Upload 7 files

upload base model

README.md

@@ -1,3 +1,1248 @@
 ---
-license: mit
+tags:
+- mteb
+model-index:
+- name: stella-base-zh
+  results:
+  - task:
+      type: STS
+    dataset:
+      type: C-MTEB/AFQMC
+      name: MTEB AFQMC
+      config: default
+      split: validation
+      revision: None
+    metrics:
+    - type: cos_sim_pearson
+      value: 49.34825050234731
+    - type: cos_sim_spearman
+      value: 51.74726338428475
+    - type: euclidean_pearson
+      value: 50.14955499038012
+    - type: euclidean_spearman
+      value: 51.74730359287025
+    - type: manhattan_pearson
+      value: 50.016703594410615
+    - type: manhattan_spearman
+      value: 51.63936364317057
+  - task:
+      type: STS
+    dataset:
+      type: C-MTEB/ATEC
+      name: MTEB ATEC
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: cos_sim_pearson
+      value: 52.26876163587667
+    - type: cos_sim_spearman
+      value: 52.818410137444374
+    - type: euclidean_pearson
+      value: 55.24925286208574
+    - type: euclidean_spearman
+      value: 52.818404507964686
+    - type: manhattan_pearson
+      value: 55.21236977375391
+    - type: manhattan_spearman
+      value: 52.80289117015117
+  - task:
+      type: Classification
+    dataset:
+      type: mteb/amazon_reviews_multi
+      name: MTEB AmazonReviewsClassification (zh)
+      config: zh
+      split: test
+      revision: 1399c76144fd37290681b995c656ef9b2e06e26d
+    metrics:
+    - type: accuracy
+      value: 40.245999999999995
+    - type: f1
+      value: 38.55443674287747
+  - task:
+      type: STS
+    dataset:
+      type: C-MTEB/BQ
+      name: MTEB BQ
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: cos_sim_pearson
+      value: 61.553652835163255
+    - type: cos_sim_spearman
+      value: 63.29065064027392
+    - type: euclidean_pearson
+      value: 62.000329557485
+    - type: euclidean_spearman
+      value: 63.290650638944825
+    - type: manhattan_pearson
+      value: 62.02786936153664
+    - type: manhattan_spearman
+      value: 63.32720383880146
+  - task:
+      type: Clustering
+    dataset:
+      type: C-MTEB/CLSClusteringP2P
+      name: MTEB CLSClusteringP2P
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: v_measure
+      value: 39.71224230526474
+  - task:
+      type: Clustering
+    dataset:
+      type: C-MTEB/CLSClusteringS2S
+      name: MTEB CLSClusteringS2S
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: v_measure
+      value: 36.55705201882987
+  - task:
+      type: Reranking
+    dataset:
+      type: C-MTEB/CMedQAv1-reranking
+      name: MTEB CMedQAv1
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: map
+      value: 85.69418720521168
+    - type: mrr
+      value: 87.97444444444446
+  - task:
+      type: Reranking
+    dataset:
+      type: C-MTEB/CMedQAv2-reranking
+      name: MTEB CMedQAv2
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: map
+      value: 86.46348358482606
+    - type: mrr
+      value: 88.81428571428572
+  - task:
+      type: Retrieval
+    dataset:
+      type: C-MTEB/CmedqaRetrieval
+      name: MTEB CmedqaRetrieval
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map_at_1
+      value: 23.721
+    - type: map_at_10
+      value: 35.428
+    - type: map_at_100
+      value: 37.438
+    - type: map_at_1000
+      value: 37.557
+    - type: map_at_3
+      value: 31.589
+    - type: map_at_5
+      value: 33.647
+    - type: mrr_at_1
+      value: 36.709
+    - type: mrr_at_10
+      value: 44.590999999999994
+    - type: mrr_at_100
+      value: 45.684999999999995
+    - type: mrr_at_1000
+      value: 45.732
+    - type: mrr_at_3
+      value: 42.331
+    - type: mrr_at_5
+      value: 43.532
+    - type: ndcg_at_1
+      value: 36.709
+    - type: ndcg_at_10
+      value: 41.858000000000004
+    - type: ndcg_at_100
+      value: 49.775999999999996
+    - type: ndcg_at_1000
+      value: 51.844
+    - type: ndcg_at_3
+      value: 37.067
+    - type: ndcg_at_5
+      value: 38.875
+    - type: precision_at_1
+      value: 36.709
+    - type: precision_at_10
+      value: 9.411999999999999
+    - type: precision_at_100
+      value: 1.5709999999999997
+    - type: precision_at_1000
+      value: 0.183
+    - type: precision_at_3
+      value: 21.154999999999998
+    - type: precision_at_5
+      value: 15.184000000000001
+    - type: recall_at_1
+      value: 23.721
+    - type: recall_at_10
+      value: 51.714000000000006
+    - type: recall_at_100
+      value: 84.60600000000001
+    - type: recall_at_1000
+      value: 98.414
+    - type: recall_at_3
+      value: 37.091
+    - type: recall_at_5
+      value: 42.978
+  - task:
+      type: PairClassification
+    dataset:
+      type: C-MTEB/CMNLI
+      name: MTEB Cmnli
+      config: default
+      split: validation
+      revision: None
+    metrics:
+    - type: cos_sim_accuracy
+      value: 73.61395069152135
+    - type: cos_sim_ap
+      value: 81.65459344597652
+    - type: cos_sim_f1
+      value: 75.66718995290425
+    - type: cos_sim_precision
+      value: 68.4918529746116
+    - type: cos_sim_recall
+      value: 84.5218611176058
+    - type: dot_accuracy
+      value: 73.61395069152135
+    - type: dot_ap
+      value: 81.64596407363373
+    - type: dot_f1
+      value: 75.66718995290425
+    - type: dot_precision
+      value: 68.4918529746116
+    - type: dot_recall
+      value: 84.5218611176058
+    - type: euclidean_accuracy
+      value: 73.61395069152135
+    - type: euclidean_ap
+      value: 81.6546013070452
+    - type: euclidean_f1
+      value: 75.66718995290425
+    - type: euclidean_precision
+      value: 68.4918529746116
+    - type: euclidean_recall
+      value: 84.5218611176058
+    - type: manhattan_accuracy
+      value: 73.51773902585688
+    - type: manhattan_ap
+      value: 81.57345451483191
+    - type: manhattan_f1
+      value: 75.7393958530681
+    - type: manhattan_precision
+      value: 68.87442572741195
+    - type: manhattan_recall
+      value: 84.12438625204582
+    - type: max_accuracy
+      value: 73.61395069152135
+    - type: max_ap
+      value: 81.6546013070452
+    - type: max_f1
+      value: 75.7393958530681
+  - task:
+      type: Retrieval
+    dataset:
+      type: C-MTEB/CovidRetrieval
+      name: MTEB CovidRetrieval
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map_at_1
+      value: 73.551
+    - type: map_at_10
+      value: 81.513
+    - type: map_at_100
+      value: 81.734
+    - type: map_at_1000
+      value: 81.73700000000001
+    - type: map_at_3
+      value: 80.27300000000001
+    - type: map_at_5
+      value: 81.017
+    - type: mrr_at_1
+      value: 73.762
+    - type: mrr_at_10
+      value: 81.479
+    - type: mrr_at_100
+      value: 81.699
+    - type: mrr_at_1000
+      value: 81.702
+    - type: mrr_at_3
+      value: 80.33
+    - type: mrr_at_5
+      value: 80.999
+    - type: ndcg_at_1
+      value: 73.867
+    - type: ndcg_at_10
+      value: 84.711
+    - type: ndcg_at_100
+      value: 85.714
+    - type: ndcg_at_1000
+      value: 85.803
+    - type: ndcg_at_3
+      value: 82.244
+    - type: ndcg_at_5
+      value: 83.514
+    - type: precision_at_1
+      value: 73.867
+    - type: precision_at_10
+      value: 9.557
+    - type: precision_at_100
+      value: 1.001
+    - type: precision_at_1000
+      value: 0.101
+    - type: precision_at_3
+      value: 29.505
+    - type: precision_at_5
+      value: 18.377
+    - type: recall_at_1
+      value: 73.551
+    - type: recall_at_10
+      value: 94.521
+    - type: recall_at_100
+      value: 99.05199999999999
+    - type: recall_at_1000
+      value: 99.789
+    - type: recall_at_3
+      value: 87.777
+    - type: recall_at_5
+      value: 90.83200000000001
+  - task:
+      type: Retrieval
+    dataset:
+      type: C-MTEB/DuRetrieval
+      name: MTEB DuRetrieval
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map_at_1
+      value: 26.230999999999998
+    - type: map_at_10
+      value: 80.635
+    - type: map_at_100
+      value: 83.393
+    - type: map_at_1000
+      value: 83.431
+    - type: map_at_3
+      value: 55.717000000000006
+    - type: map_at_5
+      value: 70.387
+    - type: mrr_at_1
+      value: 90.75
+    - type: mrr_at_10
+      value: 93.569
+    - type: mrr_at_100
+      value: 93.648
+    - type: mrr_at_1000
+      value: 93.65
+    - type: mrr_at_3
+      value: 93.27499999999999
+    - type: mrr_at_5
+      value: 93.482
+    - type: ndcg_at_1
+      value: 90.75
+    - type: ndcg_at_10
+      value: 87.801
+    - type: ndcg_at_100
+      value: 90.44
+    - type: ndcg_at_1000
+      value: 90.776
+    - type: ndcg_at_3
+      value: 86.556
+    - type: ndcg_at_5
+      value: 85.468
+    - type: precision_at_1
+      value: 90.75
+    - type: precision_at_10
+      value: 42.08
+    - type: precision_at_100
+      value: 4.816
+    - type: precision_at_1000
+      value: 0.49
+    - type: precision_at_3
+      value: 77.60000000000001
+    - type: precision_at_5
+      value: 65.49000000000001
+    - type: recall_at_1
+      value: 26.230999999999998
+    - type: recall_at_10
+      value: 89.00200000000001
+    - type: recall_at_100
+      value: 97.866
+    - type: recall_at_1000
+      value: 99.569
+    - type: recall_at_3
+      value: 57.778
+    - type: recall_at_5
+      value: 74.895
+  - task:
+      type: Retrieval
+    dataset:
+      type: C-MTEB/EcomRetrieval
+      name: MTEB EcomRetrieval
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map_at_1
+      value: 47.599999999999994
+    - type: map_at_10
+      value: 57.296
+    - type: map_at_100
+      value: 58.011
+    - type: map_at_1000
+      value: 58.028
+    - type: map_at_3
+      value: 54.300000000000004
+    - type: map_at_5
+      value: 56.21000000000001
+    - type: mrr_at_1
+      value: 47.599999999999994
+    - type: mrr_at_10
+      value: 57.296
+    - type: mrr_at_100
+      value: 58.011
+    - type: mrr_at_1000
+      value: 58.028
+    - type: mrr_at_3
+      value: 54.300000000000004
+    - type: mrr_at_5
+      value: 56.21000000000001
+    - type: ndcg_at_1
+      value: 47.599999999999994
+    - type: ndcg_at_10
+      value: 62.458000000000006
+    - type: ndcg_at_100
+      value: 65.589
+    - type: ndcg_at_1000
+      value: 66.059
+    - type: ndcg_at_3
+      value: 56.364000000000004
+    - type: ndcg_at_5
+      value: 59.815
+    - type: precision_at_1
+      value: 47.599999999999994
+    - type: precision_at_10
+      value: 7.89
+    - type: precision_at_100
+      value: 0.928
+    - type: precision_at_1000
+      value: 0.097
+    - type: precision_at_3
+      value: 20.767
+    - type: precision_at_5
+      value: 14.14
+    - type: recall_at_1
+      value: 47.599999999999994
+    - type: recall_at_10
+      value: 78.9
+    - type: recall_at_100
+      value: 92.80000000000001
+    - type: recall_at_1000
+      value: 96.6
+    - type: recall_at_3
+      value: 62.3
+    - type: recall_at_5
+      value: 70.7
+  - task:
+      type: Classification
+    dataset:
+      type: C-MTEB/IFlyTek-classification
+      name: MTEB IFlyTek
+      config: default
+      split: validation
+      revision: None
+    metrics:
+    - type: accuracy
+      value: 47.46440938822624
+    - type: f1
+      value: 34.587004997852524
+  - task:
+      type: Classification
+    dataset:
+      type: C-MTEB/JDReview-classification
+      name: MTEB JDReview
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: accuracy
+      value: 84.9906191369606
+    - type: ap
+      value: 52.31309789960497
+    - type: f1
+      value: 79.55556102310072
+  - task:
+      type: STS
+    dataset:
+      type: C-MTEB/LCQMC
+      name: MTEB LCQMC
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: cos_sim_pearson
+      value: 69.80872804636063
+    - type: cos_sim_spearman
+      value: 75.83290476813391
+    - type: euclidean_pearson
+      value: 74.09865882324753
+    - type: euclidean_spearman
+      value: 75.83290698376118
+    - type: manhattan_pearson
+      value: 74.0616102379577
+    - type: manhattan_spearman
+      value: 75.81278969865738
+  - task:
+      type: Retrieval
+    dataset:
+      type: C-MTEB/MMarcoRetrieval
+      name: MTEB MMarcoRetrieval
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map_at_1
+      value: 65.029
+    - type: map_at_10
+      value: 74.39
+    - type: map_at_100
+      value: 74.734
+    - type: map_at_1000
+      value: 74.74300000000001
+    - type: map_at_3
+      value: 72.52
+    - type: map_at_5
+      value: 73.724
+    - type: mrr_at_1
+      value: 67.192
+    - type: mrr_at_10
+      value: 74.95100000000001
+    - type: mrr_at_100
+      value: 75.25500000000001
+    - type: mrr_at_1000
+      value: 75.263
+    - type: mrr_at_3
+      value: 73.307
+    - type: mrr_at_5
+      value: 74.355
+    - type: ndcg_at_1
+      value: 67.192
+    - type: ndcg_at_10
+      value: 78.22200000000001
+    - type: ndcg_at_100
+      value: 79.76299999999999
+    - type: ndcg_at_1000
+      value: 80.018
+    - type: ndcg_at_3
+      value: 74.656
+    - type: ndcg_at_5
+      value: 76.697
+    - type: precision_at_1
+      value: 67.192
+    - type: precision_at_10
+      value: 9.513
+    - type: precision_at_100
+      value: 1.027
+    - type: precision_at_1000
+      value: 0.105
+    - type: precision_at_3
+      value: 28.204
+    - type: precision_at_5
+      value: 18.009
+    - type: recall_at_1
+      value: 65.029
+    - type: recall_at_10
+      value: 89.462
+    - type: recall_at_100
+      value: 96.418
+    - type: recall_at_1000
+      value: 98.409
+    - type: recall_at_3
+      value: 80.029
+    - type: recall_at_5
+      value: 84.882
+  - task:
+      type: Classification
+    dataset:
+      type: mteb/amazon_massive_intent
+      name: MTEB MassiveIntentClassification (zh-CN)
+      config: zh-CN
+      split: test
+      revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
+    metrics:
+    - type: accuracy
+      value: 65.56489576328177
+    - type: f1
+      value: 63.37174551232159
+  - task:
+      type: Classification
+    dataset:
+      type: mteb/amazon_massive_scenario
+      name: MTEB MassiveScenarioClassification (zh-CN)
+      config: zh-CN
+      split: test
+      revision: 7d571f92784cd94a019292a1f45445077d0ef634
+    metrics:
+    - type: accuracy
+      value: 71.4862138533961
+    - type: f1
+      value: 71.171374964826
+  - task:
+      type: Retrieval
+    dataset:
+      type: C-MTEB/MedicalRetrieval
+      name: MTEB MedicalRetrieval
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map_at_1
+      value: 48.6
+    - type: map_at_10
+      value: 54.92700000000001
+    - type: map_at_100
+      value: 55.528
+    - type: map_at_1000
+      value: 55.584
+    - type: map_at_3
+      value: 53.55
+    - type: map_at_5
+      value: 54.379999999999995
+    - type: mrr_at_1
+      value: 48.8
+    - type: mrr_at_10
+      value: 55.028999999999996
+    - type: mrr_at_100
+      value: 55.629
+    - type: mrr_at_1000
+      value: 55.684999999999995
+    - type: mrr_at_3
+      value: 53.65
+    - type: mrr_at_5
+      value: 54.48
+    - type: ndcg_at_1
+      value: 48.6
+    - type: ndcg_at_10
+      value: 57.965999999999994
+    - type: ndcg_at_100
+      value: 61.043000000000006
+    - type: ndcg_at_1000
+      value: 62.624
+    - type: ndcg_at_3
+      value: 55.132000000000005
+    - type: ndcg_at_5
+      value: 56.621
+    - type: precision_at_1
+      value: 48.6
+    - type: precision_at_10
+      value: 6.75
+    - type: precision_at_100
+      value: 0.823
+    - type: precision_at_1000
+      value: 0.095
+    - type: precision_at_3
+      value: 19.900000000000002
+    - type: precision_at_5
+      value: 12.659999999999998
+    - type: recall_at_1
+      value: 48.6
+    - type: recall_at_10
+      value: 67.5
+    - type: recall_at_100
+      value: 82.3
+    - type: recall_at_1000
+      value: 94.89999999999999
+    - type: recall_at_3
+      value: 59.699999999999996
+    - type: recall_at_5
+      value: 63.3
+  - task:
+      type: Reranking
+    dataset:
+      type: C-MTEB/Mmarco-reranking
+      name: MTEB MMarcoReranking
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map
+      value: 29.196130696027474
+    - type: mrr
+      value: 28.43730158730159
+  - task:
+      type: Classification
+    dataset:
+      type: C-MTEB/MultilingualSentiment-classification
+      name: MTEB MultilingualSentiment
+      config: default
+      split: validation
+      revision: None
+    metrics:
+    - type: accuracy
+      value: 72.48333333333333
+    - type: f1
+      value: 72.00258522357558
+  - task:
+      type: PairClassification
+    dataset:
+      type: C-MTEB/OCNLI
+      name: MTEB Ocnli
+      config: default
+      split: validation
+      revision: None
+    metrics:
+    - type: cos_sim_accuracy
+      value: 65.13264753654575
+    - type: cos_sim_ap
+      value: 70.52831936800807
+    - type: cos_sim_f1
+      value: 71.35353535353535
+    - type: cos_sim_precision
+      value: 57.787958115183244
+    - type: cos_sim_recall
+      value: 93.24181626187962
+    - type: dot_accuracy
+      value: 65.13264753654575
+    - type: dot_ap
+      value: 70.52828597418102
+    - type: dot_f1
+      value: 71.35353535353535
+    - type: dot_precision
+      value: 57.787958115183244
+    - type: dot_recall
+      value: 93.24181626187962
+    - type: euclidean_accuracy
+      value: 65.13264753654575
+    - type: euclidean_ap
+      value: 70.52828597418102
+    - type: euclidean_f1
+      value: 71.35353535353535
+    - type: euclidean_precision
+      value: 57.787958115183244
+    - type: euclidean_recall
+      value: 93.24181626187962
+    - type: manhattan_accuracy
+      value: 64.8077964266378
+    - type: manhattan_ap
+      value: 70.39954487476643
+    - type: manhattan_f1
+      value: 71.2270200940573
+    - type: manhattan_precision
+      value: 59.84195402298851
+    - type: manhattan_recall
+      value: 87.96198521647307
+    - type: max_accuracy
+      value: 65.13264753654575
+    - type: max_ap
+      value: 70.52831936800807
+    - type: max_f1
+      value: 71.35353535353535
+  - task:
+      type: Classification
+    dataset:
+      type: C-MTEB/OnlineShopping-classification
+      name: MTEB OnlineShopping
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: accuracy
+      value: 90.34
+    - type: ap
+      value: 87.79622626876444
+    - type: f1
+      value: 90.32357430051181
+  - task:
+      type: STS
+    dataset:
+      type: C-MTEB/PAWSX
+      name: MTEB PAWSX
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: cos_sim_pearson
+      value: 27.9175458105215
+    - type: cos_sim_spearman
+      value: 32.024302491613014
+    - type: euclidean_pearson
+      value: 33.01780461609846
+    - type: euclidean_spearman
+      value: 32.024301939183374
+    - type: manhattan_pearson
+      value: 32.94874897942371
+    - type: manhattan_spearman
+      value: 31.902283210178012
+  - task:
+      type: STS
+    dataset:
+      type: C-MTEB/QBQTC
+      name: MTEB QBQTC
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: cos_sim_pearson
+      value: 36.288219964332754
+    - type: cos_sim_spearman
+      value: 36.46838652731507
+    - type: euclidean_pearson
+      value: 35.11414028811812
+    - type: euclidean_spearman
+      value: 36.468386523814104
+    - type: manhattan_pearson
+      value: 35.20922826624027
+    - type: manhattan_spearman
+      value: 36.55349180906185
+  - task:
+      type: STS
+    dataset:
+      type: mteb/sts22-crosslingual-sts
+      name: MTEB STS22 (zh)
+      config: zh
+      split: test
+      revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
+    metrics:
+    - type: cos_sim_pearson
+      value: 66.18186265837434
+    - type: cos_sim_spearman
+      value: 67.52365178443915
+    - type: euclidean_pearson
+      value: 65.46342439169497
+    - type: euclidean_spearman
+      value: 67.52365178443915
+    - type: manhattan_pearson
+      value: 67.3476263677961
+    - type: manhattan_spearman
+      value: 69.09476240936812
+  - task:
+      type: STS
+    dataset:
+      type: C-MTEB/STSB
+      name: MTEB STSB
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: cos_sim_pearson
+      value: 72.53864906415339
+    - type: cos_sim_spearman
+      value: 72.63037820118355
+    - type: euclidean_pearson
+      value: 72.42255276991672
+    - type: euclidean_spearman
+      value: 72.63037820118355
+    - type: manhattan_pearson
+      value: 72.36324244766192
+    - type: manhattan_spearman
+      value: 72.58609772740323
+  - task:
+      type: Reranking
+    dataset:
+      type: C-MTEB/T2Reranking
+      name: MTEB T2Reranking
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map
+      value: 66.45708148192449
+    - type: mrr
+      value: 76.08372693469173
+  - task:
+      type: Retrieval
+    dataset:
+      type: C-MTEB/T2Retrieval
+      name: MTEB T2Retrieval
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map_at_1
+      value: 26.436999999999998
+    - type: map_at_10
+      value: 74.516
+    - type: map_at_100
+      value: 78.29899999999999
+    - type: map_at_1000
+      value: 78.372
+    - type: map_at_3
+      value: 52.217
+    - type: map_at_5
+      value: 64.24
+    - type: mrr_at_1
+      value: 88.23
+    - type: mrr_at_10
+      value: 91.06400000000001
+    - type: mrr_at_100
+      value: 91.18
+    - type: mrr_at_1000
+      value: 91.184
+    - type: mrr_at_3
+      value: 90.582
+    - type: mrr_at_5
+      value: 90.88300000000001
+    - type: ndcg_at_1
+      value: 88.23
+    - type: ndcg_at_10
+      value: 82.511
+    - type: ndcg_at_100
+      value: 86.531
+    - type: ndcg_at_1000
+      value: 87.244
+    - type: ndcg_at_3
+      value: 83.987
+    - type: ndcg_at_5
+      value: 82.46900000000001
+    - type: precision_at_1
+      value: 88.23
+    - type: precision_at_10
+      value: 41.245
+    - type: precision_at_100
+      value: 4.987
+    - type: precision_at_1000
+      value: 0.515
+    - type: precision_at_3
+      value: 73.675
+    - type: precision_at_5
+      value: 61.71
+    - type: recall_at_1
+      value: 26.436999999999998
+    - type: recall_at_10
+      value: 81.547
+    - type: recall_at_100
+      value: 94.548
+    - type: recall_at_1000
+      value: 98.197
+    - type: recall_at_3
+      value: 54.056000000000004
+    - type: recall_at_5
+      value: 67.93
+  - task:
+      type: Classification
+    dataset:
+      type: C-MTEB/TNews-classification
+      name: MTEB TNews
+      config: default
+      split: validation
+      revision: None
+    metrics:
+    - type: accuracy
+      value: 50.784
+    - type: f1
+      value: 48.89471168071432
+  - task:
+      type: Clustering
+    dataset:
+      type: C-MTEB/ThuNewsClusteringP2P
+      name: MTEB ThuNewsClusteringP2P
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: v_measure
+      value: 63.19039347990962
+  - task:
+      type: Clustering
+    dataset:
+      type: C-MTEB/ThuNewsClusteringS2S
+      name: MTEB ThuNewsClusteringS2S
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: v_measure
+      value: 55.357378578603225
+  - task:
+      type: Retrieval
+    dataset:
+      type: C-MTEB/VideoRetrieval
+      name: MTEB VideoRetrieval
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map_at_1
+      value: 58.8
+    - type: map_at_10
+      value: 68.623
+    - type: map_at_100
+      value: 69.074
+    - type: map_at_1000
+      value: 69.085
+    - type: map_at_3
+      value: 66.767
+    - type: map_at_5
+      value: 67.972
+    - type: mrr_at_1
+      value: 58.699999999999996
+    - type: mrr_at_10
+      value: 68.573
+    - type: mrr_at_100
+      value: 69.024
+    - type: mrr_at_1000
+      value: 69.035
+    - type: mrr_at_3
+      value: 66.717
+    - type: mrr_at_5
+      value: 67.92200000000001
+    - type: ndcg_at_1
+      value: 58.8
+    - type: ndcg_at_10
+      value: 73.038
+    - type: ndcg_at_100
+      value: 75.16199999999999
+    - type: ndcg_at_1000
+      value: 75.422
+    - type: ndcg_at_3
+      value: 69.297
+    - type: ndcg_at_5
+      value: 71.475
+    - type: precision_at_1
+      value: 58.8
+    - type: precision_at_10
+      value: 8.67
+    - type: precision_at_100
+      value: 0.9650000000000001
+    - type: precision_at_1000
+      value: 0.099
+    - type: precision_at_3
+      value: 25.533
+    - type: precision_at_5
+      value: 16.38
+    - type: recall_at_1
+      value: 58.8
+    - type: recall_at_10
+      value: 86.7
+    - type: recall_at_100
+      value: 96.5
+    - type: recall_at_1000
+      value: 98.5
+    - type: recall_at_3
+      value: 76.6
+    - type: recall_at_5
+      value: 81.89999999999999
+  - task:
+      type: Classification
+    dataset:
+      type: C-MTEB/waimai-classification
+      name: MTEB Waimai
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: accuracy
+      value: 86.61999999999999
+    - type: ap
+      value: 69.93149123197975
+    - type: f1
+      value: 84.99670691559903
 ---
+
+## stella model
+
+stella是一个通用的中文文本编码模型，目前有两个版本：base 和 large，**2个版本的模型均支持1024的输入长度**。
+
+完整的训练思路和训练过程已记录在[博客](https://zhuanlan.zhihu.com/p/655322183)，欢迎阅读讨论。
+
+**训练数据：**
+
+1. 开源数据(wudao_base_200GB[1]、m3e[2]和simclue[3])，着重挑选了长度大于512的文本
+2. 在通用语料库上使用LLM构造一批(question, paragraph)和(sentence, paragraph)数据
+
+**训练方法：**
+
+1. 对比学习损失函数
+2. 带有难负例的对比学习损失函数(分别基于bm25和vector构造了难负例)
+3. EWC(Elastic Weights Consolidation)[4]
+4. cosent loss[5]
+5. 每一种类型的数据一个迭代器，分别计算loss进行更新
+
+**初始权重：**\
+stella-base-zh和stella-large-zh分别以piccolo-base-zh[6]和piccolo-large-zh作为基础模型，512-1024的position embedding使用层次分解位置编码[7]进行初始化。\
+感谢商汤科技研究院开源的[piccolo系列模型](https://huggingface.co/sensenova)。
+
+stella is a general-purpose Chinese text encoding model, currently with two versions: base and large, **both of them
+support input lengths of 1024.**
+
+The training data mainly includes:
+
+1. Open-source training data (wudao_base_200GB, m3e, and simclue), with a focus on selecting texts with lengths greater
+   than 512.
+2. A batch of (question, paragraph) and (sentence, paragraph) data constructed on a general corpus using LLM.
+
+The loss functions mainly include:
+
+1. Contrastive learning loss function
+2. Contrastive learning loss function with hard negative examples (based on bm25 and vector hard negatives)
+3. EWC (Elastic Weights Consolidation)
+4. cosent loss
+
+Model weight initialization:\
+stella-base-zh and stella-large-zh use piccolo-base-zh and piccolo-large-zh as the base models, respectively, and the
+512-1024 position embedding uses the initialization strategy of hierarchical decomposed position encoding.
+
+Training strategy:\
+One iterator for each type of data, separately calculating the loss.
+
+## Metric
+
+#### C-MTEB leaderboard
+
+stella模型在C-MTEB[8]的结果，评测脚本请参见博客。
+
+|        Model Name        | Model Size (GB) | Dimension | Sequence Length | Average (35) | Classification (9) | Clustering (4) | Pair Classification (2) | Reranking (4) | Retrieval (8) | STS (8) |
+|:------------------------:|:---------------:|:---------:|:---------------:|:------------:|:------------------:|:--------------:|:-----------------------:|:-------------:|:-------------:|:-------:|
+|   **stella-large-zh**    |      0.65       |   1024    |    **1024**     |  **64.54**   |       67.62        |     48.65      |          78.72          |     65.98     |     71.02     |  58.3   |
+|    **stella-base-zh**    |       0.2       |    768    |    **1024**     |  **64.16**   |       67.77        |      48.7      |          76.09          |     66.95     |     71.07     |  56.54  |
+|     piccolo-large-zh     |      0.65       |   1024    |       512       |    64.11     |       67.03        |     47.04      |          78.38          |     65.98     |     70.93     |  58.02  |
+|       bge-large-zh       |       1.3       |   1024    |       512       |    63.96     |       68.32        |     48.39      |          78.94          |     65.11     |     71.52     |  54.98  |
+|     piccolo-base-zh      |       0.2       |    768    |       512       |    63.66     |       66.98        |     47.12      |          76.61          |     66.68     |     71.2      |  55.9   |
+| bge-large-zh-no-instruct |       1.3       |   1024    |       512       |     63.4     |       68.58        |     50.01      |          76.77          |     64.9      |     70.54     |   53    |
+|       [bge-base-zh       |      0.41       |    768    |       512       |     62.8     |       67.07        |     47.64      |          77.5           |     64.91     |     69.53     |  54.12  |
+
+#### Evaluation for long text
+
+经过实际观察发现，C-MTEB的评测数据长度基本都是小于512的，
+更致命的是那些长度大于512的文本，其重点都在前半部分
+这里以CMRC2018的数据为例说明这个问题：
+
+```
+question: 《无双大蛇z》是谁旗下ω-force开发的动作游戏？
+
+passage：《无双大蛇z》是光荣旗下ω-force开发的动作游戏，于2009年3月12日登陆索尼playstation3，并于2009年11月27日推......
+```
+
+passage长度为800多，大于512，但是对于这个question而言只需要前面40个字就足以检索，��的内容对于模型而言是一种噪声，反而降低了效果。\
+简言之，现有数据集的2个问题：\
+1）长度大于512的过少\
+2）即便大于512，对于检索而言也只需要前512的文本内容\
+导致**无法准确评估模型的长文本编码能力。**
+
+为了解决这个问题，搜集了相关开源数据并使用规则进行过滤，最终整理了6份长文本测试集,他们分别是：
+
+- CMRC2018，通用百科
+- CAIL，法律阅读理解
+- DRCD，繁体百科，已转简体
+- Military，军工问答
+- Squad，英文阅读理解，已转中文
+- Multifieldqa_zh，清华的大模型长文本理解能力评测数据[9]
+
+处理规则是选取答案在512长度之后的文本，短的测试数据会欠采样一下，长短文本占比约为1:2，所以模型既得理解短文本也得理解长文本。
+除了Military数据集，我们提供了其他5个测试数据的下载地址：https://drive.google.com/file/d/1WC6EWaCbVgz-vPMDFH4TwAMkLyh5WNcN/view?usp=sharing
+
+评测指标为Recall@5, 结果如下：
+
+|     Dataset     | piccolo-base-zh | piccolo-large-zh | bge-base-zh | bge-large-zh | stella-base-zh | stella-large-zh | 
+|:---------------:|:---------------:|:----------------:|:-----------:|:------------:|:--------------:|:---------------:|
+|    CMRC2018     |      94.34      |      93.82       |    91.56    |    93.12     |     96.08      |      95.56      | 
+|      CAIL       |      28.04      |      33.64       |    31.22    |    33.94     |     34.62      |      37.18      | 
+|      DRCD       |      78.25      |       77.9       |    78.34    |    80.26     |     86.14      |      84.58      | 
+|    Military     |      76.61      |      73.06       |    75.65    |    75.81     |     83.71      |      80.48      | 
+|      Squad      |      91.21      |      86.61       |    87.87    |    90.38     |     93.31      |      91.21      | 
+| Multifieldqa_zh |      81.41      |      83.92       |    83.92    |    83.42     |      79.9      |      80.4       | 
+|   **Average**   |      74.98      |      74.83       |    74.76    |    76.15     |   **78.96**    |    **78.24**    | 
+
+
+**注意：** 因为长文本评测数据数量稀少，所以构造时也使用了train部分，如果自行评测，请注意模型的训练数据以免数据泄露。
+
+## Usage
+
+本模型是在piccolo基础上训练的，因此**用法和piccolo完全一致**。\
+**注意**：在stella中instruction里的冒号是英文冒号, 即`查询: `和`结果: `。
+
+在sentence-transformer库中的使用方法：
+
+```python
+# 对于短对短数据集，下面是通用的使用方式
+from sentence_transformers import SentenceTransformer
+
+sentences = ["数据1", "数据2"]
+model = SentenceTransformer('infgrad/stella-base-zh')
+print(model.max_seq_length)
+embeddings_1 = model.encode(sentences, normalize_embeddings=True)
+embeddings_2 = model.encode(sentences, normalize_embeddings=True)
+similarity = embeddings_1 @ embeddings_2.T
+print(similarity)
+# 如果是短对长数据集，推荐添加instruction，来帮助模型更好地进行检索。
+# 注意instruction里的是英文的冒号
+```
+
+直接使用transformers库：
+
+```python
+from transformers import AutoModel, AutoTokenizer
+from sklearn.preprocessing import normalize
+
+model = AutoModel.from_pretrained('infgrad/stella-base-zh')
+tokenizer = AutoTokenizer.from_pretrained('infgrad/stella-base-zh')
+sentences = ["数据1", "数据ABCDEFGH"]
+batch_data = tokenizer(
+    batch_text_or_text_pairs=sentences,
+    padding="longest",
+    return_tensors="pt",
+    max_length=1024,
+    truncation=True,
+)
+attention_mask = batch_data["attention_mask"]
+model_output = model(**batch_data)
+last_hidden = model_output.last_hidden_state.masked_fill(~attention_mask[..., None].bool(), 0.0)
+vectors = last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
+vectors = normalize(vectors, norm="l2", axis=1, )
+print(vectors.shape)  # 2,768
+```
+
+## Training Detail
+
+**硬件：** 单卡A100-80GB
+
+**环境：** torch1.13.*; transformers-trainer + deepspeed + gradient-checkpointing
+
+**学习率：** 1e-6
+
+**batch_size：** base模型为1024，额外增加20%的难负例；large模型为768，额外增加20%的难负例
+
+**数据量：** 约100万，其中用LLM构造的数据约有200K. LLM模型大小为13b
+
+## ToDoList
+
+**评测的稳定性：**
+评测过程中发现Clustering任务会和官方的结果不一致，大约有±0.0x的小差距，基本上可以忽略不计，不影响评测结论。\
+但是不完全一样还是比较难理解的，本人试了bge和piccolo系列的模型都存在这个问题，个人猜测可能和使用的库、batch_size等环境有关。
+
+**更高质量的长文本训练和测试数据：** 训练数据多是用13b模型构造的，肯定会存在噪声。
+测试数据基本都是从mrc数据整理来的，所以问题都是factoid类型，不符合真实分布。
+
+**OOD的性能：** 虽然近期出现了很多向量编码模型，但是对于不是那么通用的domain，这一众模型包括stella、openai和cohere,
+它们的效果均比不上BM25。
+
+## Reference
+
+1. https://www.scidb.cn/en/detail?dataSetId=c6a3fe684227415a9db8e21bac4a15ab
+2. https://github.com/wangyuxinwhy/uniem
+3. https://github.com/CLUEbenchmark/SimCLUE
+4. https://arxiv.org/abs/1612.00796
+5. https://kexue.fm/archives/8847
+6. https://huggingface.co/sensenova/piccolo-base-zh
+7. https://kexue.fm/archives/7947
+8. https://github.com/FlagOpen/FlagEmbedding
+9. https://github.com/THUDM/LongBench
+
+
+

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "/triton-nas/users/tmp_zhangdun/public_model/piccolo-base-zh-1024",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 1024,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.2",
+  "type_vocab_size": 2,
+  "uniem_pooling_strategy": "last_mean",
+  "use_cache": true,
+  "vocab_size": 21128
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18bb804df8a017b436f207056465f9b134cbc50175bf611be78aa6b8de837790
+size 205397037

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1024,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}