Upload README.md

README.md

@@ -1,5 +1,4 @@
 ---
-library_name: sentence-transformers
 model-index:
 - name: XYZ-embedding-zh
   results:
@@ -11,11 +10,11 @@ model-index:
       type: C-MTEB/CMedQAv1-reranking
     metrics:
     - type: map
-      value: 89.61792115239176
+      value: 89.9766367822762
     - type: mrr
-      value: 91.46722222222222
+      value: 91.88896825396824
     - type: main_score
-      value: 89.61792115239176
+      value: 89.9766367822762
     task:
       type: Reranking
   - dataset:
@@ -26,11 +25,11 @@ model-index:
       type: C-MTEB/CMedQAv2-reranking
     metrics:
     - type: map
-      value: 89.22040591564271
+      value: 89.04628340075982
     - type: mrr
-      value: 91.2995238095238
+      value: 91.21702380952381
     - type: main_score
-      value: 89.22040591564271
+      value: 89.04628340075982
     task:
       type: Reranking
   - dataset:
@@ -41,67 +40,67 @@ model-index:
       type: C-MTEB/CmedqaRetrieval
     metrics:
     - type: map_at_1
-      value: 27.939000000000004
+      value: 27.796
     - type: map_at_10
-      value: 41.227999999999994
+      value: 41.498000000000005
     - type: map_at_100
-      value: 43.018
+      value: 43.332
     - type: map_at_1000
-      value: 43.120000000000005
+      value: 43.429
     - type: map_at_3
-      value: 36.895
+      value: 37.172
     - type: map_at_5
-      value: 39.373999999999995
+      value: 39.617000000000004
     - type: mrr_at_1
-      value: 42.136
+      value: 42.111
     - type: mrr_at_10
-      value: 50.394000000000005
+      value: 50.726000000000006
     - type: mrr_at_100
-      value: 51.288
+      value: 51.632
     - type: mrr_at_1000
-      value: 51.324000000000005
+      value: 51.67
     - type: mrr_at_3
-      value: 47.887
+      value: 48.429
     - type: mrr_at_5
-      value: 49.362
+      value: 49.662
     - type: ndcg_at_1
-      value: 42.136
+      value: 42.111
     - type: ndcg_at_10
-      value: 47.899
+      value: 48.294
     - type: ndcg_at_100
-      value: 54.730999999999995
+      value: 55.135999999999996
     - type: ndcg_at_1000
-      value: 56.462999999999994
+      value: 56.818000000000005
     - type: ndcg_at_3
-      value: 42.66
+      value: 43.185
     - type: ndcg_at_5
-      value: 44.913
+      value: 45.266
     - type: precision_at_1
-      value: 42.136
+      value: 42.111
     - type: precision_at_10
-      value: 10.52
+      value: 10.635
     - type: precision_at_100
-      value: 1.6070000000000002
+      value: 1.619
     - type: precision_at_1000
       value: 0.183
     - type: precision_at_3
-      value: 24.064
+      value: 24.539
     - type: precision_at_5
-      value: 17.374000000000002
+      value: 17.644000000000002
     - type: recall_at_1
-      value: 27.939000000000004
+      value: 27.796
     - type: recall_at_10
-      value: 58.29600000000001
+      value: 59.034
     - type: recall_at_100
-      value: 86.504
+      value: 86.991
     - type: recall_at_1000
-      value: 98.105
+      value: 98.304
     - type: recall_at_3
-      value: 42.475
+      value: 43.356
     - type: recall_at_5
-      value: 49.454
+      value: 49.998
     - type: main_score
-      value: 47.899
+      value: 48.294
     task:
       type: Retrieval
   - dataset:
@@ -112,67 +111,67 @@ model-index:
       type: C-MTEB/CovidRetrieval
     metrics:
     - type: map_at_1
-      value: 77.371
+      value: 80.479
     - type: map_at_10
-      value: 85.229
+      value: 87.984
     - type: map_at_100
-      value: 85.358
+      value: 88.036
     - type: map_at_1000
-      value: 85.36
+      value: 88.03699999999999
     - type: map_at_3
-      value: 84.176
+      value: 87.083
     - type: map_at_5
-      value: 84.79299999999999
+      value: 87.694
     - type: mrr_at_1
-      value: 77.661
+      value: 80.927
     - type: mrr_at_10
-      value: 85.207
+      value: 88.046
     - type: mrr_at_100
-      value: 85.33699999999999
+      value: 88.099
     - type: mrr_at_1000
-      value: 85.339
+      value: 88.1
     - type: mrr_at_3
-      value: 84.229
+      value: 87.215
     - type: mrr_at_5
-      value: 84.79299999999999
+      value: 87.768
     - type: ndcg_at_1
-      value: 77.766
+      value: 80.927
     - type: ndcg_at_10
-      value: 88.237
+      value: 90.756
     - type: ndcg_at_100
-      value: 88.777
+      value: 90.96
     - type: ndcg_at_1000
-      value: 88.818
+      value: 90.975
     - type: ndcg_at_3
-      value: 86.16
+      value: 89.032
     - type: ndcg_at_5
-      value: 87.22
+      value: 90.106
     - type: precision_at_1
-      value: 77.766
+      value: 80.927
     - type: precision_at_10
-      value: 9.841999999999999
+      value: 10.011000000000001
     - type: precision_at_100
-      value: 1.0070000000000001
+      value: 1.009
     - type: precision_at_1000
       value: 0.101
     - type: precision_at_3
-      value: 30.875000000000004
+      value: 31.752999999999997
     - type: precision_at_5
-      value: 19.073
+      value: 19.6
     - type: recall_at_1
-      value: 77.371
+      value: 80.479
     - type: recall_at_10
-      value: 97.366
+      value: 99.05199999999999
     - type: recall_at_100
-      value: 99.684
+      value: 99.895
     - type: recall_at_1000
       value: 100.0
     - type: recall_at_3
-      value: 91.702
+      value: 94.494
     - type: recall_at_5
-      value: 94.31
+      value: 97.102
     - type: main_score
-      value: 88.237
+      value: 90.756
     task:
       type: Retrieval
   - dataset:
@@ -183,67 +182,67 @@ model-index:
       type: C-MTEB/DuRetrieval
     metrics:
     - type: map_at_1
-      value: 27.772000000000002
+      value: 27.853
     - type: map_at_10
-      value: 84.734
+      value: 85.13199999999999
     - type: map_at_100
-      value: 87.298
+      value: 87.688
     - type: map_at_1000
-      value: 87.32900000000001
+      value: 87.712
     - type: map_at_3
-      value: 59.431
+      value: 59.705
     - type: map_at_5
-      value: 74.82900000000001
+      value: 75.139
     - type: mrr_at_1
       value: 93.65
     - type: mrr_at_10
-      value: 95.568
+      value: 95.682
     - type: mrr_at_100
-      value: 95.608
+      value: 95.722
     - type: mrr_at_1000
-      value: 95.609
+      value: 95.724
     - type: mrr_at_3
-      value: 95.267
+      value: 95.467
     - type: mrr_at_5
-      value: 95.494
+      value: 95.612
     - type: ndcg_at_1
       value: 93.65
     - type: ndcg_at_10
-      value: 90.794
+      value: 91.155
     - type: ndcg_at_100
-      value: 92.88300000000001
+      value: 93.183
     - type: ndcg_at_1000
-      value: 93.144
+      value: 93.38499999999999
     - type: ndcg_at_3
-      value: 90.32
+      value: 90.648
     - type: ndcg_at_5
-      value: 89.242
+      value: 89.47699999999999
     - type: precision_at_1
       value: 93.65
     - type: precision_at_10
-      value: 42.9
+      value: 43.11
     - type: precision_at_100
-      value: 4.835
+      value: 4.854
     - type: precision_at_1000
-      value: 0.49
+      value: 0.49100000000000005
     - type: precision_at_3
-      value: 80.85
+      value: 81.11699999999999
     - type: precision_at_5
-      value: 68.14
+      value: 68.28999999999999
     - type: recall_at_1
-      value: 27.772000000000002
+      value: 27.853
     - type: recall_at_10
-      value: 91.183
+      value: 91.678
     - type: recall_at_100
-      value: 98.219
+      value: 98.553
     - type: recall_at_1000
-      value: 99.55000000000001
+      value: 99.553
     - type: recall_at_3
-      value: 60.911
+      value: 61.381
     - type: recall_at_5
-      value: 78.31099999999999
+      value: 78.605
     - type: main_score
-      value: 90.794
+      value: 91.155
     task:
       type: Retrieval
   - dataset:
@@ -254,67 +253,67 @@ model-index:
       type: C-MTEB/EcomRetrieval
     metrics:
     - type: map_at_1
-      value: 54.6
+      value: 54.50000000000001
     - type: map_at_10
-      value: 64.742
+      value: 65.167
     - type: map_at_100
-      value: 65.289
+      value: 65.664
     - type: map_at_1000
-      value: 65.29700000000001
+      value: 65.67399999999999
     - type: map_at_3
-      value: 62.183
+      value: 62.633
     - type: map_at_5
-      value: 63.883
+      value: 64.208
     - type: mrr_at_1
-      value: 54.6
+      value: 54.50000000000001
     - type: mrr_at_10
-      value: 64.742
+      value: 65.167
     - type: mrr_at_100
-      value: 65.289
+      value: 65.664
     - type: mrr_at_1000
-      value: 65.29700000000001
+      value: 65.67399999999999
     - type: mrr_at_3
-      value: 62.183
+      value: 62.633
     - type: mrr_at_5
-      value: 63.883
+      value: 64.208
     - type: ndcg_at_1
-      value: 54.6
+      value: 54.50000000000001
     - type: ndcg_at_10
-      value: 69.719
+      value: 70.294
     - type: ndcg_at_100
-      value: 72.148
+      value: 72.564
     - type: ndcg_at_1000
-      value: 72.393
+      value: 72.841
     - type: ndcg_at_3
-      value: 64.606
+      value: 65.128
     - type: ndcg_at_5
-      value: 67.682
+      value: 67.96799999999999
     - type: precision_at_1
-      value: 54.6
+      value: 54.50000000000001
     - type: precision_at_10
-      value: 8.53
+      value: 8.64
     - type: precision_at_100
-      value: 0.962
+      value: 0.967
     - type: precision_at_1000
-      value: 0.098
+      value: 0.099
     - type: precision_at_3
-      value: 23.867
+      value: 24.099999999999998
     - type: precision_at_5
-      value: 15.82
+      value: 15.840000000000002
     - type: recall_at_1
-      value: 54.6
+      value: 54.50000000000001
     - type: recall_at_10
-      value: 85.3
+      value: 86.4
     - type: recall_at_100
-      value: 96.2
+      value: 96.7
     - type: recall_at_1000
-      value: 98.2
+      value: 98.9
     - type: recall_at_3
-      value: 71.6
+      value: 72.3
     - type: recall_at_5
-      value: 79.10000000000001
+      value: 79.2
     - type: main_score
-      value: 69.719
+      value: 70.294
     task:
       type: Retrieval
   - dataset:
@@ -325,11 +324,11 @@ model-index:
       type: C-MTEB/Mmarco-reranking
     metrics:
     - type: map
-      value: 35.30260957061897
+      value: 37.68251937316638
     - type: mrr
-      value: 34.098015873015875
+      value: 36.61746031746032
     - type: main_score
-      value: 35.30260957061897
+      value: 37.68251937316638
     task:
       type: Reranking
   - dataset:
@@ -340,67 +339,67 @@ model-index:
       type: C-MTEB/MMarcoRetrieval
     metrics:
     - type: map_at_1
-      value: 69.51899999999999
+      value: 69.401
     - type: map_at_10
-      value: 78.816
+      value: 78.8
     - type: map_at_100
-      value: 79.08500000000001
+      value: 79.077
     - type: map_at_1000
-      value: 79.091
+      value: 79.081
     - type: map_at_3
-      value: 76.999
+      value: 76.97
     - type: map_at_5
-      value: 78.194
+      value: 78.185
     - type: mrr_at_1
-      value: 71.80499999999999
+      value: 71.719
     - type: mrr_at_10
-      value: 79.29899999999999
+      value: 79.327
     - type: mrr_at_100
-      value: 79.532
+      value: 79.56400000000001
     - type: mrr_at_1000
-      value: 79.537
+      value: 79.56800000000001
     - type: mrr_at_3
-      value: 77.703
+      value: 77.736
     - type: mrr_at_5
-      value: 78.75999999999999
+      value: 78.782
     - type: ndcg_at_1
-      value: 71.80499999999999
+      value: 71.719
     - type: ndcg_at_10
-      value: 82.479
+      value: 82.505
     - type: ndcg_at_100
-      value: 83.611
+      value: 83.673
     - type: ndcg_at_1000
-      value: 83.76400000000001
+      value: 83.786
     - type: ndcg_at_3
-      value: 79.065
+      value: 79.07600000000001
     - type: ndcg_at_5
-      value: 81.092
+      value: 81.122
     - type: precision_at_1
-      value: 71.80499999999999
+      value: 71.719
     - type: precision_at_10
-      value: 9.91
+      value: 9.924
     - type: precision_at_100
-      value: 1.046
+      value: 1.049
     - type: precision_at_1000
       value: 0.106
     - type: precision_at_3
-      value: 29.727999999999998
+      value: 29.742
     - type: precision_at_5
-      value: 18.908
+      value: 18.937
     - type: recall_at_1
-      value: 69.51899999999999
+      value: 69.401
     - type: recall_at_10
-      value: 93.24
+      value: 93.349
     - type: recall_at_100
-      value: 98.19099999999999
+      value: 98.492
     - type: recall_at_1000
-      value: 99.36500000000001
+      value: 99.384
     - type: recall_at_3
-      value: 84.308
+      value: 84.385
     - type: recall_at_5
-      value: 89.119
+      value: 89.237
     - type: main_score
-      value: 82.479
+      value: 82.505
     task:
       type: Retrieval
   - dataset:
@@ -413,65 +412,65 @@ model-index:
     - type: map_at_1
       value: 57.8
     - type: map_at_10
-      value: 64.215
+      value: 64.696
     - type: map_at_100
-      value: 64.78
+      value: 65.294
     - type: map_at_1000
-      value: 64.81099999999999
+      value: 65.328
     - type: map_at_3
-      value: 62.64999999999999
+      value: 62.949999999999996
     - type: map_at_5
-      value: 63.57000000000001
+      value: 64.095
     - type: mrr_at_1
       value: 58.099999999999994
     - type: mrr_at_10
-      value: 64.371
+      value: 64.85
     - type: mrr_at_100
-      value: 64.936
+      value: 65.448
     - type: mrr_at_1000
-      value: 64.96600000000001
+      value: 65.482
     - type: mrr_at_3
-      value: 62.8
+      value: 63.1
     - type: mrr_at_5
-      value: 63.739999999999995
+      value: 64.23
     - type: ndcg_at_1
       value: 57.8
     - type: ndcg_at_10
-      value: 67.415
+      value: 68.041
     - type: ndcg_at_100
-      value: 70.38799999999999
+      value: 71.074
     - type: ndcg_at_1000
-      value: 71.229
+      value: 71.919
     - type: ndcg_at_3
-      value: 64.206
+      value: 64.584
     - type: ndcg_at_5
-      value: 65.858
+      value: 66.625
     - type: precision_at_1
       value: 57.8
     - type: precision_at_10
-      value: 7.75
+      value: 7.85
     - type: precision_at_100
-      value: 0.919
+      value: 0.9289999999999999
     - type: precision_at_1000
       value: 0.099
     - type: precision_at_3
-      value: 22.900000000000002
+      value: 23.1
     - type: precision_at_5
-      value: 14.540000000000001
+      value: 14.84
     - type: recall_at_1
       value: 57.8
     - type: recall_at_10
-      value: 77.5
+      value: 78.5
     - type: recall_at_100
-      value: 91.9
+      value: 92.9
     - type: recall_at_1000
-      value: 98.6
+      value: 99.4
     - type: recall_at_3
-      value: 68.7
+      value: 69.3
     - type: recall_at_5
-      value: 72.7
+      value: 74.2
     - type: main_score
-      value: 67.415
+      value: 68.041
     task:
       type: Retrieval
   - dataset:
@@ -482,11 +481,11 @@ model-index:
       type: C-MTEB/T2Reranking
     metrics:
     - type: map
-      value: 69.06615146698508
+      value: 69.13287570713865
     - type: mrr
-      value: 79.7588755091294
+      value: 79.95326487625066
     - type: main_score
-      value: 69.06615146698508
+      value: 69.13287570713865
     task:
       type: Reranking
   - dataset:
@@ -497,67 +496,67 @@ model-index:
       type: C-MTEB/T2Retrieval
     metrics:
     - type: map_at_1
-      value: 28.084999999999997
+      value: 28.041
     - type: map_at_10
-      value: 78.583
+      value: 78.509
     - type: map_at_100
-      value: 82.14399999999999
+      value: 82.083
     - type: map_at_1000
-      value: 82.204
+      value: 82.143
     - type: map_at_3
-      value: 55.422000000000004
+      value: 55.345
     - type: map_at_5
-      value: 67.973
+      value: 67.899
     - type: mrr_at_1
-      value: 91.014
+      value: 90.86
     - type: mrr_at_10
-      value: 93.381
+      value: 93.31
     - type: mrr_at_100
-      value: 93.45400000000001
+      value: 93.388
     - type: mrr_at_1000
-      value: 93.45599999999999
+      value: 93.391
     - type: mrr_at_3
-      value: 92.99300000000001
+      value: 92.92200000000001
     - type: mrr_at_5
-      value: 93.234
+      value: 93.167
     - type: ndcg_at_1
-      value: 91.014
+      value: 90.86
     - type: ndcg_at_10
-      value: 85.931
+      value: 85.875
     - type: ndcg_at_100
-      value: 89.31
+      value: 89.269
     - type: ndcg_at_1000
-      value: 89.869
+      value: 89.827
     - type: ndcg_at_3
-      value: 87.348
+      value: 87.254
     - type: ndcg_at_5
-      value: 85.929
+      value: 85.855
     - type: precision_at_1
-      value: 91.014
+      value: 90.86
     - type: precision_at_10
-      value: 42.495
+      value: 42.488
     - type: precision_at_100
-      value: 5.029999999999999
+      value: 5.029
     - type: precision_at_1000
       value: 0.516
     - type: precision_at_3
-      value: 76.248
+      value: 76.172
     - type: precision_at_5
-      value: 63.817
+      value: 63.759
     - type: recall_at_1
-      value: 28.084999999999997
+      value: 28.041
     - type: recall_at_10
-      value: 84.88
+      value: 84.829
     - type: recall_at_100
-      value: 95.902
+      value: 95.89999999999999
     - type: recall_at_1000
-      value: 98.699
+      value: 98.665
     - type: recall_at_3
-      value: 57.113
+      value: 57.009
     - type: recall_at_5
-      value: 71.251
+      value: 71.188
     - type: main_score
-      value: 85.931
+      value: 85.875
     task:
       type: Retrieval
   - dataset:
@@ -568,121 +567,99 @@ model-index:
       type: C-MTEB/VideoRetrieval
     metrics:
     - type: map_at_1
-      value: 66.4
+      value: 67.30000000000001
     - type: map_at_10
-      value: 75.86
+      value: 76.819
     - type: map_at_100
-      value: 76.185
+      value: 77.141
     - type: map_at_1000
-      value: 76.188
+      value: 77.142
     - type: map_at_3
-      value: 74.167
+      value: 75.233
     - type: map_at_5
-      value: 75.187
+      value: 76.163
     - type: mrr_at_1
-      value: 66.4
+      value: 67.30000000000001
     - type: mrr_at_10
-      value: 75.86
+      value: 76.819
     - type: mrr_at_100
-      value: 76.185
+      value: 77.141
     - type: mrr_at_1000
-      value: 76.188
+      value: 77.142
     - type: mrr_at_3
-      value: 74.167
+      value: 75.233
     - type: mrr_at_5
-      value: 75.187
+      value: 76.163
     - type: ndcg_at_1
-      value: 66.4
+      value: 67.30000000000001
     - type: ndcg_at_10
-      value: 80.03099999999999
+      value: 80.93599999999999
     - type: ndcg_at_100
-      value: 81.459
+      value: 82.311
     - type: ndcg_at_1000
-      value: 81.527
+      value: 82.349
     - type: ndcg_at_3
-      value: 76.621
+      value: 77.724
     - type: ndcg_at_5
-      value: 78.446
+      value: 79.406
     - type: precision_at_1
-      value: 66.4
+      value: 67.30000000000001
     - type: precision_at_10
-      value: 9.29
+      value: 9.36
     - type: precision_at_100
-      value: 0.992
+      value: 0.996
     - type: precision_at_1000
       value: 0.1
     - type: precision_at_3
-      value: 27.900000000000002
+      value: 28.299999999999997
     - type: precision_at_5
-      value: 17.62
+      value: 17.8
     - type: recall_at_1
-      value: 66.4
+      value: 67.30000000000001
     - type: recall_at_10
-      value: 92.9
+      value: 93.60000000000001
     - type: recall_at_100
-      value: 99.2
+      value: 99.6
     - type: recall_at_1000
-      value: 99.7
+      value: 99.9
     - type: recall_at_3
-      value: 83.7
+      value: 84.89999999999999
     - type: recall_at_5
-      value: 88.1
+      value: 89.0
     - type: main_score
-      value: 80.03099999999999
+      value: 80.93599999999999
     task:
       type: Retrieval
-pipeline_tag: sentence-similarity
 tags:
-- sentence-transformers
-- feature-extraction
-- sentence-similarity
 - mteb
 ---
--
-
-# XYZ-embedding-zh
+XYZ-embedding-zh
 
-This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1792 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+## Usage (Sentence Transformers)
 
-<!--- Describe your model here -->
+First install the Sentence Transformers library:
 
-## Usage (Sentence-Transformers)
-
-Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
-
-```
+```bash
 pip install -U sentence-transformers
 ```
-
-Then you can use the model like this:
-
+Then you can load this model and run inference.
 ```python
 from sentence_transformers import SentenceTransformer
-sentences = ["This is an example sentence", "Each sentence is converted"]
 
-model = SentenceTransformer('fangxq/XYZ-embedding-zh')
+# Download from the 🤗 Hub
+model = SentenceTransformer("fangxq/XYZ-embedding-zh")
+# Run inference
+sentences = [
+    'The weather is lovely today.',
+    "It's so sunny outside!",
+    'He drove to the stadium.',
+]
 embeddings = model.encode(sentences)
-print(embeddings)
-```
-
-
-
-## Evaluation Results
-
-<!--- Describe how your model was evaluated -->
-
-For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
+print(embeddings.shape)
+# [3, 1792]
 
-
-
-## Full Model Architecture
-```
-SentenceTransformer(
-  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
-  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
-  (2): Dense({'in_features': 1024, 'out_features': 1792, 'bias': True, 'activation_function': 'torch.nn.modules.linear.Identity'})
-)
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
 ```
-
-## Citing & Authors
-