metadata
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:124788
- loss:GISTEmbedLoss
base_model: BAAI/bge-m3
widget:
- source_sentence: 其他机械、设备和有形货物租赁服务代表
sentences:
- 其他机械和设备租赁服务工作人员
- 电子和电信设备及零部件物流经理
- 工业主厨
- source_sentence: 公交车司机
sentences:
- 表演灯光设计师
- 乙烯基地板安装工
- 国际巴士司机
- source_sentence: online communication manager
sentences:
- trades union official
- social media manager
- budget manager
- source_sentence: Projektmanagerin
sentences:
- Projektmanager/Projektmanagerin
- Category-Manager
- Infanterist
- source_sentence: Volksvertreter
sentences:
- Parlamentarier
- Oberbürgermeister
- Konsul
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
- cosine_accuracy@1
- cosine_accuracy@20
- cosine_accuracy@50
- cosine_accuracy@100
- cosine_accuracy@150
- cosine_accuracy@200
- cosine_precision@1
- cosine_precision@20
- cosine_precision@50
- cosine_precision@100
- cosine_precision@150
- cosine_precision@200
- cosine_recall@1
- cosine_recall@20
- cosine_recall@50
- cosine_recall@100
- cosine_recall@150
- cosine_recall@200
- cosine_ndcg@1
- cosine_ndcg@20
- cosine_ndcg@50
- cosine_ndcg@100
- cosine_ndcg@150
- cosine_ndcg@200
- cosine_mrr@1
- cosine_mrr@20
- cosine_mrr@50
- cosine_mrr@100
- cosine_mrr@150
- cosine_mrr@200
- cosine_map@1
- cosine_map@20
- cosine_map@50
- cosine_map@100
- cosine_map@150
- cosine_map@200
- cosine_map@500
model-index:
- name: SentenceTransformer based on BAAI/bge-m3
results:
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: full en
type: full_en
metrics:
- type: cosine_accuracy@1
value: 0.6571428571428571
name: Cosine Accuracy@1
- type: cosine_accuracy@20
value: 0.9904761904761905
name: Cosine Accuracy@20
- type: cosine_accuracy@50
value: 0.9904761904761905
name: Cosine Accuracy@50
- type: cosine_accuracy@100
value: 0.9904761904761905
name: Cosine Accuracy@100
- type: cosine_accuracy@150
value: 0.9904761904761905
name: Cosine Accuracy@150
- type: cosine_accuracy@200
value: 0.9904761904761905
name: Cosine Accuracy@200
- type: cosine_precision@1
value: 0.6571428571428571
name: Cosine Precision@1
- type: cosine_precision@20
value: 0.501904761904762
name: Cosine Precision@20
- type: cosine_precision@50
value: 0.30514285714285716
name: Cosine Precision@50
- type: cosine_precision@100
value: 0.18476190476190474
name: Cosine Precision@100
- type: cosine_precision@150
value: 0.13238095238095238
name: Cosine Precision@150
- type: cosine_precision@200
value: 0.10223809523809524
name: Cosine Precision@200
- type: cosine_recall@1
value: 0.06749696615971254
name: Cosine Recall@1
- type: cosine_recall@20
value: 0.5348166179254283
name: Cosine Recall@20
- type: cosine_recall@50
value: 0.7176194992567407
name: Cosine Recall@50
- type: cosine_recall@100
value: 0.8203546241789754
name: Cosine Recall@100
- type: cosine_recall@150
value: 0.8712408549365904
name: Cosine Recall@150
- type: cosine_recall@200
value: 0.8993000584751492
name: Cosine Recall@200
- type: cosine_ndcg@1
value: 0.6571428571428571
name: Cosine Ndcg@1
- type: cosine_ndcg@20
value: 0.6791929962471466
name: Cosine Ndcg@20
- type: cosine_ndcg@50
value: 0.6958143211009435
name: Cosine Ndcg@50
- type: cosine_ndcg@100
value: 0.7493655431536407
name: Cosine Ndcg@100
- type: cosine_ndcg@150
value: 0.7715718645271473
name: Cosine Ndcg@150
- type: cosine_ndcg@200
value: 0.7814931000676181
name: Cosine Ndcg@200
- type: cosine_mrr@1
value: 0.6571428571428571
name: Cosine Mrr@1
- type: cosine_mrr@20
value: 0.8026984126984127
name: Cosine Mrr@20
- type: cosine_mrr@50
value: 0.8026984126984127
name: Cosine Mrr@50
- type: cosine_mrr@100
value: 0.8026984126984127
name: Cosine Mrr@100
- type: cosine_mrr@150
value: 0.8026984126984127
name: Cosine Mrr@150
- type: cosine_mrr@200
value: 0.8026984126984127
name: Cosine Mrr@200
- type: cosine_map@1
value: 0.6571428571428571
name: Cosine Map@1
- type: cosine_map@20
value: 0.5371258373378305
name: Cosine Map@20
- type: cosine_map@50
value: 0.5243155763407285
name: Cosine Map@50
- type: cosine_map@100
value: 0.5561427452138551
name: Cosine Map@100
- type: cosine_map@150
value: 0.5652920456249697
name: Cosine Map@150
- type: cosine_map@200
value: 0.5681007357520309
name: Cosine Map@200
- type: cosine_map@500
value: 0.5730541345190991
name: Cosine Map@500
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: full es
type: full_es
metrics:
- type: cosine_accuracy@1
value: 0.10810810810810811
name: Cosine Accuracy@1
- type: cosine_accuracy@20
value: 1
name: Cosine Accuracy@20
- type: cosine_accuracy@50
value: 1
name: Cosine Accuracy@50
- type: cosine_accuracy@100
value: 1
name: Cosine Accuracy@100
- type: cosine_accuracy@150
value: 1
name: Cosine Accuracy@150
- type: cosine_accuracy@200
value: 1
name: Cosine Accuracy@200
- type: cosine_precision@1
value: 0.10810810810810811
name: Cosine Precision@1
- type: cosine_precision@20
value: 0.5667567567567569
name: Cosine Precision@20
- type: cosine_precision@50
value: 0.3877837837837838
name: Cosine Precision@50
- type: cosine_precision@100
value: 0.25156756756756754
name: Cosine Precision@100
- type: cosine_precision@150
value: 0.18954954954954953
name: Cosine Precision@150
- type: cosine_precision@200
value: 0.15067567567567566
name: Cosine Precision@200
- type: cosine_recall@1
value: 0.0033677005752683685
name: Cosine Recall@1
- type: cosine_recall@20
value: 0.3790230473715137
name: Cosine Recall@20
- type: cosine_recall@50
value: 0.5587328778405388
name: Cosine Recall@50
- type: cosine_recall@100
value: 0.670664457795493
name: Cosine Recall@100
- type: cosine_recall@150
value: 0.7335635895457856
name: Cosine Recall@150
- type: cosine_recall@200
value: 0.766278425246947
name: Cosine Recall@200
- type: cosine_ndcg@1
value: 0.10810810810810811
name: Cosine Ndcg@1
- type: cosine_ndcg@20
value: 0.613008635976177
name: Cosine Ndcg@20
- type: cosine_ndcg@50
value: 0.5878242736285791
name: Cosine Ndcg@50
- type: cosine_ndcg@100
value: 0.6148703843706662
name: Cosine Ndcg@100
- type: cosine_ndcg@150
value: 0.6471060871986968
name: Cosine Ndcg@150
- type: cosine_ndcg@200
value: 0.6634453873788777
name: Cosine Ndcg@200
- type: cosine_mrr@1
value: 0.10810810810810811
name: Cosine Mrr@1
- type: cosine_mrr@20
value: 0.5509009009009009
name: Cosine Mrr@20
- type: cosine_mrr@50
value: 0.5509009009009009
name: Cosine Mrr@50
- type: cosine_mrr@100
value: 0.5509009009009009
name: Cosine Mrr@100
- type: cosine_mrr@150
value: 0.5509009009009009
name: Cosine Mrr@150
- type: cosine_mrr@200
value: 0.5509009009009009
name: Cosine Mrr@200
- type: cosine_map@1
value: 0.10810810810810811
name: Cosine Map@1
- type: cosine_map@20
value: 0.48105434805966624
name: Cosine Map@20
- type: cosine_map@50
value: 0.42917908716630376
name: Cosine Map@50
- type: cosine_map@100
value: 0.4322285035959748
name: Cosine Map@100
- type: cosine_map@150
value: 0.4473320611795549
name: Cosine Map@150
- type: cosine_map@200
value: 0.45413116686066823
name: Cosine Map@200
- type: cosine_map@500
value: 0.4666628908850396
name: Cosine Map@500
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: full de
type: full_de
metrics:
- type: cosine_accuracy@1
value: 0.2955665024630542
name: Cosine Accuracy@1
- type: cosine_accuracy@20
value: 0.9852216748768473
name: Cosine Accuracy@20
- type: cosine_accuracy@50
value: 0.9852216748768473
name: Cosine Accuracy@50
- type: cosine_accuracy@100
value: 0.9901477832512315
name: Cosine Accuracy@100
- type: cosine_accuracy@150
value: 0.9901477832512315
name: Cosine Accuracy@150
- type: cosine_accuracy@200
value: 0.9901477832512315
name: Cosine Accuracy@200
- type: cosine_precision@1
value: 0.2955665024630542
name: Cosine Precision@1
- type: cosine_precision@20
value: 0.5438423645320197
name: Cosine Precision@20
- type: cosine_precision@50
value: 0.3827586206896551
name: Cosine Precision@50
- type: cosine_precision@100
value: 0.2493103448275862
name: Cosine Precision@100
- type: cosine_precision@150
value: 0.1868965517241379
name: Cosine Precision@150
- type: cosine_precision@200
value: 0.150320197044335
name: Cosine Precision@200
- type: cosine_recall@1
value: 0.01108543831680986
name: Cosine Recall@1
- type: cosine_recall@20
value: 0.3450860009022403
name: Cosine Recall@20
- type: cosine_recall@50
value: 0.5334236440941986
name: Cosine Recall@50
- type: cosine_recall@100
value: 0.6498536020861698
name: Cosine Recall@100
- type: cosine_recall@150
value: 0.7091695139240046
name: Cosine Recall@150
- type: cosine_recall@200
value: 0.7496224791667186
name: Cosine Recall@200
- type: cosine_ndcg@1
value: 0.2955665024630542
name: Cosine Ndcg@1
- type: cosine_ndcg@20
value: 0.567054203369494
name: Cosine Ndcg@20
- type: cosine_ndcg@50
value: 0.5519557348354142
name: Cosine Ndcg@50
- type: cosine_ndcg@100
value: 0.5786968752325107
name: Cosine Ndcg@100
- type: cosine_ndcg@150
value: 0.6099446866772629
name: Cosine Ndcg@150
- type: cosine_ndcg@200
value: 0.6301254755200327
name: Cosine Ndcg@200
- type: cosine_mrr@1
value: 0.2955665024630542
name: Cosine Mrr@1
- type: cosine_mrr@20
value: 0.5163441238564384
name: Cosine Mrr@20
- type: cosine_mrr@50
value: 0.5163441238564384
name: Cosine Mrr@50
- type: cosine_mrr@100
value: 0.5164370692974646
name: Cosine Mrr@100
- type: cosine_mrr@150
value: 0.5164370692974646
name: Cosine Mrr@150
- type: cosine_mrr@200
value: 0.5164370692974646
name: Cosine Mrr@200
- type: cosine_map@1
value: 0.2955665024630542
name: Cosine Map@1
- type: cosine_map@20
value: 0.4243293426584066
name: Cosine Map@20
- type: cosine_map@50
value: 0.37874837593471367
name: Cosine Map@50
- type: cosine_map@100
value: 0.3817891460614099
name: Cosine Map@100
- type: cosine_map@150
value: 0.39643664920094024
name: Cosine Map@150
- type: cosine_map@200
value: 0.40443608704984707
name: Cosine Map@200
- type: cosine_map@500
value: 0.4176754500966089
name: Cosine Map@500
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: full zh
type: full_zh
metrics:
- type: cosine_accuracy@1
value: 0.6601941747572816
name: Cosine Accuracy@1
- type: cosine_accuracy@20
value: 0.9902912621359223
name: Cosine Accuracy@20
- type: cosine_accuracy@50
value: 0.9902912621359223
name: Cosine Accuracy@50
- type: cosine_accuracy@100
value: 0.9902912621359223
name: Cosine Accuracy@100
- type: cosine_accuracy@150
value: 0.9902912621359223
name: Cosine Accuracy@150
- type: cosine_accuracy@200
value: 0.9902912621359223
name: Cosine Accuracy@200
- type: cosine_precision@1
value: 0.6601941747572816
name: Cosine Precision@1
- type: cosine_precision@20
value: 0.47038834951456326
name: Cosine Precision@20
- type: cosine_precision@50
value: 0.27941747572815534
name: Cosine Precision@50
- type: cosine_precision@100
value: 0.17242718446601943
name: Cosine Precision@100
- type: cosine_precision@150
value: 0.1239482200647249
name: Cosine Precision@150
- type: cosine_precision@200
value: 0.09762135922330097
name: Cosine Precision@200
- type: cosine_recall@1
value: 0.06553457566936532
name: Cosine Recall@1
- type: cosine_recall@20
value: 0.5048889923213504
name: Cosine Recall@20
- type: cosine_recall@50
value: 0.6723480900580502
name: Cosine Recall@50
- type: cosine_recall@100
value: 0.7839824295594963
name: Cosine Recall@100
- type: cosine_recall@150
value: 0.8346078714936033
name: Cosine Recall@150
- type: cosine_recall@200
value: 0.868005364909913
name: Cosine Recall@200
- type: cosine_ndcg@1
value: 0.6601941747572816
name: Cosine Ndcg@1
- type: cosine_ndcg@20
value: 0.6489154249968472
name: Cosine Ndcg@20
- type: cosine_ndcg@50
value: 0.6582544798801073
name: Cosine Ndcg@50
- type: cosine_ndcg@100
value: 0.7132853867809429
name: Cosine Ndcg@100
- type: cosine_ndcg@150
value: 0.7351428110305336
name: Cosine Ndcg@150
- type: cosine_ndcg@200
value: 0.7489033638336042
name: Cosine Ndcg@200
- type: cosine_mrr@1
value: 0.6601941747572816
name: Cosine Mrr@1
- type: cosine_mrr@20
value: 0.8105987055016182
name: Cosine Mrr@20
- type: cosine_mrr@50
value: 0.8105987055016182
name: Cosine Mrr@50
- type: cosine_mrr@100
value: 0.8105987055016182
name: Cosine Mrr@100
- type: cosine_mrr@150
value: 0.8105987055016182
name: Cosine Mrr@150
- type: cosine_mrr@200
value: 0.8105987055016182
name: Cosine Mrr@200
- type: cosine_map@1
value: 0.6601941747572816
name: Cosine Map@1
- type: cosine_map@20
value: 0.5020661402654003
name: Cosine Map@20
- type: cosine_map@50
value: 0.4804116383814884
name: Cosine Map@50
- type: cosine_map@100
value: 0.5096988475054017
name: Cosine Map@100
- type: cosine_map@150
value: 0.5182607426785758
name: Cosine Map@150
- type: cosine_map@200
value: 0.5226490945380862
name: Cosine Map@200
- type: cosine_map@500
value: 0.5274856682898562
name: Cosine Map@500
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: mix es
type: mix_es
metrics:
- type: cosine_accuracy@1
value: 0.7358294331773271
name: Cosine Accuracy@1
- type: cosine_accuracy@20
value: 0.9615184607384295
name: Cosine Accuracy@20
- type: cosine_accuracy@50
value: 0.983359334373375
name: Cosine Accuracy@50
- type: cosine_accuracy@100
value: 0.9921996879875195
name: Cosine Accuracy@100
- type: cosine_accuracy@150
value: 0.9942797711908476
name: Cosine Accuracy@150
- type: cosine_accuracy@200
value: 0.9947997919916797
name: Cosine Accuracy@200
- type: cosine_precision@1
value: 0.7358294331773271
name: Cosine Precision@1
- type: cosine_precision@20
value: 0.12477899115964639
name: Cosine Precision@20
- type: cosine_precision@50
value: 0.05174206968278733
name: Cosine Precision@50
- type: cosine_precision@100
value: 0.02630265210608425
name: Cosine Precision@100
- type: cosine_precision@150
value: 0.017652972785578088
name: Cosine Precision@150
- type: cosine_precision@200
value: 0.013294331773270933
name: Cosine Precision@200
- type: cosine_recall@1
value: 0.28398831191342894
name: Cosine Recall@1
- type: cosine_recall@20
value: 0.9220748829953198
name: Cosine Recall@20
- type: cosine_recall@50
value: 0.9548448604610851
name: Cosine Recall@50
- type: cosine_recall@100
value: 0.9711388455538221
name: Cosine Recall@100
- type: cosine_recall@150
value: 0.9777604437510833
name: Cosine Recall@150
- type: cosine_recall@200
value: 0.9823019587450165
name: Cosine Recall@200
- type: cosine_ndcg@1
value: 0.7358294331773271
name: Cosine Ndcg@1
- type: cosine_ndcg@20
value: 0.8104398530748719
name: Cosine Ndcg@20
- type: cosine_ndcg@50
value: 0.8194810222604678
name: Cosine Ndcg@50
- type: cosine_ndcg@100
value: 0.8230427127064399
name: Cosine Ndcg@100
- type: cosine_ndcg@150
value: 0.8243283104602539
name: Cosine Ndcg@150
- type: cosine_ndcg@200
value: 0.8251186561711241
name: Cosine Ndcg@200
- type: cosine_mrr@1
value: 0.7358294331773271
name: Cosine Mrr@1
- type: cosine_mrr@20
value: 0.8034886386855536
name: Cosine Mrr@20
- type: cosine_mrr@50
value: 0.8042294348215404
name: Cosine Mrr@50
- type: cosine_mrr@100
value: 0.8043610639446989
name: Cosine Mrr@100
- type: cosine_mrr@150
value: 0.8043778926448901
name: Cosine Mrr@150
- type: cosine_mrr@200
value: 0.8043807816493392
name: Cosine Mrr@200
- type: cosine_map@1
value: 0.7358294331773271
name: Cosine Map@1
- type: cosine_map@20
value: 0.742446597316252
name: Cosine Map@20
- type: cosine_map@50
value: 0.7448760952950458
name: Cosine Map@50
- type: cosine_map@100
value: 0.7453727938942869
name: Cosine Map@100
- type: cosine_map@150
value: 0.7454980553388746
name: Cosine Map@150
- type: cosine_map@200
value: 0.7455568923614244
name: Cosine Map@200
- type: cosine_map@500
value: 0.7456455633479137
name: Cosine Map@500
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: mix de
type: mix_de
metrics:
- type: cosine_accuracy@1
value: 0.6942277691107644
name: Cosine Accuracy@1
- type: cosine_accuracy@20
value: 0.9667186687467498
name: Cosine Accuracy@20
- type: cosine_accuracy@50
value: 0.983359334373375
name: Cosine Accuracy@50
- type: cosine_accuracy@100
value: 0.9916796671866874
name: Cosine Accuracy@100
- type: cosine_accuracy@150
value: 0.9932397295891836
name: Cosine Accuracy@150
- type: cosine_accuracy@200
value: 0.9942797711908476
name: Cosine Accuracy@200
- type: cosine_precision@1
value: 0.6942277691107644
name: Cosine Precision@1
- type: cosine_precision@20
value: 0.12784711388455536
name: Cosine Precision@20
- type: cosine_precision@50
value: 0.05319812792511702
name: Cosine Precision@50
- type: cosine_precision@100
value: 0.0270306812272491
name: Cosine Precision@100
- type: cosine_precision@150
value: 0.018110591090310275
name: Cosine Precision@150
- type: cosine_precision@200
value: 0.013616744669786796
name: Cosine Precision@200
- type: cosine_recall@1
value: 0.26120644825793027
name: Cosine Recall@1
- type: cosine_recall@20
value: 0.927873114924597
name: Cosine Recall@20
- type: cosine_recall@50
value: 0.9637285491419657
name: Cosine Recall@50
- type: cosine_recall@100
value: 0.9789391575663027
name: Cosine Recall@100
- type: cosine_recall@150
value: 0.9837926850407349
name: Cosine Recall@150
- type: cosine_recall@200
value: 0.9862194487779511
name: Cosine Recall@200
- type: cosine_ndcg@1
value: 0.6942277691107644
name: Cosine Ndcg@1
- type: cosine_ndcg@20
value: 0.7952836406043297
name: Cosine Ndcg@20
- type: cosine_ndcg@50
value: 0.8052399503452229
name: Cosine Ndcg@50
- type: cosine_ndcg@100
value: 0.8086752401344494
name: Cosine Ndcg@100
- type: cosine_ndcg@150
value: 0.8096382458419952
name: Cosine Ndcg@150
- type: cosine_ndcg@200
value: 0.810085192105751
name: Cosine Ndcg@200
- type: cosine_mrr@1
value: 0.6942277691107644
name: Cosine Mrr@1
- type: cosine_mrr@20
value: 0.7761581892584265
name: Cosine Mrr@20
- type: cosine_mrr@50
value: 0.7766868481375114
name: Cosine Mrr@50
- type: cosine_mrr@100
value: 0.7768104145556238
name: Cosine Mrr@100
- type: cosine_mrr@150
value: 0.7768244234791826
name: Cosine Mrr@150
- type: cosine_mrr@200
value: 0.7768305684544853
name: Cosine Mrr@200
- type: cosine_map@1
value: 0.6942277691107644
name: Cosine Map@1
- type: cosine_map@20
value: 0.7188197545745756
name: Cosine Map@20
- type: cosine_map@50
value: 0.7215707141808124
name: Cosine Map@50
- type: cosine_map@100
value: 0.7220898692554206
name: Cosine Map@100
- type: cosine_map@150
value: 0.7221900369972237
name: Cosine Map@150
- type: cosine_map@200
value: 0.7222223600003219
name: Cosine Map@200
- type: cosine_map@500
value: 0.7222810622423789
name: Cosine Map@500
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: mix zh
type: mix_zh
metrics:
- type: cosine_accuracy@1
value: 0.18200728029121166
name: Cosine Accuracy@1
- type: cosine_accuracy@20
value: 1
name: Cosine Accuracy@20
- type: cosine_accuracy@50
value: 1
name: Cosine Accuracy@50
- type: cosine_accuracy@100
value: 1
name: Cosine Accuracy@100
- type: cosine_accuracy@150
value: 1
name: Cosine Accuracy@150
- type: cosine_accuracy@200
value: 1
name: Cosine Accuracy@200
- type: cosine_precision@1
value: 0.18200728029121166
name: Cosine Precision@1
- type: cosine_precision@20
value: 0.15439417576703063
name: Cosine Precision@20
- type: cosine_precision@50
value: 0.0617576703068123
name: Cosine Precision@50
- type: cosine_precision@100
value: 0.03087883515340615
name: Cosine Precision@100
- type: cosine_precision@150
value: 0.020585890102270757
name: Cosine Precision@150
- type: cosine_precision@200
value: 0.015439417576703075
name: Cosine Precision@200
- type: cosine_recall@1
value: 0.05850234009360374
name: Cosine Recall@1
- type: cosine_recall@20
value: 1
name: Cosine Recall@20
- type: cosine_recall@50
value: 1
name: Cosine Recall@50
- type: cosine_recall@100
value: 1
name: Cosine Recall@100
- type: cosine_recall@150
value: 1
name: Cosine Recall@150
- type: cosine_recall@200
value: 1
name: Cosine Recall@200
- type: cosine_ndcg@1
value: 0.18200728029121166
name: Cosine Ndcg@1
- type: cosine_ndcg@20
value: 0.5450053067257837
name: Cosine Ndcg@20
- type: cosine_ndcg@50
value: 0.5450053067257837
name: Cosine Ndcg@50
- type: cosine_ndcg@100
value: 0.5450053067257837
name: Cosine Ndcg@100
- type: cosine_ndcg@150
value: 0.5450053067257837
name: Cosine Ndcg@150
- type: cosine_ndcg@200
value: 0.5450053067257837
name: Cosine Ndcg@200
- type: cosine_mrr@1
value: 0.18200728029121166
name: Cosine Mrr@1
- type: cosine_mrr@20
value: 0.40246777114951904
name: Cosine Mrr@20
- type: cosine_mrr@50
value: 0.40246777114951904
name: Cosine Mrr@50
- type: cosine_mrr@100
value: 0.40246777114951904
name: Cosine Mrr@100
- type: cosine_mrr@150
value: 0.40246777114951904
name: Cosine Mrr@150
- type: cosine_mrr@200
value: 0.40246777114951904
name: Cosine Mrr@200
- type: cosine_map@1
value: 0.18200728029121166
name: Cosine Map@1
- type: cosine_map@20
value: 0.3277096647667185
name: Cosine Map@20
- type: cosine_map@50
value: 0.3277096647667185
name: Cosine Map@50
- type: cosine_map@100
value: 0.3277096647667185
name: Cosine Map@100
- type: cosine_map@150
value: 0.3277096647667185
name: Cosine Map@150
- type: cosine_map@200
value: 0.3277096647667185
name: Cosine Map@200
- type: cosine_map@500
value: 0.3277096647667185
name: Cosine Map@500
SentenceTransformer based on BAAI/bge-m3
This is a sentence-transformers model finetuned from BAAI/bge-m3 on the full_en, full_de, full_es, full_zh and mix datasets. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
Model Details
Model Description
- Model Type: Sentence Transformer
- Base model: BAAI/bge-m3
- Maximum Sequence Length: 512 tokens
- Output Dimensionality: 1024 dimensions
- Similarity Function: Cosine Similarity
- Training Datasets:
- full_en
- full_de
- full_es
- full_zh
- mix
Model Sources
- Documentation: Sentence Transformers Documentation
- Repository: Sentence Transformers on GitHub
- Hugging Face: Sentence Transformers on Hugging Face
Full Model Architecture
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Normalize()
)
Usage
Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
pip install -U sentence-transformers
Then you can load this model and run inference.
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
'Volksvertreter',
'Parlamentarier',
'Oberbürgermeister',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
Evaluation
Metrics
Information Retrieval
- Datasets:
full_en,full_es,full_de,full_zh,mix_es,mix_deandmix_zh - Evaluated with
InformationRetrievalEvaluator
| Metric | full_en | full_es | full_de | full_zh | mix_es | mix_de | mix_zh |
|---|---|---|---|---|---|---|---|
| cosine_accuracy@1 | 0.6571 | 0.1081 | 0.2956 | 0.6602 | 0.7358 | 0.6942 | 0.182 |
| cosine_accuracy@20 | 0.9905 | 1.0 | 0.9852 | 0.9903 | 0.9615 | 0.9667 | 1.0 |
| cosine_accuracy@50 | 0.9905 | 1.0 | 0.9852 | 0.9903 | 0.9834 | 0.9834 | 1.0 |
| cosine_accuracy@100 | 0.9905 | 1.0 | 0.9901 | 0.9903 | 0.9922 | 0.9917 | 1.0 |
| cosine_accuracy@150 | 0.9905 | 1.0 | 0.9901 | 0.9903 | 0.9943 | 0.9932 | 1.0 |
| cosine_accuracy@200 | 0.9905 | 1.0 | 0.9901 | 0.9903 | 0.9948 | 0.9943 | 1.0 |
| cosine_precision@1 | 0.6571 | 0.1081 | 0.2956 | 0.6602 | 0.7358 | 0.6942 | 0.182 |
| cosine_precision@20 | 0.5019 | 0.5668 | 0.5438 | 0.4704 | 0.1248 | 0.1278 | 0.1544 |
| cosine_precision@50 | 0.3051 | 0.3878 | 0.3828 | 0.2794 | 0.0517 | 0.0532 | 0.0618 |
| cosine_precision@100 | 0.1848 | 0.2516 | 0.2493 | 0.1724 | 0.0263 | 0.027 | 0.0309 |
| cosine_precision@150 | 0.1324 | 0.1895 | 0.1869 | 0.1239 | 0.0177 | 0.0181 | 0.0206 |
| cosine_precision@200 | 0.1022 | 0.1507 | 0.1503 | 0.0976 | 0.0133 | 0.0136 | 0.0154 |
| cosine_recall@1 | 0.0675 | 0.0034 | 0.0111 | 0.0655 | 0.284 | 0.2612 | 0.0585 |
| cosine_recall@20 | 0.5348 | 0.379 | 0.3451 | 0.5049 | 0.9221 | 0.9279 | 1.0 |
| cosine_recall@50 | 0.7176 | 0.5587 | 0.5334 | 0.6723 | 0.9548 | 0.9637 | 1.0 |
| cosine_recall@100 | 0.8204 | 0.6707 | 0.6499 | 0.784 | 0.9711 | 0.9789 | 1.0 |
| cosine_recall@150 | 0.8712 | 0.7336 | 0.7092 | 0.8346 | 0.9778 | 0.9838 | 1.0 |
| cosine_recall@200 | 0.8993 | 0.7663 | 0.7496 | 0.868 | 0.9823 | 0.9862 | 1.0 |
| cosine_ndcg@1 | 0.6571 | 0.1081 | 0.2956 | 0.6602 | 0.7358 | 0.6942 | 0.182 |
| cosine_ndcg@20 | 0.6792 | 0.613 | 0.5671 | 0.6489 | 0.8104 | 0.7953 | 0.545 |
| cosine_ndcg@50 | 0.6958 | 0.5878 | 0.552 | 0.6583 | 0.8195 | 0.8052 | 0.545 |
| cosine_ndcg@100 | 0.7494 | 0.6149 | 0.5787 | 0.7133 | 0.823 | 0.8087 | 0.545 |
| cosine_ndcg@150 | 0.7716 | 0.6471 | 0.6099 | 0.7351 | 0.8243 | 0.8096 | 0.545 |
| cosine_ndcg@200 | 0.7815 | 0.6634 | 0.6301 | 0.7489 | 0.8251 | 0.8101 | 0.545 |
| cosine_mrr@1 | 0.6571 | 0.1081 | 0.2956 | 0.6602 | 0.7358 | 0.6942 | 0.182 |
| cosine_mrr@20 | 0.8027 | 0.5509 | 0.5163 | 0.8106 | 0.8035 | 0.7762 | 0.4025 |
| cosine_mrr@50 | 0.8027 | 0.5509 | 0.5163 | 0.8106 | 0.8042 | 0.7767 | 0.4025 |
| cosine_mrr@100 | 0.8027 | 0.5509 | 0.5164 | 0.8106 | 0.8044 | 0.7768 | 0.4025 |
| cosine_mrr@150 | 0.8027 | 0.5509 | 0.5164 | 0.8106 | 0.8044 | 0.7768 | 0.4025 |
| cosine_mrr@200 | 0.8027 | 0.5509 | 0.5164 | 0.8106 | 0.8044 | 0.7768 | 0.4025 |
| cosine_map@1 | 0.6571 | 0.1081 | 0.2956 | 0.6602 | 0.7358 | 0.6942 | 0.182 |
| cosine_map@20 | 0.5371 | 0.4811 | 0.4243 | 0.5021 | 0.7424 | 0.7188 | 0.3277 |
| cosine_map@50 | 0.5243 | 0.4292 | 0.3787 | 0.4804 | 0.7449 | 0.7216 | 0.3277 |
| cosine_map@100 | 0.5561 | 0.4322 | 0.3818 | 0.5097 | 0.7454 | 0.7221 | 0.3277 |
| cosine_map@150 | 0.5653 | 0.4473 | 0.3964 | 0.5183 | 0.7455 | 0.7222 | 0.3277 |
| cosine_map@200 | 0.5681 | 0.4541 | 0.4044 | 0.5226 | 0.7456 | 0.7222 | 0.3277 |
| cosine_map@500 | 0.5731 | 0.4667 | 0.4177 | 0.5275 | 0.7456 | 0.7223 | 0.3277 |
Training Details
Training Datasets
full_en
full_en
- Dataset: full_en
- Size: 28,880 training samples
- Columns:
anchorandpositive - Approximate statistics based on the first 1000 samples:
anchor positive type string string details - min: 3 tokens
- mean: 5.68 tokens
- max: 11 tokens
- min: 3 tokens
- mean: 5.76 tokens
- max: 12 tokens
- Samples:
anchor positive air commodoreflight lieutenantcommand and control officerflight officerair commodorecommand and control officer - Loss:
GISTEmbedLosswith these parameters:{'guide': SentenceTransformer( (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 384, '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() ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
full_de
full_de
- Dataset: full_de
- Size: 23,023 training samples
- Columns:
anchorandpositive - Approximate statistics based on the first 1000 samples:
anchor positive type string string details - min: 3 tokens
- mean: 7.99 tokens
- max: 30 tokens
- min: 3 tokens
- mean: 8.19 tokens
- max: 30 tokens
- Samples:
anchor positive StaffelkommandantinKommodoreLuftwaffenoffizierinLuftwaffenoffizier/LuftwaffenoffizierinStaffelkommandantinLuftwaffenoffizierin - Loss:
GISTEmbedLosswith these parameters:{'guide': SentenceTransformer( (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 384, '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() ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
full_es
full_es
- Dataset: full_es
- Size: 20,724 training samples
- Columns:
anchorandpositive - Approximate statistics based on the first 1000 samples:
anchor positive type string string details - min: 3 tokens
- mean: 9.13 tokens
- max: 32 tokens
- min: 3 tokens
- mean: 8.84 tokens
- max: 32 tokens
- Samples:
anchor positive jefe de escuadróninstructorcomandante de aeronaveinstructor de simuladorinstructoroficial del Ejército del Aire - Loss:
GISTEmbedLosswith these parameters:{'guide': SentenceTransformer( (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 384, '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() ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
full_zh
full_zh
- Dataset: full_zh
- Size: 30,401 training samples
- Columns:
anchorandpositive - Approximate statistics based on the first 1000 samples:
anchor positive type string string details - min: 5 tokens
- mean: 7.15 tokens
- max: 14 tokens
- min: 5 tokens
- mean: 7.46 tokens
- max: 21 tokens
- Samples:
anchor positive 技术总监技术和运营总监技术总监技术主管技术总监技术艺术总监 - Loss:
GISTEmbedLosswith these parameters:{'guide': SentenceTransformer( (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 384, '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() ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
mix
mix
- Dataset: mix
- Size: 21,760 training samples
- Columns:
anchorandpositive - Approximate statistics based on the first 1000 samples:
anchor positive type string string details - min: 2 tokens
- mean: 6.71 tokens
- max: 19 tokens
- min: 2 tokens
- mean: 7.69 tokens
- max: 19 tokens
- Samples:
anchor positive technical managerTechnischer Direktor für Bühne, Film und Fernsehenhead of technicaldirectora técnicahead of technical department技术艺术总监 - Loss:
GISTEmbedLosswith these parameters:{'guide': SentenceTransformer( (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 384, '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() ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy: stepsper_device_train_batch_size: 64per_device_eval_batch_size: 128gradient_accumulation_steps: 2num_train_epochs: 5warmup_ratio: 0.05log_on_each_node: Falsefp16: Truedataloader_num_workers: 4ddp_find_unused_parameters: Truebatch_sampler: no_duplicates
All Hyperparameters
Click to expand
overwrite_output_dir: Falsedo_predict: Falseeval_strategy: stepsprediction_loss_only: Trueper_device_train_batch_size: 64per_device_eval_batch_size: 128per_gpu_train_batch_size: Noneper_gpu_eval_batch_size: Nonegradient_accumulation_steps: 2eval_accumulation_steps: Nonetorch_empty_cache_steps: Nonelearning_rate: 5e-05weight_decay: 0.0adam_beta1: 0.9adam_beta2: 0.999adam_epsilon: 1e-08max_grad_norm: 1.0num_train_epochs: 5max_steps: -1lr_scheduler_type: linearlr_scheduler_kwargs: {}warmup_ratio: 0.05warmup_steps: 0log_level: passivelog_level_replica: warninglog_on_each_node: Falselogging_nan_inf_filter: Truesave_safetensors: Truesave_on_each_node: Falsesave_only_model: Falserestore_callback_states_from_checkpoint: Falseno_cuda: Falseuse_cpu: Falseuse_mps_device: Falseseed: 42data_seed: Nonejit_mode_eval: Falseuse_ipex: Falsebf16: Falsefp16: Truefp16_opt_level: O1half_precision_backend: autobf16_full_eval: Falsefp16_full_eval: Falsetf32: Nonelocal_rank: 0ddp_backend: Nonetpu_num_cores: Nonetpu_metrics_debug: Falsedebug: []dataloader_drop_last: Truedataloader_num_workers: 4dataloader_prefetch_factor: Nonepast_index: -1disable_tqdm: Falseremove_unused_columns: Truelabel_names: Noneload_best_model_at_end: Falseignore_data_skip: Falsefsdp: []fsdp_min_num_params: 0fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}tp_size: 0fsdp_transformer_layer_cls_to_wrap: Noneaccelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}deepspeed: Nonelabel_smoothing_factor: 0.0optim: adamw_torchoptim_args: Noneadafactor: Falsegroup_by_length: Falselength_column_name: lengthddp_find_unused_parameters: Trueddp_bucket_cap_mb: Noneddp_broadcast_buffers: Falsedataloader_pin_memory: Truedataloader_persistent_workers: Falseskip_memory_metrics: Trueuse_legacy_prediction_loop: Falsepush_to_hub: Falseresume_from_checkpoint: Nonehub_model_id: Nonehub_strategy: every_savehub_private_repo: Nonehub_always_push: Falsegradient_checkpointing: Falsegradient_checkpointing_kwargs: Noneinclude_inputs_for_metrics: Falseinclude_for_metrics: []eval_do_concat_batches: Truefp16_backend: autopush_to_hub_model_id: Nonepush_to_hub_organization: Nonemp_parameters:auto_find_batch_size: Falsefull_determinism: Falsetorchdynamo: Noneray_scope: lastddp_timeout: 1800torch_compile: Falsetorch_compile_backend: Nonetorch_compile_mode: Noneinclude_tokens_per_second: Falseinclude_num_input_tokens_seen: Falseneftune_noise_alpha: Noneoptim_target_modules: Nonebatch_eval_metrics: Falseeval_on_start: Falseuse_liger_kernel: Falseeval_use_gather_object: Falseaverage_tokens_across_devices: Falseprompts: Nonebatch_sampler: no_duplicatesmulti_dataset_batch_sampler: proportional
Training Logs
| Epoch | Step | Training Loss | full_en_cosine_ndcg@200 | full_es_cosine_ndcg@200 | full_de_cosine_ndcg@200 | full_zh_cosine_ndcg@200 | mix_es_cosine_ndcg@200 | mix_de_cosine_ndcg@200 | mix_zh_cosine_ndcg@200 |
|---|---|---|---|---|---|---|---|---|---|
| -1 | -1 | - | 0.6856 | 0.5207 | 0.4655 | 0.6713 | 0.6224 | 0.5604 | 0.5548 |
| 0.0010 | 1 | 5.3354 | - | - | - | - | - | - | - |
| 0.1027 | 100 | 2.665 | - | - | - | - | - | - | - |
| 0.2053 | 200 | 1.3375 | 0.7691 | 0.6530 | 0.6298 | 0.7517 | 0.7513 | 0.7393 | 0.5490 |
| 0.3080 | 300 | 1.1101 | - | - | - | - | - | - | - |
| 0.4107 | 400 | 0.9453 | 0.7802 | 0.6643 | 0.6246 | 0.7531 | 0.7610 | 0.7441 | 0.5493 |
| 0.5133 | 500 | 0.9202 | - | - | - | - | - | - | - |
| 0.6160 | 600 | 0.7887 | 0.7741 | 0.6549 | 0.6171 | 0.7542 | 0.7672 | 0.7540 | 0.5482 |
| 0.7187 | 700 | 0.7604 | - | - | - | - | - | - | - |
| 0.8214 | 800 | 0.7219 | 0.7846 | 0.6674 | 0.6244 | 0.7648 | 0.7741 | 0.7592 | 0.5497 |
| 0.9240 | 900 | 0.6965 | - | - | - | - | - | - | - |
| 1.0267 | 1000 | 0.6253 | 0.7646 | 0.6391 | 0.6122 | 0.7503 | 0.7825 | 0.7704 | 0.5463 |
| 1.1294 | 1100 | 0.4737 | - | - | - | - | - | - | - |
| 1.2320 | 1200 | 0.5055 | 0.7758 | 0.6582 | 0.6178 | 0.7514 | 0.7857 | 0.7764 | 0.5501 |
| 1.3347 | 1300 | 0.5042 | - | - | - | - | - | - | - |
| 1.4374 | 1400 | 0.5073 | 0.7613 | 0.6578 | 0.6178 | 0.7505 | 0.7829 | 0.7762 | 0.5452 |
| 1.5400 | 1500 | 0.4975 | - | - | - | - | - | - | - |
| 1.6427 | 1600 | 0.5242 | 0.7736 | 0.6673 | 0.6279 | 0.7555 | 0.7940 | 0.7859 | 0.5477 |
| 1.7454 | 1700 | 0.4713 | - | - | - | - | - | - | - |
| 1.8480 | 1800 | 0.4814 | 0.7845 | 0.6733 | 0.6285 | 0.7642 | 0.7992 | 0.7904 | 0.5449 |
| 1.9507 | 1900 | 0.4526 | - | - | - | - | - | - | - |
| 2.0544 | 2000 | 0.36 | 0.7790 | 0.6639 | 0.6252 | 0.7500 | 0.8032 | 0.7888 | 0.5499 |
| 2.1571 | 2100 | 0.3744 | - | - | - | - | - | - | - |
| 2.2598 | 2200 | 0.3031 | 0.7787 | 0.6614 | 0.6190 | 0.7537 | 0.7993 | 0.7811 | 0.5476 |
| 2.3624 | 2300 | 0.3638 | - | - | - | - | - | - | - |
| 2.4651 | 2400 | 0.358 | 0.7798 | 0.6615 | 0.6258 | 0.7497 | 0.8018 | 0.7828 | 0.5481 |
| 2.5678 | 2500 | 0.3247 | - | - | - | - | - | - | - |
| 2.6704 | 2600 | 0.3247 | 0.7854 | 0.6663 | 0.6248 | 0.7560 | 0.8081 | 0.7835 | 0.5452 |
| 2.7731 | 2700 | 0.3263 | - | - | - | - | - | - | - |
| 2.8758 | 2800 | 0.3212 | 0.7761 | 0.6681 | 0.6250 | 0.7517 | 0.8121 | 0.7927 | 0.5458 |
| 2.9784 | 2900 | 0.3291 | - | - | - | - | - | - | - |
| 3.0821 | 3000 | 0.2816 | 0.7727 | 0.6604 | 0.6163 | 0.7370 | 0.8163 | 0.7985 | 0.5473 |
| 3.1848 | 3100 | 0.2698 | - | - | - | - | - | - | - |
| 3.2875 | 3200 | 0.2657 | 0.7757 | 0.6615 | 0.6247 | 0.7417 | 0.8117 | 0.8004 | 0.5436 |
| 3.3901 | 3300 | 0.2724 | - | - | - | - | - | - | - |
| 3.4928 | 3400 | 0.2584 | 0.7850 | 0.6583 | 0.6320 | 0.7458 | 0.8120 | 0.7980 | 0.5454 |
| 3.5955 | 3500 | 0.2573 | - | - | - | - | - | - | - |
| 3.6982 | 3600 | 0.2744 | 0.7796 | 0.6552 | 0.6237 | 0.7409 | 0.8193 | 0.8018 | 0.5466 |
| 3.8008 | 3700 | 0.3054 | - | - | - | - | - | - | - |
| 3.9035 | 3800 | 0.2727 | 0.7825 | 0.6642 | 0.6293 | 0.7504 | 0.8213 | 0.8058 | 0.5463 |
| 4.0062 | 3900 | 0.2353 | - | - | - | - | - | - | - |
| 4.1088 | 4000 | 0.2353 | 0.7747 | 0.6628 | 0.6263 | 0.7384 | 0.8239 | 0.8065 | 0.5447 |
| 4.2115 | 4100 | 0.2385 | - | - | - | - | - | - | - |
| 4.3142 | 4200 | 0.231 | 0.7811 | 0.6608 | 0.6254 | 0.7463 | 0.8226 | 0.8051 | 0.5442 |
| 4.4168 | 4300 | 0.2115 | - | - | - | - | - | - | - |
| 4.5195 | 4400 | 0.2151 | 0.7815 | 0.6634 | 0.6301 | 0.7489 | 0.8251 | 0.8101 | 0.5450 |
Framework Versions
- Python: 3.11.11
- Sentence Transformers: 4.1.0
- Transformers: 4.51.2
- PyTorch: 2.6.0+cu124
- Accelerate: 1.6.0
- Datasets: 3.5.0
- Tokenizers: 0.21.1
Citation
BibTeX
Sentence Transformers
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
GISTEmbedLoss
@misc{solatorio2024gistembed,
title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning},
author={Aivin V. Solatorio},
year={2024},
eprint={2402.16829},
archivePrefix={arXiv},
primaryClass={cs.LG}
}