Update README.md
Browse filesUpload Chinese benchmarks completed version
README.md
CHANGED
|
@@ -15,6 +15,48 @@ model-index:
|
|
| 15 |
metrics:
|
| 16 |
- type: v_measure
|
| 17 |
value: 4.6762575299584555
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
- task:
|
| 19 |
type: Classification
|
| 20 |
dataset:
|
|
@@ -164,6 +206,27 @@ model-index:
|
|
| 164 |
value: 53.987091172373944
|
| 165 |
- type: mrr
|
| 166 |
value: 67.65840038693224
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 167 |
- task:
|
| 168 |
type: BitextMining
|
| 169 |
dataset:
|
|
@@ -837,6 +900,27 @@ model-index:
|
|
| 837 |
value: 39.86267586660359
|
| 838 |
- type: f1
|
| 839 |
value: 71.07975139386433
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 840 |
- task:
|
| 841 |
type: Classification
|
| 842 |
dataset:
|
|
@@ -2631,6 +2715,27 @@ model-index:
|
|
| 2631 |
value: 72.7490265036156
|
| 2632 |
- type: f1
|
| 2633 |
value: 55.67596841902006
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2634 |
- task:
|
| 2635 |
type: PairClassification
|
| 2636 |
dataset:
|
|
@@ -2767,6 +2872,27 @@ model-index:
|
|
| 2767 |
value: 17.57085020242915
|
| 2768 |
- type: f1
|
| 2769 |
value: 13.699227854176883
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2770 |
- task:
|
| 2771 |
type: Clustering
|
| 2772 |
dataset:
|
|
@@ -2844,6 +2970,48 @@ model-index:
|
|
| 2844 |
value: 46.514972647839905
|
| 2845 |
- type: max_f1
|
| 2846 |
value: 53.48066298342542
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2847 |
- task:
|
| 2848 |
type: Classification
|
| 2849 |
dataset:
|
|
|
|
| 15 |
metrics:
|
| 16 |
- type: v_measure
|
| 17 |
value: 4.6762575299584555
|
| 18 |
+
- task:
|
| 19 |
+
type: STS
|
| 20 |
+
dataset:
|
| 21 |
+
type: C-MTEB/AFQMC
|
| 22 |
+
name: MTEB AFQMC
|
| 23 |
+
config: default
|
| 24 |
+
split: validation
|
| 25 |
+
revision: None
|
| 26 |
+
metrics:
|
| 27 |
+
- type: cos_sim_pearson
|
| 28 |
+
value: 39.92944665836267
|
| 29 |
+
- type: cos_sim_spearman
|
| 30 |
+
value: 44.25208147787637
|
| 31 |
+
- type: euclidean_pearson
|
| 32 |
+
value: 42.772842908404925
|
| 33 |
+
- type: euclidean_spearman
|
| 34 |
+
value: 44.25208147787637
|
| 35 |
+
- type: manhattan_pearson
|
| 36 |
+
value: 42.600565541302124
|
| 37 |
+
- type: manhattan_spearman
|
| 38 |
+
value: 44.10077657065955
|
| 39 |
+
- task:
|
| 40 |
+
type: STS
|
| 41 |
+
dataset:
|
| 42 |
+
type: C-MTEB/ATEC
|
| 43 |
+
name: MTEB ATEC
|
| 44 |
+
config: default
|
| 45 |
+
split: test
|
| 46 |
+
revision: None
|
| 47 |
+
metrics:
|
| 48 |
+
- type: cos_sim_pearson
|
| 49 |
+
value: 40.99236789888241
|
| 50 |
+
- type: cos_sim_spearman
|
| 51 |
+
value: 48.23930486989189
|
| 52 |
+
- type: euclidean_pearson
|
| 53 |
+
value: 48.58722571676781
|
| 54 |
+
- type: euclidean_spearman
|
| 55 |
+
value: 48.23930486989189
|
| 56 |
+
- type: manhattan_pearson
|
| 57 |
+
value: 48.46099247089918
|
| 58 |
+
- type: manhattan_spearman
|
| 59 |
+
value: 48.146434253428446
|
| 60 |
- task:
|
| 61 |
type: Classification
|
| 62 |
dataset:
|
|
|
|
| 206 |
value: 53.987091172373944
|
| 207 |
- type: mrr
|
| 208 |
value: 67.65840038693224
|
| 209 |
+
- task:
|
| 210 |
+
type: STS
|
| 211 |
+
dataset:
|
| 212 |
+
type: C-MTEB/BQ
|
| 213 |
+
name: MTEB BQ
|
| 214 |
+
config: default
|
| 215 |
+
split: test
|
| 216 |
+
revision: None
|
| 217 |
+
metrics:
|
| 218 |
+
- type: cos_sim_pearson
|
| 219 |
+
value: 54.56093256747345
|
| 220 |
+
- type: cos_sim_spearman
|
| 221 |
+
value: 56.27367976851523
|
| 222 |
+
- type: euclidean_pearson
|
| 223 |
+
value: 55.38528627937832
|
| 224 |
+
- type: euclidean_spearman
|
| 225 |
+
value: 56.27367284031196
|
| 226 |
+
- type: manhattan_pearson
|
| 227 |
+
value: 55.30402898692059
|
| 228 |
+
- type: manhattan_spearman
|
| 229 |
+
value: 56.19811385550433
|
| 230 |
- task:
|
| 231 |
type: BitextMining
|
| 232 |
dataset:
|
|
|
|
| 900 |
value: 39.86267586660359
|
| 901 |
- type: f1
|
| 902 |
value: 71.07975139386433
|
| 903 |
+
- task:
|
| 904 |
+
type: STS
|
| 905 |
+
dataset:
|
| 906 |
+
type: C-MTEB/LCQMC
|
| 907 |
+
name: MTEB LCQMC
|
| 908 |
+
config: default
|
| 909 |
+
split: test
|
| 910 |
+
revision: None
|
| 911 |
+
metrics:
|
| 912 |
+
- type: cos_sim_pearson
|
| 913 |
+
value: 68.22943962011342
|
| 914 |
+
- type: cos_sim_spearman
|
| 915 |
+
value: 74.09285052519111
|
| 916 |
+
- type: euclidean_pearson
|
| 917 |
+
value: 72.99465307442854
|
| 918 |
+
- type: euclidean_spearman
|
| 919 |
+
value: 74.09285052519111
|
| 920 |
+
- type: manhattan_pearson
|
| 921 |
+
value: 73.00139084439715
|
| 922 |
+
- type: manhattan_spearman
|
| 923 |
+
value: 74.07472412844967
|
| 924 |
- task:
|
| 925 |
type: Classification
|
| 926 |
dataset:
|
|
|
|
| 2715 |
value: 72.7490265036156
|
| 2716 |
- type: f1
|
| 2717 |
value: 55.67596841902006
|
| 2718 |
+
- task:
|
| 2719 |
+
type: STS
|
| 2720 |
+
dataset:
|
| 2721 |
+
type: C-MTEB/PAWSX
|
| 2722 |
+
name: MTEB PAWSX
|
| 2723 |
+
config: default
|
| 2724 |
+
split: test
|
| 2725 |
+
revision: None
|
| 2726 |
+
metrics:
|
| 2727 |
+
- type: cos_sim_pearson
|
| 2728 |
+
value: 11.928849138540556
|
| 2729 |
+
- type: cos_sim_spearman
|
| 2730 |
+
value: 12.182908575820269
|
| 2731 |
+
- type: euclidean_pearson
|
| 2732 |
+
value: 14.455528347393356
|
| 2733 |
+
- type: euclidean_spearman
|
| 2734 |
+
value: 12.182908575820269
|
| 2735 |
+
- type: manhattan_pearson
|
| 2736 |
+
value: 14.506141564058982
|
| 2737 |
+
- type: manhattan_spearman
|
| 2738 |
+
value: 12.25397844569351
|
| 2739 |
- task:
|
| 2740 |
type: PairClassification
|
| 2741 |
dataset:
|
|
|
|
| 2872 |
value: 17.57085020242915
|
| 2873 |
- type: f1
|
| 2874 |
value: 13.699227854176883
|
| 2875 |
+
- task:
|
| 2876 |
+
type: STS
|
| 2877 |
+
dataset:
|
| 2878 |
+
type: C-MTEB/QBQTC
|
| 2879 |
+
name: MTEB QBQTC
|
| 2880 |
+
config: default
|
| 2881 |
+
split: test
|
| 2882 |
+
revision: None
|
| 2883 |
+
metrics:
|
| 2884 |
+
- type: cos_sim_pearson
|
| 2885 |
+
value: 28.3302552745107
|
| 2886 |
+
- type: cos_sim_spearman
|
| 2887 |
+
value: 29.935415470590353
|
| 2888 |
+
- type: euclidean_pearson
|
| 2889 |
+
value: 28.406125326818536
|
| 2890 |
+
- type: euclidean_spearman
|
| 2891 |
+
value: 29.935394196825893
|
| 2892 |
+
- type: manhattan_pearson
|
| 2893 |
+
value: 28.535226539445524
|
| 2894 |
+
- type: manhattan_spearman
|
| 2895 |
+
value: 30.110291572017182
|
| 2896 |
- task:
|
| 2897 |
type: Clustering
|
| 2898 |
dataset:
|
|
|
|
| 2970 |
value: 46.514972647839905
|
| 2971 |
- type: max_f1
|
| 2972 |
value: 53.48066298342542
|
| 2973 |
+
- task:
|
| 2974 |
+
type: STS
|
| 2975 |
+
dataset:
|
| 2976 |
+
type: mteb/sts22-crosslingual-sts
|
| 2977 |
+
name: MTEB STS22 (zh)
|
| 2978 |
+
config: zh
|
| 2979 |
+
split: test
|
| 2980 |
+
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
|
| 2981 |
+
metrics:
|
| 2982 |
+
- type: cos_sim_pearson
|
| 2983 |
+
value: 65.06521909332356
|
| 2984 |
+
- type: cos_sim_spearman
|
| 2985 |
+
value: 66.05535986394263
|
| 2986 |
+
- type: euclidean_pearson
|
| 2987 |
+
value: 65.77030042276493
|
| 2988 |
+
- type: euclidean_spearman
|
| 2989 |
+
value: 66.05535986394263
|
| 2990 |
+
- type: manhattan_pearson
|
| 2991 |
+
value: 65.91869122430603
|
| 2992 |
+
- type: manhattan_spearman
|
| 2993 |
+
value: 66.15477943325074
|
| 2994 |
+
- task:
|
| 2995 |
+
type: STS
|
| 2996 |
+
dataset:
|
| 2997 |
+
type: C-MTEB/STSB
|
| 2998 |
+
name: MTEB STSB
|
| 2999 |
+
config: default
|
| 3000 |
+
split: test
|
| 3001 |
+
revision: None
|
| 3002 |
+
metrics:
|
| 3003 |
+
- type: cos_sim_pearson
|
| 3004 |
+
value: 79.77776864632986
|
| 3005 |
+
- type: cos_sim_spearman
|
| 3006 |
+
value: 80.54295891407341
|
| 3007 |
+
- type: euclidean_pearson
|
| 3008 |
+
value: 80.15310049503712
|
| 3009 |
+
- type: euclidean_spearman
|
| 3010 |
+
value: 80.54295891407341
|
| 3011 |
+
- type: manhattan_pearson
|
| 3012 |
+
value: 80.16703044389185
|
| 3013 |
+
- type: manhattan_spearman
|
| 3014 |
+
value: 80.61034669195091
|
| 3015 |
- task:
|
| 3016 |
type: Classification
|
| 3017 |
dataset:
|