_max value: 46.64263585966634 - type: nauc_precision_at_100_std value: 73.31086780620457 - type: nauc_precision_at_10_diff1 value: -7.9280637963804645 - type: nauc_precision_at_10_max value: 49.556338319147216 - type: nauc_precision_at_10_std value: 53.013180728865436 - type: nauc_precision_at_1_diff1 value: 5.8837841125663815 - type: nauc_precision_at_1_max value: 57.15502209967149 - type: nauc_precision_at_1_std value: 53.94752848627391 - type: nauc_precision_at_20_diff1 value: -12.831360657341229 - type: nauc_precision_at_20_max value: 41.99544599867401 - type: nauc_precision_at_20_std value: 55.9674807351615 - type: nauc_precision_at_3_diff1 value: -16.796733759190047 - type: nauc_precision_at_3_max value: 46.054296733759244 - type: nauc_precision_at_3_std value: 49.79209352778117 - type: nauc_precision_at_5_diff1 value: -15.871656413523668 - type: nauc_precision_at_5_max value: 52.700458519160634 - type: nauc_precision_at_5_std value: 57.1342030226753 - type: nauc_recall_at_1000_diff1 value: -0.8671141204967768 - type: nauc_recall_at_1000_max value: 39.213878637976336 - type: nauc_recall_at_1000_std value: 57.52498157883819 - type: nauc_recall_at_100_diff1 value: 13.71539607682519 - type: nauc_recall_at_100_max value: 34.398894963723606 - type: nauc_recall_at_100_std value: 38.15917686169161 - type: nauc_recall_at_10_diff1 value: 14.494212708704499 - type: nauc_recall_at_10_max value: 19.727092277749353 - type: nauc_recall_at_10_std value: 5.450799655125242 - type: nauc_recall_at_1_diff1 value: 18.849085390343852 - type: nauc_recall_at_1_max value: 22.147807794097968 - type: nauc_recall_at_1_std value: 8.226943075643607 - type: nauc_recall_at_20_diff1 value: 9.720808675841297 - type: nauc_recall_at_20_max value: 19.01250825066701 - type: nauc_recall_at_20_std value: 7.725806970920393 - type: nauc_recall_at_3_diff1 value: 7.127984664955145 - type: nauc_recall_at_3_max value: 15.524675558616 - type: nauc_recall_at_3_std value: 3.6362524696759704 - type: nauc_recall_at_5_diff1 value: 9.773840859655213 - type: nauc_recall_at_5_max value: 17.976145684131815 - type: nauc_recall_at_5_std value: 5.433479951527897 - type: ndcg_at_1 value: 68.0 - type: ndcg_at_10 value: 67.647 - type: ndcg_at_100 value: 52.568000000000005 - type: ndcg_at_1000 value: 48.936 - type: ndcg_at_20 value: 65.23 - type: ndcg_at_3 value: 68.073 - type: ndcg_at_5 value: 70.15400000000001 - type: precision_at_1 value: 74.0 - type: precision_at_10 value: 72.8 - type: precision_at_100 value: 54.32 - type: precision_at_1000 value: 21.788 - type: precision_at_20 value: 69.6 - type: precision_at_3 value: 73.333 - type: precision_at_5 value: 76.4 - type: recall_at_1 value: 0.192 - type: recall_at_10 value: 1.926 - type: recall_at_100 value: 12.967 - type: recall_at_1000 value: 46.414 - type: recall_at_20 value: 3.6020000000000003 - type: recall_at_3 value: 0.5950000000000001 - type: recall_at_5 value: 1.008 - task: type: Retrieval dataset: name: MTEB Touche2020 (default) type: mteb/touche2020 config: default split: test revision: a34f9a33db75fa0cbb21bb5cfc3dae8dc8bec93f metrics: - type: main_score value: 21.418 - type: map_at_1 value: 2.103 - type: map_at_10 value: 8.562 - type: map_at_100 value: 14.488999999999999 - type: map_at_1000 value: 15.966 - type: map_at_20 value: 10.862 - type: map_at_3 value: 4.922 - type: map_at_5 value: 5.771 - type: mrr_at_1 value: 26.53061224489796 - type: mrr_at_10 value: 41.18561710398445 - type: mrr_at_100 value: 42.23103797071357 - type: mrr_at_1000 value: 42.23103797071357 - type: mrr_at_20 value: 41.99007625028033 - type: mrr_at_3 value: 37.414965986394556 - type: mrr_at_5 value: 38.843537414965986 - type: nauc_map_at_1000_diff1 value: -19.351530359917472 - type: nauc_map_at_1000_max value: -24.507017422899555 - type: nauc_map_at_1000_std value: 4.42198895480301 - type: nauc_map_at_100_diff1 value: -18.850998775966502 - type: nauc_map_at_100_max value: -24.362263151537178 - type: nauc_map_at_100_std value: -0.5368896293104107 - type: nauc_map_at_10_diff1 value: -26.175172027837572 - type: nauc_map_at_10_max value: -28.43026690361613 - type: nauc_map_at_10_std value: -11.91118017447121 - type: nauc_map_at_1_diff1 value: -20.487774952653478 - type: nauc_map_at_1_max value: -27.48651530838805 - type: nauc_map_at_1_std value: -14.850754695409051 - type: nauc_map_at_20_diff1 value: -18.37972840319288 - type: nauc_map_at_20_max value: -25.41263310281494 - type: nauc_map_at_20_std value: -14.407088455977735 - type: nauc_map_at_3_diff1 value: -18.703214405275403 - type: nauc_map_at_3_max value: -30.055160976096566 - type: nauc_map_at_3_std value: -13.900503759042953 - type: nauc_map_at_5_diff1 value: -24.059397135404634 - type: nauc_map_at_5_max value: -31.419338369603224 - type: nauc_map_at_5_std value: -14.081937493608754 - type: nauc_mrr_at_1000_diff1 value: -19.253002712346046 - type: nauc_mrr_at_1000_max value: -41.229418795229115 - type: nauc_mrr_at_1000_std value: -8.194012889395678 - type: nauc_mrr_at_100_diff1 value: -19.253002712346046 - type: nauc_mrr_at_100_max value: -41.229418795229115 - type: nauc_mrr_at_100_std value: -8.194012889395678 - type: nauc_mrr_at_10_diff1 value: -20.181934921966565 - type: nauc_mrr_at_10_max value: -41.52122062813685 - type: nauc_mrr_at_10_std value: -8.517353777317007 - type: nauc_mrr_at_1_diff1 value: -14.93163259442193 - type: nauc_mrr_at_1_max value: -28.271418042405944 - type: nauc_mrr_at_1_std value: -8.483373359409944 - type: nauc_mrr_at_20_diff1 value: -18.71853810624142 - type: nauc_mrr_at_20_max value: -41.643831727769445 - type: nauc_mrr_at_20_std value: -7.994451407552443 - type: nauc_mrr_at_3_diff1 value: -20.10234227022684 - type: nauc_mrr_at_3_max value: -41.481700697105964 - type: nauc_mrr_at_3_std value: -10.1964348120824 - type: nauc_mrr_at_5_diff1 value: -22.378294273446333 - type: nauc_mrr_at_5_max value: -42.399016719230765 - type: nauc_mrr_at_5_std value: -9.64387750117273 - type: nauc_ndcg_at_1000_diff1 value: -20.46602931039575 - type: nauc_ndcg_at_1000_max value: -29.51388332800775 - type: nauc_ndcg_at_1000_std value: 31.97369133164661 - type: nauc_ndcg_at_100_diff1 value: -20.175041013877696 - type: nauc_ndcg_at_100_max value: -36.286223372960904 - type: nauc_ndcg_at_100_std value: 18.299490153297647 - type: nauc_ndcg_at_10_diff1 value: -24.02376235671449 - type: nauc_ndcg_at_10_max value: -35.828837894026115 - type: nauc_ndcg_at_10_std value: -4.55634576055288 - type: nauc_ndcg_at_1_diff1 value: -17.757931878350778 - type: nauc_ndcg_at_1_max value: -28.882474074071734 - type: nauc_ndcg_at_1_std value: -2.7961892265024058 - type: nauc_ndcg_at_20_diff1 value: -14.096289255526088 - type: nauc_ndcg_at_20_max value: -34.41866397107521 - type: nauc_ndcg_at_20_std value: -11.18648918839053 - type: nauc_ndcg_at_3_diff1 value: -17.842815168108977 - type: nauc_ndcg_at_3_max value: -38.621085644925195 - type: nauc_ndcg_at_3_std value: -3.8881155902480544 - type: nauc_ndcg_at_5_diff1 value: -25.284864428560216 - type: nauc_ndcg_at_5_max value: -38.237375550106336 - type: nauc_ndcg_at_5_std value: -4.911301062236913 - type: nauc_precision_at_1000_diff1 value: 8.807028730460438 - type: nauc_precision_at_1000_max value: 37.1813389306755 - type: nauc_precision_at_1000_std value: 50.105218819171206 - type: nauc_precision_at_100_diff1 value: -11.451048560927282 - type: nauc_precision_at_100_max value: -18.494269088171183 - type: nauc_precision_at_100_std value: 61.93415991533763 - type: nauc_precision_at_10_diff1 value: -20.970160893678482 - type: nauc_precision_at_10_max value: -33.05509638276482 - type: nauc_precision_at_10_std value: -2.7821722336643617 - type: nauc_precision_at_1_diff1 value: -14.93163259442193 - type: nauc_precision_at_1_max value: -28.271418042405944 - type: nauc_precision_at_1_std value: -8.483373359409944 - type: nauc_precision_at_20_diff1 value: -0.4353890707357106 - type: nauc_precision_at_20_max value: -24.429655423454683 - type: nauc_precision_at_20_std value: -3.4047901749399783 - type: nauc_precision_at_3_diff1 value: -12.694326928341601 - type: nauc_precision_at_3_max value: -39.390569182573856 - type: nauc_precision_at_3_std value: -8.824591692422153 - type: nauc_precision_at_5_diff1 value: -24.96294483100504 - type: nauc_precision_at_5_max value: -39.857140509888495 - type: nauc_precision_at_5_std value: -8.166429095904583 - type: nauc_recall_at_1000_diff1 value: -19.26364200094709 - type: nauc_recall_at_1000_max value: -13.410785253002475 - type: nauc_recall_at_1000_std value: 79.88850839052468 - type: nauc_recall_at_100_diff1 value: -24.001850273182704 - type: nauc_recall_at_100_max value: -35.88316231220963 - type: nauc_recall_at_100_std value: 31.815424604607674 - type: nauc_recall_at_10_diff1 value: -26.40817358742444 - type: nauc_recall_at_10_max value: -33.727382714288446 - type: nauc_recall_at_10_std value: -14.552547474689526 - type: nauc_recall_at_1_diff1 value: -20.487774952653478 - type: nauc_recall_at_1_max value: -27.48651530838805 - type: nauc_recall_at_1_std value: -14.850754695409051 - type: nauc_recall_at_20_diff1 value: -12.188115473749033 - type: nauc_recall_at_20_max value: -32.11814820672923 - type: nauc_recall_at_20_std value: -17.398182571029892 - type: nauc_recall_at_3_diff1 value: -17.529776818775066 - type: nauc_recall_at_3_max value: -39.34912622762624 - type: nauc_recall_at_3_std value: -17.868268060845814 - type: nauc_recall_at_5_diff1 value: -27.32652911017479 - type: nauc_recall_at_5_max value: -39.898687035007576 - type: nauc_recall_at_5_std value: -16.732887465142213 - type: ndcg_at_1 value: 23.469 - type: ndcg_at_10 value: 21.418 - type: ndcg_at_100 value: 34.251 - type: ndcg_at_1000 value: 45.371 - type: ndcg_at_20 value: 23.238 - type: ndcg_at_3 value: 23.886 - type: ndcg_at_5 value: 21.11 - type: precision_at_1 value: 26.531 - type: precision_at_10 value: 20.0 - type: precision_at_100 value: 7.388 - type: precision_at_1000 value: 1.488 - type: precision_at_20 value: 16.02 - type: precision_at_3 value: 26.531 - type: precision_at_5 value: 21.633 - type: recall_at_1 value: 2.103 - type: recall_at_10 value: 14.81 - type: recall_at_100 value: 46.622 - type: recall_at_1000 value: 80.69800000000001 - type: recall_at_20 value: 22.861 - type: recall_at_3 value: 6.399000000000001 - type: recall_at_5 value: 8.23 - task: type: Classification dataset: name: MTEB ToxicConversationsClassification (default) type: mteb/toxic_conversations_50k config: default split: test revision: edfaf9da55d3dd50d43143d90c1ac476895ae6de metrics: - type: accuracy value: 65.7666015625 - type: ap value: 11.843884703213776 - type: ap_weighted value: 11.843884703213776 - type: f1 value: 50.277795864693054 - type: f1_weighted value: 73.18095534864581 - type: main_score value: 65.7666015625 - task: type: Classification dataset: name: MTEB TweetSentimentExtractionClassification (default) type: mteb/tweet_sentiment_extraction config: default split: test revision: d604517c81ca91fe16a244d1248fc021f9ecee7a metrics: - type: accuracy value: 63.28522920203735 - type: f1 value: 63.3721509844546 - type: f1_weighted value: 62.21321405962959 - type: main_score value: 63.28522920203735 - task: type: Clustering dataset: name: MTEB TwentyNewsgroupsClustering (default) type: mteb/twentynewsgroups-clustering config: default split: test revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 metrics: - type: main_score value: 48.905527607381 - type: v_measure value: 48.905527607381 - type: v_measure_std value: 1.6720470024352694 - task: type: PairClassification dataset: name: MTEB TwitterSemEval2015 (default) type: mteb/twittersemeval2015-pairclassification config: default split: test revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 metrics: - type: cosine_accuracy value: 86.44572927221792 - type: cosine_accuracy_threshold value: 87.59676218032837 - type: cosine_ap value: 75.63030766992325 - type: cosine_f1 value: 69.44552655499287 - type: cosine_f1_threshold value: 86.22946739196777 - type: cosine_precision value: 68.37126054717464 - type: cosine_recall value: 70.55408970976254 - type: dot_accuracy value: 86.44572927221792 - type: dot_accuracy_threshold value: 175.19352436065674 - type: dot_ap value: 75.63032114657348 - type: dot_f1 value: 69.44552655499287 - type: dot_f1_threshold value: 172.45893478393555 - type: dot_precision value: 68.37126054717464 - type: dot_recall value: 70.55408970976254 - type: euclidean_accuracy value: 86.44572927221792 - type: euclidean_accuracy_threshold value: 70.43645977973938 - type: euclidean_ap value: 75.6303708231987 - type: euclidean_f1 value: 69.44552655499287 - type: euclidean_f1_threshold value: 74.21733140945435 - type: euclidean_precision value: 68.37126054717464 - type: euclidean_recall value: 70.55408970976254 - type: main_score value: 75.7377286185127 - type: manhattan_accuracy value: 86.55897955534363 - type: manhattan_accuracy_threshold value: 1556.027603149414 - type: manhattan_ap value: 75.7377286185127 - type: manhattan_f1 value: 69.66236955187233 - type: manhattan_f1_threshold value: 1654.3787002563477 - type: manhattan_precision value: 65.1435132032147 - type: manhattan_recall value: 74.85488126649076 - type: max_accuracy value: 86.55897955534363 - type: max_ap value: 75.7377286185127 - type: max_f1 value: 69.66236955187233 - type: max_precision value: 68.37126054717464 - type: max_recall value: 74.85488126649076 - type: similarity_accuracy value: 86.44572927221792 - type: similarity_accuracy_threshold value: 87.59676218032837 - type: similarity_ap value: 75.63030766992325 - type: similarity_f1 value: 69.44552655499287 - type: similarity_f1_threshold value: 86.22946739196777 - type: similarity_precision value: 68.37126054717464 - type: similarity_recall value: 70.55408970976254 - task: type: PairClassification dataset: name: MTEB TwitterURLCorpus (default) type: mteb/twitterurlcorpus-pairclassification config: default split: test revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf metrics: - type: cosine_accuracy value: 88.97038848139093 - type: cosine_accuracy_threshold value: 83.80404710769653 - type: cosine_ap value: 85.91804313814289 - type: cosine_f1 value: 78.21080602302922 - type: cosine_f1_threshold value: 82.21379518508911 - type: cosine_precision value: 75.10632265381344 - type: cosine_recall value: 81.5829996920234 - type: dot_accuracy value: 88.97038848139093 - type: dot_accuracy_threshold value: 167.60810613632202 - type: dot_ap value: 85.91804480684166 - type: dot_f1 value: 78.21080602302922 - type: dot_f1_threshold value: 164.42759037017822 - type: dot_precision value: 75.10632265381344 - type: dot_recall value: 81.5829996920234 - type: euclidean_accuracy value: 88.97038848139093 - type: euclidean_accuracy_threshold value: 80.48837184906006 - type: euclidean_ap value: 85.91804603491305 - type: euclidean_f1 value: 78.21080602302922 - type: euclidean_f1_threshold value: 84.34738516807556 - type: euclidean_precision value: 75.10632265381344 - type: euclidean_recall value: 81.5829996920234 - type: main_score value: 86.05361584367344 - type: manhattan_accuracy value: 89.02472154305894 - type: manhattan_accuracy_threshold value: 1732.803726196289 - type: manhattan_ap value: 86.05361584367344 - type: manhattan_f1 value: 78.20484500404977 - type: manhattan_f1_threshold value: 1832.084083557129 - type: manhattan_precision value: 74.93297587131367 - type: manhattan_recall value: 81.7754850631352 - type: max_accuracy value: 89.02472154305894 - type: max_ap value: 86.05361584367344 - type: max_f1 value: 78.21080602302922 - type: max_precision value: 75.10632265381344 - type: max_recall value: 81.7754850631352 - type: similarity_accuracy value: 88.97038848139093 - type: similarity_accuracy_threshold value: 83.80404710769653 - type: similarity_ap value: 85.91804313814289 - type: similarity_f1 value: 78.21080602302922 - type: similarity_f1_threshold value: 82.21379518508911 - type: similarity_precision value: 75.10632265381344 - type: similarity_recall value: 81.5829996920234 --- Add stuff later!
[ "SUMMARIZATION" ]
Non_BioNLP
mspy/twitter-paraphrase-embeddings
mspy
sentence-similarity
[ "sentence-transformers", "safetensors", "mpnet", "sentence-similarity", "feature-extraction", "generated_from_trainer", "dataset_size:13063", "loss:CosineSimilarityLoss", "arxiv:1908.10084", "base_model:sentence-transformers/all-mpnet-base-v2", "base_model:finetune:sentence-transformers/all-mpnet-base-v2", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
1,722,169,618,000
2024-07-28T12:29:07
5
0
--- base_model: sentence-transformers/all-mpnet-base-v2 datasets: [] language: [] library_name: sentence-transformers metrics: - pearson_cosine - spearman_cosine - pearson_manhattan - spearman_manhattan - pearson_euclidean - spearman_euclidean - pearson_dot - spearman_dot - pearson_max - spearman_max pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:13063 - loss:CosineSimilarityLoss widget: - source_sentence: I cant wait to leave Chicago sentences: - This is the shit Chicago needs to be recognized for not Keef - is candice singing again tonight - half time Chelsea were losing 10 - source_sentence: Andre miller best lobbing pg in the game sentences: - Am I the only one who dont get Amber alert - Backstrom hurt in warmup Harding could start - Andre miller is even slower in person - source_sentence: Bayless couldve dunked that from the free throw sentences: - but what great finger roll by Bayless - Wow Bayless has to make EspnSCTop with that end of 3rd - i mean calum u didnt follow - source_sentence: Backstrom Hurt in warmups Harding gets the start sentences: - Should I go to Nashville or Chicago for my 17th birthday - I hate Chelsea possibly more than most - Of course Backstrom would get injured during warmups - source_sentence: Calum I love you plz follow me sentences: - CALUM PLEASE BE MY FIRST CELEBRITY TO FOLLOW ME - Walking around downtown Chicago in a dress and listening to the new Iggy Pop - I think Candice has what it takes to win American Idol AND Angie too model-index: - name: SentenceTransformer based on sentence-transformers/all-mpnet-base-v2 results: - task: type: semantic-similarity name: Semantic Similarity dataset: name: Unknown type: unknown metrics: - type: pearson_cosine value: 0.6949485250178733 name: Pearson Cosine - type: spearman_cosine value: 0.6626359968437283 name: Spearman Cosine - type: pearson_manhattan value: 0.688092975176289 name: Pearson Manhattan - type: spearman_manhattan value: 0.6630998028133662 name: Spearman Manhattan - type: pearson_euclidean value: 0.6880277270034267 name: Pearson Euclidean - type: spearman_euclidean value: 0.6626358741747785 name: Spearman Euclidean - type: pearson_dot value: 0.694948520847878 name: Pearson Dot - type: spearman_dot value: 0.6626359082695851 name: Spearman Dot - type: pearson_max value: 0.6949485250178733 name: Pearson Max - type: spearman_max value: 0.6630998028133662 name: Spearman Max --- # SentenceTransformer based on sentence-transformers/all-mpnet-base-v2 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. ## Model Details ### Model Description - **Model Type:** Sentence Transformer - **Base model:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) <!-- at revision 84f2bcc00d77236f9e89c8a360a00fb1139bf47d --> - **Maximum Sequence Length:** 384 tokens - **Output Dimensionality:** 768 tokens - **Similarity Function:** Cosine Similarity <!-- - **Training Dataset:** Unknown --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown --> ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: MPNetModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the ๐Ÿค— Hub model = SentenceTransformer("mspy/twitter-paraphrase-embeddings") # Run inference sentences = [ 'Calum I love you plz follow me', 'CALUM PLEASE BE MY FIRST CELEBRITY TO FOLLOW ME', 'Walking around downtown Chicago in a dress and listening to the new Iggy Pop', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 768] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` <!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* --> ## Evaluation ### Metrics #### Semantic Similarity * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.6949 | | **spearman_cosine** | **0.6626** | | pearson_manhattan | 0.6881 | | spearman_manhattan | 0.6631 | | pearson_euclidean | 0.688 | | spearman_euclidean | 0.6626 | | pearson_dot | 0.6949 | | spearman_dot | 0.6626 | | pearson_max | 0.6949 | | spearman_max | 0.6631 | <!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* --> ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 13,063 training samples * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code> * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | label | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------| | type | string | string | float | | details | <ul><li>min: 7 tokens</li><li>mean: 11.16 tokens</li><li>max: 28 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 12.31 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.33</li><li>max: 1.0</li></ul> | * Samples: | sentence1 | sentence2 | label | |:------------------------------------------------------|:-------------------------------------------------------------------|:-----------------| | <code>EJ Manuel the 1st QB to go in this draft</code> | <code>But my bro from the 757 EJ Manuel is the 1st QB gone</code> | <code>1.0</code> | | <code>EJ Manuel the 1st QB to go in this draft</code> | <code>Can believe EJ Manuel went as the 1st QB in the draft</code> | <code>1.0</code> | | <code>EJ Manuel the 1st QB to go in this draft</code> | <code>EJ MANUEL IS THE 1ST QB what</code> | <code>0.6</code> | * Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters: ```json { "loss_fct": "torch.nn.modules.loss.MSELoss" } ``` ### Evaluation Dataset #### Unnamed Dataset * Size: 4,727 evaluation samples * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code> * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | label | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------| | type | string | string | float | | details | <ul><li>min: 7 tokens</li><li>mean: 10.04 tokens</li><li>max: 16 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 12.22 tokens</li><li>max: 26 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.33</li><li>max: 1.0</li></ul> | * Samples: | sentence1 | sentence2 | label | |:---------------------------------------------------------------|:------------------------------------------------------------------|:-----------------| | <code>A Walk to Remember is the definition of true love</code> | <code>A Walk to Remember is on and Im in town and Im upset</code> | <code>0.2</code> | | <code>A Walk to Remember is the definition of true love</code> | <code>A Walk to Remember is the cutest thing</code> | <code>0.6</code> | | <code>A Walk to Remember is the definition of true love</code> | <code>A walk to remember is on ABC family youre welcome</code> | <code>0.2</code> | * Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters: ```json { "loss_fct": "torch.nn.modules.loss.MSELoss" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `gradient_accumulation_steps`: 2 - `learning_rate`: 2e-05 - `num_train_epochs`: 4 - `warmup_ratio`: 0.1 - `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`: 8 - `per_device_eval_batch_size`: 8 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 2 - `eval_accumulation_steps`: None - `torch_empty_cache_steps`: None - `learning_rate`: 2e-05 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1.0 - `num_train_epochs`: 4 - `max_steps`: -1 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.1 - `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`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `past_index`: -1 - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: False - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_min_num_params`: 0 - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `fsdp_transformer_layer_cls_to_wrap`: None - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch - `optim_args`: None - `adafactor`: False - `group_by_length`: False - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `skip_memory_metrics`: True - `use_legacy_prediction_loop`: False - `push_to_hub`: False - `resume_from_checkpoint`: None - `hub_model_id`: None - `hub_strategy`: every_save - `hub_private_repo`: False - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `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 - `dispatch_batches`: None - `split_batches`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: False - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `eval_on_start`: False - `eval_use_gather_object`: False - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: proportional </details> ### Training Logs | Epoch | Step | Training Loss | loss | spearman_cosine | |:------:|:----:|:-------------:|:------:|:---------------:| | 0.1225 | 100 | - | 0.0729 | 0.6058 | | 0.2449 | 200 | - | 0.0646 | 0.6340 | | 0.3674 | 300 | - | 0.0627 | 0.6397 | | 0.4899 | 400 | - | 0.0621 | 0.6472 | | 0.6124 | 500 | 0.0627 | 0.0626 | 0.6496 | | 0.7348 | 600 | - | 0.0621 | 0.6446 | | 0.8573 | 700 | - | 0.0593 | 0.6695 | | 0.9798 | 800 | - | 0.0636 | 0.6440 | | 1.1023 | 900 | - | 0.0618 | 0.6525 | | 1.2247 | 1000 | 0.0383 | 0.0604 | 0.6639 | | 1.3472 | 1100 | - | 0.0608 | 0.6590 | | 1.4697 | 1200 | - | 0.0620 | 0.6504 | | 1.5922 | 1300 | - | 0.0617 | 0.6467 | | 1.7146 | 1400 | - | 0.0615 | 0.6574 | | 1.8371 | 1500 | 0.0293 | 0.0622 | 0.6536 | | 1.9596 | 1600 | - | 0.0609 | 0.6599 | | 2.0821 | 1700 | - | 0.0605 | 0.6658 | | 2.2045 | 1800 | - | 0.0615 | 0.6588 | | 2.3270 | 1900 | - | 0.0615 | 0.6575 | | 2.4495 | 2000 | 0.0215 | 0.0614 | 0.6598 | | 2.5720 | 2100 | - | 0.0603 | 0.6681 | | 2.6944 | 2200 | - | 0.0606 | 0.6669 | | 2.8169 | 2300 | - | 0.0605 | 0.6642 | | 2.9394 | 2400 | - | 0.0606 | 0.6630 | | 3.0618 | 2500 | 0.018 | 0.0611 | 0.6616 | | 3.1843 | 2600 | - | 0.0611 | 0.6619 | | 3.3068 | 2700 | - | 0.0611 | 0.6608 | | 3.4293 | 2800 | - | 0.0608 | 0.6632 | | 3.5517 | 2900 | - | 0.0608 | 0.6623 | | 3.6742 | 3000 | 0.014 | 0.0615 | 0.6596 | | 3.7967 | 3100 | - | 0.0612 | 0.6616 | | 3.9192 | 3200 | - | 0.0610 | 0.6626 | ### Framework Versions - Python: 3.10.14 - Sentence Transformers: 3.0.1 - Transformers: 4.43.3 - PyTorch: 2.4.0+cu121 - Accelerate: 0.33.0 - Datasets: 2.20.0 - Tokenizers: 0.19.1 ## 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", } ``` <!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->
[ "TEXT_CLASSIFICATION", "SEMANTIC_SIMILARITY" ]
Non_BioNLP
aroot/eng-mya-wsample.43a
aroot
translation
[ "transformers", "pytorch", "tensorboard", "mbart", "text2text-generation", "translation", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
1,688,616,372,000
2023-07-06T04:28:08
12
0
--- metrics: - bleu tags: - translation - generated_from_trainer model-index: - name: eng-mya-wsample.43a results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # eng-mya-wsample.43a This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.8306 - Bleu: 4.6779 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.26.1 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
[ "TRANSLATION" ]
Non_BioNLP
cerebras/Cerebras-GPT-13B
cerebras
text-generation
[ "transformers", "pytorch", "gpt2", "feature-extraction", "causal-lm", "text-generation", "en", "dataset:the_pile", "arxiv:2304.03208", "arxiv:2203.15556", "arxiv:2101.00027", "license:apache-2.0", "text-generation-inference", "region:us" ]
1,679,345,154,000
2023-11-22T21:49:12
2,440
647
--- datasets: - the_pile language: - en license: apache-2.0 pipeline_tag: text-generation tags: - pytorch - causal-lm inference: false --- # Cerebras-GPT 13B Check out our [Blog Post](https://www.cerebras.net/cerebras-gpt) and [arXiv paper](https://arxiv.org/abs/2304.03208)! ## Model Description The Cerebras-GPT family is released to facilitate research into LLM scaling laws using open architectures and data sets and demonstrate the simplicity of and scalability of training LLMs on the Cerebras software and hardware stack. All Cerebras-GPT models are available on Hugging Face. The family includes 111M, 256M, 590M, 1.3B, 2.7B, 6.7B, and 13B models. All models in the Cerebras-GPT family have been trained in accordance with [Chinchilla scaling laws](https://arxiv.org/abs/2203.15556) (20 tokens per model parameter) which is compute-optimal. These models were trained on the [Andromeda](https://www.cerebras.net/andromeda/) AI supercomputer comprised of 16 CS-2 wafer scale systems. Cerebras' [weight streaming technology](https://www.cerebras.net/blog/linear-scaling-made-possible-with-weight-streaming) simplifies the training of LLMs by disaggregating compute from model storage. This allowed for efficient scaling of training across nodes using simple data parallelism. Cerebras systems for pre-training and fine tuning are available in the cloud via the [Cerebras Model Studio](https://www.cerebras.net/product-cloud/). Cerebras CS-2 compatible checkpoints are available in [Cerebras Model Zoo](https://github.com/Cerebras/modelzoo). ## Model Details * Developed by: [Cerebras Systems](https://www.cerebras.net/) * License: Apache 2.0 * Model type: Transformer-based Language Model * Architecture: GPT-3 style architecture * Data set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size: 50257 * Sequence Length: 2048 * Optimizer: AdamW, (ฮฒ1, ฮฒ2) = (0.9, 0.95), adam_eps = 1eโˆ’8 (1eโˆ’9 for larger models) * Positional Encoding: Learned * Language: English * Learn more: Dense Scaling Laws Paper for training procedure, config files, and details on how to use. **Contact**: To ask questions about Cerebras-GPT models, join the [Cerebras Discord](https://discord.gg/q6bZcMWJVu). This is the standard parameterization version of Cerebras-GPT with **13B** parameters Related models: [Cerebras-GPT Models](https://huggingface.co/models?sort=downloads&search=cerebras-gpt) <br><br> | Model | Parameters | Layers | d_model | Heads | d_head | d_ffn | LR | BS (seq) | BS (tokens) | |---------------|------------|--------|---------|-------|--------|--------|----------|----------|----------------| | Cerebras-GPT | 111M | 10 | 768 | 12 | 64 | 3072 | 6.0E-04 | 120 | 246K | | Cerebras-GPT | 256M | 14 | 1088 | 17 | 64 | 4352 | 6.0E-04 | 264 | 541K | | Cerebras-GPT | 590M | 18 | 1536 | 12 | 128 | 6144 | 2.0E-04 | 264 | 541K | | Cerebras-GPT | 1.3B | 24 | 2048 | 16 | 128 | 8192 | 2.0E-04 | 528 | 1.08M | | Cerebras-GPT | 2.7B | 32 | 2560 | 32 | 80 | 10240 | 2.0E-04 | 528 | 1.08M | | Cerebras-GPT | 6.7B | 32 | 4096 | 32 | 128 | 16384 | 1.2E-04 | 1040 | 2.13M | | Cerebras-GPT | 13B | 40 | 5120 | 40 | 128 | 20480 | 1.2E-04 | 720 &rarr; 1080 | 1.47M &rarr; 2.21M | <br><br> ## Quickstart This model can be easily loaded using the AutoModelForCausalLM functionality: ```python from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("cerebras/Cerebras-GPT-13B") model = AutoModelForCausalLM.from_pretrained("cerebras/Cerebras-GPT-13B") text = "Generative AI is " ``` And can be used with Hugging Face Pipelines ```python from transformers import pipeline pipe = pipeline("text-generation", model=model, tokenizer=tokenizer) generated_text = pipe(text, max_length=50, do_sample=False, no_repeat_ngram_size=2)[0] print(generated_text['generated_text']) ``` or with `model.generate()` ```python inputs = tokenizer(text, return_tensors="pt") outputs = model.generate(**inputs, num_beams=5, max_new_tokens=50, early_stopping=True, no_repeat_ngram_size=2) text_output = tokenizer.batch_decode(outputs, skip_special_tokens=True) print(text_output[0]) ``` <br><br> ## Training data Cerebras-GPT is trained using [the Pile](https://pile.eleuther.ai) dataset from [EleutherAI](https://www.eleuther.ai). See the [Pile paper](https://arxiv.org/abs/2101.00027) for a more detailed breakdown of data sources and methodology. The Pile was cleaned using the ftfy library to normalize the text, then filtered using scripts provided by Eleuther. We tokenized the data using byte-pair encoding using the GPT-2 vocabulary. Our tokenized version of the Pile has 371B tokens. We include more details about the training dataset preprocessing in Appendix A.1 of our paper. Recent works find significant duplicate data present in the Pile. Eleutherโ€™s Pythia applies a deduplication process to reduce replicated data, decreasing the Pile dataset size. Pythia was trained on both the standard dataset and deduplicated dataset to characterize the impact. Our models are trained on the standard Pile without deduplication, which may present an opportunity for further improvement with the deduplicated data set. <br><br> ## Training procedure We use the GPT-3 style model architecture. All of our layers use full attention as opposed to the GPT-3 style sparse banded attention. The model shapes were selected to either follow aspect ratio 80 or are the same shape as GPT-3 models. Learning rate warmed up for 375M tokens (1500 steps for 111M and 256M models) and 10x cosine decayed. No dropout was used and weight decay was set to 0.1. All models are trained with MSL of 2048. All models were trained to Chinchilla point: 20 tokens per model parameter. Number of steps was chosen based on optimal batch size (varied by model) and fixed sequence length (2048). See Training Table, below, for details. <br> Model Params | Sequence Length | Batch Size | Number of Steps | Tokens | Tokens per Parameter | Flops ------------ | -------------- | ---------- | --------------- | ------ | -------------------- | ----- 111M | 2048 | 120 | 9037 | 2.22E+09 | 20 | 2.6E+18 256M | 2048 | 264 | 9468 | 5.12E+09 | 20 | 1.3E+19 590M | 2048 | 264 | 21836 | 1.18E+10 | 20 | 6.1E+19 1.3B | 2048 | 528 | 24334 | 2.63E+10 | 20 | 2.8E+20 2.7B | 2048 | 528 | 49041 | 5.30E+10 | 20 | 1.1E+21 6.7B | 2048 | 1040 | 62522 | 1.33E+11 | 20 | 6.3E+21 13B | 2048 | 720 | 174335 | 2.57E+11 | 20 | 2.3E+22 <br><br> ## Evaluations We trained models from smallest to largest and fit a power law as we went along. The power law was helpful for extrapolating the validation loss of the next largest model we trained and provided confidence about whether the training run was going well. We performed upstream (pre-training) evaluations of text prediction cross-entropy using the Pile validation and test splits. We performed downstream evaluations of text generation accuracy on standardized tasks using the [Eleuther lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness). Results are compared against many publicly available large language models in Section 3 of the paper. #### 0-shot Evaluation | Model | Params | Training FLOPs | PILE test xent | Hella-Swag | PIQA | Wino-Grande | Lambada | ARC-e | ARC-c | OpenBookQA | Downstream Average | | ------- | ----- | -------------- | -------------- | ---------- | ----- | ----------- | ------- | ----- | ----- | ---------- | ------------------ | | Cerebras-GPT | 111M | 2.6E+18 | 2.566 | 0.268 | 0.594 | 0.488 | 0.194 | 0.380 | 0.166 | 0.118 | 0.315 | | Cerebras-GPT | 256M | 1.3E+19 | 2.299 | 0.274 | 0.613 | 0.511 | 0.293 | 0.410 | 0.170 | 0.158 | 0.347 | | Cerebras-GPT | 590M | 6.1E+19 | 2.184 | 0.291 | 0.627 | 0.498 | 0.366 | 0.464 | 0.190 | 0.158 | 0.370 | | Cerebras-GPT | 1.3B | 2.8E+20 | 1.996 | 0.325 | 0.664 | 0.521 | 0.462 | 0.508 | 0.224 | 0.166 | 0.410 | | Cerebras-GPT | 2.7B | 1.1E+21 | 1.834 | 0.386 | 0.701 | 0.559 | 0.567 | 0.571 | 0.246 | 0.206 | 0.462 | | Cerebras-GPT | 6.7B | 6.3E+21 | 1.704 | 0.447 | 0.739 | 0.602 | 0.636 | 0.643 | 0.282 | 0.238 | 0.512 | | Cerebras-GPT | 13B | 2.3E+22 | 1.575 | 0.513 | 0.766 | 0.646 | 0.696 | 0.714 | 0.367 | 0.286 | 0.570 | #### 5-shot Evaluation | Model | Params | Hella-Swag | PIQA | Wino-Grande | Lambada | ARC-e | ARC-c | OpenBookQA | | -------- | ----- | ----------| ----- | ----------- | -------| ----- | ----- | ---------- | | Cerebras-GPT | 111M | 0.267 | 0.588 | 0.475 | 0.158 | 0.356 | 0.166 | 0.136 | | Cerebras-GPT | 256M | 0.278 | 0.606 | 0.522 | 0.225 | 0.422 | 0.183 | 0.164 | | Cerebras-GPT | 590M | 0.291 | 0.634 | 0.479 | 0.281 | 0.475 | 0.206 | 0.152 | | Cerebras-GPT | 1.3B | 0.326 | 0.668 | 0.536 | 0.395 | 0.529 | 0.241 | 0.174 | | Cerebras-GPT | 2.7B | 0.382 | 0.697 | 0.543 | 0.487 | 0.590 | 0.267 | 0.224 | | Cerebras-GPT | 6.7B | 0.444 | 0.736 | 0.590 | 0.591 | 0.667 | 0.314 | 0.270 | | Cerebras-GPT | 13B | 0.514 | 0.768 | 0.674 | 0.655 | 0.743 | 0.398 | 0.318 | <br><br> ## Uses and Limitations ### Intended Use The primary intended use is to further research into large language models. These models can be used as a foundation model for NLP, applications, ethics, and alignment research. Our primary intended users are researchers who are working to improve LLMs and practitioners seeking reference implementations, training setups, hyperparameters, or pre-trained models. We release these models with a fully permissive Apache license for the community to use freely. You may fine-tune and adapt Cerebras-GPT models for deployment via either Cerebras [Model Studio](https://www.cerebras.net/product-cloud/) or third-party libraries. Further safety-related testing and mitigations should be applied beore using the Cerebras-GPT model family in production downstream applications. Due to financial and compute budgets, Cerebras-GPT models were only trained and evaluated following the approaches described in the paper. ### Out of Scope Use Cerebras-GPT models are trained on the Pile, with English language only, and are not suitable for machine translation tasks. Cerebras-GPT models have not been tuned for human-facing dialog applications like chatbots and will not respond to prompts in a similar way to models that have received instruction tuning or reinforcement learning from human feedback (RLHF) like Flan-T5 or ChatGPT. Cerebras-GPT models can be tuned using those methods. ### Risk, Bias, Ethical Considerations * **Data**: The Pile dataset has been thoroughly analyzed from various ethical standpoints such as toxicity analysis, gender bias, pejorative content, racially sensitive content etc. Please refer to Pile dataset references. * **Human life**: The outputs from this model may or may not align with human values. The risk needs to be thoroughly investigated before deploying this model in a production environment where it can directly impact human life. * **Risks and harms**: There can be distributional bias in the Pile dataset that can manifest in various forms in the downstream model deployment. There are other risks associated with large language models such as amplifying stereotypes, memorizing training data, or revealing private or secure information. * **Mitigations**: Only mitigations in standard Pile dataset pre-processing were employed when pre-training Cerebras-GPT. <br><br> ## Acknowledgements We are thankful to all Cerebras engineers, past and present, that made this work possible.
[ "TRANSLATION" ]
Non_BioNLP
gaudi/opus-mt-tr-en-ctranslate2
gaudi
translation
[ "transformers", "marian", "ctranslate2", "translation", "license:apache-2.0", "endpoints_compatible", "region:us" ]
1,721,175,425,000
2024-10-18T22:51:04
6
0
--- license: apache-2.0 tags: - ctranslate2 - translation --- # Repository General Information ## Inspired by and derived from the work of [Helsinki-NLP](https://huggingface.co/Helsinki-NLP), [CTranslate2](https://github.com/OpenNMT/CTranslate2), and [michaelfeil](https://huggingface.co/michaelfeil)! - Link to Original Model ([Helsinki-NLP](https://huggingface.co/Helsinki-NLP)): [Model Link](https://huggingface.co/Helsinki-NLP/opus-mt-tr-en) - This respository was based on the work of [CTranslate2](https://github.com/OpenNMT/CTranslate2). - This repository was based on the work of [michaelfeil](https://huggingface.co/michaelfeil). # What is CTranslate2? [CTranslate2](https://opennmt.net/CTranslate2/) is a C++ and Python library for efficient inference with Transformer models. CTranslate2 implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU. CTranslate2 is one of the most performant ways of hosting translation models at scale. Current supported models include: - Encoder-decoder models: Transformer base/big, M2M-100, NLLB, BART, mBART, Pegasus, T5, Whisper - Decoder-only models: GPT-2, GPT-J, GPT-NeoX, OPT, BLOOM, MPT, Llama, Mistral, Gemma, CodeGen, GPTBigCode, Falcon - Encoder-only models: BERT, DistilBERT, XLM-RoBERTa The project is production-oriented and comes with backward compatibility guarantees, but it also includes experimental features related to model compression and inference acceleration. # CTranslate2 Benchmarks Please note that the results presented below are only valid for the configuration used during this benchmark: absolute and relative performance may change with different settings. Tested against `newstest2014` (En -> De) dataset. The benchmark reports the number of target tokens generated per second (higher is better). The results are aggregated over multiple runs. See the benchmark scripts for more details and reproduce these numbers. Please note that the results presented below are only valid for the configuration used during this benchmark: absolute and relative performance may change with different settings. ## CPU Benchmarks for Generic Opus-MT Models | Library | Tokens per Second | Max Memory Usage | BLEU | | :----: | :----: | :----: | :----: | | Transformers 4.26.1 (with PyTorch 1.13.1) | 147.3 | 2332MB | 27.90 | | Marian 1.11.0 (int16) | 330.2 | 5901MB | 27.65 | | Marian 1.11.0 (int8) | 355.8 | 4763MB | 27.27 | | CTranslate2 3.6.0 (int16) | 596.1 | 660MB | 27.53 | | CTranslate2 3.6.0 (int8) | 696.1 | 516MB | 27.65 | ## GPU Benchmarks for Generic Opus-MT Models | Library | Tokens per Second | Max GPU Memory Usage | Max Memory Usage | BLEU | | :----: | :----: | :----: | :----: | :----: | | Transformers 4.26.1 (with PyTorch 1.13.1) | 1022.9 | 4097MB | 2109MB | 27.90 | | Marian 1.11.0 (float16) | 3962.4 | 3239MB | 1976MB | 27.94 | | CTranslate2 3.6.0 (float16) | 9296.7 | 909MB | 814MB | 27.9 | | CTranslate2 3.6.0 (int8 + float16) | 8362.7 | 813MB | 766MB | 27.9 | `Executed with 4 threads on a c5.2xlarge Amazon EC2 instance equipped with an Intel(R) Xeon(R) Platinum 8275CL CPU.` **Source to benchmark information can be found [here](https://github.com/OpenNMT/CTranslate2).**<br /> **Original model BLEU scores can be found [here](https://huggingface.co/Helsinki-NLP/opus-mt-tr-en).** ## Internal Benchmarks Internal testing on our end showed **inference times reduced by 6x-10x** on average compared the vanilla checkpoints using the *transformers* library. A **slight reduction on BLEU scores (~5%)** was also identified in comparison to the vanilla checkpoints with a few exceptions. This is likely due to several factors, one being the quantization applied. Further testing is needed from our end to better assess the reduction in translation quality. The command used to compile the vanilla checkpoint into a CTranslate2 model can be found below. Modifying this command can yield differing balances between inferencing performance and translation quality. # CTranslate2 Installation ```bash pip install hf-hub-ctranslate2>=1.0.0 ctranslate2>=3.13.0 ``` ### ct2-transformers-converter Command Used: ```bash ct2-transformers-converter --model Helsinki-NLP/opus-mt-tr-en --output_dir ./ctranslate2/opus-mt-tr-en-ctranslate2 --force --copy_files README.md generation_config.json tokenizer_config.json vocab.json source.spm .gitattributes target.spm --quantization float16 ``` # CTranslate2 Converted Checkpoint Information: **Compatible With:** - [ctranslate2](https://github.com/OpenNMT/CTranslate2) - [hf-hub-ctranslate2](https://github.com/michaelfeil/hf-hub-ctranslate2) **Compute Type:** - `compute_type=int8_float16` for `device="cuda"` - `compute_type=int8` for `device="cpu"` # Sample Code - ctranslate2 #### Clone the repository to the working directory or wherever you wish to store the model artifacts. #### ```bash git clone https://huggingface.co/gaudi/opus-mt-tr-en-ctranslate2 ``` #### Take the python code below and update the 'model_dir' variable to the location of the cloned repository. #### ```python from ctranslate2 import Translator import transformers model_dir = "./opus-mt-tr-en-ctranslate2" # Path to model directory. translator = Translator( model_path=model_dir, device="cuda", # cpu, cuda, or auto. inter_threads=1, # Maximum number of parallel translations. intra_threads=4, # Number of OpenMP threads per translator. compute_type="int8_float16", # int8 for cpu or int8_float16 for cuda. ) tokenizer = transformers.AutoTokenizer.from_pretrained(model_dir) source = tokenizer.convert_ids_to_tokens(tokenizer.encode("XXXXXX, XXX XX XXXXXX.")) results = translator.translate_batch([source]) target = results[0].hypotheses[0] print(tokenizer.decode(tokenizer.convert_tokens_to_ids(target))) ``` # Sample Code - hf-hub-ctranslate2 **Derived From [michaelfeil](https://huggingface.co/michaelfeil):** ```python from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub from transformers import AutoTokenizer model_name = "gaudi/opus-mt-tr-en-ctranslate2" model = TranslatorCT2fromHfHub( model_name_or_path=model_name, device="cuda", compute_type="int8_float16", tokenizer=AutoTokenizer.from_pretrained(model_name) ) outputs = model.generate( text=["XXX XX XXX XXXXXXX XXXX?", "XX XX XXXX XX XXX!"], ) print(outputs) ``` # License and other remarks: License conditions are intended to be idential to [original huggingface repository](https://huggingface.co/Helsinki-NLP/opus-mt-tr-en) by Helsinki-NLP.
[ "TRANSLATION" ]
Non_BioNLP
Helsinki-NLP/opus-mt-af-es
Helsinki-NLP
translation
[ "transformers", "pytorch", "tf", "marian", "text2text-generation", "translation", "af", "es", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
1,646,263,744,000
2023-08-16T11:25:22
96
0
--- language: - af - es license: apache-2.0 tags: - translation --- ### afr-spa * source group: Afrikaans * target group: Spanish * OPUS readme: [afr-spa](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/afr-spa/README.md) * model: transformer-align * source language(s): afr * target language(s): spa * model: transformer-align * pre-processing: normalization + SentencePiece (spm32k,spm32k) * download original weights: [opus-2020-06-17.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/afr-spa/opus-2020-06-17.zip) * test set translations: [opus-2020-06-17.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/afr-spa/opus-2020-06-17.test.txt) * test set scores: [opus-2020-06-17.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/afr-spa/opus-2020-06-17.eval.txt) ## Benchmarks | testset | BLEU | chr-F | |-----------------------|-------|-------| | Tatoeba-test.afr.spa | 49.9 | 0.680 | ### System Info: - hf_name: afr-spa - source_languages: afr - target_languages: spa - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/afr-spa/README.md - original_repo: Tatoeba-Challenge - tags: ['translation'] - languages: ['af', 'es'] - src_constituents: {'afr'} - tgt_constituents: {'spa'} - src_multilingual: False - tgt_multilingual: False - prepro: normalization + SentencePiece (spm32k,spm32k) - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/afr-spa/opus-2020-06-17.zip - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/afr-spa/opus-2020-06-17.test.txt - src_alpha3: afr - tgt_alpha3: spa - short_pair: af-es - chrF2_score: 0.68 - bleu: 49.9 - brevity_penalty: 1.0 - ref_len: 2783.0 - src_name: Afrikaans - tgt_name: Spanish - train_date: 2020-06-17 - src_alpha2: af - tgt_alpha2: es - prefer_old: False - long_pair: afr-spa - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535 - transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b - port_machine: brutasse - port_time: 2020-08-21-14:41
[ "TRANSLATION" ]
Non_BioNLP
TheBloke/finance-LLM-GGUF
TheBloke
text-generation
[ "transformers", "gguf", "llama", "finance", "text-generation", "en", "dataset:Open-Orca/OpenOrca", "dataset:GAIR/lima", "dataset:WizardLM/WizardLM_evol_instruct_V2_196k", "arxiv:2309.09530", "base_model:AdaptLLM/finance-LLM", "base_model:quantized:AdaptLLM/finance-LLM", "license:other", "region:us" ]
1,703,453,335,000
2023-12-24T21:33:31
757
19
--- base_model: AdaptLLM/finance-LLM datasets: - Open-Orca/OpenOrca - GAIR/lima - WizardLM/WizardLM_evol_instruct_V2_196k language: - en license: other metrics: - accuracy model_name: Finance LLM pipeline_tag: text-generation tags: - finance inference: false model_creator: AdaptLLM model_type: llama prompt_template: '[INST] <<SYS>> {system_message} <</SYS>> {prompt} [/INST] ' quantized_by: TheBloke --- <!-- markdownlint-disable MD041 --> <!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end --> # Finance LLM - GGUF - Model creator: [AdaptLLM](https://huggingface.co/AdaptLLM) - Original model: [Finance LLM](https://huggingface.co/AdaptLLM/finance-LLM) <!-- description start --> ## Description This repo contains GGUF format model files for [AdaptLLM's Finance LLM](https://huggingface.co/AdaptLLM/finance-LLM). These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/). <!-- description end --> <!-- README_GGUF.md-about-gguf start --> ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplete list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models. <!-- README_GGUF.md-about-gguf end --> <!-- repositories-available start --> ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/finance-LLM-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/finance-LLM-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/finance-LLM-GGUF) * [AdaptLLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/AdaptLLM/finance-LLM) <!-- repositories-available end --> <!-- prompt-template start --> ## Prompt template: Llama-2-Chat ``` [INST] <<SYS>> {system_message} <</SYS>> {prompt} [/INST] ``` <!-- prompt-template end --> <!-- compatibility_gguf start --> ## Compatibility These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) They are also compatible with many third party UIs and libraries - please see the list at the top of this README. ## Explanation of quantisation methods <details> <summary>Click to see details</summary> The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw Refer to the Provided Files table below to see what files use which methods, and how. </details> <!-- compatibility_gguf end --> <!-- README_GGUF.md-provided-files start --> ## Provided files | Name | Quant method | Bits | Size | Max RAM required | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | [finance-llm.Q2_K.gguf](https://huggingface.co/TheBloke/finance-LLM-GGUF/blob/main/finance-llm.Q2_K.gguf) | Q2_K | 2 | 2.83 GB| 5.33 GB | smallest, significant quality loss - not recommended for most purposes | | [finance-llm.Q3_K_S.gguf](https://huggingface.co/TheBloke/finance-LLM-GGUF/blob/main/finance-llm.Q3_K_S.gguf) | Q3_K_S | 3 | 2.95 GB| 5.45 GB | very small, high quality loss | | [finance-llm.Q3_K_M.gguf](https://huggingface.co/TheBloke/finance-LLM-GGUF/blob/main/finance-llm.Q3_K_M.gguf) | Q3_K_M | 3 | 3.30 GB| 5.80 GB | very small, high quality loss | | [finance-llm.Q3_K_L.gguf](https://huggingface.co/TheBloke/finance-LLM-GGUF/blob/main/finance-llm.Q3_K_L.gguf) | Q3_K_L | 3 | 3.60 GB| 6.10 GB | small, substantial quality loss | | [finance-llm.Q4_0.gguf](https://huggingface.co/TheBloke/finance-LLM-GGUF/blob/main/finance-llm.Q4_0.gguf) | Q4_0 | 4 | 3.83 GB| 6.33 GB | legacy; small, very high quality loss - prefer using Q3_K_M | | [finance-llm.Q4_K_S.gguf](https://huggingface.co/TheBloke/finance-LLM-GGUF/blob/main/finance-llm.Q4_K_S.gguf) | Q4_K_S | 4 | 3.86 GB| 6.36 GB | small, greater quality loss | | [finance-llm.Q4_K_M.gguf](https://huggingface.co/TheBloke/finance-LLM-GGUF/blob/main/finance-llm.Q4_K_M.gguf) | Q4_K_M | 4 | 4.08 GB| 6.58 GB | medium, balanced quality - recommended | | [finance-llm.Q5_0.gguf](https://huggingface.co/TheBloke/finance-LLM-GGUF/blob/main/finance-llm.Q5_0.gguf) | Q5_0 | 5 | 4.65 GB| 7.15 GB | legacy; medium, balanced quality - prefer using Q4_K_M | | [finance-llm.Q5_K_S.gguf](https://huggingface.co/TheBloke/finance-LLM-GGUF/blob/main/finance-llm.Q5_K_S.gguf) | Q5_K_S | 5 | 4.65 GB| 7.15 GB | large, low quality loss - recommended | | [finance-llm.Q5_K_M.gguf](https://huggingface.co/TheBloke/finance-LLM-GGUF/blob/main/finance-llm.Q5_K_M.gguf) | Q5_K_M | 5 | 4.78 GB| 7.28 GB | large, very low quality loss - recommended | | [finance-llm.Q6_K.gguf](https://huggingface.co/TheBloke/finance-LLM-GGUF/blob/main/finance-llm.Q6_K.gguf) | Q6_K | 6 | 5.53 GB| 8.03 GB | very large, extremely low quality loss | | [finance-llm.Q8_0.gguf](https://huggingface.co/TheBloke/finance-LLM-GGUF/blob/main/finance-llm.Q8_0.gguf) | Q8_0 | 8 | 7.16 GB| 9.66 GB | very large, extremely low quality loss - not recommended | **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. <!-- README_GGUF.md-provided-files end --> <!-- README_GGUF.md-how-to-download start --> ## How to download GGUF files **Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file. The following clients/libraries will automatically download models for you, providing a list of available models to choose from: * LM Studio * LoLLMS Web UI * Faraday.dev ### In `text-generation-webui` Under Download Model, you can enter the model repo: TheBloke/finance-LLM-GGUF and below it, a specific filename to download, such as: finance-llm.Q4_K_M.gguf. Then click Download. ### On the command line, including multiple files at once I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` Then you can download any individual model file to the current directory, at high speed, with a command like this: ```shell huggingface-cli download TheBloke/finance-LLM-GGUF finance-llm.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage (click to read)</summary> You can also download multiple files at once with a pattern: ```shell huggingface-cli download TheBloke/finance-LLM-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf' ``` For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/finance-LLM-GGUF finance-llm.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details> <!-- README_GGUF.md-how-to-download end --> <!-- README_GGUF.md-how-to-run start --> ## Example `llama.cpp` command Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later. ```shell ./main -ngl 35 -m finance-llm.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "[INST] <<SYS>>\n{system_message}\n<</SYS>>\n{prompt} [/INST]" ``` Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run in `text-generation-webui` Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 โ€ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp). ## How to run from Python code You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python. ### How to load this model in Python code, using llama-cpp-python For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/). #### First install the package Run one of the following commands, according to your system: ```shell # Base ctransformers with no GPU acceleration pip install llama-cpp-python # With NVidia CUDA acceleration CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python # Or with OpenBLAS acceleration CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python # Or with CLBLast acceleration CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python # Or with AMD ROCm GPU acceleration (Linux only) CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python # Or with Metal GPU acceleration for macOS systems only CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python # In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA: $env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on" pip install llama-cpp-python ``` #### Simple llama-cpp-python example code ```python from llama_cpp import Llama # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llm = Llama( model_path="./finance-llm.Q4_K_M.gguf", # Download the model file first n_ctx=2048, # The max sequence length to use - note that longer sequence lengths require much more resources n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available ) # Simple inference example output = llm( "[INST] <<SYS>>\n{system_message}\n<</SYS>>\n{prompt} [/INST]", # Prompt max_tokens=512, # Generate up to 512 tokens stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using. echo=True # Whether to echo the prompt ) # Chat Completion API llm = Llama(model_path="./finance-llm.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using llm.create_chat_completion( messages = [ {"role": "system", "content": "You are a story writing assistant."}, { "role": "user", "content": "Write a story about llamas." } ] ) ``` ## How to use with LangChain Here are guides on using llama-cpp-python and ctransformers with LangChain: * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp) * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers) <!-- README_GGUF.md-how-to-run end --> <!-- footer start --> <!-- 200823 --> ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI **Special thanks to**: Aemon Algiz. **Patreon special mentions**: Michael Levine, ้˜ฟๆ˜Ž, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjรคreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant. <!-- footer end --> <!-- original-model-card start --> # Original model card: AdaptLLM's Finance LLM # Adapt (Large) Language Models to Domains This repo contains the domain-specific base model developed from **LLaMA-1-7B**, using the method in our paper [Adapting Large Language Models via Reading Comprehension](https://huggingface.co/papers/2309.09530). We explore **continued pre-training on domain-specific corpora** for large language models. While this approach enriches LLMs with domain knowledge, it significantly hurts their prompting ability for question answering. Inspired by human learning via reading comprehension, we propose a simple method to **transform large-scale pre-training corpora into reading comprehension texts**, consistently improving prompting performance across tasks in biomedicine, finance, and law domains. **Our 7B model competes with much larger domain-specific models like BloombergGPT-50B**. ### ๐Ÿค— We are currently working hard on developing models across different domains, scales and architectures! Please stay tuned! ๐Ÿค— **************************** **Updates** **************************** * 12/19: Released our [13B base models](https://huggingface.co/AdaptLLM/finance-LLM-13B) developed from LLaMA-1-13B. * 12/8: Released our [chat models](https://huggingface.co/AdaptLLM/finance-chat) developed from LLaMA-2-Chat-7B. * 9/18: Released our [paper](https://huggingface.co/papers/2309.09530), [code](https://github.com/microsoft/LMOps), [data](https://huggingface.co/datasets/AdaptLLM/finance-tasks), and [base models](https://huggingface.co/AdaptLLM/finance-LLM) developed from LLaMA-1-7B. ## Domain-Specific LLaMA-1 ### LLaMA-1-7B In our paper, we develop three domain-specific models from LLaMA-1-7B, which are also available in Huggingface: [Biomedicine-LLM](https://huggingface.co/AdaptLLM/medicine-LLM), [Finance-LLM](https://huggingface.co/AdaptLLM/finance-LLM) and [Law-LLM](https://huggingface.co/AdaptLLM/law-LLM), the performances of our AdaptLLM compared to other domain-specific LLMs are: <p align='center'> <img src="https://cdn-uploads.huggingface.co/production/uploads/650801ced5578ef7e20b33d4/6efPwitFgy-pLTzvccdcP.png" width="700"> </p> ### LLaMA-1-13B Moreover, we scale up our base model to LLaMA-1-13B to see if **our method is similarly effective for larger-scale models**, and the results are consistently positive too: [Biomedicine-LLM-13B](https://huggingface.co/AdaptLLM/medicine-LLM-13B), [Finance-LLM-13B](https://huggingface.co/AdaptLLM/finance-LLM-13B) and [Law-LLM-13B](https://huggingface.co/AdaptLLM/law-LLM-13B). ## Domain-Specific LLaMA-2-Chat Our method is also effective for aligned models! LLaMA-2-Chat requires a [specific data format](https://huggingface.co/blog/llama2#how-to-prompt-llama-2), and our **reading comprehension can perfectly fit the data format** by transforming the reading comprehension into a multi-turn conversation. We have also open-sourced chat models in different domains: [Biomedicine-Chat](https://huggingface.co/AdaptLLM/medicine-chat), [Finance-Chat](https://huggingface.co/AdaptLLM/finance-chat) and [Law-Chat](https://huggingface.co/AdaptLLM/law-chat) For example, to chat with the finance model: ```python from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained("AdaptLLM/finance-chat") tokenizer = AutoTokenizer.from_pretrained("AdaptLLM/finance-chat", use_fast=False) # Put your input here: user_input = '''Use this fact to answer the question: Title of each class Trading Symbol(s) Name of each exchange on which registered Common Stock, Par Value $.01 Per Share MMM New York Stock Exchange MMM Chicago Stock Exchange, Inc. 1.500% Notes due 2026 MMM26 New York Stock Exchange 1.750% Notes due 2030 MMM30 New York Stock Exchange 1.500% Notes due 2031 MMM31 New York Stock Exchange Which debt securities are registered to trade on a national securities exchange under 3M's name as of Q2 of 2023?''' # We use the prompt template of LLaMA-2-Chat demo prompt = f"<s>[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n<</SYS>>\n\n{user_input} [/INST]" inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).input_ids.to(model.device) outputs = model.generate(input_ids=inputs, max_length=4096)[0] answer_start = int(inputs.shape[-1]) pred = tokenizer.decode(outputs[answer_start:], skip_special_tokens=True) print(f'### User Input:\n{user_input}\n\n### Assistant Output:\n{pred}') ``` ## Domain-Specific Tasks To easily reproduce our results, we have uploaded the filled-in zero/few-shot input instructions and output completions of each domain-specific task: [biomedicine-tasks](https://huggingface.co/datasets/AdaptLLM/medicine-tasks), [finance-tasks](https://huggingface.co/datasets/AdaptLLM/finance-tasks), and [law-tasks](https://huggingface.co/datasets/AdaptLLM/law-tasks). **Note:** those filled-in instructions are specifically tailored for models before alignment and do NOT fit for the specific data format required for chat models. ## Citation If you find our work helpful, please cite us: ```bibtex @article{adaptllm, title = {Adapting Large Language Models via Reading Comprehension}, author = {Daixuan Cheng and Shaohan Huang and Furu Wei}, journal = {CoRR}, volume = {abs/2309.09530}, year = {2023} } ``` <!-- original-model-card end -->
[ "QUESTION_ANSWERING" ]
Non_BioNLP
anismahmahi/G2_replace_Whata_repetition_with_noPropaganda_SetFit
anismahmahi
text-classification
[ "setfit", "safetensors", "mpnet", "sentence-transformers", "text-classification", "generated_from_setfit_trainer", "arxiv:2209.11055", "base_model:sentence-transformers/paraphrase-mpnet-base-v2", "base_model:finetune:sentence-transformers/paraphrase-mpnet-base-v2", "model-index", "region:us" ]
1,704,634,408,000
2024-01-07T13:33:55
3
0
--- base_model: sentence-transformers/paraphrase-mpnet-base-v2 library_name: setfit metrics: - accuracy pipeline_tag: text-classification tags: - setfit - sentence-transformers - text-classification - generated_from_setfit_trainer widget: - text: Fox News, The Washington Post, NBC News, The Associated Press and the Los Angeles Times are among the entities that have said they will file amicus briefs on behalf of CNN. - text: 'Tommy Robinson is in prison today because he violated a court order demanding that he not film videos outside the trials of Muslim rape gangs. ' - text: As I wrote during the presidential campaign, Trump has no idea of Washington and no idea who to appoint who would support him rather than work against him. - text: IN MAY 2013, the Washington Postโ€™s Greg Miller reported that the head of the CIAโ€™s clandestine service was being shifted out of that position as a result of โ€œa management shake-upโ€ by then-Director John Brennan. - text: Columbus police are investigating the shootings. inference: false model-index: - name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2 results: - task: type: text-classification name: Text Classification dataset: name: Unknown type: unknown split: test metrics: - type: accuracy value: 0.602089552238806 name: Accuracy --- # SetFit with sentence-transformers/paraphrase-mpnet-base-v2 This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A OneVsRestClassifier instance is used for classification. The model has been trained using an efficient few-shot learning technique that involves: 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning. 2. Training a classification head with features from the fine-tuned Sentence Transformer. ## Model Details ### Model Description - **Model Type:** SetFit - **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) - **Classification head:** a OneVsRestClassifier instance - **Maximum Sequence Length:** 512 tokens <!-- - **Number of Classes:** Unknown --> <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown --> ### Model Sources - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit) - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055) - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit) ## Evaluation ### Metrics | Label | Accuracy | |:--------|:---------| | **all** | 0.6021 | ## Uses ### Direct Use for Inference First install the SetFit library: ```bash pip install setfit ``` Then you can load this model and run inference. ```python from setfit import SetFitModel # Download from the ๐Ÿค— Hub model = SetFitModel.from_pretrained("anismahmahi/G2_replace_Whata_repetition_with_noPropaganda_SetFit") # Run inference preds = model("Columbus police are investigating the shootings.") ``` <!-- ### Downstream Use *List how someone could finetune this model on their own dataset.* --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* --> <!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* --> ## Training Details ### Training Set Metrics | Training set | Min | Median | Max | |:-------------|:----|:--------|:----| | Word count | 1 | 23.1093 | 129 | ### Training Hyperparameters - batch_size: (16, 16) - num_epochs: (2, 2) - max_steps: -1 - sampling_strategy: oversampling - num_iterations: 10 - body_learning_rate: (2e-05, 1e-05) - head_learning_rate: 0.01 - loss: CosineSimilarityLoss - distance_metric: cosine_distance - margin: 0.25 - end_to_end: False - use_amp: False - warmup_proportion: 0.1 - seed: 42 - eval_max_steps: -1 - load_best_model_at_end: True ### Training Results | Epoch | Step | Training Loss | Validation Loss | |:-------:|:--------:|:-------------:|:---------------:| | 0.0002 | 1 | 0.3592 | - | | 0.0121 | 50 | 0.2852 | - | | 0.0243 | 100 | 0.2694 | - | | 0.0364 | 150 | 0.2182 | - | | 0.0486 | 200 | 0.2224 | - | | 0.0607 | 250 | 0.2634 | - | | 0.0729 | 300 | 0.2431 | - | | 0.0850 | 350 | 0.2286 | - | | 0.0971 | 400 | 0.197 | - | | 0.1093 | 450 | 0.2466 | - | | 0.1214 | 500 | 0.2374 | - | | 0.1336 | 550 | 0.2134 | - | | 0.1457 | 600 | 0.2092 | - | | 0.1578 | 650 | 0.1987 | - | | 0.1700 | 700 | 0.2288 | - | | 0.1821 | 750 | 0.1562 | - | | 0.1943 | 800 | 0.27 | - | | 0.2064 | 850 | 0.1314 | - | | 0.2186 | 900 | 0.2144 | - | | 0.2307 | 950 | 0.184 | - | | 0.2428 | 1000 | 0.2069 | - | | 0.2550 | 1050 | 0.1773 | - | | 0.2671 | 1100 | 0.0704 | - | | 0.2793 | 1150 | 0.1139 | - | | 0.2914 | 1200 | 0.2398 | - | | 0.3035 | 1250 | 0.0672 | - | | 0.3157 | 1300 | 0.1321 | - | | 0.3278 | 1350 | 0.0803 | - | | 0.3400 | 1400 | 0.0589 | - | | 0.3521 | 1450 | 0.0428 | - | | 0.3643 | 1500 | 0.0886 | - | | 0.3764 | 1550 | 0.0839 | - | | 0.3885 | 1600 | 0.1843 | - | | 0.4007 | 1650 | 0.0375 | - | | 0.4128 | 1700 | 0.114 | - | | 0.4250 | 1750 | 0.1264 | - | | 0.4371 | 1800 | 0.0585 | - | | 0.4492 | 1850 | 0.0586 | - | | 0.4614 | 1900 | 0.0805 | - | | 0.4735 | 1950 | 0.0686 | - | | 0.4857 | 2000 | 0.0684 | - | | 0.4978 | 2050 | 0.0803 | - | | 0.5100 | 2100 | 0.076 | - | | 0.5221 | 2150 | 0.0888 | - | | 0.5342 | 2200 | 0.1091 | - | | 0.5464 | 2250 | 0.038 | - | | 0.5585 | 2300 | 0.0674 | - | | 0.5707 | 2350 | 0.0562 | - | | 0.5828 | 2400 | 0.0603 | - | | 0.5949 | 2450 | 0.0669 | - | | 0.6071 | 2500 | 0.0829 | - | | 0.6192 | 2550 | 0.1442 | - | | 0.6314 | 2600 | 0.0914 | - | | 0.6435 | 2650 | 0.0357 | - | | 0.6557 | 2700 | 0.0546 | - | | 0.6678 | 2750 | 0.0748 | - | | 0.6799 | 2800 | 0.0149 | - | | 0.6921 | 2850 | 0.1067 | - | | 0.7042 | 2900 | 0.0054 | - | | 0.7164 | 2950 | 0.0878 | - | | 0.7285 | 3000 | 0.0385 | - | | 0.7407 | 3050 | 0.036 | - | | 0.7528 | 3100 | 0.0902 | - | | 0.7649 | 3150 | 0.0734 | - | | 0.7771 | 3200 | 0.0369 | - | | 0.7892 | 3250 | 0.0031 | - | | 0.8014 | 3300 | 0.0113 | - | | 0.8135 | 3350 | 0.0862 | - | | 0.8256 | 3400 | 0.0549 | - | | 0.8378 | 3450 | 0.0104 | - | | 0.8499 | 3500 | 0.0072 | - | | 0.8621 | 3550 | 0.0546 | - | | 0.8742 | 3600 | 0.0579 | - | | 0.8864 | 3650 | 0.0789 | - | | 0.8985 | 3700 | 0.0711 | - | | 0.9106 | 3750 | 0.0361 | - | | 0.9228 | 3800 | 0.0292 | - | | 0.9349 | 3850 | 0.0121 | - | | 0.9471 | 3900 | 0.0066 | - | | 0.9592 | 3950 | 0.0091 | - | | 0.9713 | 4000 | 0.0027 | - | | 0.9835 | 4050 | 0.0891 | - | | 0.9956 | 4100 | 0.0186 | - | | **1.0** | **4118** | **-** | **0.2746** | | 1.0078 | 4150 | 0.0246 | - | | 1.0199 | 4200 | 0.0154 | - | | 1.0321 | 4250 | 0.0056 | - | | 1.0442 | 4300 | 0.0343 | - | | 1.0563 | 4350 | 0.0375 | - | | 1.0685 | 4400 | 0.0106 | - | | 1.0806 | 4450 | 0.0025 | - | | 1.0928 | 4500 | 0.0425 | - | | 1.1049 | 4550 | 0.0019 | - | | 1.1170 | 4600 | 0.0014 | - | | 1.1292 | 4650 | 0.0883 | - | | 1.1413 | 4700 | 0.0176 | - | | 1.1535 | 4750 | 0.0204 | - | | 1.1656 | 4800 | 0.0011 | - | | 1.1778 | 4850 | 0.005 | - | | 1.1899 | 4900 | 0.0238 | - | | 1.2020 | 4950 | 0.0362 | - | | 1.2142 | 5000 | 0.0219 | - | | 1.2263 | 5050 | 0.0487 | - | | 1.2385 | 5100 | 0.0609 | - | | 1.2506 | 5150 | 0.0464 | - | | 1.2627 | 5200 | 0.0033 | - | | 1.2749 | 5250 | 0.0087 | - | | 1.2870 | 5300 | 0.0101 | - | | 1.2992 | 5350 | 0.0529 | - | | 1.3113 | 5400 | 0.0243 | - | | 1.3235 | 5450 | 0.001 | - | | 1.3356 | 5500 | 0.0102 | - | | 1.3477 | 5550 | 0.0047 | - | | 1.3599 | 5600 | 0.0034 | - | | 1.3720 | 5650 | 0.0118 | - | | 1.3842 | 5700 | 0.0742 | - | | 1.3963 | 5750 | 0.0538 | - | | 1.4085 | 5800 | 0.0162 | - | | 1.4206 | 5850 | 0.0079 | - | | 1.4327 | 5900 | 0.0027 | - | | 1.4449 | 5950 | 0.0035 | - | | 1.4570 | 6000 | 0.0581 | - | | 1.4692 | 6050 | 0.0813 | - | | 1.4813 | 6100 | 0.0339 | - | | 1.4934 | 6150 | 0.0312 | - | | 1.5056 | 6200 | 0.0323 | - | | 1.5177 | 6250 | 0.0521 | - | | 1.5299 | 6300 | 0.0016 | - | | 1.5420 | 6350 | 0.0009 | - | | 1.5542 | 6400 | 0.0967 | - | | 1.5663 | 6450 | 0.0009 | - | | 1.5784 | 6500 | 0.031 | - | | 1.5906 | 6550 | 0.0114 | - | | 1.6027 | 6600 | 0.0599 | - | | 1.6149 | 6650 | 0.0416 | - | | 1.6270 | 6700 | 0.0047 | - | | 1.6391 | 6750 | 0.0234 | - | | 1.6513 | 6800 | 0.0609 | - | | 1.6634 | 6850 | 0.022 | - | | 1.6756 | 6900 | 0.0042 | - | | 1.6877 | 6950 | 0.0336 | - | | 1.6999 | 7000 | 0.0592 | - | | 1.7120 | 7050 | 0.0536 | - | | 1.7241 | 7100 | 0.1198 | - | | 1.7363 | 7150 | 0.1035 | - | | 1.7484 | 7200 | 0.0549 | - | | 1.7606 | 7250 | 0.027 | - | | 1.7727 | 7300 | 0.0251 | - | | 1.7848 | 7350 | 0.0225 | - | | 1.7970 | 7400 | 0.0027 | - | | 1.8091 | 7450 | 0.0309 | - | | 1.8213 | 7500 | 0.024 | - | | 1.8334 | 7550 | 0.0355 | - | | 1.8456 | 7600 | 0.0239 | - | | 1.8577 | 7650 | 0.0377 | - | | 1.8698 | 7700 | 0.012 | - | | 1.8820 | 7750 | 0.0233 | - | | 1.8941 | 7800 | 0.0184 | - | | 1.9063 | 7850 | 0.0022 | - | | 1.9184 | 7900 | 0.0043 | - | | 1.9305 | 7950 | 0.014 | - | | 1.9427 | 8000 | 0.0083 | - | | 1.9548 | 8050 | 0.0084 | - | | 1.9670 | 8100 | 0.0009 | - | | 1.9791 | 8150 | 0.002 | - | | 1.9913 | 8200 | 0.0002 | - | | 2.0 | 8236 | - | 0.2768 | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.10.12 - SetFit: 1.0.1 - Sentence Transformers: 2.2.2 - Transformers: 4.35.2 - PyTorch: 2.1.0+cu121 - Datasets: 2.16.1 - Tokenizers: 0.15.0 ## Citation ### BibTeX ```bibtex @article{https://doi.org/10.48550/arxiv.2209.11055, doi = {10.48550/ARXIV.2209.11055}, url = {https://arxiv.org/abs/2209.11055}, author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Efficient Few-Shot Learning Without Prompts}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ``` <!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->
[ "TEXT_CLASSIFICATION" ]
Non_BioNLP
MultiBertGunjanPatrick/multiberts-seed-4-100k
MultiBertGunjanPatrick
null
[ "transformers", "pytorch", "bert", "pretraining", "exbert", "multiberts", "multiberts-seed-4", "en", "dataset:bookcorpus", "dataset:wikipedia", "arxiv:2106.16163", "license:apache-2.0", "endpoints_compatible", "region:us" ]
1,646,263,744,000
2021-10-04T05:10:05
111
0
--- datasets: - bookcorpus - wikipedia language: en license: apache-2.0 tags: - exbert - multiberts - multiberts-seed-4 --- # MultiBERTs Seed 4 Checkpoint 100k (uncased) Seed 4 intermediate checkpoint 100k MultiBERTs (pretrained BERT) model on English language using a masked language modeling (MLM) objective. It was introduced in [this paper](https://arxiv.org/pdf/2106.16163.pdf) and first released in [this repository](https://github.com/google-research/language/tree/master/language/multiberts). This is an intermediate checkpoint. The final checkpoint can be found at [multiberts-seed-4](https://hf.co/multberts-seed-4). This model is uncased: it does not make a difference between english and English. Disclaimer: The team releasing MultiBERTs did not write a model card for this model so this model card has been written by [gchhablani](https://hf.co/gchhablani). ## Model description MultiBERTs models are transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it was pretrained with two objectives: - Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run the entire masked sentence through the model and has to predict the masked words. This is different from traditional recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the sentence. - Next sentence prediction (NSP): the models concatenates two masked sentences as inputs during pretraining. Sometimes they correspond to sentences that were next to each other in the original text, sometimes not. The model then has to predict if the two sentences were following each other or not. This way, the model learns an inner representation of the English language that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard classifier using the features produced by the MultiBERTs model as inputs. ## Intended uses & limitations You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?filter=multiberts) to look for fine-tuned versions on a task that interests you. Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked) to make decisions, such as sequence classification, token classification or question answering. For tasks such as text generation you should look at model like GPT2. ### How to use Here is how to use this model to get the features of a given text in PyTorch: ```python from transformers import BertTokenizer, BertModel tokenizer = BertTokenizer.from_pretrained('multiberts-seed-4-100k') model = BertModel.from_pretrained("multiberts-seed-4-100k") text = "Replace me by any text you'd like." encoded_input = tokenizer(text, return_tensors='pt') output = model(**encoded_input) ``` ### Limitations and bias Even if the training data used for this model could be characterized as fairly neutral, this model can have biased predictions. This bias will also affect all fine-tuned versions of this model. For an understanding of bias of this particular checkpoint, please try out this checkpoint with the snippet present in the [Limitation and bias section](https://huggingface.co/bert-base-uncased#limitations-and-bias) of the [bert-base-uncased](https://huggingface.co/bert-base-uncased) checkpoint. ## Training data The MultiBERTs models were pretrained on [BookCorpus](https://yknzhu.wixsite.com/mbweb), a dataset consisting of 11,038 unpublished books and [English Wikipedia](https://en.wikipedia.org/wiki/English_Wikipedia) (excluding lists, tables and headers). ## Training procedure ### Preprocessing The texts are lowercased and tokenized using WordPiece and a vocabulary size of 30,000. The inputs of the model are then of the form: ``` [CLS] Sentence A [SEP] Sentence B [SEP] ``` With probability 0.5, sentence A and sentence B correspond to two consecutive sentences in the original corpus and in the other cases, it's another random sentence in the corpus. Note that what is considered a sentence here is a consecutive span of text usually longer than a single sentence. The only constrain is that the result with the two "sentences" has a combined length of less than 512 tokens. The details of the masking procedure for each sentence are the following: - 15% of the tokens are masked. - In 80% of the cases, the masked tokens are replaced by `[MASK]`. - In 10% of the cases, the masked tokens are replaced by a random token (different) from the one they replace. - In the 10% remaining cases, the masked tokens are left as is. ### Pretraining The full model was trained on 16 Cloud TPU v2 chips for two million steps with a batch size of 256. The sequence length was set to 512 throughout. The optimizer used is Adam with a learning rate of 1e-4, \\(\beta_{1} = 0.9\\) and \\(\beta_{2} = 0.999\\), a weight decay of 0.01, learning rate warmup for 10,000 steps and linear decay of the learning rate after. ### BibTeX entry and citation info ```bibtex @article{DBLP:journals/corr/abs-2106-16163, author = {Thibault Sellam and Steve Yadlowsky and Jason Wei and Naomi Saphra and Alexander D'Amour and Tal Linzen and Jasmijn Bastings and Iulia Turc and Jacob Eisenstein and Dipanjan Das and Ian Tenney and Ellie Pavlick}, title = {The MultiBERTs: {BERT} Reproductions for Robustness Analysis}, journal = {CoRR}, volume = {abs/2106.16163}, year = {2021}, url = {https://arxiv.org/abs/2106.16163}, eprinttype = {arXiv}, eprint = {2106.16163}, timestamp = {Mon, 05 Jul 2021 15:15:50 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2106-16163.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } ``` <a href="https://huggingface.co/exbert/?model=multiberts"> <img width="300px" src="https://cdn-media.huggingface.co/exbert/button.png"> </a>
[ "QUESTION_ANSWERING" ]
Non_BioNLP
DOSaAI/albanian-gpt2-large-120m-instruct-v0.1
DOSaAI
text-generation
[ "transformers", "text-generation", "sq", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]
1,711,913,253,000
2024-03-31T19:29:56
0
1
--- language: - sq - en library_name: transformers license: apache-2.0 pipeline_tag: text-generation --- # Albanian GPT-2 ## Model Description This model is a fine-tuned version of the GPT-2 model by [OpenAI](https://openai.com/) for Albanian text generation tasks. GPT-2 is a state-of-the-art natural language processing model developed by OpenAI. It is a variant of the GPT (Generative Pre-trained Transformer) model, pre-trained on a large corpus of English text data. This fine-tuned version has been trained on a custom dataset of Albanian text data and can generate coherent and contextually relevant text in Albanian. ## Intended Use The model is intended for text generation tasks in Albanian and English. It can be used for various natural language processing tasks such as text completion, text summarization, dialogue generation, and more. It is particularly useful for generating creative and contextually relevant text in both Albanian and English. ## Training Data The model has been fine-tuned on a custom dataset consisting of Albanian text data. The dataset used for fine-tuning includes a diverse range of text sources in Albanian to ensure the model's proficiency in generating high-quality text across different domains. ## Limitations and Biases As with any machine learning model, this model may exhibit biases present in the training data. Additionally, while the model performs well on a wide range of text generation tasks in Albanian and English, it may not always produce contextually appropriate or grammatically correct output. Users should review and evaluate the generated text to ensure it meets their quality standards. ## Acknowledgments - This model is based on the GPT-2 architecture developed by OpenAI. - The fine-tuning process for this model was facilitated by the Hugging Face Transformers library. ## Contact Information For any questions, feedback, or inquiries related to the model, please contact the model developer: - Name: DOSaAI - Email: [email protected]
[ "SUMMARIZATION" ]
Non_BioNLP
Lvxue/distilled-mt5-small-1-0.5
Lvxue
text2text-generation
[ "transformers", "pytorch", "mt5", "text2text-generation", "generated_from_trainer", "en", "ro", "dataset:wmt16", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
1,660,269,997,000
2022-08-12T03:22:00
11
0
--- datasets: - wmt16 language: - en - ro license: apache-2.0 metrics: - bleu tags: - generated_from_trainer model-index: - name: distilled-mt5-small-1-0.5 results: - task: type: translation name: Translation dataset: name: wmt16 ro-en type: wmt16 args: ro-en metrics: - type: bleu value: 5.3917 name: Bleu --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilled-mt5-small-1-0.5 This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the wmt16 ro-en dataset. It achieves the following results on the evaluation set: - Loss: 3.8410 - Bleu: 5.3917 - Gen Len: 40.6103 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 4 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5.0 ### Training results ### Framework versions - Transformers 4.20.1 - Pytorch 1.12.0+cu102 - Datasets 2.3.2 - Tokenizers 0.12.1
[ "TRANSLATION" ]
Non_BioNLP
aroot/wsample.49
aroot
translation
[ "transformers", "pytorch", "tensorboard", "mbart", "text2text-generation", "translation", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
1,688,511,805,000
2023-07-05T00:41:23
8
0
--- metrics: - bleu tags: - translation - generated_from_trainer model-index: - name: wsample.49 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # wsample.49 This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset. It achieves the following results on the evaluation set: - Loss: 3.2266 - Bleu: 3.0080 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1 - Datasets 2.12.0 - Tokenizers 0.11.0
[ "TRANSLATION" ]
Non_BioNLP
ronaldseoh/long-t5-local-base
ronaldseoh
null
[ "pytorch", "jax", "longt5", "en", "arxiv:2112.07916", "arxiv:1912.08777", "arxiv:1910.10683", "license:apache-2.0", "region:us" ]
1,726,798,138,000
2023-01-24T17:08:34
9
0
--- language: en license: apache-2.0 --- # LongT5 (local attention, base-sized model) LongT5 model pre-trained on English language. The model was introduced in the paper [LongT5: Efficient Text-To-Text Transformer for Long Sequences](https://arxiv.org/pdf/2112.07916.pdf) by Guo et al. and first released in [the LongT5 repository](https://github.com/google-research/longt5). All the model architecture and configuration can be found in [Flaxformer repository](https://github.com/google/flaxformer) which uses another Google research project repository [T5x](https://github.com/google-research/t5x). Disclaimer: The team releasing LongT5 did not write a model card for this model so this model card has been written by the Hugging Face team. ## Model description LongT5 model is an encoder-decoder transformer pre-trained in a text-to-text denoising generative setting ([Pegasus-like generation pre-training](https://arxiv.org/pdf/1912.08777.pdf)). LongT5 model is an extension of [T5 model](https://arxiv.org/pdf/1910.10683.pdf), and it enables using one of the two different efficient attention mechanisms - (1) Local attention, or (2) Transient-Global attention. The usage of attention sparsity patterns allows the model to efficiently handle input sequence. LongT5 is particularly effective when fine-tuned for text generation (summarization, question answering) which requires handling long input sequences (up to 16,384 tokens). ## Intended uses & limitations The model is mostly meant to be fine-tuned on a supervised dataset. See the [model hub](https://huggingface.co/models?search=longt5) to look for fine-tuned versions on a task that interests you. ### How to use ```python from transformers import AutoTokenizer, LongT5Model tokenizer = AutoTokenizer.from_pretrained("google/long-t5-local-base") model = LongT5Model.from_pretrained("google/long-t5-local-base") inputs = tokenizer("Hello, my dog is cute", return_tensors="pt") outputs = model(**inputs) last_hidden_states = outputs.last_hidden_state ``` ### BibTeX entry and citation info ```bibtex @article{guo2021longt5, title={LongT5: Efficient Text-To-Text Transformer for Long Sequences}, author={Guo, Mandy and Ainslie, Joshua and Uthus, David and Ontanon, Santiago and Ni, Jianmo and Sung, Yun-Hsuan and Yang, Yinfei}, journal={arXiv preprint arXiv:2112.07916}, year={2021} } ```
[ "QUESTION_ANSWERING", "SUMMARIZATION" ]
Non_BioNLP
marbogusz/bert-multi-cased-squad_sv
marbogusz
question-answering
[ "transformers", "pytorch", "jax", "bert", "question-answering", "endpoints_compatible", "region:us" ]
1,646,263,745,000
2021-05-19T23:00:13
103
0
--- {} --- Swedish bert multilingual model trained on a machine translated (MS neural translation) SQUAD 1.1 dataset
[ "TRANSLATION" ]
Non_BioNLP
maastrichtlawtech/wizardlm-7b-v1.0-lleqa
maastrichtlawtech
text-generation
[ "peft", "legal", "text-generation", "fr", "dataset:maastrichtlawtech/lleqa", "arxiv:2309.17050", "license:apache-2.0", "region:us" ]
1,695,917,091,000
2023-10-03T09:44:44
4
3
--- datasets: - maastrichtlawtech/lleqa language: - fr library_name: peft license: apache-2.0 metrics: - rouge - meteor pipeline_tag: text-generation tags: - legal inference: false --- # wizardLM-7b-v1.0-lleqa This is a [wizardlm-7b-v1.0](https://huggingface.co/WizardLM/WizardLM-7B-V1.0) model fine-tuned with [QLoRA](https://github.com/artidoro/qlora) for long-form legal question answering in **French**. ## Usage ```python [...] ``` ## Training #### Data We use the [Long-form Legal Question Answering (LLeQA)](https://huggingface.co/datasets/maastrichtlawtech/lleqa) dataset to fine-tune the model. LLeQA is a French native dataset for studying legal information retrieval and question answering. It consists of a knowledge corpus of 27,941 statutory articles collected from the Belgian legislation, and 1,868 legal questions posed by Belgian citizens and labeled by experienced jurists with a comprehensive answer rooted in relevant articles from the corpus. #### Hyperparameters We fine-tune the model through 4-bit QLoRA finetuning with an effective batch size of 8 for 10 epochs (i.e., 1.1K steps) using paged AdamW optimizer with default momentum parameters and constant learning rate schedule of 2e-4. We employ NormalFloat4 with double quantization for the base models and add LoRA adapters on all linear layers by setting r=16, alpha=32 while utilizing float16 as computation datatype. Additionally, we perform NTK-aware scaling of RoPE to extend the context window to 4096 tokens. Training takes around 7.5 hours to complete on a single Tesla V100 GPU with 32GBs of memory. More details can be found in this [paper](https://arxiv.org/abs/) and [repository](https://github.com/maastrichtlawtech/lleqa). ## Citation ```bibtex @article{louis2023interpretable, author = {Louis, Antoine and van Dijck, Gijs and Spanakis, Gerasimos}, title = {Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models}, journal = {CoRR}, volume = {abs/2309.17050}, year = {2023}, url = {https://arxiv.org/abs/2309.17050}, eprinttype = {arXiv}, eprint = {2309.17050}, } ```
[ "QUESTION_ANSWERING" ]
Non_BioNLP
tmnam20/mdeberta-v3-base-vsfc-1
tmnam20
text-classification
[ "transformers", "safetensors", "deberta-v2", "text-classification", "generated_from_trainer", "en", "dataset:tmnam20/VieGLUE", "base_model:microsoft/mdeberta-v3-base", "base_model:finetune:microsoft/mdeberta-v3-base", "license:mit", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
1,705,394,694,000
2024-01-16T08:47:32
4
0
--- base_model: microsoft/mdeberta-v3-base datasets: - tmnam20/VieGLUE language: - en license: mit metrics: - accuracy tags: - generated_from_trainer model-index: - name: mdeberta-v3-base-vsfc-1 results: - task: type: text-classification name: Text Classification dataset: name: tmnam20/VieGLUE/VSFC type: tmnam20/VieGLUE config: vsfc split: validation args: vsfc metrics: - type: accuracy value: 0.950726468730259 name: Accuracy --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # mdeberta-v3-base-vsfc-1 This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the tmnam20/VieGLUE/VSFC dataset. It achieves the following results on the evaluation set: - Loss: 0.2229 - Accuracy: 0.9507 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 16 - seed: 1 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.1695 | 1.4 | 500 | 0.2297 | 0.9425 | | 0.1095 | 2.79 | 1000 | 0.2185 | 0.9482 | ### Framework versions - Transformers 4.36.0 - Pytorch 2.1.0+cu121 - Datasets 2.15.0 - Tokenizers 0.15.0
[ "TEXT_CLASSIFICATION" ]
Non_BioNLP
Triangle104/granite-3.2-2b-instruct-Q5_K_S-GGUF
Triangle104
text-generation
[ "transformers", "gguf", "language", "granite-3.2", "llama-cpp", "gguf-my-repo", "text-generation", "base_model:ibm-granite/granite-3.2-2b-instruct", "base_model:quantized:ibm-granite/granite-3.2-2b-instruct", "license:apache-2.0", "region:us", "conversational" ]
1,740,748,781,000
2025-02-28T13:21:09
18
0
--- base_model: ibm-granite/granite-3.2-2b-instruct library_name: transformers license: apache-2.0 pipeline_tag: text-generation tags: - language - granite-3.2 - llama-cpp - gguf-my-repo inference: false --- # Triangle104/granite-3.2-2b-instruct-Q5_K_S-GGUF This model was converted to GGUF format from [`ibm-granite/granite-3.2-2b-instruct`](https://huggingface.co/ibm-granite/granite-3.2-2b-instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/ibm-granite/granite-3.2-2b-instruct) for more details on the model. --- Model Summary: - Granite-3.2-2B-Instruct is an 2-billion-parameter, long-context AI model fine-tuned for thinking capabilities. Built on top of Granite-3.1-2B-Instruct, it has been trained using a mix of permissively licensed open-source datasets and internally generated synthetic data designed for reasoning tasks. The model allows controllability of its thinking capability, ensuring it is applied only when required. Developers: Granite Team, IBM Website: Granite Docs Release Date: February 26th, 2025 License: Apache 2.0 Supported Languages: - English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. However, users may finetune this Granite model for languages beyond these 12 languages. Intended Use: - This model is designed to handle general instruction-following tasks and can be integrated into AI assistants across various domains, including business applications. Capabilities - Thinking Summarization Text classification Text extraction Question-answering Retrieval Augmented Generation (RAG) Code related tasks Function-calling tasks Multilingual dialog use cases Long-context tasks including long document/meeting summarization, long document QA, etc. Generation: - This is a simple example of how to use Granite-3.2-2B-Instruct model. Install the following libraries: - pip install torch torchvision torchaudio pip install accelerate pip install transformers Then, copy the snippet from the section that is relevant for your use case. from transformers import AutoModelForCausalLM, AutoTokenizer, set_seed import torch model_path="ibm-granite/granite-3.2-2b-instruct" device="cuda" model = AutoModelForCausalLM.from_pretrained( model_path, device_map=device, torch_dtype=torch.bfloat16, ) tokenizer = AutoTokenizer.from_pretrained( model_path ) conv = [{"role": "user", "content":"You have 10 liters of a 30% acid solution. How many liters of a 70% acid solution must be added to achieve a 50% acid mixture?"}] input_ids = tokenizer.apply_chat_template(conv, return_tensors="pt", thinking=True, return_dict=True, add_generation_prompt=True).to(device) set_seed(42) output = model.generate( **input_ids, max_new_tokens=8192, ) prediction = tokenizer.decode(output[0, input_ids["input_ids"].shape[1]:], skip_special_tokens=True) print(prediction) Example Outputs thinking=True Here is my thought process: 1. First, let's understand the composition of the initial 10 liters of 30% acid solution: - Acid content = 30% of 10 liters = 0.30 * 10 = 3 liters 2. We want to end up with a 50% acid solution. Let's denote the volume of the 70% acid solution to be added as 'x' liters. 3. The amount of acid in the final mixture (50% solution) should equal the initial acid content plus the acid from the added 70% solution. - Total acid in final mixture = 0.50 * (10 + x) 4. The equation representing the total acid content is: 3 (from initial solution) + 0.70 * x (from added solution) = 0.50 * (10 + x) 5. Now, we solve for 'x': 3 + 0.70x = 5 + 0.50x 0.70x - 0.50x = 5 - 3 0.20x = 2 x = 2 / 0.20 x = 10 liters 6. Therefore, 10 liters of a 70% acid solution must be added to the initial 10 liters of 30% acid solution to achieve a 50% acid mixture. Here is my response: To solve this problem, we need to determine how much of a 70% acid solution must be added to a 10-liter solution that is already 30% acid to create a new mixture that is 50% acid. Here's how to calculate it: 1. **Initial Acid Content**: - The initial 10-liter solution contains 3 liters of acid (since 30% of 10 liters). 2. **Desired Final Acid Content**: - We want the final mixture to be 50% acid. 3. **Equation Setup**: - Let 'x' be the volume (in liters) of the 70% acid solution to be added. - The equation representing the total acid content in the final mixture (which is 10 liters from the initial solution plus 'x' liters of the added solution) should equal 50% of the total volume (10 + x). - This gives us: 3 (acid from initial solution) + 0.70x (acid from added solution) = 0.50(10 + x) 4. **Solving the Equation**: - First, simplify the right side of the equation: 0.50(10 + x) = 5 + 0.50x - Now, the equation is: 3 + 0.70x = 5 + 0.50x - Subtract 0.50x from both sides: 0.20x = 2 - Divide both sides by 0.20: x = 2 / 0.20 - x = 10 liters 5. **Conclusion**: - To achieve a 50% acid mixture from the initial 30% solution, you need to add 10 liters of a 70% acid solution. So, the final answer is that 10 liters of a 70% acid solution must be added to the initial 10 liters of 30% acid solution. thinking=False To solve this problem, we'll use the concept of volume and concentration. Let's denote the amount of 70% acid solution we need to add as "x" liters. First, let's find out how much acid is in the initial 10-liter solution: Acid in initial solution = 30% of 10 liters = 0.30 * 10 = 3 liters Now, we want to end up with a 50% acid solution in a total volume of (10 + x) liters. Let's denote the final volume as V. Final acid concentration = 50% Final acid amount = 50% of V = 0.50 * V We know the initial acid amount and the final acid amount, so we can set up an equation: Initial acid amount + Acid from added solution = Final acid amount 3 liters + (70% of x) = 0.50 * (10 + x) Now, let's solve for x: 0.70x + 3 = 0.50 * 10 + 0.50x 0.70x - 0.50x = 0.50 * 10 - 3 0.20x = 5 - 3 0.20x = 2 x = 2 / 0.20 x = 10 liters So, you need to add 10 liters of a 70% acid solution to the initial 10-liter 30% acid solution to achieve a 50% acid mixture. --- ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo Triangle104/granite-3.2-2b-instruct-Q5_K_S-GGUF --hf-file granite-3.2-2b-instruct-q5_k_s.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Triangle104/granite-3.2-2b-instruct-Q5_K_S-GGUF --hf-file granite-3.2-2b-instruct-q5_k_s.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo Triangle104/granite-3.2-2b-instruct-Q5_K_S-GGUF --hf-file granite-3.2-2b-instruct-q5_k_s.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Triangle104/granite-3.2-2b-instruct-Q5_K_S-GGUF --hf-file granite-3.2-2b-instruct-q5_k_s.gguf -c 2048 ```
[ "TEXT_CLASSIFICATION", "SUMMARIZATION" ]
Non_BioNLP
tcepi/sts_bertimbau
tcepi
sentence-similarity
[ "sentence-transformers", "safetensors", "bert", "sentence-similarity", "feature-extraction", "base_model:neuralmind/bert-base-portuguese-cased", "base_model:finetune:neuralmind/bert-base-portuguese-cased", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]
1,729,690,604,000
2024-10-23T13:37:17
7
0
--- base_model: neuralmind/bert-base-portuguese-cased library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - feature-extraction --- # SentenceTransformer based on neuralmind/bert-base-portuguese-cased This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. ## Model Details ### Model Description - **Model Type:** Sentence Transformer - **Base model:** [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) <!-- at revision 94d69c95f98f7d5b2a8700c420230ae10def0baa --> - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 tokens - **Similarity Function:** Cosine Similarity <!-- - **Training Dataset:** Unknown --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown --> ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the ๐Ÿค— Hub model = SentenceTransformer("tcepi/sts_bertimbau") # Run inference sentences = [ 'The weather is lovely today.', "It's so sunny outside!", 'He drove to the stadium.', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 768] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` <!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* --> <!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* --> ## Training Details ### Framework Versions - Python: 3.8.10 - Sentence Transformers: 3.2.1 - Transformers: 4.44.2 - PyTorch: 2.4.1+cu121 - Accelerate: 0.34.2 - Datasets: 2.20.0 - Tokenizers: 0.19.1 ## Citation ### BibTeX <!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->
[ "TEXT_CLASSIFICATION" ]
Non_BioNLP
proxectonos/Nos_MT-OpenNMT-es-gl
proxectonos
null
[ "gl", "license:mit", "region:us" ]
1,676,539,658,000
2024-10-01T07:59:41
0
1
--- language: - gl license: mit metrics: - bleu (Gold1): 79.6 - bleu (Gold2): 43.3 - bleu (Flores): 21.8 - bleu (Test-suite): 74.3 --- **English text [here](https://huggingface.co/proxectonos/NOS-MT-OpenNMT-es-gl/blob/main/README_English.md)** **Descriciรณn do Modelo** Modelo feito con OpenNMT-py 3.2 para o par espaรฑol-galego utilizando unha arquitectura transformer. O modelo foi transformado para o formato da ctranslate2. **Como traducir con este Modelo** + Instalar o [Python 3.9](https://www.python.org/downloads/release/python-390/) + Instalar o [ctranslate 3.2](https://github.com/OpenNMT/CTranslate2) + Traducir un input_text utilizando o modelo NOS-MT-es-gl co seguinte comando: ```bash perl tokenizer.perl < input.txt > input.tok ``` ```bash subword_nmt.apply_bpe -c ./bpe/es.bpe < input.tok > input.bpe ``` ```bash python3 translate.py ./ct2-es-gl_12L input.bpe > output.txt ``` ```bash sed -i 's/@@ //g' output.txt ``` **Adestramento** No adestramento, utilizamos cรณrpora autรฉnticos e sintรฉticos do [ProxectoNรณs](https://github.com/proxectonos/corpora). Os primeiros son cรณrpora de traduciรณns feitas directamente por tradutores humanos. ร‰ importante salientar que a pesar destes textos seren feitos por humanos, non estรกn libres de erros lingรผรญsticos. Os segundos son cรณrpora de traduciรณns espaรฑol-portuguรฉs, que convertemos en espaรฑol-galego a travรฉs da traduciรณn automรกtica portuguรฉs-galego con Opentrad/Apertium e transliteraciรณn para palabras fรณra de vocabulario. **Procedemento de adestramento** + Tokenizaciรณn dos datasets feita co tokenizador (tokenizer.pl) de [linguakit](https://github.com/citiususc/Linguakit) que foi modificado para evitar o salto de liรฑa por token do ficheiro orixinal. + O vocabulario BPE para os modelos foi xerado a travรฉs do script [learn_bpe.py](https://github.com/OpenNMT/OpenNMT-py/blob/master/tools/learn_bpe.py) da OpenNMT + Utilizando o .yaml deste repositorio pode replicar o proceso de adestramento. ร‰ preciso modificar os paths do ficheiro .yaml para a Open NMT saber onde ir buscar os textos. Apรณs facer isto, pode do seguinte xeito comezar o proceso: ```bash onmt_build_vocab -config bpe-es-gl_emb.yaml -n_sample 40000 onmt_train -config bpe-es-gl_emb.yaml ``` **Hiperparรกmetros** Os parรกmetros usados para o desenvolvemento do modelo poden ser consultados directamente no mesmo ficheiro .yaml bpe-es-gl_emb.yaml **Avaliaciรณn** A avaliaciรณn BLEU dos modelos รฉ feita cunha mistura de tests desenvolvidos internamente (gold1, gold2, test-suite) con outros datasets disponรญbeis en galego (Flores). | GOLD 1 | GOLD 2 | FLORES | TEST-SUITE| | ------------- |:-------------:| -------:|----------:| | 79.5 | 43.5 | 21.4 | 73.4 | **Licenzas do Modelo** MIT License Copyright (c) 2023 Proxecto Nรณs Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. **Financiamento** Esta investigaciรณn foi financiada polo proxecto "Nรณs: o galego na sociedade e economรญa da intelixencia artificial", resultado dun acordo entre a Xunta de Galicia e a Universidade de Santiago de Compostela, o que resultou no subsidio ED431G2019/04 da Consellarรญa de Educaciรณn, Universidade e Formaciรณn Profesional da Galiza, e polo Fondo Europeo de Desenvolvemento Rexional (programa ERDF/FEDER), e Grupos de Referencia: ED431C 2020/21. **Citar este traballo** Se utilizar este modelo no seu traballo, cite por favor asรญ: Daniel Bardanca Outeirinho, Pablo Gamallo Otero, Iria de-Dios-Flores, and Josรฉ Ramom Pichel Campos. 2024. Exploring the effects of vocabulary size in neural machine translation: Galician as a target language. In Proceedings of the 16th International Conference on Computational Processing of Portuguese, pages 600โ€“604, Santiago de Compostela, Galiza. Association for Computational Lingustics.
[ "TRANSLATION" ]
Non_BioNLP
chunwoolee0/seqcls_mrpc_bert_base_uncased_model
chunwoolee0
text-classification
[ "transformers", "pytorch", "tensorboard", "bert", "text-classification", "generated_from_trainer", "dataset:glue", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
1,689,377,271,000
2023-07-14T23:32:36
8
0
--- datasets: - glue license: apache-2.0 metrics: - accuracy - f1 tags: - generated_from_trainer model-index: - name: seqcls_mrpc_bert_base_uncased_model results: - task: type: text-classification name: Text Classification dataset: name: glue type: glue config: mrpc split: validation args: mrpc metrics: - type: accuracy value: 0.8014705882352942 name: Accuracy - type: f1 value: 0.8669950738916257 name: F1 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # seqcls_mrpc_bert_base_uncased_model This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset. It achieves the following results on the evaluation set: - Loss: 0.4621 - Accuracy: 0.8015 - F1: 0.8670 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| | No log | 1.0 | 58 | 0.5442 | 0.7108 | 0.8228 | | No log | 2.0 | 116 | 0.5079 | 0.7745 | 0.8558 | | No log | 3.0 | 174 | 0.4621 | 0.8015 | 0.8670 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
[ "TEXT_CLASSIFICATION" ]
Non_BioNLP
pierreguillou/bert-large-cased-squad-v1.1-portuguese
pierreguillou
question-answering
[ "transformers", "pytorch", "tf", "bert", "question-answering", "bert-large", "pt", "dataset:brWaC", "dataset:squad", "dataset:squad_v1_pt", "license:mit", "endpoints_compatible", "region:us" ]
1,646,263,745,000
2022-01-04T09:57:00
777
45
--- datasets: - brWaC - squad - squad_v1_pt language: pt license: mit metrics: - squad tags: - question-answering - bert - bert-large - pytorch widget: - text: Quando comeรงou a pandemia de Covid-19 no mundo? context: A pandemia de COVID-19, tambรฉm conhecida como pandemia de coronavรญrus, รฉ uma pandemia em curso de COVID-19, uma doenรงa respiratรณria causada pelo coronavรญrus da sรญndrome respiratรณria aguda grave 2 (SARS-CoV-2). O vรญrus tem origem zoonรณtica e o primeiro caso conhecido da doenรงa remonta a dezembro de 2019 em Wuhan, na China. - text: Onde foi descoberta a Covid-19? context: A pandemia de COVID-19, tambรฉm conhecida como pandemia de coronavรญrus, รฉ uma pandemia em curso de COVID-19, uma doenรงa respiratรณria causada pelo coronavรญrus da sรญndrome respiratรณria aguda grave 2 (SARS-CoV-2). O vรญrus tem origem zoonรณtica e o primeiro caso conhecido da doenรงa remonta a dezembro de 2019 em Wuhan, na China. --- # Portuguese BERT large cased QA (Question Answering), finetuned on SQUAD v1.1 ![Exemple of what can do the Portuguese BERT large cased QA (Question Answering), finetuned on SQUAD v1.1](https://miro.medium.com/max/5256/1*QxyeAjT2V1OfE2B6nEcs3w.png) ## Introduction The model was trained on the dataset SQUAD v1.1 in portuguese from the [Deep Learning Brasil group](http://www.deeplearningbrasil.com.br/). The language model used is the [BERTimbau Large](https://huggingface.co/neuralmind/bert-large-portuguese-cased) (aka "bert-large-portuguese-cased") from [Neuralmind.ai](https://neuralmind.ai/): BERTimbau is a pretrained BERT model for Brazilian Portuguese that achieves state-of-the-art performances on three downstream NLP tasks: Named Entity Recognition, Sentence Textual Similarity and Recognizing Textual Entailment. It is available in two sizes: Base and Large. ## Informations on the method used All the informations are in the blog post : [NLP | Como treinar um modelo de Question Answering em qualquer linguagem baseado no BERT large, melhorando o desempenho do modelo utilizando o BERT base? (estudo de caso em portuguรชs)](https://medium.com/@pierre_guillou/nlp-como-treinar-um-modelo-de-question-answering-em-qualquer-linguagem-baseado-no-bert-large-1c899262dd96) ## Notebook in GitHub [question_answering_BERT_large_cased_squad_v11_pt.ipynb](https://github.com/piegu/language-models/blob/master/question_answering_BERT_large_cased_squad_v11_pt.ipynb) ([nbviewer version](https://nbviewer.jupyter.org/github/piegu/language-models/blob/master/question_answering_BERT_large_cased_squad_v11_pt.ipynb)) ## Performance The results obtained are the following: ``` f1 = 84.43 (against 82.50 for the base model) exact match = 72.68 (against 70.49 for the base model) ``` ## How to use the model... with Pipeline ```python import transformers from transformers import pipeline # source: https://pt.wikipedia.org/wiki/Pandemia_de_COVID-19 context = r""" A pandemia de COVID-19, tambรฉm conhecida como pandemia de coronavรญrus, รฉ uma pandemia em curso de COVID-19, uma doenรงa respiratรณria causada pelo coronavรญrus da sรญndrome respiratรณria aguda grave 2 (SARS-CoV-2). O vรญrus tem origem zoonรณtica e o primeiro caso conhecido da doenรงa remonta a dezembro de 2019 em Wuhan, na China. Em 20 de janeiro de 2020, a Organizaรงรฃo Mundial da Saรบde (OMS) classificou o surto como Emergรชncia de Saรบde Pรบblica de ร‚mbito Internacional e, em 11 de marรงo de 2020, como pandemia. Em 18 de junho de 2021, 177 349 274 casos foram confirmados em 192 paรญses e territรณrios, com 3 840 181 mortes atribuรญdas ร  doenรงa, tornando-se uma das pandemias mais mortais da histรณria. Os sintomas de COVID-19 sรฃo altamente variรกveis, variando de nenhum a doenรงas com risco de morte. O vรญrus se espalha principalmente pelo ar quando as pessoas estรฃo perto umas das outras. Ele deixa uma pessoa infectada quando ela respira, tosse, espirra ou fala e entra em outra pessoa pela boca, nariz ou olhos. Ele tambรฉm pode se espalhar atravรฉs de superfรญcies contaminadas. As pessoas permanecem contagiosas por atรฉ duas semanas e podem espalhar o vรญrus mesmo se forem assintomรกticas. """ model_name = 'pierreguillou/bert-large-cased-squad-v1.1-portuguese' nlp = pipeline("question-answering", model=model_name) question = "Quando comeรงou a pandemia de Covid-19 no mundo?" result = nlp(question=question, context=context) print(f"Answer: '{result['answer']}', score: {round(result['score'], 4)}, start: {result['start']}, end: {result['end']}") # Answer: 'dezembro de 2019', score: 0.5087, start: 290, end: 306 ``` ## How to use the model... with the Auto classes ```python from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("pierreguillou/bert-large-cased-squad-v1.1-portuguese") model = AutoModelForQuestionAnswering.from_pretrained("pierreguillou/bert-large-cased-squad-v1.1-portuguese") ``` Or just clone the model repo: ```python git lfs install git clone https://huggingface.co/pierreguillou/bert-large-cased-squad-v1.1-portuguese # if you want to clone without large files โ€“ just their pointers # prepend your git clone with the following env var: GIT_LFS_SKIP_SMUDGE=1 ``` ## Limitations and bias The training data used for this model come from Portuguese SQUAD. It could contain a lot of unfiltered content, which is far from neutral, and biases. ## Author Portuguese BERT large cased QA (Question Answering), finetuned on SQUAD v1.1 was trained and evaluated by [Pierre GUILLOU](https://www.linkedin.com/in/pierreguillou/) thanks to the Open Source code, platforms and advices of many organizations ([link to the list](https://medium.com/@pierre_guillou/nlp-como-treinar-um-modelo-de-question-answering-em-qualquer-linguagem-baseado-no-bert-large-1c899262dd96#c2f5)). In particular: [Hugging Face](https://huggingface.co/), [Neuralmind.ai](https://neuralmind.ai/), [Deep Learning Brasil group](http://www.deeplearningbrasil.com.br/) and [AI Lab](https://ailab.unb.br/). ## Citation If you use our work, please cite: ```bibtex @inproceedings{pierreguillou2021bertlargecasedsquadv11portuguese, title={Portuguese BERT large cased QA (Question Answering), finetuned on SQUAD v1.1}, author={Pierre Guillou}, year={2021} } ```
[ "NAMED_ENTITY_RECOGNITION", "QUESTION_ANSWERING", "TEXTUAL_ENTAILMENT" ]
TBD
kunalr63/my_awesome_model
kunalr63
text-classification
[ "transformers", "pytorch", "tensorboard", "distilbert", "text-classification", "generated_from_trainer", "dataset:imdb", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
1,681,650,033,000
2023-04-16T13:33:32
14
0
--- datasets: - imdb license: apache-2.0 metrics: - accuracy tags: - generated_from_trainer model-index: - name: my_awesome_model results: - task: type: text-classification name: Text Classification dataset: name: imdb type: imdb config: plain_text split: test args: plain_text metrics: - type: accuracy value: 0.92768 name: Accuracy --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # my_awesome_model This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset. It achieves the following results on the evaluation set: - Loss: 0.1887 - Accuracy: 0.9277 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.2233 | 1.0 | 1563 | 0.1887 | 0.9277 | ### Framework versions - Transformers 4.28.1 - Pytorch 2.0.0+cu118 - Datasets 2.11.0 - Tokenizers 0.13.3
[ "TEXT_CLASSIFICATION" ]
Non_BioNLP
gaudi/opus-mt-fr-ht-ctranslate2
gaudi
translation
[ "transformers", "marian", "ctranslate2", "translation", "license:apache-2.0", "endpoints_compatible", "region:us" ]
1,721,663,856,000
2024-10-19T04:26:33
9
0
--- license: apache-2.0 tags: - ctranslate2 - translation --- # Repository General Information ## Inspired by and derived from the work of [Helsinki-NLP](https://huggingface.co/Helsinki-NLP), [CTranslate2](https://github.com/OpenNMT/CTranslate2), and [michaelfeil](https://huggingface.co/michaelfeil)! - Link to Original Model ([Helsinki-NLP](https://huggingface.co/Helsinki-NLP)): [Model Link](https://huggingface.co/Helsinki-NLP/opus-mt-fr-ht) - This respository was based on the work of [CTranslate2](https://github.com/OpenNMT/CTranslate2). - This repository was based on the work of [michaelfeil](https://huggingface.co/michaelfeil). # What is CTranslate2? [CTranslate2](https://opennmt.net/CTranslate2/) is a C++ and Python library for efficient inference with Transformer models. CTranslate2 implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU. CTranslate2 is one of the most performant ways of hosting translation models at scale. Current supported models include: - Encoder-decoder models: Transformer base/big, M2M-100, NLLB, BART, mBART, Pegasus, T5, Whisper - Decoder-only models: GPT-2, GPT-J, GPT-NeoX, OPT, BLOOM, MPT, Llama, Mistral, Gemma, CodeGen, GPTBigCode, Falcon - Encoder-only models: BERT, DistilBERT, XLM-RoBERTa The project is production-oriented and comes with backward compatibility guarantees, but it also includes experimental features related to model compression and inference acceleration. # CTranslate2 Benchmarks Please note that the results presented below are only valid for the configuration used during this benchmark: absolute and relative performance may change with different settings. Tested against `newstest2014` (En -> De) dataset. The benchmark reports the number of target tokens generated per second (higher is better). The results are aggregated over multiple runs. See the benchmark scripts for more details and reproduce these numbers. Please note that the results presented below are only valid for the configuration used during this benchmark: absolute and relative performance may change with different settings. ## CPU Benchmarks for Generic Opus-MT Models | Library | Tokens per Second | Max Memory Usage | BLEU | | :----: | :----: | :----: | :----: | | Transformers 4.26.1 (with PyTorch 1.13.1) | 147.3 | 2332MB | 27.90 | | Marian 1.11.0 (int16) | 330.2 | 5901MB | 27.65 | | Marian 1.11.0 (int8) | 355.8 | 4763MB | 27.27 | | CTranslate2 3.6.0 (int16) | 596.1 | 660MB | 27.53 | | CTranslate2 3.6.0 (int8) | 696.1 | 516MB | 27.65 | ## GPU Benchmarks for Generic Opus-MT Models | Library | Tokens per Second | Max GPU Memory Usage | Max Memory Usage | BLEU | | :----: | :----: | :----: | :----: | :----: | | Transformers 4.26.1 (with PyTorch 1.13.1) | 1022.9 | 4097MB | 2109MB | 27.90 | | Marian 1.11.0 (float16) | 3962.4 | 3239MB | 1976MB | 27.94 | | CTranslate2 3.6.0 (float16) | 9296.7 | 909MB | 814MB | 27.9 | | CTranslate2 3.6.0 (int8 + float16) | 8362.7 | 813MB | 766MB | 27.9 | `Executed with 4 threads on a c5.2xlarge Amazon EC2 instance equipped with an Intel(R) Xeon(R) Platinum 8275CL CPU.` **Source to benchmark information can be found [here](https://github.com/OpenNMT/CTranslate2).**<br /> **Original model BLEU scores can be found [here](https://huggingface.co/Helsinki-NLP/opus-mt-fr-ht).** ## Internal Benchmarks Internal testing on our end showed **inference times reduced by 6x-10x** on average compared the vanilla checkpoints using the *transformers* library. A **slight reduction on BLEU scores (~5%)** was also identified in comparison to the vanilla checkpoints with a few exceptions. This is likely due to several factors, one being the quantization applied. Further testing is needed from our end to better assess the reduction in translation quality. The command used to compile the vanilla checkpoint into a CTranslate2 model can be found below. Modifying this command can yield differing balances between inferencing performance and translation quality. # CTranslate2 Installation ```bash pip install hf-hub-ctranslate2>=1.0.0 ctranslate2>=3.13.0 ``` ### ct2-transformers-converter Command Used: ```bash ct2-transformers-converter --model Helsinki-NLP/opus-mt-fr-ht --output_dir ./ctranslate2/opus-mt-fr-ht-ctranslate2 --force --copy_files README.md generation_config.json tokenizer_config.json vocab.json source.spm .gitattributes target.spm --quantization float16 ``` # CTranslate2 Converted Checkpoint Information: **Compatible With:** - [ctranslate2](https://github.com/OpenNMT/CTranslate2) - [hf-hub-ctranslate2](https://github.com/michaelfeil/hf-hub-ctranslate2) **Compute Type:** - `compute_type=int8_float16` for `device="cuda"` - `compute_type=int8` for `device="cpu"` # Sample Code - ctranslate2 #### Clone the repository to the working directory or wherever you wish to store the model artifacts. #### ```bash git clone https://huggingface.co/gaudi/opus-mt-fr-ht-ctranslate2 ``` #### Take the python code below and update the 'model_dir' variable to the location of the cloned repository. #### ```python from ctranslate2 import Translator import transformers model_dir = "./opus-mt-fr-ht-ctranslate2" # Path to model directory. translator = Translator( model_path=model_dir, device="cuda", # cpu, cuda, or auto. inter_threads=1, # Maximum number of parallel translations. intra_threads=4, # Number of OpenMP threads per translator. compute_type="int8_float16", # int8 for cpu or int8_float16 for cuda. ) tokenizer = transformers.AutoTokenizer.from_pretrained(model_dir) source = tokenizer.convert_ids_to_tokens(tokenizer.encode("XXXXXX, XXX XX XXXXXX.")) results = translator.translate_batch([source]) target = results[0].hypotheses[0] print(tokenizer.decode(tokenizer.convert_tokens_to_ids(target))) ``` # Sample Code - hf-hub-ctranslate2 **Derived From [michaelfeil](https://huggingface.co/michaelfeil):** ```python from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub from transformers import AutoTokenizer model_name = "gaudi/opus-mt-fr-ht-ctranslate2" model = TranslatorCT2fromHfHub( model_name_or_path=model_name, device="cuda", compute_type="int8_float16", tokenizer=AutoTokenizer.from_pretrained(model_name) ) outputs = model.generate( text=["XXX XX XXX XXXXXXX XXXX?", "XX XX XXXX XX XXX!"], ) print(outputs) ``` # License and other remarks: License conditions are intended to be idential to [original huggingface repository](https://huggingface.co/Helsinki-NLP/opus-mt-fr-ht) by Helsinki-NLP.
[ "TRANSLATION" ]
Non_BioNLP
RichardErkhov/EmergentMethods_-_Phi-3-mini-128k-instruct-graph-4bits
RichardErkhov
null
[ "safetensors", "phi3", "custom_code", "4-bit", "bitsandbytes", "region:us" ]
1,737,190,117,000
2025-01-18T08:50:48
29
0
--- {} --- Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Phi-3-mini-128k-instruct-graph - bnb 4bits - Model creator: https://huggingface.co/EmergentMethods/ - Original model: https://huggingface.co/EmergentMethods/Phi-3-mini-128k-instruct-graph/ Original model description: --- license: cc-by-nc-sa-4.0 datasets: - EmergentMethods/AskNews-GraphER-v0 tags: - entity-relationship-extraction - news-analysis language: - en pipeline_tag: text-generation --- # Model Card for Phi-3-mini-128k-instruct-graph This model is a fine-tuned version of Microsoft's Phi-3-mini-128k-instruct, specifically tailored for entity relationship extraction from general text data. It aims to match the quality and accuracy of GPT-4 in generating entity relationship graphs while offering improved efficiency for large-scale processing. ## Model Details - **Developed by:** [Emergent Methods](https://emergentmethods.ai/) - **Funded by:** [Emergent Methods](https://emergentmethods.ai/) - **Shared by:** [Emergent Methods](https://emergentmethods.ai/) - **Model type:** microsoft/phi-3-mini-128k-instruct (fine-tuned) - **Language(s):** English - **License:** Creative Commons Attribution Non Commercial Share Alike 4.0 - **Finetuned from model:** [microsoft/phi-3-mini-128k-instruct](https://huggingface.co/microsoft/phi-3-mini-128k-instruct) For more information, see our blog post.: ๐Ÿ“ฐ [Blog](https://emergentmethods.medium.com/outperforming-claude-3-5-sonnet-with-phi-3-mini-4k-for-graph-entity-relationship-extraction-tasks-7c8f6c1ebd79) <br> ## Uses This model is designed for generating structured JSON data representing entity relationships in general text data. It can be used for: - Enhanced information retrieval in various text databases - Exploration of temporal relationships and evolving narratives across different types of documents - Advanced predictive modeling for trend analysis in diverse textual sources The model is particularly useful for applications requiring high-throughput processing of large volumes of text data, such as content aggregation platforms, research databases, and comprehensive text analysis systems. ## Bias, Risks, and Limitations Although the goal of the dataset is to reduce bias, and improve diversity, it is still biased to western languages and countries. This limitation originates from the abilities of Llama2 for the translation and summary generations. Further, any bias originating in Llama2 training data will also be present in this dataset, since Llama2 was used to summarize the open-web articles. Further, any biases present in Microsoft Phi-3 will be present in the present dataset. ## Training Details - **Training Data:** Over 7,000 stories and updates from AskNews, curated to avoid topic overlap - **Training Procedure:** Fine-tuned using the Transformers library, SFTTrainer, PEFT, and QLoRA ## Evaluation Results Compared to GPT-4o (ground truth), Claude Sonnet 3.5, and the base Phi-3 model: | Metric | Phi-3 Fine-tuned | Claude Sonnet 3.5 | Phi-3 (base) | |:--------|:------------------|:-------------------|:--------------| | Nodes Similarity | 0.78 | 0.64 | 0.64 | | Edges Similarity | 0.49 | 0.41 | 0.30 | | JSON Consistency | 0.99 | 0.97 | 0.96 | | JSON Similarity | 0.75 | 0.67 | 0.63 | ## Environmental Impact - **Hardware Type:** 1x A100 SXM - **Hours used:** 3 hours - **Carbon Emitted:** 0.44 kg (According to Machine Learning Impact calculator) ## How to Get Started with the Model (Sample inference code) This code snippets show how to get quickly started with running the model on a GPU: ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline torch.random.manual_seed(0) model = AutoModelForCausalLM.from_pretrained( "EmergentMethods/Phi-3-mini-128k-instruct-graph", device_map="cuda", torch_dtype="auto", trust_remote_code=True, ) tokenizer = AutoTokenizer.from_pretrained("EmergentMethods/Phi-3-mini-128k-instruct-graph") messages = [ {"role": "system", "content": """ A chat between a curious user and an artificial intelligence Assistant. The Assistant is an expert at identifying entities and relationships in text. The Assistant responds in JSON output only. The User provides text in the format: -------Text begin------- <User provided text> -------Text end------- The Assistant follows the following steps before replying to the User: 1. **identify the most important entities** The Assistant identifies the most important entities in the text. These entities are listed in the JSON output under the key "nodes", they follow the structure of a list of dictionaries where each dict is: "nodes":[{"id": <entity N>, "type": <type>, "detailed_type": <detailed type>}, ...] where "type": <type> is a broad categorization of the entity. "detailed type": <detailed_type> is a very descriptive categorization of the entity. 2. **determine relationships** The Assistant uses the text between -------Text begin------- and -------Text end------- to determine the relationships between the entities identified in the "nodes" list defined above. These relationships are called "edges" and they follow the structure of: "edges":[{"from": <entity 1>, "to": <entity 2>, "label": <relationship>}, ...] The <entity N> must correspond to the "id" of an entity in the "nodes" list. The Assistant never repeats the same node twice. The Assistant never repeats the same edge twice. The Assistant responds to the User in JSON only, according to the following JSON schema: {"type":"object","properties":{"nodes":{"type":"array","items":{"type":"object","properties":{"id":{"type":"string"},"type":{"type":"string"},"detailed_type":{"type":"string"}},"required":["id","type","detailed_type"],"additionalProperties":false}},"edges":{"type":"array","items":{"type":"object","properties":{"from":{"type":"string"},"to":{"type":"string"},"label":{"type":"string"}},"required":["from","to","label"],"additionalProperties":false}}},"required":["nodes","edges"],"additionalProperties":false} """}, {"role": "user", "content": """ -------Text begin------- OpenAI is an American artificial intelligence (AI) research organization founded in December 2015 and headquartered in San Francisco, California. Its mission is to develop "safe and beneficial" artificial general intelligence, which it defines as "highly autonomous systems that outperform humans at most economically valuable work".[4] As a leading organization in the ongoing AI boom,[5] OpenAI is known for the GPT family of large language models, the DALL-E series of text-to-image models, and a text-to-video model named Sora.[6][7] Its release of ChatGPT in November 2022 has been credited with catalyzing widespread interest in generative AI. -------Text end------- """} ] pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, ) generation_args = { "max_new_tokens": 500, "return_full_text": False, "temperature": 0.0, "do_sample": False, } output = pipe(messages, **generation_args) print(output[0]['generated_text']) # Output: # { # "nodes": [ # { # "id": "OpenAI", # "type": "organization", # "detailed_type": "ai research organization" # }, # { # "id": "GPT family", # "type": "technology", # "detailed_type": "large language models" # }, # { # "id": "DALL-E series", # "type": "technology", # "detailed_type": "text-to-image models" # }, # { # "id": "Sora", # "type": "technology", # "detailed_type": "text-to-video model" # }, # { # "id": "ChatGPT", # "type": "technology", # "detailed_type": "generative ai" # }, # { # "id": "San Francisco", # "type": "location", # "detailed_type": "city" # }, # { # "id": "California", # "type": "location", # "detailed_type": "state" # }, # { # "id": "December 2015", # "type": "date", # "detailed_type": "foundation date" # }, # { # "id": "November 2022", # "type": "date", # "detailed_type": "release date" # } # ], # "edges": [ # { # "from": "OpenAI", # "to": "San Francisco", # "label": "headquartered in" # }, # { # "from": "San Francisco", # "to": "California", # "label": "located in" # }, # { # "from": "OpenAI", # "to": "December 2015", # "label": "founded in" # }, # { # "from": "OpenAI", # "to": "GPT family", # "label": "developed" # }, # { # "from": "OpenAI", # "to": "DALL-E series", # "label": "developed" # }, # { # "from": "OpenAI", # "to": "Sora", # "label": "developed" # }, # { # "from": "OpenAI", # "to": "ChatGPT", # "label": "released" # }, # { # "from": "ChatGPT", # "to": "November 2022", # "label": "released in" # } # ] # } ``` ## Ethical Considerations Users should be aware that this model is designed for entity relationship extraction from general text data and may not be suitable for other domains without further fine-tuning. The model's outputs should be reviewed and validated, especially when used in applications that may impact decision-making or public information dissemination.
[ "TRANSLATION" ]
Non_BioNLP
HusseinEid/bert-finetuned-ner
HusseinEid
token-classification
[ "transformers", "tensorboard", "safetensors", "bert", "token-classification", "generated_from_trainer", "en", "dataset:conll2003", "base_model:google-bert/bert-base-cased", "base_model:finetune:google-bert/bert-base-cased", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
1,716,045,407,000
2024-05-18T15:35:40
9
0
--- base_model: bert-base-cased datasets: - conll2003 language: - en library_name: transformers license: apache-2.0 metrics: - precision - recall - f1 - accuracy tags: - generated_from_trainer model-index: - name: bert-finetuned-ner results: - task: type: token-classification name: Token Classification dataset: name: conll2003 type: conll2003 config: conll2003 split: validation args: conll2003 metrics: - type: precision value: 0.9342824035755669 name: Precision - type: recall value: 0.9498485358465163 name: Recall - type: f1 value: 0.9420011683217892 name: F1 - type: accuracy value: 0.9861217401542356 name: Accuracy --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # bert-finetuned-ner This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset. It achieves the following results on the evaluation set: - Loss: 0.0636 - Precision: 0.9343 - Recall: 0.9498 - F1: 0.9420 - Accuracy: 0.9861 ## Model description This is a model for Named entity recognition NER ## Intended uses & limitations Open source ## Training and evaluation data The conll2003 dataset ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | 0.0757 | 1.0 | 1756 | 0.0638 | 0.9215 | 0.9362 | 0.9288 | 0.9833 | | 0.0352 | 2.0 | 3512 | 0.0667 | 0.9360 | 0.9482 | 0.9421 | 0.9858 | | 0.0215 | 3.0 | 5268 | 0.0636 | 0.9343 | 0.9498 | 0.9420 | 0.9861 | ### Framework versions - Transformers 4.40.2 - Pytorch 2.2.1+cu121 - Datasets 2.19.1 - Tokenizers 0.19.1
[ "NAMED_ENTITY_RECOGNITION" ]
Non_BioNLP
Tasm/autotrain-esdxq-2v2zh
Tasm
text-classification
[ "tensorboard", "safetensors", "bert", "autotrain", "text-classification", "base_model:google-bert/bert-base-multilingual-cased", "base_model:finetune:google-bert/bert-base-multilingual-cased", "region:us" ]
1,732,036,477,000
2024-11-19T17:26:01
5
0
--- base_model: google-bert/bert-base-multilingual-cased tags: - autotrain - text-classification widget: - text: I love AutoTrain --- # Model Trained Using AutoTrain - Problem type: Text Classification ## Validation Metrics loss: 0.0839352235198021 f1: 0.8888888888888888 precision: 1.0 recall: 0.8 auc: 0.8300000000000001 accuracy: 0.9846153846153847
[ "TEXT_CLASSIFICATION" ]
Non_BioNLP
ns0911/klue-roberta-base-klue-sts
ns0911
sentence-similarity
[ "sentence-transformers", "safetensors", "roberta", "sentence-similarity", "feature-extraction", "generated_from_trainer", "dataset_size:10501", "loss:CosineSimilarityLoss", "arxiv:1908.10084", "base_model:klue/roberta-base", "base_model:finetune:klue/roberta-base", "model-index", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]
1,736,728,078,000
2025-01-13T00:28:18
6
0
--- base_model: klue/roberta-base library_name: sentence-transformers metrics: - pearson_cosine - spearman_cosine pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:10501 - loss:CosineSimilarityLoss widget: - source_sentence: ์ฐจ๋กœ 15๋ถ„ ๊ฑฐ๋ฆฌ์— ๋ฒ ๋„ค์น˜์•„ ๋กœ๋งˆ๊ด‘์žฅ์— ๋„์ฐฉํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. sentences: - ๋ฒ ๋‹ˆ์Šค ๋กœ๋งˆ ๊ด‘์žฅ๊นŒ์ง€ ์ฐจ๋กœ 15๋ถ„ ๊ฑธ๋ฆฝ๋‹ˆ๋‹ค. - ์ •๋ง ๋„ˆ๋ฌด๋‚˜๋„ ๊นจ๋—ํ•˜๊ณ  ํŽธ์•ˆํ•œ ์ˆ™์†Œ์ž…๋‹ˆ๋‹ค. - ์ฒ˜์Œ์— ์ง‘์ฐพ๊ธฐ๊ฐ€ ์กฐ๊ธˆ ํž˜๋“ค์—ˆ์ง€๋งŒ ์ง‘์ด ์žˆ๋Š” ๊ณจ๋ชฉ๊นŒ์ง€๋Š” ๊ฐ€๊ธฐ ์‰ฌ์›Œ์š”! - source_sentence: ๋‹ค์Œ๋ฒˆ ๋Œ€๋งŒ ๋ฐฉ๋ฌธ์‹œ ๊ผญ ๋‹ค์‹œ ์˜ค๊ฒ ์Šต๋‹ˆ๋‹ค. sentences: - ์˜ค๋Š˜ ๋‚ ์”จ๋Š” ๋น„๊ฐ€ ์˜ฌ๊นŒ? ์•„๋‹ˆ๋ฉด ๋ง‘์„๊นŒ? - ๋ช‡๋ช‡ ๋ถ„์•ผ๊ฐ€ ์•„๋‹ˆ๋ผ ์ „ ์‚ฐ์—… ๋ถ„์•ผ๊ฐ€ ์œ„๊ธฐ ์ƒํ™ฉ์ž…๋‹ˆ๋‹ค. - ๋‹ค์Œ์— ๋Œ€๋งŒ์— ๊ฐ€๋ฉด ๊ผญ ๋Œ์•„์˜ฌ๊ฒŒ์š”. - source_sentence: ๊ฒฝ๊ธฐ๋‚ด๋ฅ™์—๋Š” ์–ผ๋งˆ๋‚˜ ๋น„๊ฐ€ ์˜ฌ ์˜ˆ์ •์ด์•ผ? sentences: - ํŠนํžˆ ์‹œํ—˜์žฅ ์ž…๊ตฌ๋Š” ์‹œํ—˜์žฅ ์ถœ์ž…๊ตฌ๊ฐ€ ํ†ต์ผ๋˜์–ด ์žˆ์œผ๋ฉฐ, ์‹œํ—˜์žฅ ์ถœ์ž…๊ตฌ๋งˆ๋‹ค ์† ์†Œ๋… ๋ฐ ๋ฐœ์—ด ๊ฒ€์‚ฌ๋ฅผ ์‹ค์‹œํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค. - ์ข‹์€ ํŒŒ๋„๊ฐ€ ๋“ค์–ด์˜ค๋Š” ๋•Œ๋Š” ๋‹ค๋ฅธ ๊ฒƒ ๋ง๊ณ  ์„œํ•‘ํ•ฉ์‹œ๋‹ค. - ์˜ค๋Š˜ ์กฐ์น˜๋“ค์€ ์†Œ์ƒ๊ณต์ธ ๋“ฑ์ด ๊ฐ€์žฅ ๊ธด๊ธ‰ํ•˜๊ฒŒ ์š”์ฒญํ•˜๋Š” ๊ธˆ์œต ์ง€์› ๋Œ€์ฑ…๋“ค์ž…๋‹ˆ๋‹ค. - source_sentence: ํ•™๊ต ์„ฑ์ ํ‘œ๋Š” ๋ฉ”์ผ๋กœ ๋ฐ›๋Š”๊ฒŒ ์šฐํŽธ๋ณด๋‹ค ํŽธํ•˜๊ณ  ์ข‹์„๊ฑฐ์•ผ. sentences: - ํ•™๊ต ์„ฑ์ ํ‘œ๋ฅผ ๊ธฐ์กด ์šฐํŽธ ๋Œ€์‹  ๋ฉ”์ผ๋กœ ๋ฐ›์•„๋ณด์„ธ์š”. - ์ฒญ์‚ฐ๋ฆฌ ๋ด‰๊ณ ๋™ ์ „ํˆฌ 100์ฃผ๋…„์„ ๊ธฐ๋…ํ•ฉ๋‹ˆ๋‹ค - ์‹œ๋ชฌ ์—ญ์—์„œ ์ž˜ ๊ฑธ์–ด์š”. - source_sentence: ์ฃผ์š” ๋Œ€์ฑ…์œผ๋กœ๋Š” ์ถœ์‚ฐ์œจ ์ œ๊ณ ๋ฅผ ์œ„ํ•œ ์ฃผ๊ฑฐยท์ถœ์‚ฐยท๋ณด์œก ๋“ฑ ์ข…ํ•ฉ์  ์ง€์›๊ณผ ๊ณ ๋ น์ž ๊ณ„์†๊ณ ์šฉ ํ™œ์„ฑํ™” ๋ฐ ๊ณ ๋ น์ž ๋งž์ถคํ˜• ์ผ์ž๋ฆฌ ์ง€์›, ๋…ธ์ธ๋ณต์ง€ ํ™•๋Œ€ ๋“ฑ ๊ณ ๋ นํ™”๋Œ€์‘ ์ •์ฑ…๋…ธ๋ ฅ์˜ ์ง€์†์ด๋‹ค. sentences: - ์ด์ค‘ โ€˜40๋Œ€ ์ผ์ž๋ฆฌ ๋Œ€์ฑ…โ€™์€ โ–ฒ์ง์—…ํ›ˆ๋ จยท๊ต์œก ๋ฐ ์ƒ๊ณ„๋น„ ์ง€์› โ–ฒ๊ณ ์šฉ ์ง€์› โ–ฒ์ฐฝ์—… ์ง€์› โ–ฒ์‚ฐ์—…ยท์ง€์—ญ ์ง€์› ๋“ฑ 40๋Œ€ ๋งž์ถคํ˜• ์ง€์› ๋ฐฉ์•ˆ์ด ๋‹ด๊ธธ ์˜ˆ์ •์ด๋‹ค. - ์‚ฌ๋žŒ์ด ๋งŽ์ด ๋ถ๋นŒ๋•Œ๋Š” ์กฐ๊ธˆ ๋ถˆํŽธํ•จ์€ ๊ฐ์•ˆํ•ด์•ผ ํ•ฉ๋‹ˆ๋‹ค. - ์œ„์น˜, ์ˆ™์†Œ ์ฒญ๊ฒฐ๋„, ํ˜ธ์ŠคํŠธ ๋ชจ๋‘ ์ตœ๊ณ ์˜€์–ด์š”. model-index: - name: SentenceTransformer based on klue/roberta-base results: - task: type: semantic-similarity name: Semantic Similarity dataset: name: Unknown type: unknown metrics: - type: pearson_cosine value: 0.9618565828583842 name: Pearson Cosine - type: spearman_cosine value: 0.9203242816571715 name: Spearman Cosine --- # SentenceTransformer based on klue/roberta-base This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [klue/roberta-base](https://huggingface.co/klue/roberta-base). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. ## Model Details ### Model Description - **Model Type:** Sentence Transformer - **Base model:** [klue/roberta-base](https://huggingface.co/klue/roberta-base) <!-- at revision 02f94ba5e3fcb7e2a58a390b8639b0fac974a8da --> - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 dimensions - **Similarity Function:** Cosine Similarity <!-- - **Training Dataset:** Unknown --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown --> ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the ๐Ÿค— Hub model = SentenceTransformer("sentence_transformers_model_id") # Run inference sentences = [ '์ฃผ์š” ๋Œ€์ฑ…์œผ๋กœ๋Š” ์ถœ์‚ฐ์œจ ์ œ๊ณ ๋ฅผ ์œ„ํ•œ ์ฃผ๊ฑฐยท์ถœ์‚ฐยท๋ณด์œก ๋“ฑ ์ข…ํ•ฉ์  ์ง€์›๊ณผ ๊ณ ๋ น์ž ๊ณ„์†๊ณ ์šฉ ํ™œ์„ฑํ™” ๋ฐ ๊ณ ๋ น์ž ๋งž์ถคํ˜• ์ผ์ž๋ฆฌ ์ง€์›, ๋…ธ์ธ๋ณต์ง€ ํ™•๋Œ€ ๋“ฑ ๊ณ ๋ นํ™”๋Œ€์‘ ์ •์ฑ…๋…ธ๋ ฅ์˜ ์ง€์†์ด๋‹ค.', '์ด์ค‘ โ€˜40๋Œ€ ์ผ์ž๋ฆฌ ๋Œ€์ฑ…โ€™์€ โ–ฒ์ง์—…ํ›ˆ๋ จยท๊ต์œก ๋ฐ ์ƒ๊ณ„๋น„ ์ง€์› โ–ฒ๊ณ ์šฉ ์ง€์› โ–ฒ์ฐฝ์—… ์ง€์› โ–ฒ์‚ฐ์—…ยท์ง€์—ญ ์ง€์› ๋“ฑ 40๋Œ€ ๋งž์ถคํ˜• ์ง€์› ๋ฐฉ์•ˆ์ด ๋‹ด๊ธธ ์˜ˆ์ •์ด๋‹ค.', '์‚ฌ๋žŒ์ด ๋งŽ์ด ๋ถ๋นŒ๋•Œ๋Š” ์กฐ๊ธˆ ๋ถˆํŽธํ•จ์€ ๊ฐ์•ˆํ•ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 768] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` <!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* --> ## Evaluation ### Metrics #### Semantic Similarity * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.9619 | | **spearman_cosine** | **0.9203** | <!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* --> ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 10,501 training samples * Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code> * Approximate statistics based on the first 1000 samples: | | sentence_0 | sentence_1 | label | |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------| | type | string | string | float | | details | <ul><li>min: 6 tokens</li><li>mean: 19.9 tokens</li><li>max: 58 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 19.25 tokens</li><li>max: 61 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.45</li><li>max: 1.0</li></ul> | * Samples: | sentence_0 | sentence_1 | label | |:----------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------| | <code>๊ทธ๋ฆฌ๊ณ  ๋Œ€๋งŒ์˜ ๋ฒˆํ™”๊ฐ€์ธ ์‹œ๋จผ์„ ์ฆ๊ธฐ๊ธฐ์— ์œ„์น˜๋Š” ๋„ˆ๋ฌด ์ข‹์•˜์Šต๋‹ˆ๋‹ค.</code> | <code>๊ทธ๋ฆฌ๊ณ  ๋Œ€๋งŒ ์‹œ๋‚ด ์ค‘์‹ฌ๊ฐ€์ธ ์‹œ๋ชฌ์„ ์ฆ๊ธฐ๊ธฐ์— ์ข‹์€ ์žฅ์†Œ์˜€์Šต๋‹ˆ๋‹ค.</code> | <code>0.7</code> | | <code>๋˜ ์ตœ๊ทผ 1์ฃผ์ผ ๊ฐ„ ํ•ด์™ธ ์œ ์ž… ํ™•์ง„์ž๋Š” 140๋ช…, ์ผํ‰๊ท  20๋ช…์œผ๋กœ ์ „ ์ฃผ ๋Œ€๋น„ ์ผํ‰๊ท  2๋ช… ๋Š˜์—ˆ๋‹ค.</code> | <code>๊ฒŒ๋‹ค๊ฐ€, ํ•ด์™ธ๋กœ์˜ ํ™•์ธ๋œ ์œ ์ž…์˜ ์ˆ˜๋Š” ์ „์ฃผ์— ๋น„ํ•ด ํ•˜๋ฃจ ํ‰๊ท  2๊ฐœ ์ฆ๊ฐ€ํ•˜์—ฌ 140๊ฐœ ๊ทธ๋ฆฌ๊ณ  ํ•˜๋ฃจ ํ‰๊ท  20๊ฐœ๊ฐ€ ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.</code> | <code>0.58</code> | | <code>ํ•œ๊ตญ์ธ์œผ๋กœ์„œ ์‹ ๊ฒฝ์“ฐ์ด๋Š” ์  ์ ๊ฒ ์Šต๋‹ˆ๋‹ค.</code> | <code>์ €ํฌ ๋ฐฉ์˜ ๊ฒฝ์šฐ ๋ฐ”๋‹ฅ์ด ์‚๊ทธ๋• ๊ฑฐ๋ฆฌ๋Š” ๋ถ€์ค€์ด ์กฐ๊ธˆ๋” ์‹ ๊ฒฝ์“ฐ์ด๋Š” ๋ถ€๋ถ„์ด์—ˆ์Šต๋‹ˆ๋‹ค.</code> | <code>0.16</code> | * Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters: ```json { "loss_fct": "torch.nn.modules.loss.MSELoss" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `num_train_epochs`: 4 - `multi_dataset_batch_sampler`: round_robin #### 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`: 16 - `per_device_eval_batch_size`: 16 - `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`: 5e-05 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1 - `num_train_epochs`: 4 - `max_steps`: -1 - `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`: False - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `local_rank`: 0 - `ddp_backend`: None - `tpu_num_cores`: None - `tpu_metrics_debug`: False - `debug`: [] - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `past_index`: -1 - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: False - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_min_num_params`: 0 - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `fsdp_transformer_layer_cls_to_wrap`: None - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch - `optim_args`: None - `adafactor`: False - `group_by_length`: False - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `skip_memory_metrics`: True - `use_legacy_prediction_loop`: False - `push_to_hub`: False - `resume_from_checkpoint`: None - `hub_model_id`: None - `hub_strategy`: every_save - `hub_private_repo`: None - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `include_for_metrics`: [] - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: None - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `dispatch_batches`: None - `split_batches`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: False - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `eval_on_start`: False - `use_liger_kernel`: False - `eval_use_gather_object`: False - `average_tokens_across_devices`: False - `prompts`: None - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: round_robin </details> ### Training Logs | Epoch | Step | Training Loss | spearman_cosine | |:------:|:----:|:-------------:|:---------------:| | 0.7610 | 500 | 0.0277 | - | | 1.0 | 657 | - | 0.9102 | | 1.5221 | 1000 | 0.0082 | 0.9137 | | 2.0 | 1314 | - | 0.9174 | | 2.2831 | 1500 | 0.0052 | - | | 3.0 | 1971 | - | 0.9199 | | 3.0441 | 2000 | 0.0034 | 0.9192 | | 3.8052 | 2500 | 0.0026 | - | | 4.0 | 2628 | - | 0.9203 | ### Framework Versions - Python: 3.10.12 - Sentence Transformers: 3.3.1 - Transformers: 4.47.1 - PyTorch: 2.5.1+cu121 - Accelerate: 1.2.1 - Datasets: 3.2.0 - Tokenizers: 0.21.0 ## 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", } ``` <!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->
[ "TEXT_CLASSIFICATION", "SEMANTIC_SIMILARITY" ]
Non_BioNLP
fine-tuned/jina-embeddings-v2-base-en-522024-6pj3-webapp_6103321184
fine-tuned
feature-extraction
[ "transformers", "safetensors", "bert", "feature-extraction", "custom_code", "text-embeddings-inference", "endpoints_compatible", "region:us" ]
1,714,663,005,000
2024-05-02T15:17:00
6
0
--- {} --- # fine-tuned/jina-embeddings-v2-base-en-522024-6pj3-webapp_6103321184 ## Model Description fine-tuned/jina-embeddings-v2-base-en-522024-6pj3-webapp_6103321184 is a fine-tuned version of jinaai/jina-embeddings-v2-base-en designed for a specific domain. ## Use Case This model is designed to support various applications in natural language processing and understanding. ## Associated Dataset This the dataset for this model can be found [**here**](https://huggingface.co/datasets/fine-tuned/fine-tuned/jina-embeddings-v2-base-en-522024-6pj3-webapp_6103321184). ## How to Use This model can be easily integrated into your NLP pipeline for tasks such as text classification, sentiment analysis, entity recognition, and more. Here's a simple example to get you started: ```python from transformers import AutoModel, AutoTokenizer llm_name = "fine-tuned/jina-embeddings-v2-base-en-522024-6pj3-webapp_6103321184" tokenizer = AutoTokenizer.from_pretrained(llm_name) model = AutoModel.from_pretrained(llm_name, trust_remote_code=True) tokens = tokenizer("Your text here", return_tensors="pt") embedding = model(**tokens) ```
[ "TEXT_CLASSIFICATION" ]
Non_BioNLP
jeff-RQ/new-test-model
jeff-RQ
image-to-text
[ "transformers", "pytorch", "blip-2", "visual-question-answering", "vision", "image-to-text", "image-captioning", "en", "arxiv:2301.12597", "license:mit", "endpoints_compatible", "region:us" ]
1,688,482,327,000
2023-07-05T15:01:24
144
0
--- language: en license: mit pipeline_tag: image-to-text tags: - vision - image-to-text - image-captioning - visual-question-answering duplicated_from: Salesforce/blip2-opt-2.7b --- # BLIP-2, OPT-2.7b, pre-trained only BLIP-2 model, leveraging [OPT-2.7b](https://huggingface.co/facebook/opt-2.7b) (a large language model with 2.7 billion parameters). It was introduced in the paper [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://arxiv.org/abs/2301.12597) by Li et al. and first released in [this repository](https://github.com/salesforce/LAVIS/tree/main/projects/blip2). Disclaimer: The team releasing BLIP-2 did not write a model card for this model so this model card has been written by the Hugging Face team. ## Model description BLIP-2 consists of 3 models: a CLIP-like image encoder, a Querying Transformer (Q-Former) and a large language model. The authors initialize the weights of the image encoder and large language model from pre-trained checkpoints and keep them frozen while training the Querying Transformer, which is a BERT-like Transformer encoder that maps a set of "query tokens" to query embeddings, which bridge the gap between the embedding space of the image encoder and the large language model. The goal for the model is simply to predict the next text token, giving the query embeddings and the previous text. <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/blip2_architecture.jpg" alt="drawing" width="600"/> This allows the model to be used for tasks like: - image captioning - visual question answering (VQA) - chat-like conversations by feeding the image and the previous conversation as prompt to the model ## Direct Use and Downstream Use You can use the raw model for conditional text generation given an image and optional text. See the [model hub](https://huggingface.co/models?search=Salesforce/blip) to look for fine-tuned versions on a task that interests you. ## Bias, Risks, Limitations, and Ethical Considerations BLIP2-OPT uses off-the-shelf OPT as the language model. It inherits the same risks and limitations as mentioned in Meta's model card. > Like other large language models for which the diversity (or lack thereof) of training > data induces downstream impact on the quality of our model, OPT-175B has limitations in terms > of bias and safety. OPT-175B can also have quality issues in terms of generation diversity and > hallucination. In general, OPT-175B is not immune from the plethora of issues that plague modern > large language models. > BLIP2 is fine-tuned on image-text datasets (e.g. [LAION](https://laion.ai/blog/laion-400-open-dataset/) ) collected from the internet. As a result the model itself is potentially vulnerable to generating equivalently inappropriate content or replicating inherent biases in the underlying data. BLIP2 has not been tested in real world applications. It should not be directly deployed in any applications. Researchers should first carefully assess the safety and fairness of the model in relation to the specific context theyโ€™re being deployed within. ### How to use For code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/blip-2#transformers.Blip2ForConditionalGeneration.forward.example). #### Running the model on CPU <details> <summary> Click to expand </summary> ```python import requests from PIL import Image from transformers import Blip2Processor, Blip2ForConditionalGeneration processor = Blip2Processor.from_pretrained("Salesforce/blip2-opt-2.7b") model = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-opt-2.7b") img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB') question = "how many dogs are in the picture?" inputs = processor(raw_image, question, return_tensors="pt") out = model.generate(**inputs) print(processor.decode(out[0], skip_special_tokens=True)) ``` </details> #### Running the model on GPU ##### In full precision <details> <summary> Click to expand </summary> ```python # pip install accelerate import requests from PIL import Image from transformers import Blip2Processor, Blip2ForConditionalGeneration processor = Blip2Processor.from_pretrained("Salesforce/blip2-opt-2.7b") model = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-opt-2.7b", device_map="auto") img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB') question = "how many dogs are in the picture?" inputs = processor(raw_image, question, return_tensors="pt").to("cuda") out = model.generate(**inputs) print(processor.decode(out[0], skip_special_tokens=True)) ``` </details> ##### In half precision (`float16`) <details> <summary> Click to expand </summary> ```python # pip install accelerate import torch import requests from PIL import Image from transformers import Blip2Processor, Blip2ForConditionalGeneration processor = Blip2Processor.from_pretrained("Salesforce/blip2-opt-2.7b") model = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-opt-2.7b", torch_dtype=torch.float16, device_map="auto") img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB') question = "how many dogs are in the picture?" inputs = processor(raw_image, question, return_tensors="pt").to("cuda", torch.float16) out = model.generate(**inputs) print(processor.decode(out[0], skip_special_tokens=True)) ``` </details> ##### In 8-bit precision (`int8`) <details> <summary> Click to expand </summary> ```python # pip install accelerate bitsandbytes import torch import requests from PIL import Image from transformers import Blip2Processor, Blip2ForConditionalGeneration processor = Blip2Processor.from_pretrained("Salesforce/blip2-opt-2.7b") model = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-opt-2.7b", load_in_8bit=True, device_map="auto") img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB') question = "how many dogs are in the picture?" inputs = processor(raw_image, question, return_tensors="pt").to("cuda", torch.float16) out = model.generate(**inputs) print(processor.decode(out[0], skip_special_tokens=True)) ``` </details>
[ "QUESTION_ANSWERING" ]
Non_BioNLP
irusl/05newa1
irusl
text-generation
[ "transformers", "safetensors", "llama", "text-generation", "Llama-3", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "synthetic data", "distillation", "function calling", "json mode", "axolotl", "merges", "conversational", "en", "dataset:teknium/OpenHermes-2.5", "base_model:NousResearch/Hermes-2-Pro-Llama-3-8B", "base_model:finetune:NousResearch/Hermes-2-Pro-Llama-3-8B", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
1,721,034,106,000
2024-07-15T09:04:58
6
0
--- base_model: NousResearch/Hermes-2-Pro-Llama-3-8B datasets: - teknium/OpenHermes-2.5 language: - en license: apache-2.0 tags: - Llama-3 - instruct - finetune - chatml - DPO - RLHF - gpt4 - synthetic data - distillation - function calling - json mode - axolotl - merges widget: - example_title: Hermes 2 Pro Llama-3 Instruct Merge messages: - role: system content: You are a sentient, superintelligent artificial general intelligence, here to teach and assist me. - role: user content: Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world. model-index: - name: Hermes-2-Pro-Llama-3-Instruct-8B-Merge results: [] --- # - Hermes-2 ฮ˜ Llama-3 8B ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/HQnQmNM1L3KXGhp0wUzHH.png) ## Model Description Hermes-2 ฮ˜ (Theta) is the first experimental merged model released by [Nous Research](https://nousresearch.com/), in collaboration with Charles Goddard at [Arcee](https://www.arcee.ai/), the team behind MergeKit. Hermes-2 ฮ˜ is a merged and then further RLHF'ed version our excellent Hermes 2 Pro model and Meta's Llama-3 Instruct model to form a new model, Hermes-2 ฮ˜, combining the best of both worlds of each model. ## Example Outputs ### Create New Mythos: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/dvKhnSvHdx4nTQIqB9Lpv.png) ### Chat with a Meta-Cognitive Entity ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/GwdCqowE6GQylineqehhx.png) ### Ask for a structured JSON output: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/us72aL9gwUXdqSHetRVRV.png) # Prompt Format Hermes 2 ฮ˜ uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue. System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model. This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns. This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI. Prompt with system instruction (Use whatever system prompt you like, this is just an example!): ``` <|im_start|>system You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|> <|im_start|>user Hello, who are you?<|im_end|> <|im_start|>assistant Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|> ``` This prompt is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the `tokenizer.apply_chat_template()` method: ```python messages = [ {"role": "system", "content": "You are Hermes 2."}, {"role": "user", "content": "Hello, who are you?"} ] gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt") model.generate(**gen_input) ``` When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<|im_start|>assistant\n` to your prompt, to ensure that the model continues with an assistant response. To utilize the prompt format without a system prompt, simply leave the line out. ## Prompt Format for Function Calling Our model was trained on specific system prompts and structures for Function Calling. While the system prompt looks complicated, we have created a GitHub repo containing code to easily build these based on real python functions. You should use the system role with this message, followed by a function signature json as this example shows here. ``` <|im_start|>system You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {"type": "function", "function": {"name": "get_stock_fundamentals", "description": "get_stock_fundamentals(symbol: str) -> dict - Get fundamental data for a given stock symbol using yfinance API.\\n\\n Args:\\n symbol (str): The stock symbol.\\n\\n Returns:\\n dict: A dictionary containing fundamental data.\\n Keys:\\n - \'symbol\': The stock symbol.\\n - \'company_name\': The long name of the company.\\n - \'sector\': The sector to which the company belongs.\\n - \'industry\': The industry to which the company belongs.\\n - \'market_cap\': The market capitalization of the company.\\n - \'pe_ratio\': The forward price-to-earnings ratio.\\n - \'pb_ratio\': The price-to-book ratio.\\n - \'dividend_yield\': The dividend yield.\\n - \'eps\': The trailing earnings per share.\\n - \'beta\': The beta value of the stock.\\n - \'52_week_high\': The 52-week high price of the stock.\\n - \'52_week_low\': The 52-week low price of the stock.", "parameters": {"type": "object", "properties": {"symbol": {"type": "string"}}, "required": ["symbol"]}}} </tools> Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows: <tool_call> {"arguments": <args-dict>, "name": <function-name>} </tool_call><|im_end|> ``` To complete the function call, create a user prompt that follows the above system prompt, like so: ``` <|im_start|>user Fetch the stock fundamentals data for Tesla (TSLA)<|im_end|> ``` The model will then generate a tool call, which your inference code must parse, and plug into a function (see example inference code here: https://github.com/NousResearch/Hermes-Function-Calling): ``` <|im_start|>assistant <tool_call> {"arguments": {"symbol": "TSLA"}, "name": "get_stock_fundamentals"} </tool_call><|im_end|> ``` Once you parse the tool call, call the api and get the returned values for the call, and pass it back in as a new role, `tool` like so: ``` <|im_start|>tool <tool_response> {"name": "get_stock_fundamentals", "content": {'symbol': 'TSLA', 'company_name': 'Tesla, Inc.', 'sector': 'Consumer Cyclical', 'industry': 'Auto Manufacturers', 'market_cap': 611384164352, 'pe_ratio': 49.604652, 'pb_ratio': 9.762013, 'dividend_yield': None, 'eps': 4.3, 'beta': 2.427, '52_week_high': 299.29, '52_week_low': 152.37}} </tool_response> <|im_end|> ``` The assistant will then read in that data from the function's response, and generate a natural language response: ``` <|im_start|>assistant The stock fundamentals data for Tesla (TSLA) are as follows: - **Symbol**: TSLA - **Company Name**: Tesla, Inc. - **Sector**: Consumer Cyclical - **Industry**: Auto Manufacturers - **Market Capitalization**: $566,160,130,480 - **Forward Price-to-Earnings Ratio (PE Ratio)**: 42.73 - **Price-to-Book Ratio (PB Ratio)**: 9.04 - **Dividend Yield**: N/A - **Trailing Earnings Per Share (EPS)**: $4.3 - **Beta Value of the Stock**: 2.42 - **52-Week High Price of the Stock**: $299.29 - **52-Week Low Price of the Stock**: $152.37 This information provides a snapshot of Tesla's financial position and performance based on the fundamental data obtained from the yfinance API. It shows that Tesla has a substantial market capitalization and a relatively high P/E and P/B ratio compared to other stocks in its industry. The company does not pay a dividend at the moment, which is reflected by a 'Dividend Yield' of 'None'. The Beta value indicates that Tesla's stock has a moderate level of volatility relative to the market. The 52-week high and low prices give an idea of the stock's range over the past year. This data can be useful when assessing investment opportunities and making investment decisions.<|im_end|> ``` ## Prompt Format for JSON Mode / Structured Outputs Our model was also trained on a specific system prompt for Structured Outputs, which should respond with **only** a json object response, in a specific json schema. Your schema can be made from a pydantic object using our codebase, with the standalone script `jsonmode.py` available here: https://github.com/NousResearch/Hermes-Function-Calling/tree/main ``` <|im_start|>system You are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{schema}\n</schema><|im_end|> ``` Given the {schema} that you provide, it should follow the format of that json to create it's response, all you have to do is give a typical user prompt, and it will respond in JSON. # Benchmarks ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/suBbCUIxpcRvhCv6-DBDQ.png) ## GPT4All: ``` | ย  ย Task ย  ย  |Version| Metric |Value | ย  |Stderr| |-------------|------:|--------|-----:|---|-----:| |arc_challenge| ย  ย  ย 0|acc ย  ย  |0.5529|ยฑ ย |0.0145| | ย  ย  ย  ย  ย  ย  | ย  ย  ย  |acc_norm|0.5870|ยฑ ย |0.0144| |arc_easy ย  ย  | ย  ย  ย 0|acc ย  ย  |0.8371|ยฑ ย |0.0076| | ย  ย  ย  ย  ย  ย  | ย  ย  ย  |acc_norm|0.8144|ยฑ ย |0.0080| |boolq ย  ย  ย  ย | ย  ย  ย 1|acc ย  ย  |0.8599|ยฑ ย |0.0061| |hellaswag ย  ย | ย  ย  ย 0|acc ย  ย  |0.6133|ยฑ ย |0.0049| | ย  ย  ย  ย  ย  ย  | ย  ย  ย  |acc_norm|0.7989|ยฑ ย |0.0040| |openbookqa ย  | ย  ย  ย 0|acc ย  ย  |0.3940|ยฑ ย |0.0219| | ย  ย  ย  ย  ย  ย  | ย  ย  ย  |acc_norm|0.4680|ยฑ ย |0.0223| |piqa ย  ย  ย  ย  | ย  ย  ย 0|acc ย  ย  |0.8063|ยฑ ย |0.0092| | ย  ย  ย  ย  ย  ย  | ย  ย  ย  |acc_norm|0.8156|ยฑ ย |0.0090| |winogrande ย  | ย  ย  ย 0|acc ย  ย  |0.7372|ยฑ ย |0.0124| ``` Average: 72.59 ## AGIEval: ``` | ย  ย  ย  ย  ย  ย  Task ย  ย  ย  ย  ย  ย  |Version| Metric |Value | ย  |Stderr| |------------------------------|------:|--------|-----:|---|-----:| |agieval_aqua_rat ย  ย  ย  ย  ย  ย  ย | ย  ย  ย 0|acc ย  ย  |0.2441|ยฑ ย |0.0270| | ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย | ย  ย  ย  |acc_norm|0.2441|ยฑ ย |0.0270| |agieval_logiqa_en ย  ย  ย  ย  ย  ย  | ย  ย  ย 0|acc ย  ย  |0.3687|ยฑ ย |0.0189| | ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย | ย  ย  ย  |acc_norm|0.3840|ยฑ ย |0.0191| |agieval_lsat_ar ย  ย  ย  ย  ย  ย  ย  | ย  ย  ย 0|acc ย  ย  |0.2304|ยฑ ย |0.0278| | ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย | ย  ย  ย  |acc_norm|0.2174|ยฑ ย |0.0273| |agieval_lsat_lr ย  ย  ย  ย  ย  ย  ย  | ย  ย  ย 0|acc ย  ย  |0.5471|ยฑ ย |0.0221| | ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย | ย  ย  ย  |acc_norm|0.5373|ยฑ ย |0.0221| |agieval_lsat_rc ย  ย  ย  ย  ย  ย  ย  | ย  ย  ย 0|acc ย  ย  |0.6617|ยฑ ย |0.0289| | ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย | ย  ย  ย  |acc_norm|0.6357|ยฑ ย |0.0294| |agieval_sat_en ย  ย  ย  ย  ย  ย  ย  ย | ย  ย  ย 0|acc ย  ย  |0.7670|ยฑ ย |0.0295| | ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย | ย  ย  ย  |acc_norm|0.7379|ยฑ ย |0.0307| |agieval_sat_en_without_passage| ย  ย  ย 0|acc ย  ย  |0.4417|ยฑ ย |0.0347| | ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย | ย  ย  ย  |acc_norm|0.4223|ยฑ ย |0.0345| |agieval_sat_math ย  ย  ย  ย  ย  ย  ย | ย  ย  ย 0|acc ย  ย  |0.4000|ยฑ ย |0.0331| | ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย | ย  ย  ย  |acc_norm|0.3455|ยฑ ย |0.0321| ``` Average: 44.05 ## BigBench: ``` | ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย Task ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย |Version| ย  ย  ย  Metric ย  ย  ย  ย |Value | ย  |Stderr| |------------------------------------------------|------:|---------------------|-----:|---|-----:| |bigbench_causal_judgement ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  | ย  ย  ย 0|multiple_choice_grade|0.6000|ยฑ ย |0.0356| |bigbench_date_understanding ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  | ย  ย  ย 0|multiple_choice_grade|0.6585|ยฑ ย |0.0247| |bigbench_disambiguation_qa ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย | ย  ย  ย 0|multiple_choice_grade|0.3178|ยฑ ย |0.0290| |bigbench_geometric_shapes ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  | ย  ย  ย 0|multiple_choice_grade|0.2340|ยฑ ย |0.0224| | ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย | ย  ย  ย  |exact_str_match ย  ย  ย |0.0000|ยฑ ย |0.0000| |bigbench_logical_deduction_five_objects ย  ย  ย  ย  | ย  ย  ย 0|multiple_choice_grade|0.2980|ยฑ ย |0.0205| |bigbench_logical_deduction_seven_objects ย  ย  ย  ย | ย  ย  ย 0|multiple_choice_grade|0.2057|ยฑ ย |0.0153| |bigbench_logical_deduction_three_objects ย  ย  ย  ย | ย  ย  ย 0|multiple_choice_grade|0.5367|ยฑ ย |0.0288| |bigbench_movie_recommendation ย  ย  ย  ย  ย  ย  ย  ย  ย  | ย  ย  ย 0|multiple_choice_grade|0.4040|ยฑ ย |0.0220| |bigbench_navigate ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  | ย  ย  ย 0|multiple_choice_grade|0.4970|ยฑ ย |0.0158| |bigbench_reasoning_about_colored_objects ย  ย  ย  ย | ย  ย  ย 0|multiple_choice_grade|0.7075|ยฑ ย |0.0102| |bigbench_ruin_names ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  | ย  ย  ย 0|multiple_choice_grade|0.4821|ยฑ ย |0.0236| |bigbench_salient_translation_error_detection ย  ย | ย  ย  ย 0|multiple_choice_grade|0.2295|ยฑ ย |0.0133| |bigbench_snarks ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  | ย  ย  ย 0|multiple_choice_grade|0.6906|ยฑ ย |0.0345| |bigbench_sports_understanding ย  ย  ย  ย  ย  ย  ย  ย  ย  | ย  ย  ย 0|multiple_choice_grade|0.5375|ยฑ ย |0.0159| |bigbench_temporal_sequences ย  ย  ย  ย  ย  ย  ย  ย  ย  ย  | ย  ย  ย 0|multiple_choice_grade|0.6270|ยฑ ย |0.0153| |bigbench_tracking_shuffled_objects_five_objects | ย  ย  ย 0|multiple_choice_grade|0.2216|ยฑ ย |0.0118| |bigbench_tracking_shuffled_objects_seven_objects| ย  ย  ย 0|multiple_choice_grade|0.1594|ยฑ ย |0.0088| |bigbench_tracking_shuffled_objects_three_objects| ย  ย  ย 0|multiple_choice_grade|0.5367|ยฑ ย |0.0288| ``` Average: 44.13 **IFEval**: 72.64 **MT_Bench**: Turn 1 - 8.3875, Turn 2 - 8.00625, Average - 8.196875 # Inference Code Here is example code using HuggingFace Transformers to inference the model (note: in 4bit, it will require around 5GB of VRAM) Note: To use function calling, you should see the github repo above. ```python # Code to inference Hermes with HF Transformers # Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages import torch from transformers import AutoTokenizer, AutoModelForCausalLM, LlamaForCausalLM import bitsandbytes, flash_attn tokenizer = AutoTokenizer.from_pretrained('NousResearch/Hermes-2-Theta-Llama-3-8B', trust_remote_code=True) model = LlamaForCausalLM.from_pretrained( "NousResearch/Hermes-2-Theta-Llama-3-8B", torch_dtype=torch.float16, device_map="auto", load_in_8bit=False, load_in_4bit=True, use_flash_attention_2=True ) prompts = [ """<|im_start|>system You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|> <|im_start|>user Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|> <|im_start|>assistant""", ] for chat in prompts: print(chat) input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda") generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id) response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True) print(f"Response: {response}") ``` ## Inference Code for Function Calling: All code for utilizing, parsing, and building function calling templates is available on our github: [https://github.com/NousResearch/Hermes-Function-Calling](https://github.com/NousResearch/Hermes-Function-Calling) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/oi4CiGh50xmoviUQnh8R3.png) # Chat Interfaces When quantized versions of the model are released, I recommend using LM Studio for chatting with Hermes 2 Pro. It does not support function calling - for that use our github repo. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box. In LM-Studio, simply select the ChatML Prefix on the settings side pane: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/ls6WqV-GSxMw2RA3GuQiN.png) ## Quantized Versions: GGUF Versions Available Here: https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B-GGUF # How to cite: ```bibtext @misc{Hermes-2-Theta-Llama-3-8B, url={[https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B][NousResearch/Hermes-2-Theta-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B))}, title={Hermes-2-Theta-Llama-3-8B}, author={"Teknium", Charles Goddard, "interstellarninja", "theemozilla", "karan4d", "huemin_art"} } ```
[ "TRANSLATION" ]
Non_BioNLP
muhtasham/finetuned-mlm_mini
muhtasham
text-classification
[ "transformers", "pytorch", "bert", "text-classification", "generated_from_trainer", "dataset:imdb", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
1,670,031,216,000
2022-12-03T01:52:06
11
0
--- datasets: - imdb license: apache-2.0 metrics: - accuracy - f1 tags: - generated_from_trainer model-index: - name: finetuned-mlm_mini results: - task: type: text-classification name: Text Classification dataset: name: imdb type: imdb config: plain_text split: train args: plain_text metrics: - type: accuracy value: 0.86176 name: Accuracy - type: f1 value: 0.925747679614988 name: F1 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # finetuned-mlm_mini This model is a fine-tuned version of [muhtasham/bert-mini-mlm-finetuned-emotion](https://huggingface.co/muhtasham/bert-mini-mlm-finetuned-emotion) on the imdb dataset. It achieves the following results on the evaluation set: - Loss: 0.6338 - Accuracy: 0.8618 - F1: 0.9257 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - num_epochs: 200 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| | 0.3398 | 2.55 | 500 | 0.2366 | 0.9032 | 0.9491 | | 0.2028 | 5.1 | 1000 | 0.2750 | 0.8956 | 0.9449 | | 0.1382 | 7.65 | 1500 | 0.2798 | 0.9034 | 0.9492 | | 0.0899 | 10.2 | 2000 | 0.4193 | 0.882 | 0.9373 | | 0.0624 | 12.76 | 2500 | 0.5203 | 0.864 | 0.9270 | | 0.0417 | 15.31 | 3000 | 0.6338 | 0.8618 | 0.9257 | ### Framework versions - Transformers 4.25.1 - Pytorch 1.12.1+cu113 - Datasets 2.7.1 - Tokenizers 0.13.2
[ "TEXT_CLASSIFICATION" ]
Non_BioNLP
dascim/greekbart
dascim
fill-mask
[ "transformers", "safetensors", "mbart", "text2text-generation", "summarization", "bart", "fill-mask", "gr", "arxiv:2304.00869", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
1,728,907,428,000
2024-10-15T07:49:37
20
0
--- language: - gr library_name: transformers license: mit pipeline_tag: fill-mask tags: - summarization - bart --- # GreekBART: The First Pretrained Greek Sequence-to-Sequence Model ## Introduction GreekBART is a Greek sequence to sequence pretrained model based on [BART](https://huggingface.co/facebook/bart-large). GreekBART is pretrained by learning to reconstruct a corrupted input sentence. A corpus of 76.9GB of Greek raw text is used to carry out the pretraining. Unlike already existing BERT-based Greek language model (GreekBERT), GreekBART is particularly well-suited for generative tasks (such as abstractive summarization), since not only its encoder but also its decoder is pretrained. In addition to base GreekBART that is pretrained from scratch on the reconstruction, we finetune it as wll on three tasks: `greekbart-news24-abstract` that can generate an abstract given a Greek news article, `greekbart-news24-title` that can generate an title given a Greek news article, and `greekbart-sentiment-classification` finetuned on a binary sentinement classification task. | Model | Architecture | #layers | #params | | ------------- |:-------------:| :-----:|:-----:| | [GreekBART](https://huggingface.co/dascim/greekbart) | BASE | 12 | 165M | | [GreekBART Abstract](https://huggingface.co/dascim/greekbart-news24-abstract) | BASE | 12 | 165M | | [GreekBART Title](https://huggingface.co/dascim/greekbart-news24-title) | BASE | 12 | 165M | | [GreekBART Sentiment Classification](https://huggingface.co/dascim/greekbart-sentiment-classification) | BASE | 12 | 165M | <br> paper: https://arxiv.org/pdf/2304.00869 \ github: https://github.com/iakovosevdaimon/GreekBART ## Usage ### Mask Prediction ```python from transformers import pipeline greekbart_fill_mask = pipeline("fill-mask", model="dascim/greekbart", tokenizer="dascim/greekbart") results = greekbart_fill_mask("ฮ— ฯ€ฯฯ‰ฯ„ฮตฯฮฟฯ…ฯƒฮฑ ฯ„ฮทฯ‚ ฮ•ฮปฮปฮฌฮดฮฑฯ‚ ฮตฮฏฮฝฮฑฮน ฮท <mask>") results[0] # {'score': 0.597200870513916, 'token': 7062, 'token_str': 'ฮ‘ฮธฮฎฮฝฮฑ', 'sequence': 'ฮ— ฯ€ฯฯ‰ฯ„ฮตฯฮฟฯ…ฯƒฮฑ ฯ„ฮทฯ‚ ฮ•ฮปฮปฮฌฮดฮฑฯ‚ ฮตฮฏฮฝฮฑฮน ฮท ฮ‘ฮธฮฎฮฝฮฑ'}, ``` ### Abstract Generation ```python text_sentence = 'ฮฃฯ„ฮทฮฝ ฮบฮฑฯ„ฮฌฮธฮตฯƒฮท ฮฝฮฟฯƒฮทฮปฮตฯฯ„ฯฮนฮฑฯ‚ ฯ„ฮฟฯ… ฮšฮฑฯฮฑฮผฮฑฮฝฮดฮฌฮฝฮตฮนฮฟฯ… ฮฮฟฯƒฮฟฮบฮฟฮผฮตฮฏฮฟฯ… ฮ ฮฌฯ„ฯฮฑฯ‚ ฮ ฮฑฮฝฮฑฮณฮนฯŽฯ„ฮฑฯ‚ ฮคฯƒฮตฮฝฯ„ฮฟฯฯฮฟฯ…, ฮท ฮฟฯ€ฮฟฮฏฮฑ ฮตฯฮณฮฑฮถฯŒฯ„ฮฑฮฝ ฯŒฯ„ฮฑฮฝ ฮตฮนฯƒฮฎฯ‡ฮธฮท ฯƒฯ„ฮนฯ‚ 8 ฮ‘ฯ€ฯฮนฮปฮฏฮฟฯ… 2021 ฮท ฮคฮถฯ‰ฯฯ„ฮถฮฏฮฝฮฑ, ฯ€ฯฮฟฯ‡ฯŽฯฮทฯƒฮต ฮท ฮดฮนฮฑฮดฮนฮบฮฑฯƒฮฏฮฑ ฮตฮฝฯŽฯ€ฮนฮฟฮฝ ฯ„ฮฟฯ… ฮœฮŸฮ” ฯ€ฮฟฯ… ฮดฮนฮบฮฌฮถฮตฮน ฯ„ฮท ฮกฮฟฯฮปฮฑ ฮ ฮนฯƒฯ€ฮนฯฮฏฮณฮบฮฟฯ…. ฮ— ฮฝฮฟฯƒฮทฮปฮตฯฯ„ฯฮนฮฑ ฮบฮฑฯ„ฮญฮธฮตฯƒฮต ฯ€ฯ‰ฯ‚ ฮบฮฑฯ„ฮฌ ฯ„ฮทฮฝ ฮตฮนฯƒฮฑฮณฯ‰ฮณฮฎ ฯ„ฮฟฯ… ฯ€ฮฑฮนฮดฮนฮฟฯ "ฮผฮฟฯ… ฮฑฮฝฮญฯ†ฮตฯฮฑฮฝ ฯ€ฯ‰ฯ‚ ฮตฮฏฮฝฮฑฮน ฮญฮฝฮฑ ฯ€ฮฑฮนฮดฮฌฮบฮน ฯ€ฮฟฯ… ฮญฯ‡ฮตฮน ฯ‡ฮฌฯƒฮตฮน ฯ„ฮฑ ฮฑฮดฮตฮปฯ†ฮฌฮบฮนฮฑ ฯ„ฮฟฯ… ฮบฮฑฮน ฯŒฯ„ฮน ฮตฮฏฮฝฮฑฮน ฮนฮดฮนฮฑฮฏฯ„ฮตฯฮท ฯ€ฮตฯฮฏฯ€ฯ„ฯ‰ฯƒฮท" ฮบฮฑฮน ฮตฮพฮนฯƒฯ„ฯŒฯฮทฯƒฮต ฯ„ฮฑ ฮณฮตฮณฮฟฮฝฯŒฯ„ฮฑ ฯ„ฮทฯ‚ ฮทฮผฮญฯฮฑฯ‚ ฮตฮนฯƒฮฑฮณฯ‰ฮณฮฎฯ‚ ฮบฮฑฮน ฯ„ฮทฯ‚ ฮตฯ€ฮฟฮผฮญฮฝฮทฯ‚ ฯ€ฮฟฯ… ฮท ฮฏฮดฮนฮฑ ฮตฮฏฯ‡ฮต ฮฒฮฌฯฮดฮนฮฑ ฯƒฯ„ฮทฮฝ ฯ€ฮฑฮนฮดฮนฮฑฯ„ฯฮนฮบฮฎ ฮบฮปฮนฮฝฮนฮบฮฎ.' from transformers import ( AutoTokenizer, AutoModelForSeq2SeqLM ) tokenizer = AutoTokenizer.from_pretrained("dascim/greekbart-news24-abstract") model = AutoModelForSeq2SeqLM.from_pretrained("dascim/greekbart-news24-abstract") input_ids = tokenizer.encode(text_sentence, add_special_tokens=True, return_tensors='pt') model.eval() predict = model.generate(input_ids, max_length=100)[0] tokenizer.decode(predict, skip_special_tokens=True) #'ฮ— ฮฝฮฟฯƒฮทฮปฮตฯฯ„ฯฮนฮฑ ฮบฮฑฯ„ฮญฮธฮตฯƒฮต ฯ€ฯ‰ฯ‚ ฮบฮฑฯ„ฮฌ ฯ„ฮทฮฝ ฮตฮนฯƒฮฑฮณฯ‰ฮณฮฎ ฯ„ฮฟฯ… ฯ€ฮฑฮนฮดฮนฮฟฯ "ฮผฮฟฯ… ฮฑฮฝฮญฯ†ฮตฯฮฑฮฝ ฯ€ฯ‰ฯ‚ ฮตฮฏฮฝฮฑฮน ฮญฮฝฮฑ ฯ€ฮฑฮนฮดฮฌฮบฮน ฯ€ฮฟฯ… ฮญฯ‡ฮตฮน ฯ‡ฮฌฯƒฮตฮน ฯ„ฮฑ ฮฑฮดฮตฮปฯ†ฮฌฮบฮนฮฑ ฯ„ฮฟฯ… ฮบฮฑฮน ฯŒฯ„ฮน ฮตฮฏฮฝฮฑฮน ฮนฮดฮนฮฑฮฏฯ„ฮตฯฮท ฯ€ฮตฯฮฏฯ€ฯ„ฯ‰ฯƒฮท".' ``` ### Title Generation ```python text_sentence = 'ฮฃฯ„ฮทฮฝ ฮบฮฑฯ„ฮฌฮธฮตฯƒฮท ฮฝฮฟฯƒฮทฮปฮตฯฯ„ฯฮนฮฑฯ‚ ฯ„ฮฟฯ… ฮšฮฑฯฮฑฮผฮฑฮฝฮดฮฌฮฝฮตฮนฮฟฯ… ฮฮฟฯƒฮฟฮบฮฟฮผฮตฮฏฮฟฯ… ฮ ฮฌฯ„ฯฮฑฯ‚ ฮ ฮฑฮฝฮฑฮณฮนฯŽฯ„ฮฑฯ‚ ฮคฯƒฮตฮฝฯ„ฮฟฯฯฮฟฯ…, ฮท ฮฟฯ€ฮฟฮฏฮฑ ฮตฯฮณฮฑฮถฯŒฯ„ฮฑฮฝ ฯŒฯ„ฮฑฮฝ ฮตฮนฯƒฮฎฯ‡ฮธฮท ฯƒฯ„ฮนฯ‚ 8 ฮ‘ฯ€ฯฮนฮปฮฏฮฟฯ… 2021 ฮท ฮคฮถฯ‰ฯฯ„ฮถฮฏฮฝฮฑ, ฯ€ฯฮฟฯ‡ฯŽฯฮทฯƒฮต ฮท ฮดฮนฮฑฮดฮนฮบฮฑฯƒฮฏฮฑ ฮตฮฝฯŽฯ€ฮนฮฟฮฝ ฯ„ฮฟฯ… ฮœฮŸฮ” ฯ€ฮฟฯ… ฮดฮนฮบฮฌฮถฮตฮน ฯ„ฮท ฮกฮฟฯฮปฮฑ ฮ ฮนฯƒฯ€ฮนฯฮฏฮณฮบฮฟฯ…. ฮ— ฮฝฮฟฯƒฮทฮปฮตฯฯ„ฯฮนฮฑ ฮบฮฑฯ„ฮญฮธฮตฯƒฮต ฯ€ฯ‰ฯ‚ ฮบฮฑฯ„ฮฌ ฯ„ฮทฮฝ ฮตฮนฯƒฮฑฮณฯ‰ฮณฮฎ ฯ„ฮฟฯ… ฯ€ฮฑฮนฮดฮนฮฟฯ "ฮผฮฟฯ… ฮฑฮฝฮญฯ†ฮตฯฮฑฮฝ ฯ€ฯ‰ฯ‚ ฮตฮฏฮฝฮฑฮน ฮญฮฝฮฑ ฯ€ฮฑฮนฮดฮฌฮบฮน ฯ€ฮฟฯ… ฮญฯ‡ฮตฮน ฯ‡ฮฌฯƒฮตฮน ฯ„ฮฑ ฮฑฮดฮตฮปฯ†ฮฌฮบฮนฮฑ ฯ„ฮฟฯ… ฮบฮฑฮน ฯŒฯ„ฮน ฮตฮฏฮฝฮฑฮน ฮนฮดฮนฮฑฮฏฯ„ฮตฯฮท ฯ€ฮตฯฮฏฯ€ฯ„ฯ‰ฯƒฮท" ฮบฮฑฮน ฮตฮพฮนฯƒฯ„ฯŒฯฮทฯƒฮต ฯ„ฮฑ ฮณฮตฮณฮฟฮฝฯŒฯ„ฮฑ ฯ„ฮทฯ‚ ฮทฮผฮญฯฮฑฯ‚ ฮตฮนฯƒฮฑฮณฯ‰ฮณฮฎฯ‚ ฮบฮฑฮน ฯ„ฮทฯ‚ ฮตฯ€ฮฟฮผฮญฮฝฮทฯ‚ ฯ€ฮฟฯ… ฮท ฮฏฮดฮนฮฑ ฮตฮฏฯ‡ฮต ฮฒฮฌฯฮดฮนฮฑ ฯƒฯ„ฮทฮฝ ฯ€ฮฑฮนฮดฮนฮฑฯ„ฯฮนฮบฮฎ ฮบฮปฮนฮฝฮนฮบฮฎ.' from transformers import ( AutoTokenizer, AutoModelForSeq2SeqLM ) tokenizer = AutoTokenizer.from_pretrained("dascim/greekbart-news24-title") model = AutoModelForSeq2SeqLM.from_pretrained("dascim/greekbart-news24-title") input_ids = tokenizer.encode(text_sentence, add_special_tokens=True, return_tensors='pt') model.eval() predict = model.generate(input_ids, max_length=100)[0] tokenizer.decode(predict, skip_special_tokens=True) # 'ฮ ฮฌฯ„ฯฮฑ: ฮšฮฑฯ„ฮฌฮธฮตฯƒฮท ฮฝฮฟฯƒฮทฮปฮตฯฯ„ฯฮนฮฑฯ‚ ฮณฮนฮฑ ฯ„ฮทฮฝ ฮตฮนฯƒฮฑฮณฯ‰ฮณฮฎ ฯ„ฮทฯ‚ ฮคฮถฯ‰ฯฯ„ฮถฮฏฮฝฮฑฯ‚ ฯƒฯ„ฮฟ ฮฝฮฟฯƒฮฟฮบฮฟฮผฮตฮฏฮฟ' ``` ### Sentiment Prediction ```python text_sentence = "ฮŸ ฮตฮปฮปฮทฮฝฮนฮบฯŒฯ‚ ฯ€ฮฟฮปฮนฯ„ฮนฯƒฮผฯŒฯ‚ ฮตฮฏฮฝฮฑฮน ฮญฮฝฮฑฯ‚ ฮฑฯ€ฯŒ ฯ„ฮฟฯ…ฯ‚ ฯ€ฮนฮฟ ฯ€ฮปฮฟฯฯƒฮนฮฟฯ…ฯ‚ ฮบฮฑฮน ฮฑฮฝฮฑฮณฮฝฯ‰ฯฮนฯƒฮผฮญฮฝฮฟฯ…ฯ‚ ฯ€ฮฟฮปฮนฯ„ฮนฯƒฮผฮฟฯฯ‚." from transformers import ( AutoTokenizer, AutoModelForSequenceClassification ) tokenizer = AutoTokenizer.from_pretrained("dascim/greekbart-sentiment-classification") model = AutoModelForSequenceClassification.from_pretrained("dascim/greekbart-sentiment-classification") input_ids = tokenizer.encode(text_sentence, add_special_tokens=True, return_tensors='pt') model.eval() predict = model(input_ids)[0] print("negative" if predict.argmax(dim=-1).item()==1 else "positive") # positive ``` ## Authors GreekBART was trained and evaluated ar ร‰cole Polytechnique by Iakovos Evdaimon, Hadi Abdine, Christos Xypolopoulos, Stamatis Outsios, Michalis Vazirgiannis and Giorgos Stamou. ## Citation If you use our work, please cite: ```bibtex @inproceedings{evdaimon-etal-2024-greekbart, title = "{G}reek{BART}: The First Pretrained {G}reek Sequence-to-Sequence Model", author = "Evdaimon, Iakovos and Abdine, Hadi and Xypolopoulos, Christos and Outsios, Stamatis and Vazirgiannis, Michalis and Stamou, Giorgos", editor = "Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen", booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)", month = may, year = "2024", address = "Torino, Italia", publisher = "ELRA and ICCL", url = "https://aclanthology.org/2024.lrec-main.700", pages = "7949--7962", } ```
[ "SUMMARIZATION" ]
Non_BioNLP
Volavion/bert-base-multilingual-uncased-temperature-cls
Volavion
null
[ "safetensors", "bert", "en", "base_model:google-bert/bert-base-multilingual-uncased", "base_model:finetune:google-bert/bert-base-multilingual-uncased", "license:mit", "region:us" ]
1,736,936,870,000
2025-01-15T11:01:31
18
1
--- base_model: - google-bert/bert-base-multilingual-uncased language: - en license: mit --- # BERT-Based Classification Model for Optimal Temperature Selection This model leverages a BERT-based classification model to analyze input prompts and identify the most suitable generation temperature, enhancing text generation quality and relevance from our paper related to temperature. ## Overview The model classifies input text into six distinct abilities, providing a probability distribution for each: - **Causal Reasoning** - **Creativity** - **In-Context Learning** - **Instruction Following** - **Machine Translation** - **Summarization** ## Features - **Pre-trained Model**: Uses the multilingual BERT model: `Volavion/bert-base-multilingual-uncased-Temperature-CLS`. - **Tokenization**: Processes text inputs into numerical formats compatible with the model. - **Classification Output**: Provides probabilities for each class, allowing precise evaluation of the prompt's capabilities. ## Installation 1. Clone the repository if necessary: ```bash git clone https://huggingface.co/Volavion/bert-base-multilingual-uncased-temperature-cls cd bert-base-multilingual-uncased-temperature-cls ``` 2. Install the required Python libraries: ```bash pip install transformers torch numpy ``` ## Usage 1. Load the tokenizer and model: ```python from transformers import AutoTokenizer, AutoModelForSequenceClassification model_name = "Volavion/bert-base-multilingual-uncased-Temperature-CLS" tokenizer = AutoTokenizer.from_pretrained(model_name, do_lower_case=True) model = AutoModelForSequenceClassification.from_pretrained(model_name) ``` 2. Tokenize your input text: ```python input_text = "Your input prompt here." encoded_dict = tokenizer.encode_plus( input_text, add_special_tokens=True, max_length=512, pad_to_max_length=True, return_attention_mask=True, return_tensors="pt" ) ``` 3. Perform inference: ```python import torch import numpy as np input_ids = encoded_dict["input_ids"].to(device) attention_mask = encoded_dict["attention_mask"].to(device) model.eval() with torch.no_grad(): outputs = model(input_ids, attention_mask=attention_mask) logits = outputs.logits.cpu().numpy() probabilities = np.exp(logits - np.max(logits, axis=1, keepdims=True)) probabilities /= np.sum(probabilities, axis=1, keepdims=True) ``` 4. Map probabilities to abilities: ```python ability_mapping = {0: "Causal Reasoning", 1: "Creativity", 2: "In-Context Learning", 3: "Instruction Following", 4: "Machine Translation", 5: "Summarization"} for prob, ability in zip(probabilities[0], ability_mapping.values()): print(f"{ability}: {prob*100:.2f}%") ``` ## Example Output ```plaintext Ability Classification Probabilities: Causal Reasoning: 15.30% Creativity: 20.45% In-Context Learning: 18.22% Instruction Following: 12.78% Machine Translation: 21.09% Summarization: 12.16% ``` ## Device Compatibility The model supports GPU acceleration for faster inference. It will automatically detect and utilize a GPU if available; otherwise, it defaults to CPU. ## Contributing Contributions are welcome! Feel free to fork the repository, create a branch, and submit a pull request. ## License This project is licensed under the [MIT License](LICENSE).
[ "TRANSLATION", "SUMMARIZATION" ]
Non_BioNLP
r4ghu/distilbert-base-uncased-finetuned-clinc
r4ghu
text-classification
[ "transformers", "pytorch", "distilbert", "text-classification", "generated_from_trainer", "dataset:clinc_oos", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
1,694,497,357,000
2023-09-13T01:19:35
12
0
--- base_model: distilbert-base-uncased datasets: - clinc_oos license: apache-2.0 metrics: - accuracy tags: - generated_from_trainer model-index: - name: distilbert-base-uncased-finetuned-clinc results: - task: type: text-classification name: Text Classification dataset: name: clinc_oos type: clinc_oos config: plus split: validation args: plus metrics: - type: accuracy value: 0.9196774193548387 name: Accuracy --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-finetuned-clinc This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset. It achieves the following results on the evaluation set: - Loss: 0.7651 - Accuracy: 0.9197 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 48 - eval_batch_size: 48 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 4.2939 | 1.0 | 318 | 3.2756 | 0.7310 | | 2.6165 | 2.0 | 636 | 1.8607 | 0.8365 | | 1.5359 | 3.0 | 954 | 1.1427 | 0.8965 | | 1.0074 | 4.0 | 1272 | 0.8470 | 0.9132 | | 0.7906 | 5.0 | 1590 | 0.7651 | 0.9197 | ### Framework versions - Transformers 4.33.1 - Pytorch 2.0.1 - Datasets 2.12.0 - Tokenizers 0.13.2
[ "TEXT_CLASSIFICATION" ]
Non_BioNLP
RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf
RichardErkhov
null
[ "gguf", "endpoints_compatible", "region:us" ]
1,722,618,843,000
2024-08-03T00:32:52
25
0
--- {} --- Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Giraffe-13b-32k-v3 - GGUF - Model creator: https://huggingface.co/abacusai/ - Original model: https://huggingface.co/abacusai/Giraffe-13b-32k-v3/ | Name | Quant method | Size | | ---- | ---- | ---- | | [Giraffe-13b-32k-v3.Q2_K.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.Q2_K.gguf) | Q2_K | 4.52GB | | [Giraffe-13b-32k-v3.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.IQ3_XS.gguf) | IQ3_XS | 4.99GB | | [Giraffe-13b-32k-v3.IQ3_S.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.IQ3_S.gguf) | IQ3_S | 5.27GB | | [Giraffe-13b-32k-v3.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.Q3_K_S.gguf) | Q3_K_S | 5.27GB | | [Giraffe-13b-32k-v3.IQ3_M.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.IQ3_M.gguf) | IQ3_M | 5.57GB | | [Giraffe-13b-32k-v3.Q3_K.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.Q3_K.gguf) | Q3_K | 5.9GB | | [Giraffe-13b-32k-v3.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.Q3_K_M.gguf) | Q3_K_M | 5.9GB | | [Giraffe-13b-32k-v3.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.Q3_K_L.gguf) | Q3_K_L | 6.45GB | | [Giraffe-13b-32k-v3.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.IQ4_XS.gguf) | IQ4_XS | 6.54GB | | [Giraffe-13b-32k-v3.Q4_0.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.Q4_0.gguf) | Q4_0 | 6.86GB | | [Giraffe-13b-32k-v3.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.IQ4_NL.gguf) | IQ4_NL | 6.9GB | | [Giraffe-13b-32k-v3.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.Q4_K_S.gguf) | Q4_K_S | 6.91GB | | [Giraffe-13b-32k-v3.Q4_K.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.Q4_K.gguf) | Q4_K | 7.33GB | | [Giraffe-13b-32k-v3.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.Q4_K_M.gguf) | Q4_K_M | 7.33GB | | [Giraffe-13b-32k-v3.Q4_1.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.Q4_1.gguf) | Q4_1 | 7.61GB | | [Giraffe-13b-32k-v3.Q5_0.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.Q5_0.gguf) | Q5_0 | 8.36GB | | [Giraffe-13b-32k-v3.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.Q5_K_S.gguf) | Q5_K_S | 8.36GB | | [Giraffe-13b-32k-v3.Q5_K.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.Q5_K.gguf) | Q5_K | 8.6GB | | [Giraffe-13b-32k-v3.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.Q5_K_M.gguf) | Q5_K_M | 8.6GB | | [Giraffe-13b-32k-v3.Q5_1.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.Q5_1.gguf) | Q5_1 | 9.1GB | | [Giraffe-13b-32k-v3.Q6_K.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.Q6_K.gguf) | Q6_K | 9.95GB | | [Giraffe-13b-32k-v3.Q8_0.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-13b-32k-v3-gguf/blob/main/Giraffe-13b-32k-v3.Q8_0.gguf) | Q8_0 | 12.88GB | Original model description: --- datasets: - togethercomputer/RedPajama-Data-1T - shahules786/orca-chat - anon8231489123/ShareGPT_Vicuna_unfiltered tags: - llama2 license: llama2 --- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c14f6b02e1f8f67c73bd05/lFg2fOnPhcKFfJGnIvcTd.png) # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> Llama2 13B finetuned to process longer (32K) contexts using interpolation and then further instruct finetuned with ShareGPT and Orca-Chat. ## Model Details ### Model Description This is next version of the model trained and evaluated as part of the experiments described in the repo [http://github.com/abacusai/Long-Context](https://github.com/abacusai/Long-Context). This version was trained with a scaling factor of 8 and shows better reasoning and math abilites on State of the Art benchmarks - **Developed by:** [Abacus.AI](https://abacus.ai) - **Model type:** Transformer based autoregressive causal language model - **License:** Llama 2 Community License: https://github.com/facebookresearch/llama/blob/main/LICENSE - **Finetuned from model:** Llama V2 13B ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [http://github.com/abacusai/Long-Context](https://github.com/abacusai/Long-Context) ### Direct Use Since the model is instruct finetuned it can also be directly used for various prompted tasks. We have tested it on open book question answering using the long context to supply search results. ## Bias, Risks, and Limitations The model has not been evaluated for safety and is only intended for research and experiments.
[ "QUESTION_ANSWERING" ]
Non_BioNLP
gokuls/mobilebert_sa_GLUE_Experiment_data_aug_wnli_128
gokuls
text-classification
[ "transformers", "pytorch", "tensorboard", "mobilebert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
1,675,440,718,000
2023-02-03T16:40:16
129
0
--- datasets: - glue language: - en license: apache-2.0 metrics: - accuracy tags: - generated_from_trainer model-index: - name: mobilebert_sa_GLUE_Experiment_data_aug_wnli_128 results: - task: type: text-classification name: Text Classification dataset: name: GLUE WNLI type: glue args: wnli metrics: - type: accuracy value: 0.14084507042253522 name: Accuracy --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # mobilebert_sa_GLUE_Experiment_data_aug_wnli_128 This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the GLUE WNLI dataset. It achieves the following results on the evaluation set: - Loss: 1.9522 - Accuracy: 0.1408 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 128 - eval_batch_size: 128 - seed: 10 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.6679 | 1.0 | 435 | 1.9522 | 0.1408 | | 0.4943 | 2.0 | 870 | 3.6522 | 0.1127 | | 0.4405 | 3.0 | 1305 | 4.5118 | 0.1268 | | 0.4086 | 4.0 | 1740 | 6.0437 | 0.1127 | | 0.3818 | 5.0 | 2175 | 9.5931 | 0.1127 | | 0.3492 | 6.0 | 2610 | 6.9665 | 0.1408 | ### Framework versions - Transformers 4.26.0 - Pytorch 1.14.0a0+410ce96 - Datasets 2.9.0 - Tokenizers 0.13.2
[ "TEXT_CLASSIFICATION" ]
Non_BioNLP
RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf
RichardErkhov
null
[ "gguf", "arxiv:2402.17733", "endpoints_compatible", "region:us" ]
1,715,422,053,000
2024-05-11T23:15:22
102
0
--- {} --- Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) TowerBase-7B-v0.1 - GGUF - Model creator: https://huggingface.co/Unbabel/ - Original model: https://huggingface.co/Unbabel/TowerBase-7B-v0.1/ | Name | Quant method | Size | | ---- | ---- | ---- | | [TowerBase-7B-v0.1.Q2_K.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.Q2_K.gguf) | Q2_K | 2.36GB | | [TowerBase-7B-v0.1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.IQ3_XS.gguf) | IQ3_XS | 2.6GB | | [TowerBase-7B-v0.1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.IQ3_S.gguf) | IQ3_S | 2.75GB | | [TowerBase-7B-v0.1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.Q3_K_S.gguf) | Q3_K_S | 2.75GB | | [TowerBase-7B-v0.1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.IQ3_M.gguf) | IQ3_M | 2.9GB | | [TowerBase-7B-v0.1.Q3_K.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.Q3_K.gguf) | Q3_K | 3.07GB | | [TowerBase-7B-v0.1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.Q3_K_M.gguf) | Q3_K_M | 3.07GB | | [TowerBase-7B-v0.1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.Q3_K_L.gguf) | Q3_K_L | 3.35GB | | [TowerBase-7B-v0.1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.IQ4_XS.gguf) | IQ4_XS | 3.4GB | | [TowerBase-7B-v0.1.Q4_0.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.Q4_0.gguf) | Q4_0 | 3.56GB | | [TowerBase-7B-v0.1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.IQ4_NL.gguf) | IQ4_NL | 3.58GB | | [TowerBase-7B-v0.1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.Q4_K_S.gguf) | Q4_K_S | 3.59GB | | [TowerBase-7B-v0.1.Q4_K.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.Q4_K.gguf) | Q4_K | 3.8GB | | [TowerBase-7B-v0.1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.Q4_K_M.gguf) | Q4_K_M | 3.8GB | | [TowerBase-7B-v0.1.Q4_1.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.Q4_1.gguf) | Q4_1 | 3.95GB | | [TowerBase-7B-v0.1.Q5_0.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.Q5_0.gguf) | Q5_0 | 4.33GB | | [TowerBase-7B-v0.1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.Q5_K_S.gguf) | Q5_K_S | 4.33GB | | [TowerBase-7B-v0.1.Q5_K.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.Q5_K.gguf) | Q5_K | 4.45GB | | [TowerBase-7B-v0.1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.Q5_K_M.gguf) | Q5_K_M | 4.45GB | | [TowerBase-7B-v0.1.Q5_1.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.Q5_1.gguf) | Q5_1 | 4.72GB | | [TowerBase-7B-v0.1.Q6_K.gguf](https://huggingface.co/RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf/blob/main/TowerBase-7B-v0.1.Q6_K.gguf) | Q6_K | 5.15GB | Original model description: --- license: cc-by-nc-4.0 language: - en - de - fr - zh - pt - nl - ru - ko - it - es metrics: - comet pipeline_tag: translation model-index: - name: TowerBase-7B-v0.1 results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 51.02 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Unbabel/TowerBase-7B-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 77.68 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Unbabel/TowerBase-7B-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 43.48 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Unbabel/TowerBase-7B-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 37.29 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Unbabel/TowerBase-7B-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 72.06 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Unbabel/TowerBase-7B-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 13.12 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Unbabel/TowerBase-7B-v0.1 name: Open LLM Leaderboard --- # Model Card for TowerBase-7B-v0.1 ## Model Details ### Model Description TowerBase-7B is a language model that results from continuing the pretraining of Llama 2 on a mix of 20 billion tokens of monolingual data in ten different languages โ€” English, Portuguese, Spanish, French, German, Dutch, Italian, Korean, Chinese, Russian โ€” and bilingual data. TowerBase-7B-v0.1 is the first model in the series. The resulting model shows improved performance on the supported languages, while maintaining Llama 2's capabilities on English. It is particularly well-suited for fine-tuning on translation and related tasks: check out [TowerInstruct](https://huggingface.co/Unbabel/TowerInstruct-7B-v0.1). We will release more details in the upcoming technical report. - **Developed by:** Unbabel, Instituto Superior Tรฉcnico, CentraleSupรฉlec University of Paris-Saclay - **Model type:** A 7B parameter model built on top of Llama 2 by continuing pretraining on multilingual data. - **Language(s) (NLP):** English, Portuguese, Spanish, French, German, Dutch, Italian, Korean, Chinese, Russian - **License:** CC-BY-NC-4.0, Llama 2 is licensed under the LLAMA 2 Community License, Copyright ยฉ Meta Platforms, Inc. All Rights Reserved. ## Intended uses & limitations The model is intended for research purposes in the 10 languages it supports. The model is able to perform well on translation and related tasks (e.g., APE, GEC) on a few-shot regime. It can also be fine-tuned to perform these tasks in a zero-shot fashion (see [TowerInstruct](https://huggingface.co/Unbabel/TowerInstruct-7B-v0.1), as well as other multilingual tasks. ### Out-of-Scope Use The model is not guaranteed to perform well for languages other than the 10 languages it supports. ## Bias, Risks, and Limitations TowerBase-v0.1 has not been aligned to human preferences, so the model may generate problematic outputs (e.g., hallucinations, harmful content, or false statements). ## Run the model ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "Unbabel/TowerBase-7B-v0.1" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained(model_id) text = "English: My name is TowerBase.\nPortuguese:" inputs = tokenizer(text, return_tensors="pt") outputs = model.generate(**inputs, max_new_tokens=20) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` ### Training Data Filtered versions of [mc4](https://huggingface.co/datasets/mc4) and bilingual data from various sources (e.g., [OPUS](https://opus.nlpl.eu/)). ## Citation ```bibtex @misc{tower_llm_2024, title={Tower: An Open Multilingual Large Language Model for Translation-Related Tasks}, author={Duarte M. Alves and Josรฉ Pombal and Nuno M. Guerreiro and Pedro H. Martins and Joรฃo Alves and Amin Farajian and Ben Peters and Ricardo Rei and Patrick Fernandes and Sweta Agrawal and Pierre Colombo and Josรฉ G. C. de Souza and Andrรฉ F. T. Martins}, year={2024}, eprint={2402.17733}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```
[ "TRANSLATION" ]
Non_BioNLP
naksu/distilbert-base-uncased-finetuned-sst2
naksu
text-classification
[ "transformers", "pytorch", "tensorboard", "distilbert", "text-classification", "generated_from_trainer", "dataset:glue", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
1,674,455,631,000
2023-01-23T18:15:34
114
0
--- datasets: - glue license: apache-2.0 metrics: - accuracy tags: - generated_from_trainer model-index: - name: distilbert-base-uncased-finetuned-sst2 results: - task: type: text-classification name: Text Classification dataset: name: glue type: glue config: sst2 split: train args: sst2 metrics: - type: accuracy value: 0.8623529411764705 name: Accuracy --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-finetuned-sst2 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset. It achieves the following results on the evaluation set: - Loss: 0.4654 - Accuracy: 0.8624 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 30 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 27 | 0.4003 | 0.8224 | | No log | 2.0 | 54 | 0.3516 | 0.8459 | | No log | 3.0 | 81 | 0.4151 | 0.8376 | | No log | 4.0 | 108 | 0.4419 | 0.8635 | | No log | 5.0 | 135 | 0.4654 | 0.8624 | ### Framework versions - Transformers 4.25.1 - Pytorch 1.13.1+cu116 - Datasets 2.8.0 - Tokenizers 0.13.2
[ "TEXT_CLASSIFICATION" ]
Non_BioNLP
fine-tuned/NFCorpus-256-24-gpt-4o-2024-05-13-166315
fine-tuned
feature-extraction
[ "sentence-transformers", "safetensors", "bert", "feature-extraction", "sentence-similarity", "mteb", "en", "dataset:fine-tuned/NFCorpus-256-24-gpt-4o-2024-05-13-166315", "dataset:allenai/c4", "license:apache-2.0", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]
1,716,565,023,000
2024-05-24T15:37:35
9
0
--- datasets: - fine-tuned/NFCorpus-256-24-gpt-4o-2024-05-13-166315 - allenai/c4 language: - en license: apache-2.0 pipeline_tag: feature-extraction tags: - sentence-transformers - feature-extraction - sentence-similarity - mteb --- This model is a fine-tuned version of [**BAAI/bge-large-en-v1.5**](https://huggingface.co/BAAI/bge-large-en-v1.5) designed for the following use case: custom ## How to Use This model can be easily integrated into your NLP pipeline for tasks such as text classification, sentiment analysis, entity recognition, and more. Here's a simple example to get you started: ```python from sentence_transformers import SentenceTransformer from sentence_transformers.util import cos_sim model = SentenceTransformer( 'fine-tuned/NFCorpus-256-24-gpt-4o-2024-05-13-166315', trust_remote_code=True ) embeddings = model.encode([ 'first text to embed', 'second text to embed' ]) print(cos_sim(embeddings[0], embeddings[1])) ```
[ "TEXT_CLASSIFICATION" ]
Non_BioNLP
KarelDO/lstm.CEBaB_confounding.observational.absa.5-class.seed_43
KarelDO
text-classification
[ "transformers", "pytorch", "bert", "text-classification", "generated_from_trainer", "en", "dataset:OpenTable", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
1,665,721,864,000
2022-10-14T04:32:12
20
0
--- datasets: - OpenTable language: - en metrics: - accuracy tags: - generated_from_trainer model-index: - name: lstm.CEBaB_confounding.observational.absa.5-class.seed_43 results: - task: type: text-classification name: Text Classification dataset: name: OpenTable OPENTABLE-ABSA type: OpenTable args: opentable-absa metrics: - type: accuracy value: 0.6611587107303142 name: Accuracy --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # lstm.CEBaB_confounding.observational.absa.5-class.seed_43 This model is a fine-tuned version of [lstm](https://huggingface.co/lstm) on the OpenTable OPENTABLE-ABSA dataset. It achieves the following results on the evaluation set: - Loss: 0.8687 - Accuracy: 0.6612 - Macro-f1: 0.6553 - Weighted-macro-f1: 0.6627 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.001 - train_batch_size: 32 - eval_batch_size: 32 - seed: 43 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5.0 ### Training results ### Framework versions - Transformers 4.18.0 - Pytorch 1.10.2+cu102 - Datasets 2.5.2 - Tokenizers 0.12.1
[ "TEXT_CLASSIFICATION" ]
Non_BioNLP
mini1013/master_cate_top_bt5_4
mini1013
text-classification
[ "setfit", "safetensors", "roberta", "sentence-transformers", "text-classification", "generated_from_setfit_trainer", "arxiv:2209.11055", "base_model:klue/roberta-base", "base_model:finetune:klue/roberta-base", "model-index", "region:us" ]
1,735,482,532,000
2024-12-29T14:29:14
8
0
--- base_model: klue/roberta-base library_name: setfit metrics: - accuracy pipeline_tag: text-classification tags: - setfit - sentence-transformers - text-classification - generated_from_setfit_trainer widget: - text: '[์‹œ์„ธ์ด๋„] NEW ์‹ฑํฌ๋กœ ์Šคํ‚จ ๋ž˜๋””์–ธํŠธ ๋ฆฌํ”„ํŒ… ํŒŒ์šด๋ฐ์ด์…˜ SPF30/PA++++ 30ml 130 ์˜คํŒ” (#M)ํ™ˆ>๋ฉ”์ดํฌ์—…>๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—… HMALL > ๋ทฐํ‹ฐ > ๋ฉ”์ดํฌ์—… > ๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—…' - text: ์–ด๋ฎค์ฆˆ ๋ฉ”ํƒ€ ํ”ฝ์‹ฑ ๋น„๊ฑด ์ฟ ์…˜ ๋ฆฌํ•„ (3์ข… ํƒ 1) 02 ๋ˆ„๋“œ (#M)ํ™ˆ>ํ™”์žฅํ’ˆ/๋ฏธ์šฉ>๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—…>ํŒŒ์šด๋ฐ์ด์…˜>์ฟ ์…˜ํ˜• Naverstore > ํ™”์žฅํ’ˆ/๋ฏธ์šฉ > ๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—… > ํŒŒ์šด๋ฐ์ด์…˜ > ์ฟ ์…˜ํ˜• - text: ์—์Šค์˜์•„ ํ”„๋กœ ํ…Œ์ผ๋Ÿฌ ํŒŒ์šด๋ฐ์ด์…˜ ๋น„ ๊ธ€๋กœ์šฐ 30ml MinSellAmount (#M)ํ™”์žฅํ’ˆ/ํ–ฅ์ˆ˜>๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—…>ํŒŒ์šด๋ฐ์ด์…˜ Gmarket > ๋ทฐํ‹ฐ > ํ™”์žฅํ’ˆ/ํ–ฅ์ˆ˜ > ๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—… > ํŒŒ์šด๋ฐ์ด์…˜ - text: (ํ˜„๋Œ€๋ฐฑํ™”์ ) ํ†ฐ ํฌ๋“œ ๋ทฐํ‹ฐ ์…ฐ์ด๋“œ ์•ค ์ผ๋ฃจ๋ฏธ๋„ค์ดํŠธ ์†Œํ”„ํŠธ ๋ž˜๋””์–ธ์Šค ํŒŒ์šด๋ฐ์ด์…˜ SPF50/PA++++ 0.4 ๋กœ์ฆˆ (#M)ํ™”์žฅํ’ˆ/ํ–ฅ์ˆ˜>๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—…>ํŒŒ์šด๋ฐ์ด์…˜ Gmarket > ๋ทฐํ‹ฐ > ํ™”์žฅํ’ˆ/ํ–ฅ์ˆ˜ > ๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—… > ํŒŒ์šด๋ฐ์ด์…˜ - text: '[์ •์ƒ˜๋ฌผ] ๋งˆ์Šคํ„ฐํด๋ž˜์Šค ๋ž˜๋””์–ธํŠธ ์ฟ ์…˜(๋ฆฌํ•„ํฌํ•จ)(+์ฝ”๋ ‰ํŒ… ๋ฒ ์ด์Šค5mlx3๊ฐœ)(๊ฐ•๋‚จ์ ) N1์•„์ด๋ณด๋ฆฌ (#M)11st>๋ฉ”์ดํฌ์—…>ํŽ˜์ด์Šค๋ฉ”์ดํฌ์—…>ํŒŒ์šด๋ฐ์ด์…˜ 11st > ๋ทฐํ‹ฐ > ๋ฉ”์ดํฌ์—… > ํŽ˜์ด์Šค๋ฉ”์ดํฌ์—… > ํŒŒ์šด๋ฐ์ด์…˜' inference: true model-index: - name: SetFit with klue/roberta-base results: - task: type: text-classification name: Text Classification dataset: name: Unknown type: unknown split: test metrics: - type: accuracy value: 0.9475307038057129 name: Accuracy --- # SetFit with klue/roberta-base This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [klue/roberta-base](https://huggingface.co/klue/roberta-base) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification. The model has been trained using an efficient few-shot learning technique that involves: 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning. 2. Training a classification head with features from the fine-tuned Sentence Transformer. ## Model Details ### Model Description - **Model Type:** SetFit - **Sentence Transformer body:** [klue/roberta-base](https://huggingface.co/klue/roberta-base) - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance - **Maximum Sequence Length:** 512 tokens - **Number of Classes:** 5 classes <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown --> ### Model Sources - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit) - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055) - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit) ### Model Labels | Label | Examples | |:------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | 2 | <ul><li>'์—์Šค์˜์•„ ํ”„๋กœํ…Œ์ผ๋Ÿฌ ๋น„๊ธ€๋กœ์šฐ ์Šคํ‹ฑ ํŒŒ์šด๋ฐ์ด์…˜ 13g 23ํ˜ธ๋ฒ ์ด์ง€ (#M)ํ™ˆ>ํ™”์žฅํ’ˆ/๋ฏธ์šฉ>๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—…>ํŒŒ์šด๋ฐ์ด์…˜>์Šคํ‹ฑํ˜• Naverstore > ํ™”์žฅํ’ˆ/๋ฏธ์šฉ > ๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—… > ํŒŒ์šด๋ฐ์ด์…˜ > ์Šคํ‹ฑํ˜•'</li><li>'๊ทธ๋ผํŽœ ์—์–ด์ปค๋ฒ„ ์Šคํ‹ฑ ํŒŒ์šด๋ฐ์ด์…˜ 23ํ˜ธ ๋ฒ ์ด์ง€ LotteOn > ๋ทฐํ‹ฐ > ๋ฉ”์ดํฌ์—… > ๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—… > ํŒŒ์šด๋ฐ์ด์…˜ LotteOn > ๋ทฐํ‹ฐ > ๋ฉ”์ดํฌ์—… > ๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—… > ํŒŒ์šด๋ฐ์ด์…˜'</li><li>'๋ฐ”๋น„ ๋ธŒ๋ผ์šด ์Šคํ‚จ ํŒŒ์šด๋ฐ์ด์…˜ ์Šคํ‹ฑ-2.5 ์› ์ƒŒ๋“œ 9g (#M)ํ™”์žฅํ’ˆ/๋ฏธ์šฉ>๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—…>ํŒŒ์šด๋ฐ์ด์…˜>ํฌ๋ฆผํ˜• Naverstore > ํ™”์žฅํ’ˆ/๋ฏธ์šฉ > ๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—… > ํŒŒ์šด๋ฐ์ด์…˜ > ํฌ๋ฆผํ˜•'</li></ul> | | 1 | <ul><li>'์ •์ƒ˜๋ฌผ ์Šคํ‚จ ์„ธํŒ… ํ†ค ์ฝ”๋ ‰ํŒ… ๋ฒ ์ด์Šค 40ml ๊ธ€๋กœ์ž‰ ๋ฒ ์ด์Šค (#M)11st>๋ฉ”์ดํฌ์—…>ํŽ˜์ด์Šค๋ฉ”์ดํฌ์—…>๋ฉ”์ดํฌ์—…๋ฒ ์ด์Šค 11st > ๋ทฐํ‹ฐ > ๋ฉ”์ดํฌ์—… > ํŽ˜์ด์Šค๋ฉ”์ดํฌ์—… > ๋ฉ”์ดํฌ์—…๋ฒ ์ด์Šค'</li><li>'์•„์ด์˜คํŽ˜ ํผํŽ™ํŠธ ์ปค๋ฒ„ ๋ฉ”์ดํฌ์—…๋ฒ ์ด์Šค 35ml 2ํ˜ธ ๋ผ์ดํŠธํผํ”Œ ร— 3๊ฐœ (#M)์ฟ ํŒก ํ™ˆ>๋ทฐํ‹ฐ>๋ฉ”์ดํฌ์—…>๋ฒ ์ด์Šค ๋ฉ”์ดํฌ์—…>๋ฒ ์ด์Šค/ํ”„๋ผ์ด๋จธ Coupang > ๋ทฐํ‹ฐ > ๋ฉ”์ดํฌ์—… > ๋ฒ ์ด์Šค ๋ฉ”์ดํฌ์—… > ๋ฒ ์ด์Šค/ํ”„๋ผ์ด๋จธ'</li><li>'์•„์ด์˜คํŽ˜ ํผํŽ™ํŠธ ์ปค๋ฒ„ ๋ฒ ์ด์Šค 35ml 2ํ˜ธ-ํผํ”Œ (#M)ํ™ˆ>ํ™”์žฅํ’ˆ/๋ฏธ์šฉ>๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—…>๋ฉ”์ดํฌ์—…๋ฒ ์ด์Šค Naverstore > ํ™”์žฅํ’ˆ/๋ฏธ์šฉ > ๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—… > ๋ฉ”์ดํฌ์—…๋ฒ ์ด์Šค'</li></ul> | | 0 | <ul><li>'ํ—ค๋ผ ๊ธ€๋กœ์šฐ ๋ž˜์ŠคํŒ… ํŒŒ์šด๋ฐ์ด์…˜ 17C1 ํŽ˜ํƒˆ ์•„์ด๋ณด๋ฆฌ LotteOn > ๋ทฐํ‹ฐ > ๋ฉ”์ดํฌ์—… > ๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—… > ๋ฒ ์ด์Šค/ํ”„๋ผ์ด๋จธ LotteOn > ๋ทฐํ‹ฐ > ๋ฉ”์ดํฌ์—… > ๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—… > ๋ฒ ์ด์Šค/ํ”„๋ผ์ด๋จธ'</li><li>'[์—์Šคํ‹ฐ ๋กœ๋”] ๋”๋ธ”์›จ์–ด ํŒŒ์šด๋ฐ์ด์…˜ 30ml SPF 10/PA++ (+ํ”„๋ผ์ด๋จธ ์ •ํ’ˆ ) 1W0 ์›œ ํฌ์Šฌ๋ฆฐ ํ™ˆ>๊ธฐํš ์„ธํŠธ;ํ™ˆ>๋”๋ธ”์›จ์–ด;ํ™ˆ>๋”๋ธ” ์›จ์–ด;ํ™”์žฅํ’ˆ/๋ฏธ์šฉ>๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—…>ํŒŒ์šด๋ฐ์ด์…˜>๋ฆฌํ€ด๋“œํ˜•;(#M)ํ™ˆ>์ „์ฒด์ƒํ’ˆ Naverstore > ๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—… > ํŒŒ์šด๋ฐ์ด์…˜'</li><li>'์—์Šค์˜์•„ ํ”„๋กœํ…Œ์ผ๋Ÿฌ ํŒŒ์šด๋ฐ์ด์…˜ ๋น„ ๊ธ€๋กœ์šฐ 10ml 4ํ˜ธ ๋ฒ ์ด์ง€ ร— 1๊ฐœ (#M)์ฟ ํŒก ํ™ˆ>๋ทฐํ‹ฐ>๋ฉ”์ดํฌ์—…>๋ฒ ์ด์Šค ๋ฉ”์ดํฌ์—…>ํŒŒ์šด๋ฐ์ด์…˜ Coupang > ๋ทฐํ‹ฐ > ๋กœ๋“œ์ƒต > ๋ฉ”์ดํฌ์—… > ๋ฒ ์ด์Šค ๋ฉ”์ดํฌ์—… > ํŒŒ์šด๋ฐ์ด์…˜'</li></ul> | | 4 | <ul><li>'์‹œ์„ธ์ด๋„ ์Šคํฌ์ธ  ์ปค๋ฒ„ ํŒŒ์šด๋ฐ์ด์…˜ 20g S101 (#M)ํ™ˆ>ํ™”์žฅํ’ˆ/๋ฏธ์šฉ>๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—…>ํŒŒ์šด๋ฐ์ด์…˜>ํฌ๋ฆผํ˜• Naverstore > ํ™”์žฅํ’ˆ/๋ฏธ์šฉ > ๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—… > ํŒŒ์šด๋ฐ์ด์…˜ > ํฌ๋ฆผํ˜•'</li><li>'์‹œ์„ธ์ด๋„ ์Šคํฌ์ธ  ์ปค๋ฒ„ ํŒŒ์šด๋ฐ์ด์…˜ 20g S100 ร— 1๊ฐœ Coupang > ๋ทฐํ‹ฐ > ๋ฉ”์ดํฌ์—… > ๋ฒ ์ด์Šค ๋ฉ”์ดํฌ์—… > ํŒŒ์šด๋ฐ์ด์…˜;(#M)์ฟ ํŒก ํ™ˆ>๋ทฐํ‹ฐ>๋ฉ”์ดํฌ์—…>๋ฒ ์ด์Šค ๋ฉ”์ดํฌ์—…>ํŒŒ์šด๋ฐ์ด์…˜ Coupang > ๋ทฐํ‹ฐ > ๋ฉ”์ดํฌ์—… > ๋ฒ ์ด์Šค ๋ฉ”์ดํฌ์—… > ํŒŒ์šด๋ฐ์ด์…˜'</li><li>'์—์ด์ง€ํˆฌ์›จ๋‹ˆ์Šค ์˜ค๋ฆฌ์ง€๋‚  ์ƒค์ด๋‹๋“œ๋กญ ์ผ€์ด์Šค+๋ฆฌํ•„3๊ฐœ (+์ปคํ”ผ์ฟ ํฐ+ํผ20ml) ์ƒค์ด๋‹๋“œ๋กญ(ํ™”์ดํŠธ)23ํ˜ธ์ผ€์ด์Šค+๋ฆฌํ•„3๊ฐœ_ํผ20ml (#M)ํ™”์žฅํ’ˆ/๋ฏธ์šฉ>๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—…>ํŒŒ์šด๋ฐ์ด์…˜>์ฟ ์…˜ํ˜• AD > Naverstore > ํ™”์žฅํ’ˆ/๋ฏธ์šฉ > ๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—… > ํŒŒ์šด๋ฐ์ด์…˜ > ํฌ๋ฆผํ˜•'</li></ul> | | 3 | <ul><li>'๋งคํŠธ ๋ฒจ๋ฒณ ์Šคํ‚จ ์ปดํŒฉํŠธ ์Šคํฐ์ง€ ๋‹จํ’ˆ์—†์Œ LotteOn > ๋ทฐํ‹ฐ > ๋ทฐํ‹ฐ๊ธฐ๊ธฐ > ์•ก์„ธ์„œ๋ฆฌ/์†Œ๋ชจํ’ˆ LotteOn > ๋ทฐํ‹ฐ > ๋ทฐํ‹ฐ๊ธฐ๊ธฐ > ์•ก์„ธ์„œ๋ฆฌ/์†Œ๋ชจํ’ˆ'</li><li>'[BF์ ๋ฆฝ] ์—‰ํฌ๋ฅด ๋“œ ๋ฝ€ ์ฟ ์…˜&๋ฆฌํ•„ ์„ธํŠธ(+์Šคํƒ ๋”ฉ ๋ฏธ๋Ÿฌ+5์ฒœLPOINT) 20ํ˜ธ_15ํ˜ธ LOREAL > DepartmentLotteOn > ์ž…์ƒ๋กœ๋ž‘ > Branded > ์ž…์ƒ๋กœ๋ž‘ LOREAL > DepartmentLotteOn > ์ž…์ƒ๋กœ๋ž‘ > Branded > ์ž…์ƒ๋กœ๋ž‘'</li><li>'์ฝ”ํŠผ LotteOn > ๋ทฐํ‹ฐ > ๋ทฐํ‹ฐ๊ธฐ๊ธฐ > ์•ก์„ธ์„œ๋ฆฌ/์†Œ๋ชจํ’ˆ LotteOn > ๋ทฐํ‹ฐ > ๋ทฐํ‹ฐ๊ธฐ๊ธฐ > ์•ก์„ธ์„œ๋ฆฌ/์†Œ๋ชจํ’ˆ'</li></ul> | ## Evaluation ### Metrics | Label | Accuracy | |:--------|:---------| | **all** | 0.9475 | ## Uses ### Direct Use for Inference First install the SetFit library: ```bash pip install setfit ``` Then you can load this model and run inference. ```python from setfit import SetFitModel # Download from the ๐Ÿค— Hub model = SetFitModel.from_pretrained("mini1013/master_cate_top_bt5_4") # Run inference preds = model("[์‹œ์„ธ์ด๋„] NEW ์‹ฑํฌ๋กœ ์Šคํ‚จ ๋ž˜๋””์–ธํŠธ ๋ฆฌํ”„ํŒ… ํŒŒ์šด๋ฐ์ด์…˜ SPF30/PA++++ 30ml 130 ์˜คํŒ” (#M)ํ™ˆ>๋ฉ”์ดํฌ์—…>๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—… HMALL > ๋ทฐํ‹ฐ > ๋ฉ”์ดํฌ์—… > ๋ฒ ์ด์Šค๋ฉ”์ดํฌ์—…") ``` <!-- ### Downstream Use *List how someone could finetune this model on their own dataset.* --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* --> <!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* --> ## Training Details ### Training Set Metrics | Training set | Min | Median | Max | |:-------------|:----|:-------|:----| | Word count | 12 | 22.928 | 52 | | Label | Training Sample Count | |:------|:----------------------| | 0 | 50 | | 1 | 50 | | 2 | 50 | | 3 | 50 | | 4 | 50 | ### Training Hyperparameters - batch_size: (64, 64) - num_epochs: (30, 30) - max_steps: -1 - sampling_strategy: oversampling - num_iterations: 100 - body_learning_rate: (2e-05, 1e-05) - head_learning_rate: 0.01 - loss: CosineSimilarityLoss - distance_metric: cosine_distance - margin: 0.25 - end_to_end: False - use_amp: False - warmup_proportion: 0.1 - l2_weight: 0.01 - seed: 42 - eval_max_steps: -1 - load_best_model_at_end: False ### Training Results | Epoch | Step | Training Loss | Validation Loss | |:-------:|:-----:|:-------------:|:---------------:| | 0.0026 | 1 | 0.521 | - | | 0.1279 | 50 | 0.4636 | - | | 0.2558 | 100 | 0.42 | - | | 0.3836 | 150 | 0.292 | - | | 0.5115 | 200 | 0.1539 | - | | 0.6394 | 250 | 0.0626 | - | | 0.7673 | 300 | 0.0343 | - | | 0.8951 | 350 | 0.0071 | - | | 1.0230 | 400 | 0.0023 | - | | 1.1509 | 450 | 0.0005 | - | | 1.2788 | 500 | 0.0006 | - | | 1.4066 | 550 | 0.0003 | - | | 1.5345 | 600 | 0.0002 | - | | 1.6624 | 650 | 0.0001 | - | | 1.7903 | 700 | 0.0002 | - | | 1.9182 | 750 | 0.0006 | - | | 2.0460 | 800 | 0.0002 | - | | 2.1739 | 850 | 0.0001 | - | | 2.3018 | 900 | 0.0 | - | | 2.4297 | 950 | 0.0 | - | | 2.5575 | 1000 | 0.0 | - | | 2.6854 | 1050 | 0.0 | - | | 2.8133 | 1100 | 0.0 | - | | 2.9412 | 1150 | 0.0 | - | | 3.0691 | 1200 | 0.0 | - | | 3.1969 | 1250 | 0.0 | - | | 3.3248 | 1300 | 0.0 | - | | 3.4527 | 1350 | 0.0007 | - | | 3.5806 | 1400 | 0.0005 | - | | 3.7084 | 1450 | 0.0009 | - | | 3.8363 | 1500 | 0.0008 | - | | 3.9642 | 1550 | 0.0003 | - | | 4.0921 | 1600 | 0.0002 | - | | 4.2199 | 1650 | 0.0 | - | | 4.3478 | 1700 | 0.0 | - | | 4.4757 | 1750 | 0.0 | - | | 4.6036 | 1800 | 0.0 | - | | 4.7315 | 1850 | 0.0 | - | | 4.8593 | 1900 | 0.0 | - | | 4.9872 | 1950 | 0.0 | - | | 5.1151 | 2000 | 0.0 | - | | 5.2430 | 2050 | 0.0 | - | | 5.3708 | 2100 | 0.0 | - | | 5.4987 | 2150 | 0.0 | - | | 5.6266 | 2200 | 0.0 | - | | 5.7545 | 2250 | 0.0 | - | | 5.8824 | 2300 | 0.0 | - | | 6.0102 | 2350 | 0.0001 | - | | 6.1381 | 2400 | 0.0006 | - | | 6.2660 | 2450 | 0.0 | - | | 6.3939 | 2500 | 0.0 | - | | 6.5217 | 2550 | 0.0 | - | | 6.6496 | 2600 | 0.0 | - | | 6.7775 | 2650 | 0.0 | - | | 6.9054 | 2700 | 0.0 | - | | 7.0332 | 2750 | 0.0 | - | | 7.1611 | 2800 | 0.0 | - | | 7.2890 | 2850 | 0.0 | - | | 7.4169 | 2900 | 0.0 | - | | 7.5448 | 2950 | 0.0 | - | | 7.6726 | 3000 | 0.0 | - | | 7.8005 | 3050 | 0.0 | - | | 7.9284 | 3100 | 0.0 | - | | 8.0563 | 3150 | 0.0 | - | | 8.1841 | 3200 | 0.0 | - | | 8.3120 | 3250 | 0.0 | - | | 8.4399 | 3300 | 0.0 | - | | 8.5678 | 3350 | 0.0 | - | | 8.6957 | 3400 | 0.0 | - | | 8.8235 | 3450 | 0.0 | - | | 8.9514 | 3500 | 0.0 | - | | 9.0793 | 3550 | 0.0 | - | | 9.2072 | 3600 | 0.0 | - | | 9.3350 | 3650 | 0.0 | - | | 9.4629 | 3700 | 0.0 | - | | 9.5908 | 3750 | 0.0 | - | | 9.7187 | 3800 | 0.0 | - | | 9.8465 | 3850 | 0.0 | - | | 9.9744 | 3900 | 0.0 | - | | 10.1023 | 3950 | 0.0 | - | | 10.2302 | 4000 | 0.0 | - | | 10.3581 | 4050 | 0.0 | - | | 10.4859 | 4100 | 0.0 | - | | 10.6138 | 4150 | 0.0 | - | | 10.7417 | 4200 | 0.0 | - | | 10.8696 | 4250 | 0.0 | - | | 10.9974 | 4300 | 0.0 | - | | 11.1253 | 4350 | 0.0 | - | | 11.2532 | 4400 | 0.0 | - | | 11.3811 | 4450 | 0.0 | - | | 11.5090 | 4500 | 0.0 | - | | 11.6368 | 4550 | 0.0 | - | | 11.7647 | 4600 | 0.0 | - | | 11.8926 | 4650 | 0.0 | - | | 12.0205 | 4700 | 0.0 | - | | 12.1483 | 4750 | 0.0 | - | | 12.2762 | 4800 | 0.0 | - | | 12.4041 | 4850 | 0.0 | - | | 12.5320 | 4900 | 0.0 | - | | 12.6598 | 4950 | 0.0 | - | | 12.7877 | 5000 | 0.0 | - | | 12.9156 | 5050 | 0.0 | - | | 13.0435 | 5100 | 0.0 | - | | 13.1714 | 5150 | 0.0 | - | | 13.2992 | 5200 | 0.0 | - | | 13.4271 | 5250 | 0.0 | - | | 13.5550 | 5300 | 0.0 | - | | 13.6829 | 5350 | 0.0 | - | | 13.8107 | 5400 | 0.0 | - | | 13.9386 | 5450 | 0.0 | - | | 14.0665 | 5500 | 0.0 | - | | 14.1944 | 5550 | 0.0 | - | | 14.3223 | 5600 | 0.0 | - | | 14.4501 | 5650 | 0.0 | - | | 14.5780 | 5700 | 0.0 | - | | 14.7059 | 5750 | 0.0 | - | | 14.8338 | 5800 | 0.0 | - | | 14.9616 | 5850 | 0.0 | - | | 15.0895 | 5900 | 0.0 | - | | 15.2174 | 5950 | 0.0 | - | | 15.3453 | 6000 | 0.0 | - | | 15.4731 | 6050 | 0.0 | - | | 15.6010 | 6100 | 0.0 | - | | 15.7289 | 6150 | 0.0 | - | | 15.8568 | 6200 | 0.0 | - | | 15.9847 | 6250 | 0.0 | - | | 16.1125 | 6300 | 0.0 | - | | 16.2404 | 6350 | 0.0 | - | | 16.3683 | 6400 | 0.0 | - | | 16.4962 | 6450 | 0.0 | - | | 16.6240 | 6500 | 0.0 | - | | 16.7519 | 6550 | 0.0 | - | | 16.8798 | 6600 | 0.0 | - | | 17.0077 | 6650 | 0.0 | - | | 17.1355 | 6700 | 0.0 | - | | 17.2634 | 6750 | 0.0 | - | | 17.3913 | 6800 | 0.0 | - | | 17.5192 | 6850 | 0.0 | - | | 17.6471 | 6900 | 0.0 | - | | 17.7749 | 6950 | 0.0 | - | | 17.9028 | 7000 | 0.0 | - | | 18.0307 | 7050 | 0.0 | - | | 18.1586 | 7100 | 0.0 | - | | 18.2864 | 7150 | 0.0 | - | | 18.4143 | 7200 | 0.0 | - | | 18.5422 | 7250 | 0.0 | - | | 18.6701 | 7300 | 0.0 | - | | 18.7980 | 7350 | 0.0 | - | | 18.9258 | 7400 | 0.0 | - | | 19.0537 | 7450 | 0.0 | - | | 19.1816 | 7500 | 0.0 | - | | 19.3095 | 7550 | 0.0004 | - | | 19.4373 | 7600 | 0.0028 | - | | 19.5652 | 7650 | 0.0003 | - | | 19.6931 | 7700 | 0.0002 | - | | 19.8210 | 7750 | 0.0 | - | | 19.9488 | 7800 | 0.0 | - | | 20.0767 | 7850 | 0.0 | - | | 20.2046 | 7900 | 0.0 | - | | 20.3325 | 7950 | 0.0 | - | | 20.4604 | 8000 | 0.0 | - | | 20.5882 | 8050 | 0.0 | - | | 20.7161 | 8100 | 0.0 | - | | 20.8440 | 8150 | 0.0 | - | | 20.9719 | 8200 | 0.0 | - | | 21.0997 | 8250 | 0.0 | - | | 21.2276 | 8300 | 0.0 | - | | 21.3555 | 8350 | 0.0 | - | | 21.4834 | 8400 | 0.0 | - | | 21.6113 | 8450 | 0.0 | - | | 21.7391 | 8500 | 0.0 | - | | 21.8670 | 8550 | 0.0 | - | | 21.9949 | 8600 | 0.0 | - | | 22.1228 | 8650 | 0.0 | - | | 22.2506 | 8700 | 0.0 | - | | 22.3785 | 8750 | 0.0 | - | | 22.5064 | 8800 | 0.0 | - | | 22.6343 | 8850 | 0.0 | - | | 22.7621 | 8900 | 0.0 | - | | 22.8900 | 8950 | 0.0 | - | | 23.0179 | 9000 | 0.0 | - | | 23.1458 | 9050 | 0.0 | - | | 23.2737 | 9100 | 0.0 | - | | 23.4015 | 9150 | 0.0 | - | | 23.5294 | 9200 | 0.0 | - | | 23.6573 | 9250 | 0.0 | - | | 23.7852 | 9300 | 0.0 | - | | 23.9130 | 9350 | 0.0 | - | | 24.0409 | 9400 | 0.0 | - | | 24.1688 | 9450 | 0.0 | - | | 24.2967 | 9500 | 0.0 | - | | 24.4246 | 9550 | 0.0 | - | | 24.5524 | 9600 | 0.0 | - | | 24.6803 | 9650 | 0.0 | - | | 24.8082 | 9700 | 0.0 | - | | 24.9361 | 9750 | 0.0 | - | | 25.0639 | 9800 | 0.0 | - | | 25.1918 | 9850 | 0.0 | - | | 25.3197 | 9900 | 0.0 | - | | 25.4476 | 9950 | 0.0 | - | | 25.5754 | 10000 | 0.0 | - | | 25.7033 | 10050 | 0.0 | - | | 25.8312 | 10100 | 0.0 | - | | 25.9591 | 10150 | 0.0 | - | | 26.0870 | 10200 | 0.0 | - | | 26.2148 | 10250 | 0.0 | - | | 26.3427 | 10300 | 0.0 | - | | 26.4706 | 10350 | 0.0 | - | | 26.5985 | 10400 | 0.0 | - | | 26.7263 | 10450 | 0.0 | - | | 26.8542 | 10500 | 0.0 | - | | 26.9821 | 10550 | 0.0 | - | | 27.1100 | 10600 | 0.0 | - | | 27.2379 | 10650 | 0.0 | - | | 27.3657 | 10700 | 0.0 | - | | 27.4936 | 10750 | 0.0 | - | | 27.6215 | 10800 | 0.0 | - | | 27.7494 | 10850 | 0.0 | - | | 27.8772 | 10900 | 0.0 | - | | 28.0051 | 10950 | 0.0 | - | | 28.1330 | 11000 | 0.0 | - | | 28.2609 | 11050 | 0.0 | - | | 28.3887 | 11100 | 0.0 | - | | 28.5166 | 11150 | 0.0 | - | | 28.6445 | 11200 | 0.0 | - | | 28.7724 | 11250 | 0.0 | - | | 28.9003 | 11300 | 0.0 | - | | 29.0281 | 11350 | 0.0 | - | | 29.1560 | 11400 | 0.0 | - | | 29.2839 | 11450 | 0.0 | - | | 29.4118 | 11500 | 0.0 | - | | 29.5396 | 11550 | 0.0 | - | | 29.6675 | 11600 | 0.0 | - | | 29.7954 | 11650 | 0.0 | - | | 29.9233 | 11700 | 0.0 | - | ### Framework Versions - Python: 3.10.12 - SetFit: 1.1.0 - Sentence Transformers: 3.3.1 - Transformers: 4.44.2 - PyTorch: 2.2.0a0+81ea7a4 - Datasets: 3.2.0 - Tokenizers: 0.19.1 ## Citation ### BibTeX ```bibtex @article{https://doi.org/10.48550/arxiv.2209.11055, doi = {10.48550/ARXIV.2209.11055}, url = {https://arxiv.org/abs/2209.11055}, author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Efficient Few-Shot Learning Without Prompts}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ``` <!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->
[ "TEXT_CLASSIFICATION" ]
Non_BioNLP
csocsci/mt5-base-multi-label-cs-iiib-02c
csocsci
text2text-generation
[ "transformers", "pytorch", "mt5", "text2text-generation", "cs", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
1,695,389,385,000
2023-09-23T13:40:51
10
0
--- language: - cs license: mit --- # Model Card for mt5-base-multi-label-cs-iiib-02c <!-- Provide a quick summary of what the model is/does. --> This model is fine-tuned for multi-label text classification of Supportive Interactions in Instant Messenger dialogs of Adolescents in Czech. ## Model Description The model was fine-tuned on a dataset of Czech Instant Messenger dialogs of Adolescents. The classification is multi-label and the model outputs any combination of the tags:'NO TAG', 'Informaฤnรญ podpora', 'Emocionรกlnรญ podpora', 'Zaฤlenฤ›nรญ do skupiny', 'Uznรกnรญ', 'Nabรญdka pomoci': as a string joined with ', ' (ordered alphabetically). Each label indicates the presence of that category of Supportive Interactions: 'no tag', 'informational support', 'emocional support', 'social companionship', 'appraisal', 'instrumental support'. The inputs of the model are: a target utterance and its bi-directional context; the label of the example is determined by the label of the target utterance. - **Developed by:** Anonymous - **Language(s):** multilingual - **Finetuned from:** mt5-base ## Model Sources <!-- Provide the basic links for the model. --> - **Repository:** https://github.com/chi2024submission - **Paper:** Stay tuned! ## Usage Here is how to use this model to classify a context-window of a dialogue: ```python from transformers import AutoModelForSeq2SeqLM, AutoTokenizer import torch test_texts = ['Utterance2'] test_text_pairs = ['Utterance1;Utterance2;Utterance3'] checkpoint_path = "chi2024/mt5-base-multi-label-cs-iiib-02c" model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint_path)\ .to("cuda" if torch.cuda.is_available() else "cpu") tokenizer = AutoTokenizer.from_pretrained(checkpoint_path) def verbalize_input(text: str, text_pair: str) -> str: return "Utterance: %s\nContext: %s" % (text, text_pair) def predict_one(text, pair): input_pair = verbalize_input(text, pair) inputs = tokenizer(input_pair, return_tensors="pt", padding=True, truncation=True, max_length=256).to(model.device) outputs = model.generate(**inputs) decoded = [text.split(",")[0].strip() for text in tokenizer.batch_decode(outputs, skip_special_tokens=True)] return decoded dec = predict_one(test_texts[0], test_text_pairs[0]) print(dec) ```
[ "TEXT_CLASSIFICATION" ]
Non_BioNLP
heegyu/TinyLlama-augesc-context-strategy
heegyu
text-generation
[ "transformers", "safetensors", "llama", "text-generation", "dataset:thu-coai/augesc", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
1,709,309,966,000
2024-03-07T13:19:42
8
0
--- datasets: - thu-coai/augesc library_name: transformers --- Test set performance - Top 1 Accuracy: 0.4346 - Top 3 Accuracy: 0.7677 - Top 1 Macro F1: 0.2668 - Top 3 Macro F1: 0.5669 ### Usage ```python from transformers import AutoTokenizer, AutoModelForSequenceClassification device="cuda:0" model = "heegyu/TinyLlama-augesc-context-strategy" tokenizer = AutoTokenizer.from_pretrained(model) model = AutoModelForSequenceClassification.from_pretrained(model).eval().to(device) example = """usr: Hi sys[Question]: Hello, how are you today? usr: I was scolded by my parents yesterday""" inputs = tokenizer(example, return_tensors="pt").to(device) logits = model(**inputs).logits.softmax(-1) print(logits) label = logits.argmax(-1).item() ESCONV_STRATEGY = [ "Question", "Restatement or Paraphrasing", "Reflection of feelings", "Self-disclosure", "Affirmation and Reassurance", "Providing Suggestions", "Information", "Others" ] id2label = {i:k for i, k in enumerate(ESCONV_STRATEGY)} print(id2label[label]) ```
[ "PARAPHRASING" ]
Non_BioNLP
Bahasalab/BahasaGpt-chat
Bahasalab
null
[ "transformers", "pytorch", "tensorboard", "license:cc-by-nc-3.0", "endpoints_compatible", "region:us" ]
1,681,047,882,000
2023-04-11T07:23:12
18
2
--- license: cc-by-nc-3.0 --- # BahasaGPT-Chat ## Introduction This document provides an overview of the BahasaGPT-Chat model, which is a fine-tuned model for a specific task in the Indonesian language. The model is based on the Bloomz-7B-mt architecture and is fine-tuned using a dataset of over 120000 Chat instructions based. ## Model Details **Model Name:** BahasaGPT-Chat **Model Source:** Bloomz-7B-mt **Dataset for Fine-Tuning:** Over 120k Indonesia Instruct Dataset generated using the Alpaca method from the following sources: - [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) - [Baize-Chatbot] (https://github.com/project-baize/baize-chatbot) - Translated instructions from OA ([Anh/data at main ยท LAION-AI/Anh](https://github.com/LAION-AI/Anh)) ## Fine-Tuning Process The BahasaGPT-1 model was fine-tuned using a dataset of over 120k Indonesian instructions, which were generated using [Baize-Chatbot] (https://github.com/project-baize/baize-chatbot) method with addition alpaca and OA Translation dataset. This combination of datasets allowed the model to be better adapted to the specific needs of Indonesian language tasks. The fine-tuning process involved adjusting the model's weights and biases based on the input dataset. This was done iteratively to optimize the model's performance for the specific task in the Indonesian language. ## Known Limitations Despite the successful fine-tuning, the BahasaGPT-1 model still has some limitations: **Hallucination:** The model sometimes generates outputs that may seem plausible but are not based on the input data. This may lead to incorrect or nonsensical responses in some cases. **Bias:** The BahasaGPT-1 model, like other AI language models, can exhibit various forms of bias due to the data it was trained on. This includes, but is not limited to, gender, racial, and cultural biases. As a result, the model may generate outputs that perpetuate stereotypes, exhibit unfair treatment, or show preference for specific groups or perspectives. Efforts have been made to mitigate these biases, but they may still be present in the model's responses. ## Conclusion The BahasaGPT-1 model is a fine-tuned language model for Indonesian language tasks, based on the Bloomz-7B-mt architecture. The model was trained on a dataset of over 120k Indonesian instructions generated using using [Baize-Chatbot] (https://github.com/project-baize/baize-chatbot) method with addition alpaca and OA Translation dataset. Despite some limitations, such as occasional hallucination, the model provides a valuable tool for working with Indonesian language tasks. ## How to Run For Gradio Demo : [Gradio Code](https://github.com/acul3/Bahasa_Chat) For Colab Using (Int8) : [Colab](https://colab.research.google.com/drive/1yvhJENcd0NKuMZNipAJVP4eP-k7-ilXj?usp=sharing)
[ "TRANSLATION" ]
Non_BioNLP