initial copy of lajavaness repo

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "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
+}

README.md

@@ -1,3 +1,1601 @@
----
-license: apache-2.0
----
+---
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+- sentence-embedding
+- mteb
+- mteb
+model-index:
+- name: e433e634850d125d8b85bee76db3a3b6a0c3bf56
+  results:
+  - task:
+      type: Clustering
+    dataset:
+      type: lyon-nlp/alloprof
+      name: MTEB AlloProfClusteringP2P
+      config: default
+      split: test
+      revision: 392ba3f5bcc8c51f578786c1fc3dae648662cb9b
+    metrics:
+    - type: v_measure
+      value: 56.88600728743999
+    - type: v_measures
+      value: [0.5396081553520281, 0.6022872403200437, 0.5515205944691852, 0.5595772885785736, 0.5632413941951575]
+  - task:
+      type: Clustering
+    dataset:
+      type: lyon-nlp/alloprof
+      name: MTEB AlloProfClusteringS2S
+      config: default
+      split: test
+      revision: 392ba3f5bcc8c51f578786c1fc3dae648662cb9b
+    metrics:
+    - type: v_measure
+      value: 38.199527329051804
+    - type: v_measures
+      value: [0.42157254138936706, 0.36882298663461527, 0.3134327610337458, 0.40391031391690396, 0.3832775043562133]
+  - task:
+      type: Reranking
+    dataset:
+      type: lyon-nlp/mteb-fr-reranking-alloprof-s2p
+      name: MTEB AlloprofReranking
+      config: default
+      split: test
+      revision: 65393d0d7a08a10b4e348135e824f385d420b0fd
+    metrics:
+    - type: map
+      value: 68.73372257500206
+    - type: mrr
+      value: 70.07434479260904
+    - type: nAUC_map_diff1
+      value: 50.95933484071007
+    - type: nAUC_map_max
+      value: 13.75463910519138
+    - type: nAUC_mrr_diff1
+      value: 50.494303783447656
+    - type: nAUC_mrr_max
+      value: 14.460935217916187
+  - task:
+      type: Retrieval
+    dataset:
+      type: lyon-nlp/alloprof
+      name: MTEB AlloprofRetrieval
+      config: default
+      split: test
+      revision: fcf295ea64c750f41fadbaa37b9b861558e1bfbd
+    metrics:
+    - type: map_at_1
+      value: 21.675
+    - type: map_at_10
+      value: 32.274
+    - type: map_at_100
+      value: 33.316
+    - type: map_at_1000
+      value: 33.387
+    - type: map_at_20
+      value: 32.864
+    - type: map_at_3
+      value: 29.166999999999998
+    - type: map_at_5
+      value: 30.946
+    - type: mrr_at_1
+      value: 21.675302245250432
+    - type: mrr_at_10
+      value: 32.274309839076714
+    - type: mrr_at_100
+      value: 33.31571024590564
+    - type: mrr_at_1000
+      value: 33.3868130424392
+    - type: mrr_at_20
+      value: 32.863978562081925
+    - type: mrr_at_3
+      value: 29.16666666666669
+    - type: mrr_at_5
+      value: 30.94559585492234
+    - type: nauc_map_at_1000_diff1
+      value: 34.85808309940442
+    - type: nauc_map_at_1000_max
+      value: 31.058801579682825
+    - type: nauc_map_at_100_diff1
+      value: 34.842898344470846
+    - type: nauc_map_at_100_max
+      value: 31.077561464904342
+    - type: nauc_map_at_10_diff1
+      value: 34.6773118480208
+    - type: nauc_map_at_10_max
+      value: 30.8489850780642
+    - type: nauc_map_at_1_diff1
+      value: 40.65773695743684
+    - type: nauc_map_at_1_max
+      value: 28.766036921254617
+    - type: nauc_map_at_20_diff1
+      value: 34.73935242577166
+    - type: nauc_map_at_20_max
+      value: 31.03143938077287
+    - type: nauc_map_at_3_diff1
+      value: 35.12059625476991
+    - type: nauc_map_at_3_max
+      value: 30.48787855768291
+    - type: nauc_map_at_5_diff1
+      value: 34.73453235094986
+    - type: nauc_map_at_5_max
+      value: 30.3860304682398
+    - type: nauc_mrr_at_1000_diff1
+      value: 34.85808309940442
+    - type: nauc_mrr_at_1000_max
+      value: 31.058801579682825
+    - type: nauc_mrr_at_100_diff1
+      value: 34.842898344470846
+    - type: nauc_mrr_at_100_max
+      value: 31.077561464904342
+    - type: nauc_mrr_at_10_diff1
+      value: 34.6773118480208
+    - type: nauc_mrr_at_10_max
+      value: 30.8489850780642
+    - type: nauc_mrr_at_1_diff1
+      value: 40.65773695743684
+    - type: nauc_mrr_at_1_max
+      value: 28.766036921254617
+    - type: nauc_mrr_at_20_diff1
+      value: 34.73935242577166
+    - type: nauc_mrr_at_20_max
+      value: 31.03143938077287
+    - type: nauc_mrr_at_3_diff1
+      value: 35.12059625476991
+    - type: nauc_mrr_at_3_max
+      value: 30.48787855768291
+    - type: nauc_mrr_at_5_diff1
+      value: 34.73453235094986
+    - type: nauc_mrr_at_5_max
+      value: 30.3860304682398
+    - type: nauc_ndcg_at_1000_diff1
+      value: 34.04342467121623
+    - type: nauc_ndcg_at_1000_max
+      value: 32.311398352704686
+    - type: nauc_ndcg_at_100_diff1
+      value: 33.67278941726764
+    - type: nauc_ndcg_at_100_max
+      value: 33.0229606203184
+    - type: nauc_ndcg_at_10_diff1
+      value: 32.93808280492078
+    - type: nauc_ndcg_at_10_max
+      value: 32.07111775221638
+    - type: nauc_ndcg_at_1_diff1
+      value: 40.65773695743684
+    - type: nauc_ndcg_at_1_max
+      value: 28.766036921254617
+    - type: nauc_ndcg_at_20_diff1
+      value: 33.141323431064585
+    - type: nauc_ndcg_at_20_max
+      value: 32.76436962238286
+    - type: nauc_ndcg_at_3_diff1
+      value: 33.77769745974645
+    - type: nauc_ndcg_at_3_max
+      value: 31.072988073016912
+    - type: nauc_ndcg_at_5_diff1
+      value: 33.091582792245696
+    - type: nauc_ndcg_at_5_max
+      value: 30.92378976230745
+    - type: nauc_precision_at_1000_diff1
+      value: 33.74743287990321
+    - type: nauc_precision_at_1000_max
+      value: 60.08005213097628
+    - type: nauc_precision_at_100_diff1
+      value: 28.869275501873236
+    - type: nauc_precision_at_100_max
+      value: 46.35483380447927
+    - type: nauc_precision_at_10_diff1
+      value: 27.910043146581497
+    - type: nauc_precision_at_10_max
+      value: 36.07399824307888
+    - type: nauc_precision_at_1_diff1
+      value: 40.65773695743684
+    - type: nauc_precision_at_1_max
+      value: 28.766036921254617
+    - type: nauc_precision_at_20_diff1
+      value: 28.144265629196163
+    - type: nauc_precision_at_20_max
+      value: 39.60361579056115
+    - type: nauc_precision_at_3_diff1
+      value: 30.31893725671278
+    - type: nauc_precision_at_3_max
+      value: 32.63695126407254
+    - type: nauc_precision_at_5_diff1
+      value: 28.699678130380235
+    - type: nauc_precision_at_5_max
+      value: 32.37908851919098
+    - type: nauc_recall_at_1000_diff1
+      value: 33.74743287990342
+    - type: nauc_recall_at_1000_max
+      value: 60.080052130975346
+    - type: nauc_recall_at_100_diff1
+      value: 28.869275501873247
+    - type: nauc_recall_at_100_max
+      value: 46.35483380447917
+    - type: nauc_recall_at_10_diff1
+      value: 27.910043146581508
+    - type: nauc_recall_at_10_max
+      value: 36.07399824307888
+    - type: nauc_recall_at_1_diff1
+      value: 40.65773695743684
+    - type: nauc_recall_at_1_max
+      value: 28.766036921254617
+    - type: nauc_recall_at_20_diff1
+      value: 28.14426562919617
+    - type: nauc_recall_at_20_max
+      value: 39.60361579056118
+    - type: nauc_recall_at_3_diff1
+      value: 30.318937256712804
+    - type: nauc_recall_at_3_max
+      value: 32.63695126407256
+    - type: nauc_recall_at_5_diff1
+      value: 28.699678130380224
+    - type: nauc_recall_at_5_max
+      value: 32.37908851919102
+    - type: ndcg_at_1
+      value: 21.675
+    - type: ndcg_at_10
+      value: 38.06
+    - type: ndcg_at_100
+      value: 43.491
+    - type: ndcg_at_1000
+      value: 45.432
+    - type: ndcg_at_20
+      value: 40.217000000000006
+    - type: ndcg_at_3
+      value: 31.642
+    - type: ndcg_at_5
+      value: 34.837
+    - type: precision_at_1
+      value: 21.675
+    - type: precision_at_10
+      value: 5.652
+    - type: precision_at_100
+      value: 0.827
+    - type: precision_at_1000
+      value: 0.098
+    - type: precision_at_20
+      value: 3.253
+    - type: precision_at_3
+      value: 12.939
+    - type: precision_at_5
+      value: 9.309000000000001
+    - type: recall_at_1
+      value: 21.675
+    - type: recall_at_10
+      value: 56.52
+    - type: recall_at_100
+      value: 82.729
+    - type: recall_at_1000
+      value: 98.1
+    - type: recall_at_20
+      value: 65.069
+    - type: recall_at_3
+      value: 38.817
+    - type: recall_at_5
+      value: 46.546
+  - task:
+      type: Classification
+    dataset:
+      type: mteb/amazon_reviews_multi
+      name: MTEB AmazonReviewsClassification (fr)
+      config: fr
+      split: test
+      revision: 1399c76144fd37290681b995c656ef9b2e06e26d
+    metrics:
+    - type: accuracy
+      value: 43.51
+    - type: f1
+      value: 41.3284674671926
+    - type: f1_weighted
+      value: 41.3284674671926
+  - task:
+      type: Retrieval
+    dataset:
+      type: maastrichtlawtech/bsard
+      name: MTEB BSARDRetrieval
+      config: default
+      split: test
+      revision: 5effa1b9b5fa3b0f9e12523e6e43e5f86a6e6d59
+    metrics:
+    - type: map_at_1
+      value: 5.405
+    - type: map_at_10
+      value: 9.008
+    - type: map_at_100
+      value: 9.932
+    - type: map_at_1000
+      value: 10.042
+    - type: map_at_20
+      value: 9.389
+    - type: map_at_3
+      value: 7.883
+    - type: map_at_5
+      value: 8.626000000000001
+    - type: mrr_at_1
+      value: 5.405405405405405
+    - type: mrr_at_10
+      value: 9.007579007579007
+    - type: mrr_at_100
+      value: 9.931517094611667
+    - type: mrr_at_1000
+      value: 10.0416462267215
+    - type: mrr_at_20
+      value: 9.38869595990339
+    - type: mrr_at_3
+      value: 7.882882882882883
+    - type: mrr_at_5
+      value: 8.626126126126126
+    - type: nauc_map_at_1000_diff1
+      value: 23.53549434486455
+    - type: nauc_map_at_1000_max
+      value: 9.977010641647402
+    - type: nauc_map_at_100_diff1
+      value: 23.50007884241435
+    - type: nauc_map_at_100_max
+      value: 9.984274734441085
+    - type: nauc_map_at_10_diff1
+      value: 24.69444512826233
+    - type: nauc_map_at_10_max
+      value: 9.726162724771594
+    - type: nauc_map_at_1_diff1
+      value: 40.88188899137848
+    - type: nauc_map_at_1_max
+      value: 12.044739470755896
+    - type: nauc_map_at_20_diff1
+      value: 23.833757177107557
+    - type: nauc_map_at_20_max
+      value: 9.94328216894336
+    - type: nauc_map_at_3_diff1
+      value: 28.320570164876653
+    - type: nauc_map_at_3_max
+      value: 11.195397944839767
+    - type: nauc_map_at_5_diff1
+      value: 25.86894200735248
+    - type: nauc_map_at_5_max
+      value: 8.43950569758736
+    - type: nauc_mrr_at_1000_diff1
+      value: 23.53549434486455
+    - type: nauc_mrr_at_1000_max
+      value: 9.977010641647402
+    - type: nauc_mrr_at_100_diff1
+      value: 23.50007884241435
+    - type: nauc_mrr_at_100_max
+      value: 9.984274734441085
+    - type: nauc_mrr_at_10_diff1
+      value: 24.69444512826233
+    - type: nauc_mrr_at_10_max
+      value: 9.726162724771594
+    - type: nauc_mrr_at_1_diff1
+      value: 40.88188899137848
+    - type: nauc_mrr_at_1_max
+      value: 12.044739470755896
+    - type: nauc_mrr_at_20_diff1
+      value: 23.833757177107557
+    - type: nauc_mrr_at_20_max
+      value: 9.94328216894336
+    - type: nauc_mrr_at_3_diff1
+      value: 28.320570164876653
+    - type: nauc_mrr_at_3_max
+      value: 11.195397944839767
+    - type: nauc_mrr_at_5_diff1
+      value: 25.86894200735248
+    - type: nauc_mrr_at_5_max
+      value: 8.43950569758736
+    - type: nauc_ndcg_at_1000_diff1
+      value: 15.939402272339343
+    - type: nauc_ndcg_at_1000_max
+      value: 10.076089125537772
+    - type: nauc_ndcg_at_100_diff1
+      value: 16.12740122067642
+    - type: nauc_ndcg_at_100_max
+      value: 10.39935154464689
+    - type: nauc_ndcg_at_10_diff1
+      value: 20.455941061369295
+    - type: nauc_ndcg_at_10_max
+      value: 9.350349883274461
+    - type: nauc_ndcg_at_1_diff1
+      value: 40.88188899137848
+    - type: nauc_ndcg_at_1_max
+      value: 12.044739470755896
+    - type: nauc_ndcg_at_20_diff1
+      value: 18.267195122936364
+    - type: nauc_ndcg_at_20_max
+      value: 10.211299135510837
+    - type: nauc_ndcg_at_3_diff1
+      value: 26.453038443158267
+    - type: nauc_ndcg_at_3_max
+      value: 10.628723618231271
+    - type: nauc_ndcg_at_5_diff1
+      value: 22.815939702854084
+    - type: nauc_ndcg_at_5_max
+      value: 6.308794763068443
+    - type: nauc_precision_at_1000_diff1
+      value: -7.915540524594587
+    - type: nauc_precision_at_1000_max
+      value: 10.441250503021037
+    - type: nauc_precision_at_100_diff1
+      value: 2.7415108070462253
+    - type: nauc_precision_at_100_max
+      value: 11.957692005514204
+    - type: nauc_precision_at_10_diff1
+      value: 12.731449206012213
+    - type: nauc_precision_at_10_max
+      value: 9.218464561250887
+    - type: nauc_precision_at_1_diff1
+      value: 40.88188899137848
+    - type: nauc_precision_at_1_max
+      value: 12.044739470755896
+    - type: nauc_precision_at_20_diff1
+      value: 8.658189595700664
+    - type: nauc_precision_at_20_max
+      value: 11.571072137198621
+    - type: nauc_precision_at_3_diff1
+      value: 22.7637681983756
+    - type: nauc_precision_at_3_max
+      value: 9.361635703809425
+    - type: nauc_precision_at_5_diff1
+      value: 17.02002973192349
+    - type: nauc_precision_at_5_max
+      value: 1.8844406919262011
+    - type: nauc_recall_at_1000_diff1
+      value: -7.915540524594531
+    - type: nauc_recall_at_1000_max
+      value: 10.441250503021028
+    - type: nauc_recall_at_100_diff1
+      value: 2.741510807046166
+    - type: nauc_recall_at_100_max
+      value: 11.957692005514156
+    - type: nauc_recall_at_10_diff1
+      value: 12.731449206012224
+    - type: nauc_recall_at_10_max
+      value: 9.218464561250883
+    - type: nauc_recall_at_1_diff1
+      value: 40.88188899137848
+    - type: nauc_recall_at_1_max
+      value: 12.044739470755896
+    - type: nauc_recall_at_20_diff1
+      value: 8.65818959570063
+    - type: nauc_recall_at_20_max
+      value: 11.571072137198572
+    - type: nauc_recall_at_3_diff1
+      value: 22.763768198375587
+    - type: nauc_recall_at_3_max
+      value: 9.361635703809409
+    - type: nauc_recall_at_5_diff1
+      value: 17.02002973192351
+    - type: nauc_recall_at_5_max
+      value: 1.8844406919262173
+    - type: ndcg_at_1
+      value: 5.405
+    - type: ndcg_at_10
+      value: 11.045
+    - type: ndcg_at_100
+      value: 16.724
+    - type: ndcg_at_1000
+      value: 20.325
+    - type: ndcg_at_20
+      value: 12.42
+    - type: ndcg_at_3
+      value: 8.746
+    - type: ndcg_at_5
+      value: 10.065
+    - type: precision_at_1
+      value: 5.405
+    - type: precision_at_10
+      value: 1.757
+    - type: precision_at_100
+      value: 0.468
+    - type: precision_at_1000
+      value: 0.077
+    - type: precision_at_20
+      value: 1.149
+    - type: precision_at_3
+      value: 3.7539999999999996
+    - type: precision_at_5
+      value: 2.883
+    - type: recall_at_1
+      value: 5.405
+    - type: recall_at_10
+      value: 17.568
+    - type: recall_at_100
+      value: 46.847
+    - type: recall_at_1000
+      value: 76.577
+    - type: recall_at_20
+      value: 22.973
+    - type: recall_at_3
+      value: 11.261000000000001
+    - type: recall_at_5
+      value: 14.414
+  - task:
+      type: Clustering
+    dataset:
+      type: lyon-nlp/clustering-hal-s2s
+      name: MTEB HALClusteringS2S
+      config: default
+      split: test
+      revision: e06ebbbb123f8144bef1a5d18796f3dec9ae2915
+    metrics:
+    - type: v_measure
+      value: 24.495384349905265
+    - type: v_measures
+      value: [0.2850587858600384, 0.274086904447773, 0.2446866774990972, 0.26946100959565517, 0.24156528297396174]
+  - task:
+      type: Clustering
+    dataset:
+      type: reciTAL/mlsum
+      name: MTEB MLSUMClusteringP2P
+      config: default
+      split: test
+      revision: b5d54f8f3b61ae17845046286940f03c6bc79bc7
+    metrics:
+    - type: v_measure
+      value: 41.7878688793447
+    - type: v_measures
+      value: [0.4201324393825989, 0.4205306567437461, 0.4221300501395374, 0.4210735177933313, 0.38124298228695813]
+  - task:
+      type: Clustering
+    dataset:
+      type: reciTAL/mlsum
+      name: MTEB MLSUMClusteringS2S
+      config: default
+      split: test
+      revision: b5d54f8f3b61ae17845046286940f03c6bc79bc7
+    metrics:
+    - type: v_measure
+      value: 41.54533473611554
+    - type: v_measures
+      value: [0.3978917671338969, 0.42610299599987944, 0.4152131658150196, 0.40558711021249855, 0.38327501252308305]
+  - task:
+      type: Classification
+    dataset:
+      type: mteb/mtop_domain
+      name: MTEB MTOPDomainClassification (fr)
+      config: fr
+      split: test
+      revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
+    metrics:
+    - type: accuracy
+      value: 85.33041027247104
+    - type: f1
+      value: 85.4043088703478
+    - type: f1_weighted
+      value: 85.22086763441686
+  - task:
+      type: Classification
+    dataset:
+      type: mteb/mtop_intent
+      name: MTEB MTOPIntentClassification (fr)
+      config: fr
+      split: test
+      revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
+    metrics:
+    - type: accuracy
+      value: 59.01346695897275
+    - type: f1
+      value: 41.296845063208316
+    - type: f1_weighted
+      value: 61.793813202867696
+  - task:
+      type: Classification
+    dataset:
+      type: mteb/masakhanews
+      name: MTEB MasakhaNEWSClassification (fra)
+      config: fra
+      split: test
+      revision: 18193f187b92da67168c655c9973a165ed9593dd
+    metrics:
+    - type: accuracy
+      value: 72.60663507109004
+    - type: f1
+      value: 68.67522100429781
+    - type: f1_weighted
+      value: 72.75616093668002
+  - task:
+      type: Clustering
+    dataset:
+      type: masakhane/masakhanews
+      name: MTEB MasakhaNEWSClusteringP2P (fra)
+      config: fra
+      split: test
+      revision: 8ccc72e69e65f40c70e117d8b3c08306bb788b60
+    metrics:
+    - type: v_measure
+      value: 49.17691007381563
+    - type: v_measures
+      value: [1.0, 0.033833191750480725, 0.5707463198244268, 0.1318223737892885, 0.7224436183265853]
+  - task:
+      type: Clustering
+    dataset:
+      type: masakhane/masakhanews
+      name: MTEB MasakhaNEWSClusteringS2S (fra)
+      config: fra
+      split: test
+      revision: 8ccc72e69e65f40c70e117d8b3c08306bb788b60
+    metrics:
+    - type: v_measure
+      value: 26.9350763881635
+    - type: v_measures
+      value: [1.0, 0.0002883507347309009, 0.18259625098776155, 0.025306110065234755, 0.1385631076204479]
+  - task:
+      type: Classification
+    dataset:
+      type: mteb/amazon_massive_intent
+      name: MTEB MassiveIntentClassification (fr)
+      config: fr
+      split: test
+      revision: 4672e20407010da34463acc759c162ca9734bca6
+    metrics:
+    - type: accuracy
+      value: 65.1546738399462
+    - type: f1
+      value: 62.81367149102006
+    - type: f1_weighted
+      value: 64.45478181518959
+  - task:
+      type: Classification
+    dataset:
+      type: mteb/amazon_massive_scenario
+      name: MTEB MassiveScenarioClassification (fr)
+      config: fr
+      split: test
+      revision: fad2c6e8459f9e1c45d9315f4953d921437d70f8
+    metrics:
+    - type: accuracy
+      value: 69.94283792871553
+    - type: f1
+      value: 69.3387310036327
+    - type: f1_weighted
+      value: 69.77979200675047
+  - task:
+      type: Retrieval
+    dataset:
+      type: jinaai/mintakaqa
+      name: MTEB MintakaRetrieval (fr)
+      config: fr
+      split: test
+      revision: efa78cc2f74bbcd21eff2261f9e13aebe40b814e
+    metrics:
+    - type: map_at_1
+      value: 14.536999999999999
+    - type: map_at_10
+      value: 22.972
+    - type: map_at_100
+      value: 24.046
+    - type: map_at_1000
+      value: 24.15
+    - type: map_at_20
+      value: 23.56
+    - type: map_at_3
+      value: 20.639
+    - type: map_at_5
+      value: 21.886
+    - type: mrr_at_1
+      value: 14.537264537264537
+    - type: mrr_at_10
+      value: 22.97172172172171
+    - type: mrr_at_100
+      value: 24.04581030084757
+    - type: mrr_at_1000
+      value: 24.15012351833827
+    - type: mrr_at_20
+      value: 23.559920001131612
+    - type: mrr_at_3
+      value: 20.63882063882061
+    - type: mrr_at_5
+      value: 21.88574938574935
+    - type: nauc_map_at_1000_diff1
+      value: 25.172495501911456
+    - type: nauc_map_at_1000_max
+      value: 39.07442097828252
+    - type: nauc_map_at_100_diff1
+      value: 25.129142743145884
+    - type: nauc_map_at_100_max
+      value: 39.03725272182565
+    - type: nauc_map_at_10_diff1
+      value: 25.52237435145409
+    - type: nauc_map_at_10_max
+      value: 39.5761256079619
+    - type: nauc_map_at_1_diff1
+      value: 31.68506359690787
+    - type: nauc_map_at_1_max
+      value: 39.251552013635425
+    - type: nauc_map_at_20_diff1
+      value: 25.223544981725286
+    - type: nauc_map_at_20_max
+      value: 39.20307777977743
+    - type: nauc_map_at_3_diff1
+      value: 26.5913043939904
+    - type: nauc_map_at_3_max
+      value: 40.38909639557377
+    - type: nauc_map_at_5_diff1
+      value: 25.90291761511258
+    - type: nauc_map_at_5_max
+      value: 40.08746876057708
+    - type: nauc_mrr_at_1000_diff1
+      value: 25.172495501911456
+    - type: nauc_mrr_at_1000_max
+      value: 39.07442097828252
+    - type: nauc_mrr_at_100_diff1
+      value: 25.129142743145884
+    - type: nauc_mrr_at_100_max
+      value: 39.03725272182565
+    - type: nauc_mrr_at_10_diff1
+      value: 25.52237435145409
+    - type: nauc_mrr_at_10_max
+      value: 39.5761256079619
+    - type: nauc_mrr_at_1_diff1
+      value: 31.68506359690787
+    - type: nauc_mrr_at_1_max
+      value: 39.251552013635425
+    - type: nauc_mrr_at_20_diff1
+      value: 25.223544981725286
+    - type: nauc_mrr_at_20_max
+      value: 39.20307777977743
+    - type: nauc_mrr_at_3_diff1
+      value: 26.5913043939904
+    - type: nauc_mrr_at_3_max
+      value: 40.38909639557377
+    - type: nauc_mrr_at_5_diff1
+      value: 25.90291761511258
+    - type: nauc_mrr_at_5_max
+      value: 40.08746876057708
+    - type: nauc_ndcg_at_1000_diff1
+      value: 23.22275566961323
+    - type: nauc_ndcg_at_1000_max
+      value: 37.77760760027764
+    - type: nauc_ndcg_at_100_diff1
+      value: 21.715763741257927
+    - type: nauc_ndcg_at_100_max
+      value: 36.46541121995108
+    - type: nauc_ndcg_at_10_diff1
+      value: 23.278761630662373
+    - type: nauc_ndcg_at_10_max
+      value: 38.7930407055593
+    - type: nauc_ndcg_at_1_diff1
+      value: 31.68506359690787
+    - type: nauc_ndcg_at_1_max
+      value: 39.251552013635425
+    - type: nauc_ndcg_at_20_diff1
+      value: 22.247483519405314
+    - type: nauc_ndcg_at_20_max
+      value: 37.52699283756433
+    - type: nauc_ndcg_at_3_diff1
+      value: 25.285332146360567
+    - type: nauc_ndcg_at_3_max
+      value: 40.49755286945492
+    - type: nauc_ndcg_at_5_diff1
+      value: 24.188132420084607
+    - type: nauc_ndcg_at_5_max
+      value: 40.023420096094924
+    - type: nauc_precision_at_1000_diff1
+      value: 22.011383616462943
+    - type: nauc_precision_at_1000_max
+      value: 33.1171975223399
+    - type: nauc_precision_at_100_diff1
+      value: 8.869925191243802
+    - type: nauc_precision_at_100_max
+      value: 24.642097404720463
+    - type: nauc_precision_at_10_diff1
+      value: 17.74075352930919
+    - type: nauc_precision_at_10_max
+      value: 36.488352516736775
+    - type: nauc_precision_at_1_diff1
+      value: 31.68506359690787
+    - type: nauc_precision_at_1_max
+      value: 39.251552013635425
+    - type: nauc_precision_at_20_diff1
+      value: 14.092673370526898
+    - type: nauc_precision_at_20_max
+      value: 32.16083119966346
+    - type: nauc_precision_at_3_diff1
+      value: 22.16344389106631
+    - type: nauc_precision_at_3_max
+      value: 40.70883095791623
+    - type: nauc_precision_at_5_diff1
+      value: 20.119543069972256
+    - type: nauc_precision_at_5_max
+      value: 39.79763147435235
+    - type: nauc_recall_at_1000_diff1
+      value: 22.011383616462528
+    - type: nauc_recall_at_1000_max
+      value: 33.117197522340085
+    - type: nauc_recall_at_100_diff1
+      value: 8.869925191243775
+    - type: nauc_recall_at_100_max
+      value: 24.64209740472041
+    - type: nauc_recall_at_10_diff1
+      value: 17.740753529309178
+    - type: nauc_recall_at_10_max
+      value: 36.48835251673679
+    - type: nauc_recall_at_1_diff1
+      value: 31.68506359690787
+    - type: nauc_recall_at_1_max
+      value: 39.251552013635425
+    - type: nauc_recall_at_20_diff1
+      value: 14.092673370526915
+    - type: nauc_recall_at_20_max
+      value: 32.160831199663455
+    - type: nauc_recall_at_3_diff1
+      value: 22.163443891066322
+    - type: nauc_recall_at_3_max
+      value: 40.708830957916234
+    - type: nauc_recall_at_5_diff1
+      value: 20.119543069972217
+    - type: nauc_recall_at_5_max
+      value: 39.79763147435234
+    - type: ndcg_at_1
+      value: 14.536999999999999
+    - type: ndcg_at_10
+      value: 27.485
+    - type: ndcg_at_100
+      value: 33.206
+    - type: ndcg_at_1000
+      value: 36.382999999999996
+    - type: ndcg_at_20
+      value: 29.635
+    - type: ndcg_at_3
+      value: 22.597
+    - type: ndcg_at_5
+      value: 24.851
+    - type: precision_at_1
+      value: 14.536999999999999
+    - type: precision_at_10
+      value: 4.189
+    - type: precision_at_100
+      value: 0.698
+    - type: precision_at_1000
+      value: 0.096
+    - type: precision_at_20
+      value: 2.52
+    - type: precision_at_3
+      value: 9.419
+    - type: precision_at_5
+      value: 6.749
+    - type: recall_at_1
+      value: 14.536999999999999
+    - type: recall_at_10
+      value: 41.892
+    - type: recall_at_100
+      value: 69.779
+    - type: recall_at_1000
+      value: 95.61800000000001
+    - type: recall_at_20
+      value: 50.41
+    - type: recall_at_3
+      value: 28.255999999999997
+    - type: recall_at_5
+      value: 33.743
+  - task:
+      type: PairClassification
+    dataset:
+      type: GEM/opusparcus
+      name: MTEB OpusparcusPC (fr)
+      config: fr
+      split: test
+      revision: 9e9b1f8ef51616073f47f306f7f47dd91663f86a
+    metrics:
+    - type: cos_sim_accuracy
+      value: 81.74386920980926
+    - type: cos_sim_ap
+      value: 93.18281680904117
+    - type: cos_sim_f1
+      value: 87.37233054781802
+    - type: cos_sim_precision
+      value: 82.04010462074979
+    - type: cos_sim_recall
+      value: 93.44587884806356
+    - type: dot_accuracy
+      value: 81.74386920980926
+    - type: dot_ap
+      value: 93.18281680904117
+    - type: dot_f1
+      value: 87.37233054781802
+    - type: dot_precision
+      value: 82.04010462074979
+    - type: dot_recall
+      value: 93.44587884806356
+    - type: euclidean_accuracy
+      value: 81.74386920980926
+    - type: euclidean_ap
+      value: 93.18281680904117
+    - type: euclidean_f1
+      value: 87.37233054781802
+    - type: euclidean_precision
+      value: 82.04010462074979
+    - type: euclidean_recall
+      value: 93.44587884806356
+    - type: manhattan_accuracy
+      value: 81.74386920980926
+    - type: manhattan_ap
+      value: 93.17517480971131
+    - type: manhattan_f1
+      value: 87.37864077669903
+    - type: manhattan_precision
+      value: 81.74740484429066
+    - type: manhattan_recall
+      value: 93.84309831181727
+    - type: max_accuracy
+      value: 81.74386920980926
+    - type: max_ap
+      value: 93.18281680904117
+    - type: max_f1
+      value: 87.37864077669903
+  - task:
+      type: PairClassification
+    dataset:
+      type: google-research-datasets/paws-x
+      name: MTEB PawsX (fr)
+      config: fr
+      split: test
+      revision: 8a04d940a42cd40658986fdd8e3da561533a3646
+    metrics:
+    - type: cos_sim_accuracy
+      value: 61.1
+    - type: cos_sim_ap
+      value: 60.75603519868964
+    - type: cos_sim_f1
+      value: 62.78646780647509
+    - type: cos_sim_precision
+      value: 46.74972914409534
+    - type: cos_sim_recall
+      value: 95.5703211517165
+    - type: dot_accuracy
+      value: 61.1
+    - type: dot_ap
+      value: 60.74807680023078
+    - type: dot_f1
+      value: 62.78646780647509
+    - type: dot_precision
+      value: 46.74972914409534
+    - type: dot_recall
+      value: 95.5703211517165
+    - type: euclidean_accuracy
+      value: 61.1
+    - type: euclidean_ap
+      value: 60.756144387817734
+    - type: euclidean_f1
+      value: 62.78646780647509
+    - type: euclidean_precision
+      value: 46.74972914409534
+    - type: euclidean_recall
+      value: 95.5703211517165
+    - type: manhattan_accuracy
+      value: 61.150000000000006
+    - type: manhattan_ap
+      value: 60.685188544775116
+    - type: manhattan_f1
+      value: 62.7721335268505
+    - type: manhattan_precision
+      value: 46.6810577441986
+    - type: manhattan_recall
+      value: 95.79180509413068
+    - type: max_accuracy
+      value: 61.150000000000006
+    - type: max_ap
+      value: 60.756144387817734
+    - type: max_f1
+      value: 62.78646780647509
+  - task:
+      type: STS
+    dataset:
+      type: Lajavaness/SICK-fr
+      name: MTEB SICKFr
+      config: default
+      split: test
+      revision: e077ab4cf4774a1e36d86d593b150422fafd8e8a
+    metrics:
+    - type: cos_sim_pearson
+      value: 83.1543597030015
+    - type: cos_sim_spearman
+      value: 77.10092303546944
+    - type: euclidean_pearson
+      value: 80.27115846915481
+    - type: euclidean_spearman
+      value: 77.10092516058822
+    - type: manhattan_pearson
+      value: 80.30090425968062
+    - type: manhattan_spearman
+      value: 77.09423647945061
+  - task:
+      type: STS
+    dataset:
+      type: mteb/sts22-crosslingual-sts
+      name: MTEB STS22 (fr)
+      config: fr
+      split: test
+      revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
+    metrics:
+    - type: cos_sim_pearson
+      value: 79.20797144286122
+    - type: cos_sim_spearman
+      value: 80.31452099282514
+    - type: euclidean_pearson
+      value: 78.43621396282957
+    - type: euclidean_spearman
+      value: 80.31452099282514
+    - type: manhattan_pearson
+      value: 78.29678738374866
+    - type: manhattan_spearman
+      value: 79.93185465249057
+  - task:
+      type: STS
+    dataset:
+      type: PhilipMay/stsb_multi_mt
+      name: MTEB STSBenchmarkMultilingualSTS (fr)
+      config: fr
+      split: test
+      revision: 29afa2569dcedaaa2fe6a3dcfebab33d28b82e8c
+    metrics:
+    - type: cos_sim_pearson
+      value: 84.69215133897265
+    - type: cos_sim_spearman
+      value: 84.35617480959016
+    - type: euclidean_pearson
+      value: 83.85371663492563
+    - type: euclidean_spearman
+      value: 84.35617480959016
+    - type: manhattan_pearson
+      value: 83.85857789722276
+    - type: manhattan_spearman
+      value: 84.30794186513978
+  - task:
+      type: Summarization
+    dataset:
+      type: lyon-nlp/summarization-summeval-fr-p2p
+      name: MTEB SummEvalFr
+      config: default
+      split: test
+      revision: b385812de6a9577b6f4d0f88c6a6e35395a94054
+    metrics:
+    - type: cos_sim_pearson
+      value: 29.187176809104393
+    - type: cos_sim_spearman
+      value: 29.65160679657583
+    - type: dot_pearson
+      value: 29.18717349611766
+    - type: dot_spearman
+      value: 29.65160679657583
+  - task:
+      type: Reranking
+    dataset:
+      type: lyon-nlp/mteb-fr-reranking-syntec-s2p
+      name: MTEB SyntecReranking
+      config: default
+      split: test
+      revision: daf0863838cd9e3ba50544cdce3ac2b338a1b0ad
+    metrics:
+    - type: map
+      value: 82.76666666666667
+    - type: mrr
+      value: 82.76666666666667
+    - type: nAUC_map_diff1
+      value: 52.548913230162405
+    - type: nAUC_map_max
+      value: -2.824065935620183
+    - type: nAUC_mrr_diff1
+      value: 52.548913230162405
+    - type: nAUC_mrr_max
+      value: -2.824065935620183
+  - task:
+      type: Retrieval
+    dataset:
+      type: lyon-nlp/mteb-fr-retrieval-syntec-s2p
+      name: MTEB SyntecRetrieval
+      config: default
+      split: test
+      revision: 19661ccdca4dfc2d15122d776b61685f48c68ca9
+    metrics:
+    - type: map_at_1
+      value: 57.99999999999999
+    - type: map_at_10
+      value: 72.356
+    - type: map_at_100
+      value: 72.625
+    - type: map_at_1000
+      value: 72.625
+    - type: map_at_20
+      value: 72.625
+    - type: map_at_3
+      value: 70.333
+    - type: map_at_5
+      value: 71.48299999999999
+    - type: mrr_at_1
+      value: 57.99999999999999
+    - type: mrr_at_10
+      value: 72.35634920634922
+    - type: mrr_at_100
+      value: 72.62532693914275
+    - type: mrr_at_1000
+      value: 72.62532693914275
+    - type: mrr_at_20
+      value: 72.62532693914275
+    - type: mrr_at_3
+      value: 70.33333333333333
+    - type: mrr_at_5
+      value: 71.48333333333333
+    - type: nauc_map_at_1000_diff1
+      value: 57.27081552588017
+    - type: nauc_map_at_1000_max
+      value: 13.401922890723771
+    - type: nauc_map_at_100_diff1
+      value: 57.27081552588017
+    - type: nauc_map_at_100_max
+      value: 13.401922890723771
+    - type: nauc_map_at_10_diff1
+      value: 57.39952453922188
+    - type: nauc_map_at_10_max
+      value: 14.093164837730344
+    - type: nauc_map_at_1_diff1
+      value: 57.23800679107291
+    - type: nauc_map_at_1_max
+      value: 11.039846765533865
+    - type: nauc_map_at_20_diff1
+      value: 57.27081552588017
+    - type: nauc_map_at_20_max
+      value: 13.401922890723771
+    - type: nauc_map_at_3_diff1
+      value: 58.14875247321224
+    - type: nauc_map_at_3_max
+      value: 14.538312305676238
+    - type: nauc_map_at_5_diff1
+      value: 57.34940275695991
+    - type: nauc_map_at_5_max
+      value: 13.675180459395065
+    - type: nauc_mrr_at_1000_diff1
+      value: 57.27081552588017
+    - type: nauc_mrr_at_1000_max
+      value: 13.401922890723771
+    - type: nauc_mrr_at_100_diff1
+      value: 57.27081552588017
+    - type: nauc_mrr_at_100_max
+      value: 13.401922890723771
+    - type: nauc_mrr_at_10_diff1
+      value: 57.39952453922188
+    - type: nauc_mrr_at_10_max
+      value: 14.093164837730344
+    - type: nauc_mrr_at_1_diff1
+      value: 57.23800679107291
+    - type: nauc_mrr_at_1_max
+      value: 11.039846765533865
+    - type: nauc_mrr_at_20_diff1
+      value: 57.27081552588017
+    - type: nauc_mrr_at_20_max
+      value: 13.401922890723771
+    - type: nauc_mrr_at_3_diff1
+      value: 58.14875247321224
+    - type: nauc_mrr_at_3_max
+      value: 14.538312305676238
+    - type: nauc_mrr_at_5_diff1
+      value: 57.34940275695991
+    - type: nauc_mrr_at_5_max
+      value: 13.675180459395065
+    - type: nauc_ndcg_at_1000_diff1
+      value: 57.38511684819052
+    - type: nauc_ndcg_at_1000_max
+      value: 13.993185568467656
+    - type: nauc_ndcg_at_100_diff1
+      value: 57.38511684819052
+    - type: nauc_ndcg_at_100_max
+      value: 13.993185568467656
+    - type: nauc_ndcg_at_10_diff1
+      value: 57.93396526410134
+    - type: nauc_ndcg_at_10_max
+      value: 17.16319020800824
+    - type: nauc_ndcg_at_1_diff1
+      value: 57.23800679107291
+    - type: nauc_ndcg_at_1_max
+      value: 11.039846765533865
+    - type: nauc_ndcg_at_20_diff1
+      value: 57.38511684819052
+    - type: nauc_ndcg_at_20_max
+      value: 13.993185568467656
+    - type: nauc_ndcg_at_3_diff1
+      value: 59.36410104940948
+    - type: nauc_ndcg_at_3_max
+      value: 17.128826753860732
+    - type: nauc_ndcg_at_5_diff1
+      value: 57.71094150714742
+    - type: nauc_ndcg_at_5_max
+      value: 15.62784584334318
+    - type: nauc_precision_at_1000_diff1
+      value: nan
+    - type: nauc_precision_at_1000_max
+      value: nan
+    - type: nauc_precision_at_100_diff1
+      value: nan
+    - type: nauc_precision_at_100_max
+      value: nan
+    - type: nauc_precision_at_10_diff1
+      value: 66.79505135387465
+    - type: nauc_precision_at_10_max
+      value: 70.47152194211033
+    - type: nauc_precision_at_1_diff1
+      value: 57.23800679107291
+    - type: nauc_precision_at_1_max
+      value: 11.039846765533865
+    - type: nauc_precision_at_20_diff1
+      value: 100.0
+    - type: nauc_precision_at_20_max
+      value: 100.0
+    - type: nauc_precision_at_3_diff1
+      value: 65.65896518060521
+    - type: nauc_precision_at_3_max
+      value: 30.198503091441538
+    - type: nauc_precision_at_5_diff1
+      value: 60.04201680672288
+    - type: nauc_precision_at_5_max
+      value: 29.000933706816145
+    - type: nauc_recall_at_1000_diff1
+      value: nan
+    - type: nauc_recall_at_1000_max
+      value: nan
+    - type: nauc_recall_at_100_diff1
+      value: nan
+    - type: nauc_recall_at_100_max
+      value: nan
+    - type: nauc_recall_at_10_diff1
+      value: 66.7950513538749
+    - type: nauc_recall_at_10_max
+      value: 70.47152194211012
+    - type: nauc_recall_at_1_diff1
+      value: 57.23800679107291
+    - type: nauc_recall_at_1_max
+      value: 11.039846765533865
+    - type: nauc_recall_at_20_diff1
+      value: nan
+    - type: nauc_recall_at_20_max
+      value: nan
+    - type: nauc_recall_at_3_diff1
+      value: 65.65896518060525
+    - type: nauc_recall_at_3_max
+      value: 30.19850309144154
+    - type: nauc_recall_at_5_diff1
+      value: 60.0420168067226
+    - type: nauc_recall_at_5_max
+      value: 29.000933706816
+    - type: ndcg_at_1
+      value: 57.99999999999999
+    - type: ndcg_at_10
+      value: 78.19800000000001
+    - type: ndcg_at_100
+      value: 79.199
+    - type: ndcg_at_1000
+      value: 79.199
+    - type: ndcg_at_20
+      value: 79.199
+    - type: ndcg_at_3
+      value: 74.119
+    - type: ndcg_at_5
+      value: 76.184
+    - type: precision_at_1
+      value: 57.99999999999999
+    - type: precision_at_10
+      value: 9.6
+    - type: precision_at_100
+      value: 1.0
+    - type: precision_at_1000
+      value: 0.1
+    - type: precision_at_20
+      value: 5.0
+    - type: precision_at_3
+      value: 28.333000000000002
+    - type: precision_at_5
+      value: 18.0
+    - type: recall_at_1
+      value: 57.99999999999999
+    - type: recall_at_10
+      value: 96.0
+    - type: recall_at_100
+      value: 100.0
+    - type: recall_at_1000
+      value: 100.0
+    - type: recall_at_20
+      value: 100.0
+    - type: recall_at_3
+      value: 85.0
+    - type: recall_at_5
+      value: 90.0
+  - task:
+      type: Retrieval
+    dataset:
+      type: jinaai/xpqa
+      name: MTEB XPQARetrieval (fr)
+      config: fr
+      split: test
+      revision: c99d599f0a6ab9b85b065da6f9d94f9cf731679f
+    metrics:
+    - type: map_at_1
+      value: 35.256
+    - type: map_at_10
+      value: 54.071999999999996
+    - type: map_at_100
+      value: 55.435
+    - type: map_at_1000
+      value: 55.53
+    - type: map_at_20
+      value: 54.855
+    - type: map_at_3
+      value: 48.762
+    - type: map_at_5
+      value: 51.949999999999996
+    - type: mrr_at_1
+      value: 56.34178905206942
+    - type: mrr_at_10
+      value: 63.30843240723078
+    - type: mrr_at_100
+      value: 63.92076387626982
+    - type: mrr_at_1000
+      value: 63.9435076251571
+    - type: mrr_at_20
+      value: 63.64110365119446
+    - type: mrr_at_3
+      value: 61.526479750778805
+    - type: mrr_at_5
+      value: 62.38762794837559
+    - type: nauc_map_at_1000_diff1
+      value: 45.88957885553053
+    - type: nauc_map_at_1000_max
+      value: 52.59013482565773
+    - type: nauc_map_at_100_diff1
+      value: 45.84948517422948
+    - type: nauc_map_at_100_max
+      value: 52.55839985303019
+    - type: nauc_map_at_10_diff1
+      value: 45.763486819482196
+    - type: nauc_map_at_10_max
+      value: 52.09054118600712
+    - type: nauc_map_at_1_diff1
+      value: 55.521911317670835
+    - type: nauc_map_at_1_max
+      value: 34.68779817675579
+    - type: nauc_map_at_20_diff1
+      value: 45.757369615751884
+    - type: nauc_map_at_20_max
+      value: 52.44708031434436
+    - type: nauc_map_at_3_diff1
+      value: 47.798733616712056
+    - type: nauc_map_at_3_max
+      value: 46.87976781177451
+    - type: nauc_map_at_5_diff1
+      value: 46.215964363315884
+    - type: nauc_map_at_5_max
+      value: 50.5765276342371
+    - type: nauc_mrr_at_1000_diff1
+      value: 55.110400510640766
+    - type: nauc_mrr_at_1000_max
+      value: 62.66171179919574
+    - type: nauc_mrr_at_100_diff1
+      value: 55.10166012000449
+    - type: nauc_mrr_at_100_max
+      value: 62.66269343813773
+    - type: nauc_mrr_at_10_diff1
+      value: 55.087629594751256
+    - type: nauc_mrr_at_10_max
+      value: 62.69978067726044
+    - type: nauc_mrr_at_1_diff1
+      value: 57.446957773325956
+    - type: nauc_mrr_at_1_max
+      value: 63.22109004948565
+    - type: nauc_mrr_at_20_diff1
+      value: 55.067208283222016
+    - type: nauc_mrr_at_20_max
+      value: 62.66935664582939
+    - type: nauc_mrr_at_3_diff1
+      value: 55.18870023658262
+    - type: nauc_mrr_at_3_max
+      value: 62.597473549957996
+    - type: nauc_mrr_at_5_diff1
+      value: 54.87651100155316
+    - type: nauc_mrr_at_5_max
+      value: 62.72845534030979
+    - type: nauc_ndcg_at_1000_diff1
+      value: 47.81162759706491
+    - type: nauc_ndcg_at_1000_max
+      value: 56.26337910947683
+    - type: nauc_ndcg_at_100_diff1
+      value: 47.119077388160676
+    - type: nauc_ndcg_at_100_max
+      value: 55.82354642959063
+    - type: nauc_ndcg_at_10_diff1
+      value: 46.784535879466496
+    - type: nauc_ndcg_at_10_max
+      value: 54.63437116703429
+    - type: nauc_ndcg_at_1_diff1
+      value: 57.446957773325956
+    - type: nauc_ndcg_at_1_max
+      value: 63.22109004948565
+    - type: nauc_ndcg_at_20_diff1
+      value: 46.756211545478905
+    - type: nauc_ndcg_at_20_max
+      value: 55.228917899613826
+    - type: nauc_ndcg_at_3_diff1
+      value: 47.66168453462149
+    - type: nauc_ndcg_at_3_max
+      value: 54.39836405112981
+    - type: nauc_ndcg_at_5_diff1
+      value: 46.97491630908418
+    - type: nauc_ndcg_at_5_max
+      value: 53.284362953526184
+    - type: nauc_precision_at_1000_diff1
+      value: -14.959536048875451
+    - type: nauc_precision_at_1000_max
+      value: 19.740731727610537
+    - type: nauc_precision_at_100_diff1
+      value: -10.329364912432421
+    - type: nauc_precision_at_100_max
+      value: 27.80165890502952
+    - type: nauc_precision_at_10_diff1
+      value: 0.7865296687777561
+    - type: nauc_precision_at_10_max
+      value: 38.46291415400641
+    - type: nauc_precision_at_1_diff1
+      value: 57.446957773325956
+    - type: nauc_precision_at_1_max
+      value: 63.22109004948565
+    - type: nauc_precision_at_20_diff1
+      value: -2.2696079664009385
+    - type: nauc_precision_at_20_max
+      value: 35.38696590671127
+    - type: nauc_precision_at_3_diff1
+      value: 14.016444043719714
+    - type: nauc_precision_at_3_max
+      value: 46.68119169258843
+    - type: nauc_precision_at_5_diff1
+      value: 6.466134759646741
+    - type: nauc_precision_at_5_max
+      value: 43.245171983039256
+    - type: nauc_recall_at_1000_diff1
+      value: 10.588340380461794
+    - type: nauc_recall_at_1000_max
+      value: 45.913607560926515
+    - type: nauc_recall_at_100_diff1
+      value: 28.995302681864565
+    - type: nauc_recall_at_100_max
+      value: 42.67608149089844
+    - type: nauc_recall_at_10_diff1
+      value: 38.958724392572854
+    - type: nauc_recall_at_10_max
+      value: 47.455666375173315
+    - type: nauc_recall_at_1_diff1
+      value: 55.521911317670835
+    - type: nauc_recall_at_1_max
+      value: 34.68779817675579
+    - type: nauc_recall_at_20_diff1
+      value: 36.623788206732016
+    - type: nauc_recall_at_20_max
+      value: 46.654888587980174
+    - type: nauc_recall_at_3_diff1
+      value: 43.46749373705754
+    - type: nauc_recall_at_3_max
+      value: 42.55592784672105
+    - type: nauc_recall_at_5_diff1
+      value: 40.49018957054939
+    - type: nauc_recall_at_5_max
+      value: 46.86884862874594
+    - type: ndcg_at_1
+      value: 56.342000000000006
+    - type: ndcg_at_10
+      value: 60.01800000000001
+    - type: ndcg_at_100
+      value: 65.182
+    - type: ndcg_at_1000
+      value: 66.809
+    - type: ndcg_at_20
+      value: 61.982000000000006
+    - type: ndcg_at_3
+      value: 55.688
+    - type: ndcg_at_5
+      value: 56.607
+    - type: precision_at_1
+      value: 56.342000000000006
+    - type: precision_at_10
+      value: 14.005
+    - type: precision_at_100
+      value: 1.821
+    - type: precision_at_1000
+      value: 0.20500000000000002
+    - type: precision_at_20
+      value: 7.684
+    - type: precision_at_3
+      value: 34.089999999999996
+    - type: precision_at_5
+      value: 24.005000000000003
+    - type: recall_at_1
+      value: 35.256
+    - type: recall_at_10
+      value: 67.583
+    - type: recall_at_100
+      value: 88.74300000000001
+    - type: recall_at_1000
+      value: 99.163
+    - type: recall_at_20
+      value: 73.87
+    - type: recall_at_3
+      value: 53.371
+    - type: recall_at_5
+      value: 59.399
+license: apache-2.0
+---
+
+# [bilingual-embedding-base](https://huggingface.co/Lajavaness/bilingual-embedding-base)
+
+Bilingual-embedding is the Embedding Model for bilingual language: french and english. This model is a specialized sentence-embedding trained specifically for the bilingual language, leveraging the robust capabilities of [XLM-RoBERTa](https://huggingface.co/FacebookAI/xlm-roberta-base), a pre-trained language model based on the [XLM-RoBERTa](https://huggingface.co/FacebookAI/xlm-roberta-base) architecture. The model utilizes xlm-roberta to encode english-french sentences into a 1024-dimensional vector space, facilitating a wide range of applications from semantic search to text clustering. The embeddings capture the nuanced meanings of english-french sentences, reflecting both the lexical and contextual layers of the language.
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BilingualModel 
+  (1): Pooling({'word_embedding_dimension': 1024, '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()
+)
+```
+
+## Training and Fine-tuning process
+#### Stage 1: NLI Training
+- Dataset: [(SNLI+XNLI) for english+french]
+- Method: Training using Multi-Negative Ranking Loss. This stage focused on improving the model's ability to discern and rank nuanced differences in sentence semantics.
+### Stage 3: Continued Fine-tuning for Semantic Textual Similarity on STS Benchmark
+- Dataset: [STSB-fr and en]
+- Method: Fine-tuning specifically for the semantic textual similarity benchmark using Siamese BERT-Networks configured with the 'sentence-transformers' library. 
+### Stage 4: Advanced Augmentation Fine-tuning
+- Dataset: STSB with generate [silver sample from gold sample](https://www.sbert.net/examples/training/data_augmentation/README.html)
+- Method: Employed an advanced strategy using [Augmented SBERT](https://arxiv.org/abs/2010.08240) with Pair Sampling Strategies, integrating both Cross-Encoder and Bi-Encoder models. This stage further refined the embeddings by enriching the training data dynamically, enhancing the model's robustness and accuracy.
+
+
+## Usage:
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+
+sentences = ["Paris est une capitale de la France", "Paris is a capital of France"]
+
+model = SentenceTransformer('Lajavaness/bilingual-embedding-base', trust_remote_code=True)
+print(embeddings)
+
+```
+
+
+
+
+
+## Evaluation
+
+TODO
+
+## Citation
+
+    @article{conneau2019unsupervised,
+      title={Unsupervised cross-lingual representation learning at scale},
+      author={Conneau, Alexis and Khandelwal, Kartikay and Goyal, Naman and Chaudhary, Vishrav and Wenzek, Guillaume and Guzm{\'a}n, Francisco and Grave, Edouard and Ott, Myle and Zettlemoyer, Luke and Stoyanov, Veselin},
+      journal={arXiv preprint arXiv:1911.02116},
+      year={2019}
+    }
+
+	@article{reimers2019sentence,
+	   title={Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks},
+	   author={Nils Reimers, Iryna Gurevych},
+	   journal={https://arxiv.org/abs/1908.10084},
+	   year={2019}
+	}
+
+    @article{thakur2020augmented,
+      title={Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks},
+      author={Thakur, Nandan and Reimers, Nils and Daxenberger, Johannes and Gurevych, Iryna},
+      journal={arXiv e-prints},
+      pages={arXiv--2010},
+      year={2020}

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "dangvantuan/bilingual_impl",
+  "architectures": [
+    "BilingualModel"
+  ],
+  "model_type": "xlm-roberta",
+  "auto_map": {
+    "AutoConfig":"dangvantuan/bilingual_impl--config.BilingualConfig",
+    "AutoModel": "dangvantuan/bilingual_impl--modeling.BilingualModel",
+    "AutoModelForMaskedLM": "dangvantuan/bilingual_impl--modeling.BilingualForMaskedLM",
+    "AutoModelForMultipleChoice": "dangvantuan/bilingual_impl--modeling.BilingualForMultipleChoice",
+    "AutoModelForQuestionAnswering": "dangvantuan/bilingual_impl--modeling.BilingualForQuestionAnswering",
+    "AutoModelForSequenceClassification": "dangvantuan/bilingual_impl--modeling.BilingualForSequenceClassification",
+    "AutoModelForTokenClassification": "dangvantuan/bilingual_impl--modeling.BilingualForTokenClassification"
+  },  
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float16",
+  "transformers_version": "4.39.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,9 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.7.0",
+    "transformers": "4.38.2",
+    "pytorch": "2.2.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3316824a5c622bf962a0dd32bf6194f12fdfb167aa25a9494e86fd08f4c3eb0a
+size 1112197096

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1cc44ad7faaeec47241864835473fd5403f2da94673f3f764a77ebcb0a803ec
+size 17083009

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}