|
|
---
|
|
|
model-index:
|
|
|
- name: FRIDA
|
|
|
results:
|
|
|
- dataset:
|
|
|
config: default
|
|
|
name: MTEB CEDRClassification (default)
|
|
|
revision: c0ba03d058e3e1b2f3fd20518875a4563dd12db4
|
|
|
split: test
|
|
|
type: ai-forever/cedr-classification
|
|
|
metrics:
|
|
|
- type: accuracy
|
|
|
value: 64.60148777895856
|
|
|
- type: f1
|
|
|
value: 70.36630348039266
|
|
|
- type: lrap
|
|
|
value: 92.47290116896953
|
|
|
- type: main_score
|
|
|
value: 64.60148777895856
|
|
|
task:
|
|
|
type: MultilabelClassification
|
|
|
- dataset:
|
|
|
config: default
|
|
|
name: MTEB GeoreviewClassification (default)
|
|
|
revision: 3765c0d1de6b7d264bc459433c45e5a75513839c
|
|
|
split: test
|
|
|
type: ai-forever/georeview-classification
|
|
|
metrics:
|
|
|
- type: accuracy
|
|
|
value: 57.70996093750001
|
|
|
- type: f1
|
|
|
value: 53.18542982057098
|
|
|
- type: f1_weighted
|
|
|
value: 53.17663229582108
|
|
|
- type: main_score
|
|
|
value: 57.70996093750001
|
|
|
task:
|
|
|
type: Classification
|
|
|
- dataset:
|
|
|
config: default
|
|
|
name: MTEB GeoreviewClusteringP2P (default)
|
|
|
revision: 97a313c8fc85b47f13f33e7e9a95c1ad888c7fec
|
|
|
split: test
|
|
|
type: ai-forever/georeview-clustering-p2p
|
|
|
metrics:
|
|
|
- type: main_score
|
|
|
value: 78.25468393043356
|
|
|
- type: v_measure
|
|
|
value: 78.25468393043356
|
|
|
- type: v_measure_std
|
|
|
value: 0.5094366871364238
|
|
|
task:
|
|
|
type: Clustering
|
|
|
- dataset:
|
|
|
config: default
|
|
|
name: MTEB HeadlineClassification (default)
|
|
|
revision: 2fe05ee6b5832cda29f2ef7aaad7b7fe6a3609eb
|
|
|
split: test
|
|
|
type: ai-forever/headline-classification
|
|
|
metrics:
|
|
|
- type: accuracy
|
|
|
value: 89.0185546875
|
|
|
- type: f1
|
|
|
value: 88.993933120612
|
|
|
- type: f1_weighted
|
|
|
value: 88.99276764225768
|
|
|
- type: main_score
|
|
|
value: 89.0185546875
|
|
|
task:
|
|
|
type: Classification
|
|
|
- dataset:
|
|
|
config: default
|
|
|
name: MTEB InappropriatenessClassification (default)
|
|
|
revision: 601651fdc45ef243751676e62dd7a19f491c0285
|
|
|
split: test
|
|
|
type: ai-forever/inappropriateness-classification
|
|
|
metrics:
|
|
|
- type: accuracy
|
|
|
value: 78.330078125
|
|
|
- type: ap
|
|
|
value: 73.17856750532495
|
|
|
- type: ap_weighted
|
|
|
value: 73.17856750532495
|
|
|
- type: f1
|
|
|
value: 78.20169867599041
|
|
|
- type: f1_weighted
|
|
|
value: 78.20169867599041
|
|
|
- type: main_score
|
|
|
value: 78.330078125
|
|
|
task:
|
|
|
type: Classification
|
|
|
- dataset:
|
|
|
config: default
|
|
|
name: MTEB KinopoiskClassification (default)
|
|
|
revision: 5911f26666ac11af46cb9c6849d0dc80a378af24
|
|
|
split: test
|
|
|
type: ai-forever/kinopoisk-sentiment-classification
|
|
|
metrics:
|
|
|
- type: accuracy
|
|
|
value: 70.46666666666665
|
|
|
- type: f1
|
|
|
value: 65.83951766538878
|
|
|
- type: f1_weighted
|
|
|
value: 65.83951766538878
|
|
|
- type: main_score
|
|
|
value: 70.46666666666665
|
|
|
task:
|
|
|
type: Classification
|
|
|
- dataset:
|
|
|
config: ru
|
|
|
name: MTEB MIRACLReranking (ru)
|
|
|
revision: 6d1962c527217f8927fca80f890f14f36b2802af
|
|
|
split: dev
|
|
|
type: miracl/mmteb-miracl-reranking
|
|
|
metrics:
|
|
|
- type: MAP@1(MIRACL)
|
|
|
value: 39.023
|
|
|
- type: MAP@10(MIRACL)
|
|
|
value: 60.208
|
|
|
- type: MAP@100(MIRACL)
|
|
|
value: 61.672000000000004
|
|
|
- type: MAP@1000(MIRACL)
|
|
|
value: 61.672000000000004
|
|
|
- type: MAP@20(MIRACL)
|
|
|
value: 61.30799999999999
|
|
|
- type: MAP@3(MIRACL)
|
|
|
value: 53.33
|
|
|
- type: MAP@5(MIRACL)
|
|
|
value: 57.289
|
|
|
- type: NDCG@1(MIRACL)
|
|
|
value: 63.352
|
|
|
- type: NDCG@10(MIRACL)
|
|
|
value: 66.042
|
|
|
- type: NDCG@100(MIRACL)
|
|
|
value: 68.702
|
|
|
- type: NDCG@1000(MIRACL)
|
|
|
value: 68.702
|
|
|
- type: NDCG@20(MIRACL)
|
|
|
value: 67.768
|
|
|
- type: NDCG@3(MIRACL)
|
|
|
value: 61.925
|
|
|
- type: NDCG@5(MIRACL)
|
|
|
value: 63.327
|
|
|
- type: P@1(MIRACL)
|
|
|
value: 63.352
|
|
|
- type: P@10(MIRACL)
|
|
|
value: 16.512
|
|
|
- type: P@100(MIRACL)
|
|
|
value: 1.9529999999999998
|
|
|
- type: P@1000(MIRACL)
|
|
|
value: 0.19499999999999998
|
|
|
- type: P@20(MIRACL)
|
|
|
value: 9.13
|
|
|
- type: P@3(MIRACL)
|
|
|
value: 37.878
|
|
|
- type: P@5(MIRACL)
|
|
|
value: 27.586
|
|
|
- type: Recall@1(MIRACL)
|
|
|
value: 39.023
|
|
|
- type: Recall@10(MIRACL)
|
|
|
value: 72.35000000000001
|
|
|
- type: Recall@100(MIRACL)
|
|
|
value: 79.952
|
|
|
- type: Recall@1000(MIRACL)
|
|
|
value: 79.952
|
|
|
- type: Recall@20(MIRACL)
|
|
|
value: 76.828
|
|
|
- type: Recall@3(MIRACL)
|
|
|
value: 57.769999999999996
|
|
|
- type: Recall@5(MIRACL)
|
|
|
value: 64.91900000000001
|
|
|
- type: main_score
|
|
|
value: 66.042
|
|
|
- type: nAUC_MAP@1000_diff1(MIRACL)
|
|
|
value: 27.150388833033052
|
|
|
- type: nAUC_MAP@1000_max(MIRACL)
|
|
|
value: 55.15672274267081
|
|
|
- type: nAUC_MAP@1000_std(MIRACL)
|
|
|
value: 30.088939934575553
|
|
|
- type: nAUC_MAP@100_diff1(MIRACL)
|
|
|
value: 27.150388833033052
|
|
|
- type: nAUC_MAP@100_max(MIRACL)
|
|
|
value: 55.15672274267081
|
|
|
- type: nAUC_MAP@100_std(MIRACL)
|
|
|
value: 30.088939934575553
|
|
|
- type: nAUC_MAP@10_diff1(MIRACL)
|
|
|
value: 27.853691773641742
|
|
|
- type: nAUC_MAP@10_max(MIRACL)
|
|
|
value: 52.89390350055654
|
|
|
- type: nAUC_MAP@10_std(MIRACL)
|
|
|
value: 28.08732516551691
|
|
|
- type: nAUC_MAP@1_diff1(MIRACL)
|
|
|
value: 43.23179150244192
|
|
|
- type: nAUC_MAP@1_max(MIRACL)
|
|
|
value: 29.923943954188864
|
|
|
- type: nAUC_MAP@1_std(MIRACL)
|
|
|
value: 7.447084370195121
|
|
|
- type: nAUC_MAP@20_diff1(MIRACL)
|
|
|
value: 27.328384072311675
|
|
|
- type: nAUC_MAP@20_max(MIRACL)
|
|
|
value: 54.60286379835721
|
|
|
- type: nAUC_MAP@20_std(MIRACL)
|
|
|
value: 29.8084128980043
|
|
|
- type: nAUC_MAP@3_diff1(MIRACL)
|
|
|
value: 31.244971536944554
|
|
|
- type: nAUC_MAP@3_max(MIRACL)
|
|
|
value: 43.63984692803854
|
|
|
- type: nAUC_MAP@3_std(MIRACL)
|
|
|
value: 18.609234683765887
|
|
|
- type: nAUC_MAP@5_diff1(MIRACL)
|
|
|
value: 29.088760492638286
|
|
|
- type: nAUC_MAP@5_max(MIRACL)
|
|
|
value: 48.30474364461509
|
|
|
- type: nAUC_MAP@5_std(MIRACL)
|
|
|
value: 23.817514353844224
|
|
|
- type: nAUC_NDCG@1000_diff1(MIRACL)
|
|
|
value: 23.12754356408408
|
|
|
- type: nAUC_NDCG@1000_max(MIRACL)
|
|
|
value: 64.24894553363303
|
|
|
- type: nAUC_NDCG@1000_std(MIRACL)
|
|
|
value: 38.19318050598967
|
|
|
- type: nAUC_NDCG@100_diff1(MIRACL)
|
|
|
value: 23.12754356408408
|
|
|
- type: nAUC_NDCG@100_max(MIRACL)
|
|
|
value: 64.24894553363303
|
|
|
- type: nAUC_NDCG@100_std(MIRACL)
|
|
|
value: 38.19318050598967
|
|
|
- type: nAUC_NDCG@10_diff1(MIRACL)
|
|
|
value: 24.779856373697275
|
|
|
- type: nAUC_NDCG@10_max(MIRACL)
|
|
|
value: 60.4054459738118
|
|
|
- type: nAUC_NDCG@10_std(MIRACL)
|
|
|
value: 35.148950441182784
|
|
|
- type: nAUC_NDCG@1_diff1(MIRACL)
|
|
|
value: 35.605865569438556
|
|
|
- type: nAUC_NDCG@1_max(MIRACL)
|
|
|
value: 65.77787399715454
|
|
|
- type: nAUC_NDCG@1_std(MIRACL)
|
|
|
value: 34.34726892885082
|
|
|
- type: nAUC_NDCG@20_diff1(MIRACL)
|
|
|
value: 23.71231783125691
|
|
|
- type: nAUC_NDCG@20_max(MIRACL)
|
|
|
value: 62.89676599488004
|
|
|
- type: nAUC_NDCG@20_std(MIRACL)
|
|
|
value: 37.697052941884316
|
|
|
- type: nAUC_NDCG@3_diff1(MIRACL)
|
|
|
value: 26.109027741640865
|
|
|
- type: nAUC_NDCG@3_max(MIRACL)
|
|
|
value: 56.22356793638693
|
|
|
- type: nAUC_NDCG@3_std(MIRACL)
|
|
|
value: 29.9437568508688
|
|
|
- type: nAUC_NDCG@5_diff1(MIRACL)
|
|
|
value: 25.98644715327336
|
|
|
- type: nAUC_NDCG@5_max(MIRACL)
|
|
|
value: 56.25032008404774
|
|
|
- type: nAUC_NDCG@5_std(MIRACL)
|
|
|
value: 31.581899860862578
|
|
|
- type: nAUC_P@1000_diff1(MIRACL)
|
|
|
value: -18.29912787064644
|
|
|
- type: nAUC_P@1000_max(MIRACL)
|
|
|
value: 31.811344878776087
|
|
|
- type: nAUC_P@1000_std(MIRACL)
|
|
|
value: 30.163820183304914
|
|
|
- type: nAUC_P@100_diff1(MIRACL)
|
|
|
value: -18.299127870646405
|
|
|
- type: nAUC_P@100_max(MIRACL)
|
|
|
value: 31.811344878776133
|
|
|
- type: nAUC_P@100_std(MIRACL)
|
|
|
value: 30.163820183304956
|
|
|
- type: nAUC_P@10_diff1(MIRACL)
|
|
|
value: -15.96416268531149
|
|
|
- type: nAUC_P@10_max(MIRACL)
|
|
|
value: 36.989578896466526
|
|
|
- type: nAUC_P@10_std(MIRACL)
|
|
|
value: 34.54507111688143
|
|
|
- type: nAUC_P@1_diff1(MIRACL)
|
|
|
value: 35.605865569438556
|
|
|
- type: nAUC_P@1_max(MIRACL)
|
|
|
value: 65.77787399715454
|
|
|
- type: nAUC_P@1_std(MIRACL)
|
|
|
value: 34.34726892885082
|
|
|
- type: nAUC_P@20_diff1(MIRACL)
|
|
|
value: -17.443963421383287
|
|
|
- type: nAUC_P@20_max(MIRACL)
|
|
|
value: 34.309618168778385
|
|
|
- type: nAUC_P@20_std(MIRACL)
|
|
|
value: 33.38820956485373
|
|
|
- type: nAUC_P@3_diff1(MIRACL)
|
|
|
value: -8.533621861815652
|
|
|
- type: nAUC_P@3_max(MIRACL)
|
|
|
value: 45.90408386776497
|
|
|
- type: nAUC_P@3_std(MIRACL)
|
|
|
value: 34.50459351305535
|
|
|
- type: nAUC_P@5_diff1(MIRACL)
|
|
|
value: -13.207968899314865
|
|
|
- type: nAUC_P@5_max(MIRACL)
|
|
|
value: 40.37718282248973
|
|
|
- type: nAUC_P@5_std(MIRACL)
|
|
|
value: 35.601417332196206
|
|
|
- type: nAUC_Recall@1000_diff1(MIRACL)
|
|
|
value: 7.907304198177226
|
|
|
- type: nAUC_Recall@1000_max(MIRACL)
|
|
|
value: 77.82197832361145
|
|
|
- type: nAUC_Recall@1000_std(MIRACL)
|
|
|
value: 52.66957487246724
|
|
|
- type: nAUC_Recall@100_diff1(MIRACL)
|
|
|
value: 7.907304198177226
|
|
|
- type: nAUC_Recall@100_max(MIRACL)
|
|
|
value: 77.82197832361145
|
|
|
- type: nAUC_Recall@100_std(MIRACL)
|
|
|
value: 52.66957487246724
|
|
|
- type: nAUC_Recall@10_diff1(MIRACL)
|
|
|
value: 15.498121023488693
|
|
|
- type: nAUC_Recall@10_max(MIRACL)
|
|
|
value: 62.24320529338724
|
|
|
- type: nAUC_Recall@10_std(MIRACL)
|
|
|
value: 40.60221460946224
|
|
|
- type: nAUC_Recall@1_diff1(MIRACL)
|
|
|
value: 43.23179150244192
|
|
|
- type: nAUC_Recall@1_max(MIRACL)
|
|
|
value: 29.923943954188864
|
|
|
- type: nAUC_Recall@1_std(MIRACL)
|
|
|
value: 7.447084370195121
|
|
|
- type: nAUC_Recall@20_diff1(MIRACL)
|
|
|
value: 11.457044176116248
|
|
|
- type: nAUC_Recall@20_max(MIRACL)
|
|
|
value: 70.3493054342368
|
|
|
- type: nAUC_Recall@20_std(MIRACL)
|
|
|
value: 49.27124296325928
|
|
|
- type: nAUC_Recall@3_diff1(MIRACL)
|
|
|
value: 25.12077828977941
|
|
|
- type: nAUC_Recall@3_max(MIRACL)
|
|
|
value: 42.903379317937166
|
|
|
- type: nAUC_Recall@3_std(MIRACL)
|
|
|
value: 20.324501722161497
|
|
|
- type: nAUC_Recall@5_diff1(MIRACL)
|
|
|
value: 20.925701235197977
|
|
|
- type: nAUC_Recall@5_max(MIRACL)
|
|
|
value: 49.85323960390812
|
|
|
- type: nAUC_Recall@5_std(MIRACL)
|
|
|
value: 29.04484539530469
|
|
|
task:
|
|
|
type: Reranking
|
|
|
- dataset:
|
|
|
config: ru
|
|
|
name: MTEB MIRACLRetrieval (ru)
|
|
|
revision: main
|
|
|
split: dev
|
|
|
type: miracl/mmteb-miracl
|
|
|
metrics:
|
|
|
- type: main_score
|
|
|
value: 71.882
|
|
|
- type: map_at_1
|
|
|
value: 37.913000000000004
|
|
|
- type: map_at_10
|
|
|
value: 62.604000000000006
|
|
|
- type: map_at_100
|
|
|
value: 64.925
|
|
|
- type: map_at_1000
|
|
|
value: 64.992
|
|
|
- type: map_at_20
|
|
|
value: 64.081
|
|
|
- type: map_at_3
|
|
|
value: 55.212
|
|
|
- type: map_at_5
|
|
|
value: 59.445
|
|
|
- type: mrr_at_1
|
|
|
value: 73.24281150159744
|
|
|
- type: mrr_at_10
|
|
|
value: 81.65043866321825
|
|
|
- type: mrr_at_100
|
|
|
value: 81.85391378818977
|
|
|
- type: mrr_at_1000
|
|
|
value: 81.85753390802569
|
|
|
- type: mrr_at_20
|
|
|
value: 81.81045606130179
|
|
|
- type: mrr_at_3
|
|
|
value: 80.56443024494146
|
|
|
- type: mrr_at_5
|
|
|
value: 81.30724174653893
|
|
|
- type: nauc_map_at_1000_diff1
|
|
|
value: 26.962150235593356
|
|
|
- type: nauc_map_at_1000_max
|
|
|
value: 29.234958037854568
|
|
|
- type: nauc_map_at_1000_std
|
|
|
value: -2.4294465103633884
|
|
|
- type: nauc_map_at_100_diff1
|
|
|
value: 26.92990252114163
|
|
|
- type: nauc_map_at_100_max
|
|
|
value: 29.206328533120118
|
|
|
- type: nauc_map_at_100_std
|
|
|
value: -2.437371090941197
|
|
|
- type: nauc_map_at_10_diff1
|
|
|
value: 25.758265691179226
|
|
|
- type: nauc_map_at_10_max
|
|
|
value: 26.949978490795317
|
|
|
- type: nauc_map_at_10_std
|
|
|
value: -5.484961002106038
|
|
|
- type: nauc_map_at_1_diff1
|
|
|
value: 34.70849461278043
|
|
|
- type: nauc_map_at_1_max
|
|
|
value: 12.778570893623042
|
|
|
- type: nauc_map_at_1_std
|
|
|
value: -13.018292652743938
|
|
|
- type: nauc_map_at_20_diff1
|
|
|
value: 26.659923008218268
|
|
|
- type: nauc_map_at_20_max
|
|
|
value: 28.341440871568185
|
|
|
- type: nauc_map_at_20_std
|
|
|
value: -3.614549844913084
|
|
|
- type: nauc_map_at_3_diff1
|
|
|
value: 27.197629021438203
|
|
|
- type: nauc_map_at_3_max
|
|
|
value: 20.701094874050856
|
|
|
- type: nauc_map_at_3_std
|
|
|
value: -12.062992301112041
|
|
|
- type: nauc_map_at_5_diff1
|
|
|
value: 25.51793537203295
|
|
|
- type: nauc_map_at_5_max
|
|
|
value: 23.80396771243794
|
|
|
- type: nauc_map_at_5_std
|
|
|
value: -8.920465695323575
|
|
|
- type: nauc_mrr_at_1000_diff1
|
|
|
value: 45.14819989592967
|
|
|
- type: nauc_mrr_at_1000_max
|
|
|
value: 53.29202156141053
|
|
|
- type: nauc_mrr_at_1000_std
|
|
|
value: 18.037336462510524
|
|
|
- type: nauc_mrr_at_100_diff1
|
|
|
value: 45.15287600228451
|
|
|
- type: nauc_mrr_at_100_max
|
|
|
value: 53.29979751928615
|
|
|
- type: nauc_mrr_at_100_std
|
|
|
value: 18.04996604778386
|
|
|
- type: nauc_mrr_at_10_diff1
|
|
|
value: 44.96865105944474
|
|
|
- type: nauc_mrr_at_10_max
|
|
|
value: 53.53323465323092
|
|
|
- type: nauc_mrr_at_10_std
|
|
|
value: 18.25001344917689
|
|
|
- type: nauc_mrr_at_1_diff1
|
|
|
value: 46.16604946873163
|
|
|
- type: nauc_mrr_at_1_max
|
|
|
value: 48.573651103547874
|
|
|
- type: nauc_mrr_at_1_std
|
|
|
value: 13.764871626330915
|
|
|
- type: nauc_mrr_at_20_diff1
|
|
|
value: 45.11925458479102
|
|
|
- type: nauc_mrr_at_20_max
|
|
|
value: 53.35685123898342
|
|
|
- type: nauc_mrr_at_20_std
|
|
|
value: 18.127344968819905
|
|
|
- type: nauc_mrr_at_3_diff1
|
|
|
value: 45.377195452730234
|
|
|
- type: nauc_mrr_at_3_max
|
|
|
value: 53.35146309217089
|
|
|
- type: nauc_mrr_at_3_std
|
|
|
value: 17.47105877186237
|
|
|
- type: nauc_mrr_at_5_diff1
|
|
|
value: 45.00525578771549
|
|
|
- type: nauc_mrr_at_5_max
|
|
|
value: 53.76227254707128
|
|
|
- type: nauc_mrr_at_5_std
|
|
|
value: 18.437290060746957
|
|
|
- type: nauc_ndcg_at_1000_diff1
|
|
|
value: 31.19215594457491
|
|
|
- type: nauc_ndcg_at_1000_max
|
|
|
value: 38.09555406458668
|
|
|
- type: nauc_ndcg_at_1000_std
|
|
|
value: 7.225628621238009
|
|
|
- type: nauc_ndcg_at_100_diff1
|
|
|
value: 30.726331247999934
|
|
|
- type: nauc_ndcg_at_100_max
|
|
|
value: 37.81369589418277
|
|
|
- type: nauc_ndcg_at_100_std
|
|
|
value: 7.242855238555071
|
|
|
- type: nauc_ndcg_at_10_diff1
|
|
|
value: 27.514048333744835
|
|
|
- type: nauc_ndcg_at_10_max
|
|
|
value: 33.10990399385253
|
|
|
- type: nauc_ndcg_at_10_std
|
|
|
value: 0.3051899572112002
|
|
|
- type: nauc_ndcg_at_1_diff1
|
|
|
value: 47.06089085235751
|
|
|
- type: nauc_ndcg_at_1_max
|
|
|
value: 47.7300872370495
|
|
|
- type: nauc_ndcg_at_1_std
|
|
|
value: 12.468605493613916
|
|
|
- type: nauc_ndcg_at_20_diff1
|
|
|
value: 29.404215438764496
|
|
|
- type: nauc_ndcg_at_20_max
|
|
|
value: 35.26967886796471
|
|
|
- type: nauc_ndcg_at_20_std
|
|
|
value: 3.7214697890813353
|
|
|
- type: nauc_ndcg_at_3_diff1
|
|
|
value: 29.448848639643067
|
|
|
- type: nauc_ndcg_at_3_max
|
|
|
value: 33.85912412370657
|
|
|
- type: nauc_ndcg_at_3_std
|
|
|
value: 0.895453646819452
|
|
|
- type: nauc_ndcg_at_5_diff1
|
|
|
value: 26.916649012613526
|
|
|
- type: nauc_ndcg_at_5_max
|
|
|
value: 30.899005979291644
|
|
|
- type: nauc_ndcg_at_5_std
|
|
|
value: -1.0001575639156615
|
|
|
- type: nauc_precision_at_1000_diff1
|
|
|
value: -8.492004667432635
|
|
|
- type: nauc_precision_at_1000_max
|
|
|
value: 14.970190384017679
|
|
|
- type: nauc_precision_at_1000_std
|
|
|
value: 32.871386621137816
|
|
|
- type: nauc_precision_at_100_diff1
|
|
|
value: -8.287314133999967
|
|
|
- type: nauc_precision_at_100_max
|
|
|
value: 17.794821961284736
|
|
|
- type: nauc_precision_at_100_std
|
|
|
value: 35.092483550562
|
|
|
- type: nauc_precision_at_10_diff1
|
|
|
value: -7.594128993028063
|
|
|
- type: nauc_precision_at_10_max
|
|
|
value: 24.691446370325732
|
|
|
- type: nauc_precision_at_10_std
|
|
|
value: 30.126552282608493
|
|
|
- type: nauc_precision_at_1_diff1
|
|
|
value: 47.06089085235751
|
|
|
- type: nauc_precision_at_1_max
|
|
|
value: 47.7300872370495
|
|
|
- type: nauc_precision_at_1_std
|
|
|
value: 12.468605493613916
|
|
|
- type: nauc_precision_at_20_diff1
|
|
|
value: -6.503872195775146
|
|
|
- type: nauc_precision_at_20_max
|
|
|
value: 21.789730053141312
|
|
|
- type: nauc_precision_at_20_std
|
|
|
value: 32.61349377558794
|
|
|
- type: nauc_precision_at_3_diff1
|
|
|
value: 0.67417079971061
|
|
|
- type: nauc_precision_at_3_max
|
|
|
value: 30.793871354370662
|
|
|
- type: nauc_precision_at_3_std
|
|
|
value: 18.35266479252011
|
|
|
- type: nauc_precision_at_5_diff1
|
|
|
value: -7.088881730215777
|
|
|
- type: nauc_precision_at_5_max
|
|
|
value: 26.539771712769006
|
|
|
- type: nauc_precision_at_5_std
|
|
|
value: 24.116262291865834
|
|
|
- type: nauc_recall_at_1000_diff1
|
|
|
value: 34.53263588412461
|
|
|
- type: nauc_recall_at_1000_max
|
|
|
value: 63.54157869100173
|
|
|
- type: nauc_recall_at_1000_std
|
|
|
value: 64.19854844792808
|
|
|
- type: nauc_recall_at_100_diff1
|
|
|
value: 22.86564728642275
|
|
|
- type: nauc_recall_at_100_max
|
|
|
value: 40.350507162549825
|
|
|
- type: nauc_recall_at_100_std
|
|
|
value: 29.24492545863015
|
|
|
- type: nauc_recall_at_10_diff1
|
|
|
value: 15.384818367225009
|
|
|
- type: nauc_recall_at_10_max
|
|
|
value: 24.41108571453699
|
|
|
- type: nauc_recall_at_10_std
|
|
|
value: -3.9216160585776323
|
|
|
- type: nauc_recall_at_1_diff1
|
|
|
value: 34.70849461278043
|
|
|
- type: nauc_recall_at_1_max
|
|
|
value: 12.778570893623042
|
|
|
- type: nauc_recall_at_1_std
|
|
|
value: -13.018292652743938
|
|
|
- type: nauc_recall_at_20_diff1
|
|
|
value: 18.122499000084208
|
|
|
- type: nauc_recall_at_20_max
|
|
|
value: 26.63104220179424
|
|
|
- type: nauc_recall_at_20_std
|
|
|
value: 3.969217732521512
|
|
|
- type: nauc_recall_at_3_diff1
|
|
|
value: 21.413050725250116
|
|
|
- type: nauc_recall_at_3_max
|
|
|
value: 16.18894988386887
|
|
|
- type: nauc_recall_at_3_std
|
|
|
value: -15.24884339282375
|
|
|
- type: nauc_recall_at_5_diff1
|
|
|
value: 16.35673072212927
|
|
|
- type: nauc_recall_at_5_max
|
|
|
value: 18.607003829267846
|
|
|
- type: nauc_recall_at_5_std
|
|
|
value: -10.463525876945454
|
|
|
- type: ndcg_at_1
|
|
|
value: 72.923
|
|
|
- type: ndcg_at_10
|
|
|
value: 71.882
|
|
|
- type: ndcg_at_100
|
|
|
value: 77.09899999999999
|
|
|
- type: ndcg_at_1000
|
|
|
value: 77.835
|
|
|
- type: ndcg_at_20
|
|
|
value: 74.497
|
|
|
- type: ndcg_at_3
|
|
|
value: 68.504
|
|
|
- type: ndcg_at_5
|
|
|
value: 69.068
|
|
|
- type: precision_at_1
|
|
|
value: 72.923
|
|
|
- type: precision_at_10
|
|
|
value: 19.936
|
|
|
- type: precision_at_100
|
|
|
value: 2.6310000000000002
|
|
|
- type: precision_at_1000
|
|
|
value: 0.27799999999999997
|
|
|
- type: precision_at_20
|
|
|
value: 11.33
|
|
|
- type: precision_at_3
|
|
|
value: 45.927
|
|
|
- type: precision_at_5
|
|
|
value: 33.131
|
|
|
- type: recall_at_1
|
|
|
value: 37.913000000000004
|
|
|
- type: recall_at_10
|
|
|
value: 78.365
|
|
|
- type: recall_at_100
|
|
|
value: 94.348
|
|
|
- type: recall_at_1000
|
|
|
value: 98.187
|
|
|
- type: recall_at_20
|
|
|
value: 85.229
|
|
|
- type: recall_at_3
|
|
|
value: 61.42999999999999
|
|
|
- type: recall_at_5
|
|
|
value: 69.56700000000001
|
|
|
task:
|
|
|
type: Retrieval
|
|
|
- dataset:
|
|
|
config: ru
|
|
|
name: MTEB MassiveIntentClassification (ru)
|
|
|
revision: 4672e20407010da34463acc759c162ca9734bca6
|
|
|
split: test
|
|
|
type: mteb/amazon_massive_intent
|
|
|
metrics:
|
|
|
- type: accuracy
|
|
|
value: 79.11903160726294
|
|
|
- type: f1
|
|
|
value: 76.22609082694545
|
|
|
- type: f1_weighted
|
|
|
value: 77.81461248063566
|
|
|
- type: main_score
|
|
|
value: 79.11903160726294
|
|
|
task:
|
|
|
type: Classification
|
|
|
- dataset:
|
|
|
config: ru
|
|
|
name: MTEB MassiveScenarioClassification (ru)
|
|
|
revision: fad2c6e8459f9e1c45d9315f4953d921437d70f8
|
|
|
split: test
|
|
|
type: mteb/amazon_massive_scenario
|
|
|
metrics:
|
|
|
- type: accuracy
|
|
|
value: 88.80632145258912
|
|
|
- type: f1
|
|
|
value: 87.53157475314829
|
|
|
- type: f1_weighted
|
|
|
value: 88.22733432521495
|
|
|
- type: main_score
|
|
|
value: 88.80632145258912
|
|
|
task:
|
|
|
type: Classification
|
|
|
- dataset:
|
|
|
config: default
|
|
|
name: MTEB RUParaPhraserSTS (default)
|
|
|
revision: 43265056790b8f7c59e0139acb4be0a8dad2c8f4
|
|
|
split: test
|
|
|
type: merionum/ru_paraphraser
|
|
|
metrics:
|
|
|
- type: cosine_pearson
|
|
|
value: 72.70307124858925
|
|
|
- type: cosine_spearman
|
|
|
value: 78.09439086920204
|
|
|
- type: euclidean_pearson
|
|
|
value: 76.2033672014715
|
|
|
- type: euclidean_spearman
|
|
|
value: 78.09439086920204
|
|
|
- type: main_score
|
|
|
value: 78.09439086920204
|
|
|
- type: manhattan_pearson
|
|
|
value: 76.11750470223116
|
|
|
- type: manhattan_spearman
|
|
|
value: 78.01081063503413
|
|
|
- type: pearson
|
|
|
value: 72.70307124858925
|
|
|
- type: spearman
|
|
|
value: 78.09439086920204
|
|
|
task:
|
|
|
type: STS
|
|
|
- dataset:
|
|
|
config: default
|
|
|
name: MTEB RiaNewsRetrieval (default)
|
|
|
revision: 82374b0bbacda6114f39ff9c5b925fa1512ca5d7
|
|
|
split: test
|
|
|
type: ai-forever/ria-news-retrieval
|
|
|
metrics:
|
|
|
- type: main_score
|
|
|
value: 86.819
|
|
|
- type: map_at_1
|
|
|
value: 78.79
|
|
|
- type: map_at_10
|
|
|
value: 84.516
|
|
|
- type: map_at_100
|
|
|
value: 84.68
|
|
|
- type: map_at_1000
|
|
|
value: 84.685
|
|
|
- type: map_at_20
|
|
|
value: 84.624
|
|
|
- type: map_at_3
|
|
|
value: 83.722
|
|
|
- type: map_at_5
|
|
|
value: 84.246
|
|
|
- type: mrr_at_1
|
|
|
value: 78.78
|
|
|
- type: mrr_at_10
|
|
|
value: 84.51815476190441
|
|
|
- type: mrr_at_100
|
|
|
value: 84.68390840473289
|
|
|
- type: mrr_at_1000
|
|
|
value: 84.68947095200002
|
|
|
- type: mrr_at_20
|
|
|
value: 84.62958130822527
|
|
|
- type: mrr_at_3
|
|
|
value: 83.74499999999964
|
|
|
- type: mrr_at_5
|
|
|
value: 84.23849999999955
|
|
|
- type: nauc_map_at_1000_diff1
|
|
|
value: 82.09914867708899
|
|
|
- type: nauc_map_at_1000_max
|
|
|
value: 43.02024854784386
|
|
|
- type: nauc_map_at_1000_std
|
|
|
value: -22.919695880762777
|
|
|
- type: nauc_map_at_100_diff1
|
|
|
value: 82.09705922783733
|
|
|
- type: nauc_map_at_100_max
|
|
|
value: 43.02697379581718
|
|
|
- type: nauc_map_at_100_std
|
|
|
value: -22.90719212899522
|
|
|
- type: nauc_map_at_10_diff1
|
|
|
value: 82.04404594672894
|
|
|
- type: nauc_map_at_10_max
|
|
|
value: 43.06752103182731
|
|
|
- type: nauc_map_at_10_std
|
|
|
value: -23.007870153273576
|
|
|
- type: nauc_map_at_1_diff1
|
|
|
value: 83.89134152210333
|
|
|
- type: nauc_map_at_1_max
|
|
|
value: 38.083626428503415
|
|
|
- type: nauc_map_at_1_std
|
|
|
value: -25.817960401194252
|
|
|
- type: nauc_map_at_20_diff1
|
|
|
value: 82.08534662247806
|
|
|
- type: nauc_map_at_20_max
|
|
|
value: 43.074305042312346
|
|
|
- type: nauc_map_at_20_std
|
|
|
value: -22.91785703613217
|
|
|
- type: nauc_map_at_3_diff1
|
|
|
value: 81.7967508697558
|
|
|
- type: nauc_map_at_3_max
|
|
|
value: 42.90927479098251
|
|
|
- type: nauc_map_at_3_std
|
|
|
value: -24.01312203859392
|
|
|
- type: nauc_map_at_5_diff1
|
|
|
value: 81.90704517505098
|
|
|
- type: nauc_map_at_5_max
|
|
|
value: 43.05204677044616
|
|
|
- type: nauc_map_at_5_std
|
|
|
value: -23.267331507554896
|
|
|
- type: nauc_mrr_at_1000_diff1
|
|
|
value: 82.11902348082472
|
|
|
- type: nauc_mrr_at_1000_max
|
|
|
value: 43.04118936353063
|
|
|
- type: nauc_mrr_at_1000_std
|
|
|
value: -22.858804296830773
|
|
|
- type: nauc_mrr_at_100_diff1
|
|
|
value: 82.11685562002263
|
|
|
- type: nauc_mrr_at_100_max
|
|
|
value: 43.0482537895494
|
|
|
- type: nauc_mrr_at_100_std
|
|
|
value: -22.84431127787993
|
|
|
- type: nauc_mrr_at_10_diff1
|
|
|
value: 82.06909958688058
|
|
|
- type: nauc_mrr_at_10_max
|
|
|
value: 43.07921689466605
|
|
|
- type: nauc_mrr_at_10_std
|
|
|
value: -22.957623576663234
|
|
|
- type: nauc_mrr_at_1_diff1
|
|
|
value: 83.91147637794326
|
|
|
- type: nauc_mrr_at_1_max
|
|
|
value: 37.91917159543152
|
|
|
- type: nauc_mrr_at_1_std
|
|
|
value: -26.141868289283266
|
|
|
- type: nauc_mrr_at_20_diff1
|
|
|
value: 82.10314004731809
|
|
|
- type: nauc_mrr_at_20_max
|
|
|
value: 43.09295406509764
|
|
|
- type: nauc_mrr_at_20_std
|
|
|
value: -22.862091782178787
|
|
|
- type: nauc_mrr_at_3_diff1
|
|
|
value: 81.82117067269036
|
|
|
- type: nauc_mrr_at_3_max
|
|
|
value: 42.94628953323521
|
|
|
- type: nauc_mrr_at_3_std
|
|
|
value: -23.852510312400714
|
|
|
- type: nauc_mrr_at_5_diff1
|
|
|
value: 81.92857441701598
|
|
|
- type: nauc_mrr_at_5_max
|
|
|
value: 43.129719354492934
|
|
|
- type: nauc_mrr_at_5_std
|
|
|
value: -23.145342272624085
|
|
|
- type: nauc_ndcg_at_1000_diff1
|
|
|
value: 81.75015729717991
|
|
|
- type: nauc_ndcg_at_1000_max
|
|
|
value: 44.7266586308995
|
|
|
- type: nauc_ndcg_at_1000_std
|
|
|
value: -20.60663899715267
|
|
|
- type: nauc_ndcg_at_100_diff1
|
|
|
value: 81.6897808298767
|
|
|
- type: nauc_ndcg_at_100_max
|
|
|
value: 44.99492791287099
|
|
|
- type: nauc_ndcg_at_100_std
|
|
|
value: -20.09637266506936
|
|
|
- type: nauc_ndcg_at_10_diff1
|
|
|
value: 81.46290312197337
|
|
|
- type: nauc_ndcg_at_10_max
|
|
|
value: 45.30218378452244
|
|
|
- type: nauc_ndcg_at_10_std
|
|
|
value: -20.70393523891777
|
|
|
- type: nauc_ndcg_at_1_diff1
|
|
|
value: 83.89134152210333
|
|
|
- type: nauc_ndcg_at_1_max
|
|
|
value: 38.083626428503415
|
|
|
- type: nauc_ndcg_at_1_std
|
|
|
value: -25.817960401194252
|
|
|
- type: nauc_ndcg_at_20_diff1
|
|
|
value: 81.61080772657213
|
|
|
- type: nauc_ndcg_at_20_max
|
|
|
value: 45.36571800492172
|
|
|
- type: nauc_ndcg_at_20_std
|
|
|
value: -20.278763852504042
|
|
|
- type: nauc_ndcg_at_3_diff1
|
|
|
value: 80.95965359410461
|
|
|
- type: nauc_ndcg_at_3_max
|
|
|
value: 44.756971949205834
|
|
|
- type: nauc_ndcg_at_3_std
|
|
|
value: -23.07797617717319
|
|
|
- type: nauc_ndcg_at_5_diff1
|
|
|
value: 81.12417712163976
|
|
|
- type: nauc_ndcg_at_5_max
|
|
|
value: 45.15727381406512
|
|
|
- type: nauc_ndcg_at_5_std
|
|
|
value: -21.52861766165519
|
|
|
- type: nauc_precision_at_1000_diff1
|
|
|
value: 76.80566850396093
|
|
|
- type: nauc_precision_at_1000_max
|
|
|
value: 82.45685370922442
|
|
|
- type: nauc_precision_at_1000_std
|
|
|
value: 46.93570976777808
|
|
|
- type: nauc_precision_at_100_diff1
|
|
|
value: 77.21645520953484
|
|
|
- type: nauc_precision_at_100_max
|
|
|
value: 73.43604108309935
|
|
|
- type: nauc_precision_at_100_std
|
|
|
value: 31.978176891671367
|
|
|
- type: nauc_precision_at_10_diff1
|
|
|
value: 77.88251664302092
|
|
|
- type: nauc_precision_at_10_max
|
|
|
value: 60.58112638995018
|
|
|
- type: nauc_precision_at_10_std
|
|
|
value: -3.674424315180332
|
|
|
- type: nauc_precision_at_1_diff1
|
|
|
value: 83.89134152210333
|
|
|
- type: nauc_precision_at_1_max
|
|
|
value: 38.083626428503415
|
|
|
- type: nauc_precision_at_1_std
|
|
|
value: -25.817960401194252
|
|
|
- type: nauc_precision_at_20_diff1
|
|
|
value: 78.16426786697438
|
|
|
- type: nauc_precision_at_20_max
|
|
|
value: 66.0723612699222
|
|
|
- type: nauc_precision_at_20_std
|
|
|
value: 6.121527084555938
|
|
|
- type: nauc_precision_at_3_diff1
|
|
|
value: 77.43122492166451
|
|
|
- type: nauc_precision_at_3_max
|
|
|
value: 52.50727288548085
|
|
|
- type: nauc_precision_at_3_std
|
|
|
value: -19.036076920799427
|
|
|
- type: nauc_precision_at_5_diff1
|
|
|
value: 77.1127254320532
|
|
|
- type: nauc_precision_at_5_max
|
|
|
value: 56.100901899221135
|
|
|
- type: nauc_precision_at_5_std
|
|
|
value: -12.009191140844198
|
|
|
- type: nauc_recall_at_1000_diff1
|
|
|
value: 76.80566850396035
|
|
|
- type: nauc_recall_at_1000_max
|
|
|
value: 82.45685370922577
|
|
|
- type: nauc_recall_at_1000_std
|
|
|
value: 46.93570976777776
|
|
|
- type: nauc_recall_at_100_diff1
|
|
|
value: 77.21645520953459
|
|
|
- type: nauc_recall_at_100_max
|
|
|
value: 73.43604108310011
|
|
|
- type: nauc_recall_at_100_std
|
|
|
value: 31.978176891671993
|
|
|
- type: nauc_recall_at_10_diff1
|
|
|
value: 77.88251664302089
|
|
|
- type: nauc_recall_at_10_max
|
|
|
value: 60.58112638994999
|
|
|
- type: nauc_recall_at_10_std
|
|
|
value: -3.6744243151805427
|
|
|
- type: nauc_recall_at_1_diff1
|
|
|
value: 83.89134152210333
|
|
|
- type: nauc_recall_at_1_max
|
|
|
value: 38.083626428503415
|
|
|
- type: nauc_recall_at_1_std
|
|
|
value: -25.817960401194252
|
|
|
- type: nauc_recall_at_20_diff1
|
|
|
value: 78.16426786697409
|
|
|
- type: nauc_recall_at_20_max
|
|
|
value: 66.07236126992217
|
|
|
- type: nauc_recall_at_20_std
|
|
|
value: 6.121527084555941
|
|
|
- type: nauc_recall_at_3_diff1
|
|
|
value: 77.43122492166454
|
|
|
- type: nauc_recall_at_3_max
|
|
|
value: 52.507272885480816
|
|
|
- type: nauc_recall_at_3_std
|
|
|
value: -19.036076920799776
|
|
|
- type: nauc_recall_at_5_diff1
|
|
|
value: 77.11272543205318
|
|
|
- type: nauc_recall_at_5_max
|
|
|
value: 56.10090189922128
|
|
|
- type: nauc_recall_at_5_std
|
|
|
value: -12.009191140843809
|
|
|
- type: ndcg_at_1
|
|
|
value: 78.79
|
|
|
- type: ndcg_at_10
|
|
|
value: 86.819
|
|
|
- type: ndcg_at_100
|
|
|
value: 87.599
|
|
|
- type: ndcg_at_1000
|
|
|
value: 87.761
|
|
|
- type: ndcg_at_20
|
|
|
value: 87.208
|
|
|
- type: ndcg_at_3
|
|
|
value: 85.222
|
|
|
- type: ndcg_at_5
|
|
|
value: 86.164
|
|
|
- type: precision_at_1
|
|
|
value: 78.79
|
|
|
- type: precision_at_10
|
|
|
value: 9.384
|
|
|
- type: precision_at_100
|
|
|
value: 0.975
|
|
|
- type: precision_at_1000
|
|
|
value: 0.099
|
|
|
- type: precision_at_20
|
|
|
value: 4.769
|
|
|
- type: precision_at_3
|
|
|
value: 29.842999999999996
|
|
|
- type: precision_at_5
|
|
|
value: 18.362000000000002
|
|
|
- type: recall_at_1
|
|
|
value: 78.79
|
|
|
- type: recall_at_10
|
|
|
value: 93.84
|
|
|
- type: recall_at_100
|
|
|
value: 97.45
|
|
|
- type: recall_at_1000
|
|
|
value: 98.76
|
|
|
- type: recall_at_20
|
|
|
value: 95.37
|
|
|
- type: recall_at_3
|
|
|
value: 89.53
|
|
|
- type: recall_at_5
|
|
|
value: 91.81
|
|
|
task:
|
|
|
type: Retrieval
|
|
|
- dataset:
|
|
|
config: default
|
|
|
name: MTEB RuBQReranking (default)
|
|
|
revision: 2e96b8f098fa4b0950fc58eacadeb31c0d0c7fa2
|
|
|
split: test
|
|
|
type: ai-forever/rubq-reranking
|
|
|
metrics:
|
|
|
- type: main_score
|
|
|
value: 77.07394404835635
|
|
|
- type: map
|
|
|
value: 77.07394404835635
|
|
|
- type: mrr
|
|
|
value: 82.53144412718882
|
|
|
- type: nAUC_map_diff1
|
|
|
value: 45.29805217456628
|
|
|
- type: nAUC_map_max
|
|
|
value: 34.39894042439188
|
|
|
- type: nAUC_map_std
|
|
|
value: 21.11309674418275
|
|
|
- type: nAUC_mrr_diff1
|
|
|
value: 54.783994737367046
|
|
|
- type: nAUC_mrr_max
|
|
|
value: 45.68526733900048
|
|
|
- type: nAUC_mrr_std
|
|
|
value: 28.22466385500339
|
|
|
task:
|
|
|
type: Reranking
|
|
|
- dataset:
|
|
|
config: default
|
|
|
name: MTEB RuBQRetrieval (default)
|
|
|
revision: e19b6ffa60b3bc248e0b41f4cc37c26a55c2a67b
|
|
|
split: test
|
|
|
type: ai-forever/rubq-retrieval
|
|
|
metrics:
|
|
|
- type: main_score
|
|
|
value: 72.392
|
|
|
- type: map_at_1
|
|
|
value: 47.370000000000005
|
|
|
- type: map_at_10
|
|
|
value: 65.503
|
|
|
- type: map_at_100
|
|
|
value: 66.38
|
|
|
- type: map_at_1000
|
|
|
value: 66.42099999999999
|
|
|
- type: map_at_20
|
|
|
value: 66.071
|
|
|
- type: map_at_3
|
|
|
value: 61.439
|
|
|
- type: map_at_5
|
|
|
value: 63.922999999999995
|
|
|
- type: mrr_at_1
|
|
|
value: 67.37588652482269
|
|
|
- type: mrr_at_10
|
|
|
value: 76.0066747345116
|
|
|
- type: mrr_at_100
|
|
|
value: 76.25754138969413
|
|
|
- type: mrr_at_1000
|
|
|
value: 76.26968825657428
|
|
|
- type: mrr_at_20
|
|
|
value: 76.17548265904622
|
|
|
- type: mrr_at_3
|
|
|
value: 74.61583924349881
|
|
|
- type: mrr_at_5
|
|
|
value: 75.46690307328608
|
|
|
- type: nauc_map_at_1000_diff1
|
|
|
value: 42.52570720187294
|
|
|
- type: nauc_map_at_1000_max
|
|
|
value: 37.40318318724238
|
|
|
- type: nauc_map_at_1000_std
|
|
|
value: 0.6037788201535506
|
|
|
- type: nauc_map_at_100_diff1
|
|
|
value: 42.493410029691226
|
|
|
- type: nauc_map_at_100_max
|
|
|
value: 37.39802489244377
|
|
|
- type: nauc_map_at_100_std
|
|
|
value: 0.6071359951887154
|
|
|
- type: nauc_map_at_10_diff1
|
|
|
value: 42.09833519659916
|
|
|
- type: nauc_map_at_10_max
|
|
|
value: 37.1184138958874
|
|
|
- type: nauc_map_at_10_std
|
|
|
value: 0.4063543094010351
|
|
|
- type: nauc_map_at_1_diff1
|
|
|
value: 49.56605205141156
|
|
|
- type: nauc_map_at_1_max
|
|
|
value: 26.251096698710384
|
|
|
- type: nauc_map_at_1_std
|
|
|
value: -4.580748485387834
|
|
|
- type: nauc_map_at_20_diff1
|
|
|
value: 42.33372393482018
|
|
|
- type: nauc_map_at_20_max
|
|
|
value: 37.416955604649985
|
|
|
- type: nauc_map_at_20_std
|
|
|
value: 0.6050577802787294
|
|
|
- type: nauc_map_at_3_diff1
|
|
|
value: 42.362234475441845
|
|
|
- type: nauc_map_at_3_max
|
|
|
value: 34.56001379838821
|
|
|
- type: nauc_map_at_3_std
|
|
|
value: -1.507636598929042
|
|
|
- type: nauc_map_at_5_diff1
|
|
|
value: 42.0202264882535
|
|
|
- type: nauc_map_at_5_max
|
|
|
value: 36.64306050200848
|
|
|
- type: nauc_map_at_5_std
|
|
|
value: -0.09509025708798424
|
|
|
- type: nauc_mrr_at_1000_diff1
|
|
|
value: 58.99601742026931
|
|
|
- type: nauc_mrr_at_1000_max
|
|
|
value: 49.61561872452777
|
|
|
- type: nauc_mrr_at_1000_std
|
|
|
value: 2.3956102974352356
|
|
|
- type: nauc_mrr_at_100_diff1
|
|
|
value: 58.9865943101085
|
|
|
- type: nauc_mrr_at_100_max
|
|
|
value: 49.6248111507265
|
|
|
- type: nauc_mrr_at_100_std
|
|
|
value: 2.411155095066369
|
|
|
- type: nauc_mrr_at_10_diff1
|
|
|
value: 58.81758131092919
|
|
|
- type: nauc_mrr_at_10_max
|
|
|
value: 49.780365572616695
|
|
|
- type: nauc_mrr_at_10_std
|
|
|
value: 2.7068696565195944
|
|
|
- type: nauc_mrr_at_1_diff1
|
|
|
value: 61.67036882487055
|
|
|
- type: nauc_mrr_at_1_max
|
|
|
value: 45.455271042821714
|
|
|
- type: nauc_mrr_at_1_std
|
|
|
value: -0.9370526815458349
|
|
|
- type: nauc_mrr_at_20_diff1
|
|
|
value: 58.93674818203478
|
|
|
- type: nauc_mrr_at_20_max
|
|
|
value: 49.703218108625215
|
|
|
- type: nauc_mrr_at_20_std
|
|
|
value: 2.4473106598190415
|
|
|
- type: nauc_mrr_at_3_diff1
|
|
|
value: 59.046856598788445
|
|
|
- type: nauc_mrr_at_3_max
|
|
|
value: 49.37161726123392
|
|
|
- type: nauc_mrr_at_3_std
|
|
|
value: 1.5110936686701506
|
|
|
- type: nauc_mrr_at_5_diff1
|
|
|
value: 58.92289378915668
|
|
|
- type: nauc_mrr_at_5_max
|
|
|
value: 49.847638994134144
|
|
|
- type: nauc_mrr_at_5_std
|
|
|
value: 2.420421880131702
|
|
|
- type: nauc_ndcg_at_1000_diff1
|
|
|
value: 45.56062215161734
|
|
|
- type: nauc_ndcg_at_1000_max
|
|
|
value: 41.507152286702
|
|
|
- type: nauc_ndcg_at_1000_std
|
|
|
value: 2.79388283208751
|
|
|
- type: nauc_ndcg_at_100_diff1
|
|
|
value: 44.84064192570408
|
|
|
- type: nauc_ndcg_at_100_max
|
|
|
value: 41.50353573562353
|
|
|
- type: nauc_ndcg_at_100_std
|
|
|
value: 3.1804999773629357
|
|
|
- type: nauc_ndcg_at_10_diff1
|
|
|
value: 43.341482144213614
|
|
|
- type: nauc_ndcg_at_10_max
|
|
|
value: 41.159590898395074
|
|
|
- type: nauc_ndcg_at_10_std
|
|
|
value: 2.945242338240843
|
|
|
- type: nauc_ndcg_at_1_diff1
|
|
|
value: 62.23623985611396
|
|
|
- type: nauc_ndcg_at_1_max
|
|
|
value: 45.04945770947091
|
|
|
- type: nauc_ndcg_at_1_std
|
|
|
value: -0.8804967656575725
|
|
|
- type: nauc_ndcg_at_20_diff1
|
|
|
value: 43.905372612093664
|
|
|
- type: nauc_ndcg_at_20_max
|
|
|
value: 41.797709837872446
|
|
|
- type: nauc_ndcg_at_20_std
|
|
|
value: 3.1853356915569653
|
|
|
- type: nauc_ndcg_at_3_diff1
|
|
|
value: 44.18163998834299
|
|
|
- type: nauc_ndcg_at_3_max
|
|
|
value: 38.352891017864636
|
|
|
- type: nauc_ndcg_at_3_std
|
|
|
value: -0.8235767021150929
|
|
|
- type: nauc_ndcg_at_5_diff1
|
|
|
value: 43.41374688421302
|
|
|
- type: nauc_ndcg_at_5_max
|
|
|
value: 40.390365601593956
|
|
|
- type: nauc_ndcg_at_5_std
|
|
|
value: 1.6743650108127537
|
|
|
- type: nauc_precision_at_1000_diff1
|
|
|
value: -9.711058370691381
|
|
|
- type: nauc_precision_at_1000_max
|
|
|
value: 6.97321343449286
|
|
|
- type: nauc_precision_at_1000_std
|
|
|
value: 7.933531916622121
|
|
|
- type: nauc_precision_at_100_diff1
|
|
|
value: -8.247029644152319
|
|
|
- type: nauc_precision_at_100_max
|
|
|
value: 10.86740140944616
|
|
|
- type: nauc_precision_at_100_std
|
|
|
value: 9.581885544675918
|
|
|
- type: nauc_precision_at_10_diff1
|
|
|
value: -2.409043695429943
|
|
|
- type: nauc_precision_at_10_max
|
|
|
value: 21.04733206074314
|
|
|
- type: nauc_precision_at_10_std
|
|
|
value: 10.03334651647101
|
|
|
- type: nauc_precision_at_1_diff1
|
|
|
value: 62.23623985611396
|
|
|
- type: nauc_precision_at_1_max
|
|
|
value: 45.04945770947091
|
|
|
- type: nauc_precision_at_1_std
|
|
|
value: -0.8804967656575725
|
|
|
- type: nauc_precision_at_20_diff1
|
|
|
value: -5.230303656931621
|
|
|
- type: nauc_precision_at_20_max
|
|
|
value: 17.77799716919181
|
|
|
- type: nauc_precision_at_20_std
|
|
|
value: 10.739127998618654
|
|
|
- type: nauc_precision_at_3_diff1
|
|
|
value: 10.40376424999862
|
|
|
- type: nauc_precision_at_3_max
|
|
|
value: 30.933333400254035
|
|
|
- type: nauc_precision_at_3_std
|
|
|
value: 6.126209127968004
|
|
|
- type: nauc_precision_at_5_diff1
|
|
|
value: 3.147398101830739
|
|
|
- type: nauc_precision_at_5_max
|
|
|
value: 27.1746309955971
|
|
|
- type: nauc_precision_at_5_std
|
|
|
value: 8.874723615388788
|
|
|
- type: nauc_recall_at_1000_diff1
|
|
|
value: 5.055940692380908
|
|
|
- type: nauc_recall_at_1000_max
|
|
|
value: 22.42031123370267
|
|
|
- type: nauc_recall_at_1000_std
|
|
|
value: 27.75476692527869
|
|
|
- type: nauc_recall_at_100_diff1
|
|
|
value: 17.86391178198642
|
|
|
- type: nauc_recall_at_100_max
|
|
|
value: 34.776134863678955
|
|
|
- type: nauc_recall_at_100_std
|
|
|
value: 18.96377158778504
|
|
|
- type: nauc_recall_at_10_diff1
|
|
|
value: 24.863097695413597
|
|
|
- type: nauc_recall_at_10_max
|
|
|
value: 37.697411651507444
|
|
|
- type: nauc_recall_at_10_std
|
|
|
value: 9.519849994253967
|
|
|
- type: nauc_recall_at_1_diff1
|
|
|
value: 49.56605205141156
|
|
|
- type: nauc_recall_at_1_max
|
|
|
value: 26.251096698710384
|
|
|
- type: nauc_recall_at_1_std
|
|
|
value: -4.580748485387834
|
|
|
- type: nauc_recall_at_20_diff1
|
|
|
value: 22.440602811005636
|
|
|
- type: nauc_recall_at_20_max
|
|
|
value: 39.538861316515
|
|
|
- type: nauc_recall_at_20_std
|
|
|
value: 11.363269553121468
|
|
|
- type: nauc_recall_at_3_diff1
|
|
|
value: 32.80302839873736
|
|
|
- type: nauc_recall_at_3_max
|
|
|
value: 32.53105685012729
|
|
|
- type: nauc_recall_at_3_std
|
|
|
value: -0.7140166410605693
|
|
|
- type: nauc_recall_at_5_diff1
|
|
|
value: 29.375386639154865
|
|
|
- type: nauc_recall_at_5_max
|
|
|
value: 36.91045781164083
|
|
|
- type: nauc_recall_at_5_std
|
|
|
value: 4.725419050262578
|
|
|
- type: ndcg_at_1
|
|
|
value: 67.13900000000001
|
|
|
- type: ndcg_at_10
|
|
|
value: 72.392
|
|
|
- type: ndcg_at_100
|
|
|
value: 75.25800000000001
|
|
|
- type: ndcg_at_1000
|
|
|
value: 75.982
|
|
|
- type: ndcg_at_20
|
|
|
value: 73.783
|
|
|
- type: ndcg_at_3
|
|
|
value: 67.269
|
|
|
- type: ndcg_at_5
|
|
|
value: 69.807
|
|
|
- type: precision_at_1
|
|
|
value: 67.13900000000001
|
|
|
- type: precision_at_10
|
|
|
value: 13.327
|
|
|
- type: precision_at_100
|
|
|
value: 1.5559999999999998
|
|
|
- type: precision_at_1000
|
|
|
value: 0.164
|
|
|
- type: precision_at_20
|
|
|
value: 7.119000000000001
|
|
|
- type: precision_at_3
|
|
|
value: 35.599
|
|
|
- type: precision_at_5
|
|
|
value: 23.936
|
|
|
- type: recall_at_1
|
|
|
value: 47.370000000000005
|
|
|
- type: recall_at_10
|
|
|
value: 82.16
|
|
|
- type: recall_at_100
|
|
|
value: 93.34
|
|
|
- type: recall_at_1000
|
|
|
value: 98.202
|
|
|
- type: recall_at_20
|
|
|
value: 86.687
|
|
|
- type: recall_at_3
|
|
|
value: 69.319
|
|
|
- type: recall_at_5
|
|
|
value: 75.637
|
|
|
task:
|
|
|
type: Retrieval
|
|
|
- dataset:
|
|
|
config: default
|
|
|
name: MTEB RuReviewsClassification (default)
|
|
|
revision: f6d2c31f4dc6b88f468552750bfec05b4b41b05a
|
|
|
split: test
|
|
|
type: ai-forever/ru-reviews-classification
|
|
|
metrics:
|
|
|
- type: accuracy
|
|
|
value: 75.0537109375
|
|
|
- type: f1
|
|
|
value: 74.00523205209554
|
|
|
- type: f1_weighted
|
|
|
value: 74.00436782840376
|
|
|
- type: main_score
|
|
|
value: 75.0537109375
|
|
|
task:
|
|
|
type: Classification
|
|
|
- dataset:
|
|
|
config: default
|
|
|
name: MTEB RuSTSBenchmarkSTS (default)
|
|
|
revision: 7cf24f325c6da6195df55bef3d86b5e0616f3018
|
|
|
split: test
|
|
|
type: ai-forever/ru-stsbenchmark-sts
|
|
|
metrics:
|
|
|
- type: cosine_pearson
|
|
|
value: 81.10255413476487
|
|
|
- type: cosine_spearman
|
|
|
value: 81.40020843157141
|
|
|
- type: euclidean_pearson
|
|
|
value: 81.25155479902466
|
|
|
- type: euclidean_spearman
|
|
|
value: 81.40020831064922
|
|
|
- type: main_score
|
|
|
value: 81.40020843157141
|
|
|
- type: manhattan_pearson
|
|
|
value: 81.1493715249014
|
|
|
- type: manhattan_spearman
|
|
|
value: 81.30973667941649
|
|
|
- type: pearson
|
|
|
value: 81.10255413476487
|
|
|
- type: spearman
|
|
|
value: 81.40020843157141
|
|
|
task:
|
|
|
type: STS
|
|
|
- dataset:
|
|
|
config: default
|
|
|
name: MTEB RuSciBenchGRNTIClassification (default)
|
|
|
revision: 673a610d6d3dd91a547a0d57ae1b56f37ebbf6a1
|
|
|
split: test
|
|
|
type: ai-forever/ru-scibench-grnti-classification
|
|
|
metrics:
|
|
|
- type: accuracy
|
|
|
value: 69.8974609375
|
|
|
- type: f1
|
|
|
value: 68.57837564785511
|
|
|
- type: f1_weighted
|
|
|
value: 68.59030489460784
|
|
|
- type: main_score
|
|
|
value: 69.8974609375
|
|
|
task:
|
|
|
type: Classification
|
|
|
- dataset:
|
|
|
config: default
|
|
|
name: MTEB RuSciBenchGRNTIClusteringP2P (default)
|
|
|
revision: 673a610d6d3dd91a547a0d57ae1b56f37ebbf6a1
|
|
|
split: test
|
|
|
type: ai-forever/ru-scibench-grnti-classification
|
|
|
metrics:
|
|
|
- type: main_score
|
|
|
value: 67.03880348548029
|
|
|
- type: v_measure
|
|
|
value: 67.03880348548029
|
|
|
- type: v_measure_std
|
|
|
value: 0.6126278133139618
|
|
|
task:
|
|
|
type: Clustering
|
|
|
- dataset:
|
|
|
config: default
|
|
|
name: MTEB RuSciBenchOECDClassification (default)
|
|
|
revision: 26c88e99dcaba32bb45d0e1bfc21902337f6d471
|
|
|
split: test
|
|
|
type: ai-forever/ru-scibench-oecd-classification
|
|
|
metrics:
|
|
|
- type: accuracy
|
|
|
value: 54.63378906250001
|
|
|
- type: f1
|
|
|
value: 51.34306420274629
|
|
|
- type: f1_weighted
|
|
|
value: 51.33495867493914
|
|
|
- type: main_score
|
|
|
value: 54.63378906250001
|
|
|
task:
|
|
|
type: Classification
|
|
|
- dataset:
|
|
|
config: default
|
|
|
name: MTEB RuSciBenchOECDClusteringP2P (default)
|
|
|
revision: 26c88e99dcaba32bb45d0e1bfc21902337f6d471
|
|
|
split: test
|
|
|
type: ai-forever/ru-scibench-oecd-classification
|
|
|
metrics:
|
|
|
- type: main_score
|
|
|
value: 56.55947121159027
|
|
|
- type: v_measure
|
|
|
value: 56.55947121159027
|
|
|
- type: v_measure_std
|
|
|
value: 0.5498882006880662
|
|
|
task:
|
|
|
type: Clustering
|
|
|
- dataset:
|
|
|
config: ru
|
|
|
name: MTEB STS22 (ru)
|
|
|
revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
|
|
|
split: test
|
|
|
type: mteb/sts22-crosslingual-sts
|
|
|
metrics:
|
|
|
- type: cosine_pearson
|
|
|
value: 61.833294921667914
|
|
|
- type: cosine_spearman
|
|
|
value: 63.53967536726357
|
|
|
- type: euclidean_pearson
|
|
|
value: 60.382865218855805
|
|
|
- type: euclidean_spearman
|
|
|
value: 63.53967536726357
|
|
|
- type: main_score
|
|
|
value: 63.53967536726357
|
|
|
- type: manhattan_pearson
|
|
|
value: 60.24879015304578
|
|
|
- type: manhattan_spearman
|
|
|
value: 63.42305760430092
|
|
|
- type: pearson
|
|
|
value: 61.833294921667914
|
|
|
- type: spearman
|
|
|
value: 63.53967536726357
|
|
|
task:
|
|
|
type: STS
|
|
|
- dataset:
|
|
|
config: default
|
|
|
name: MTEB SensitiveTopicsClassification (default)
|
|
|
revision: 416b34a802308eac30e4192afc0ff99bb8dcc7f2
|
|
|
split: test
|
|
|
type: ai-forever/sensitive-topics-classification
|
|
|
metrics:
|
|
|
- type: accuracy
|
|
|
value: 39.8193359375
|
|
|
- type: f1
|
|
|
value: 55.46591740935434
|
|
|
- type: lrap
|
|
|
value: 66.50980631510454
|
|
|
- type: main_score
|
|
|
value: 39.8193359375
|
|
|
task:
|
|
|
type: MultilabelClassification
|
|
|
- dataset:
|
|
|
config: default
|
|
|
name: MTEB TERRa (default)
|
|
|
revision: 7b58f24536063837d644aab9a023c62199b2a612
|
|
|
split: dev
|
|
|
type: ai-forever/terra-pairclassification
|
|
|
metrics:
|
|
|
- type: cosine_accuracy
|
|
|
value: 66.77524429967427
|
|
|
- type: cosine_accuracy_threshold
|
|
|
value: 55.58975338935852
|
|
|
- type: cosine_ap
|
|
|
value: 66.4567219323658
|
|
|
- type: cosine_f1
|
|
|
value: 70.64676616915423
|
|
|
- type: cosine_f1_threshold
|
|
|
value: 45.55969536304474
|
|
|
- type: cosine_precision
|
|
|
value: 57.028112449799195
|
|
|
- type: cosine_recall
|
|
|
value: 92.81045751633987
|
|
|
- type: dot_accuracy
|
|
|
value: 66.77524429967427
|
|
|
- type: dot_accuracy_threshold
|
|
|
value: 55.589759349823
|
|
|
- type: dot_ap
|
|
|
value: 66.4567219323658
|
|
|
- type: dot_f1
|
|
|
value: 70.64676616915423
|
|
|
- type: dot_f1_threshold
|
|
|
value: 45.55969536304474
|
|
|
- type: dot_precision
|
|
|
value: 57.028112449799195
|
|
|
- type: dot_recall
|
|
|
value: 92.81045751633987
|
|
|
- type: euclidean_accuracy
|
|
|
value: 66.77524429967427
|
|
|
- type: euclidean_accuracy_threshold
|
|
|
value: 94.24455165863037
|
|
|
- type: euclidean_ap
|
|
|
value: 66.4567219323658
|
|
|
- type: euclidean_f1
|
|
|
value: 70.64676616915423
|
|
|
- type: euclidean_f1_threshold
|
|
|
value: 104.34587001800537
|
|
|
- type: euclidean_precision
|
|
|
value: 57.028112449799195
|
|
|
- type: euclidean_recall
|
|
|
value: 92.81045751633987
|
|
|
- type: main_score
|
|
|
value: 66.4567219323658
|
|
|
- type: manhattan_accuracy
|
|
|
value: 66.77524429967427
|
|
|
- type: manhattan_accuracy_threshold
|
|
|
value: 2865.5345916748047
|
|
|
- type: manhattan_ap
|
|
|
value: 66.26659863769075
|
|
|
- type: manhattan_f1
|
|
|
value: 70.8542713567839
|
|
|
- type: manhattan_f1_threshold
|
|
|
value: 3212.3912811279297
|
|
|
- type: manhattan_precision
|
|
|
value: 57.55102040816327
|
|
|
- type: manhattan_recall
|
|
|
value: 92.15686274509804
|
|
|
- type: max_accuracy
|
|
|
value: 66.77524429967427
|
|
|
- type: max_ap
|
|
|
value: 66.4567219323658
|
|
|
- type: max_f1
|
|
|
value: 70.8542713567839
|
|
|
- type: max_precision
|
|
|
value: 57.55102040816327
|
|
|
- type: max_recall
|
|
|
value: 92.81045751633987
|
|
|
- type: similarity_accuracy
|
|
|
value: 66.77524429967427
|
|
|
- type: similarity_accuracy_threshold
|
|
|
value: 55.58975338935852
|
|
|
- type: similarity_ap
|
|
|
value: 66.4567219323658
|
|
|
- type: similarity_f1
|
|
|
value: 70.64676616915423
|
|
|
- type: similarity_f1_threshold
|
|
|
value: 45.55969536304474
|
|
|
- type: similarity_precision
|
|
|
value: 57.028112449799195
|
|
|
- type: similarity_recall
|
|
|
value: 92.81045751633987
|
|
|
task:
|
|
|
type: PairClassification
|
|
|
license: mit
|
|
|
language:
|
|
|
- ru
|
|
|
- en
|
|
|
tags:
|
|
|
- mteb
|
|
|
- transformers
|
|
|
- sentence-transformers
|
|
|
base_model: ai-forever/FRED-T5-1.7B
|
|
|
pipeline_tag: feature-extraction
|
|
|
datasets:
|
|
|
- ai-forever/solyanka
|
|
|
---
|
|
|
|
|
|
# Model Card for FRIDA |
|
|
|
|
|
<figure> |
|
|
<img src="img.jpg"> |
|
|
</figure> |
|
|
|
|
|
FRIDA is a full-scale finetuned general text embedding model inspired by denoising architecture based on T5. The model is based on the encoder part of [FRED-T5](https://arxiv.org/abs/2309.10931) model and continues research of text embedding models ([ruMTEB](https://arxiv.org/abs/2408.12503), [ru-en-RoSBERTa](https://huggingface.co/ai-forever/ru-en-RoSBERTa)). It has been pre-trained on a Russian-English dataset and fine-tuned for improved performance on the target task. |
|
|
|
|
|
For more model details please refer to our [article](https://habr.com/ru/companies/sberdevices/articles/909924/) (RU). |
|
|
|
|
|
## Usage |
|
|
|
|
|
The model can be used as is with prefixes. It is recommended to use CLS pooling. The choice of prefix and pooling depends on the task. |
|
|
|
|
|
We use the following basic rules to choose a prefix: |
|
|
- `"search_query: "` and `"search_document: "` prefixes are for answer or relevant paragraph retrieval |
|
|
- `"paraphrase: "` prefix is for symmetric paraphrasing related tasks (STS, paraphrase mining, deduplication) |
|
|
- `"categorize: "` prefix is for asymmetric matching of document title and body (e.g. news, scientific papers, social posts) |
|
|
- `"categorize_sentiment: "` prefix is for any tasks that rely on sentiment features (e.g. hate, toxic, emotion) |
|
|
- `"categorize_topic: "` prefix is intended for tasks where you need to group texts by topic |
|
|
- `"categorize_entailment: "` prefix is for textual entailment task (NLI) |
|
|
|
|
|
To better tailor the model to your needs, you can fine-tune it with relevant high-quality Russian and English datasets. |
|
|
|
|
|
Below are examples of texts encoding using the Transformers and SentenceTransformers libraries. |
|
|
|
|
|
### Transformers |
|
|
|
|
|
```python |
|
|
import torch |
|
|
import torch.nn.functional as F |
|
|
from transformers import AutoTokenizer, T5EncoderModel |
|
|
|
|
|
|
|
|
def pool(hidden_state, mask, pooling_method="cls"): |
|
|
if pooling_method == "mean": |
|
|
s = torch.sum(hidden_state * mask.unsqueeze(-1).float(), dim=1) |
|
|
d = mask.sum(axis=1, keepdim=True).float() |
|
|
return s / d |
|
|
elif pooling_method == "cls": |
|
|
return hidden_state[:, 0] |
|
|
|
|
|
inputs = [ |
|
|
# |
|
|
"paraphrase: В Ярославской области разрешили работу бань, но без посетителей", |
|
|
"categorize_entailment: Женщину доставили в больницу, за ее жизнь сейчас борются врачи.", |
|
|
"search_query: Сколько программистов нужно, чтобы вкрутить лампочку?", |
|
|
# |
|
|
"paraphrase: Ярославским баням разрешили работать без посетителей", |
|
|
"categorize_entailment: Женщину спасают врачи.", |
|
|
"search_document: Чтобы вкрутить лампочку, требуется три программиста: один напишет программу извлечения лампочки, другой — вкручивания лампочки, а третий проведет тестирование." |
|
|
] |
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained("ai-forever/FRIDA") |
|
|
model = T5EncoderModel.from_pretrained("ai-forever/FRIDA") |
|
|
|
|
|
tokenized_inputs = tokenizer(inputs, max_length=512, padding=True, truncation=True, return_tensors="pt") |
|
|
|
|
|
with torch.no_grad(): |
|
|
outputs = model(**tokenized_inputs) |
|
|
|
|
|
embeddings = pool( |
|
|
outputs.last_hidden_state, |
|
|
tokenized_inputs["attention_mask"], |
|
|
pooling_method="cls" # or try "mean" |
|
|
) |
|
|
|
|
|
embeddings = F.normalize(embeddings, p=2, dim=1) |
|
|
sim_scores = embeddings[:3] @ embeddings[3:].T |
|
|
print(sim_scores.diag().tolist()) |
|
|
# [0.9360030293464661, 0.8591322302818298, 0.728583037853241] |
|
|
``` |
|
|
|
|
|
### SentenceTransformers |
|
|
|
|
|
```python |
|
|
from sentence_transformers import SentenceTransformer |
|
|
|
|
|
inputs = [ |
|
|
# |
|
|
"paraphrase: В Ярославской области разрешили работу бань, но без посетителей", |
|
|
"categorize_entailment: Женщину доставили в больницу, за ее жизнь сейчас борются врачи.", |
|
|
"search_query: Сколько программистов нужно, чтобы вкрутить лампочку?", |
|
|
# |
|
|
"paraphrase: Ярославским баням разрешили работать без посетителей", |
|
|
"categorize_entailment: Женщину спасают врачи.", |
|
|
"search_document: Чтобы вкрутить лампочку, требуется три программиста: один напишет программу извлечения лампочки, другой — вкручивания лампочки, а третий проведет тестирование." |
|
|
] |
|
|
|
|
|
# loads model with CLS pooling |
|
|
model = SentenceTransformer("ai-forever/FRIDA") |
|
|
|
|
|
# embeddings are normalized by default |
|
|
embeddings = model.encode(inputs, convert_to_tensor=True) |
|
|
|
|
|
sim_scores = embeddings[:3] @ embeddings[3:].T |
|
|
print(sim_scores.diag().tolist()) |
|
|
# [0.9360026717185974, 0.8591331243515015, 0.7285830974578857] |
|
|
``` |
|
|
|
|
|
or using prompts (sentence-transformers>=2.4.0): |
|
|
|
|
|
```python |
|
|
from sentence_transformers import SentenceTransformer |
|
|
|
|
|
# loads model with CLS pooling |
|
|
model = SentenceTransformer("ai-forever/FRIDA") |
|
|
|
|
|
paraphrase = model.encode(["В Ярославской области разрешили работу бань, но без посетителей", "Ярославским баням разрешили работать без посетителей"], prompt_name="paraphrase") |
|
|
print(paraphrase[0] @ paraphrase[1].T) # 0.9360032 |
|
|
|
|
|
categorize_entailment = model.encode(["Женщину доставили в больницу, за ее жизнь сейчас борются врачи.", "Женщину спасают врачи."], prompt_name="categorize_entailment") |
|
|
print(categorize_entailment[0] @ categorize_entailment[1].T) # 0.8591322 |
|
|
|
|
|
query_embedding = model.encode("Сколько программистов нужно, чтобы вкрутить лампочку?", prompt_name="search_query") |
|
|
document_embedding = model.encode("Чтобы вкрутить лампочку, требуется три программиста: один напишет программу извлечения лампочки, другой — вкручивания лампочки, а третий проведет тестирование.", prompt_name="search_document") |
|
|
print(query_embedding @ document_embedding.T) # 0.7285831 |
|
|
``` |
|
|
|
|
|
## Authors |
|
|
+ [SaluteDevices](https://sberdevices.ru/) AI for B2C RnD Team. |
|
|
+ Artem Snegirev: [HF profile](https://huggingface.co/artemsnegirev), [Github](https://github.com/artemsnegirev); |
|
|
+ Anna Maksimova [HF profile](https://huggingface.co/anpalmak); |
|
|
+ Aleksandr Abramov: [HF profile](https://huggingface.co/Andrilko), [Github](https://github.com/Ab1992ao), [Kaggle Competitions Master](https://www.kaggle.com/andrilko) |
|
|
|
|
|
|
|
|
## Citation |
|
|
|
|
|
``` |
|
|
@misc{TODO |
|
|
} |
|
|
``` |
|
|
|
|
|
## Limitations |
|
|
|
|
|
The model is designed to process texts in Russian, the quality in English is unknown. Maximum input text length is limited to 512 tokens. |
