Specify library_name metadata

#1
by tomaarsen HF staff - opened
Files changed (1) hide show
  1. README.md +30 -29
README.md CHANGED
@@ -946,7 +946,7 @@ model-index:
946
  - type: precision_at_10
947
  value: 5.743
948
  - type: precision_at_100
949
- value: 1.0
950
  - type: precision_at_1000
951
  value: 0.14300000000000002
952
  - type: precision_at_3
@@ -2223,7 +2223,7 @@ model-index:
2223
  - type: map_at_5
2224
  value: 70.15
2225
  - type: mrr_at_1
2226
- value: 64.0
2227
  - type: mrr_at_10
2228
  value: 71.82300000000001
2229
  - type: mrr_at_100
@@ -2235,7 +2235,7 @@ model-index:
2235
  - type: mrr_at_5
2236
  value: 71.11699999999999
2237
  - type: ndcg_at_1
2238
- value: 64.0
2239
  - type: ndcg_at_10
2240
  value: 75.286
2241
  - type: ndcg_at_100
@@ -2247,7 +2247,7 @@ model-index:
2247
  - type: ndcg_at_5
2248
  value: 73.36399999999999
2249
  - type: precision_at_1
2250
- value: 64.0
2251
  - type: precision_at_10
2252
  value: 9.9
2253
  - type: precision_at_100
@@ -2288,7 +2288,7 @@ model-index:
2288
  - type: cos_sim_precision
2289
  value: 92.3076923076923
2290
  - type: cos_sim_recall
2291
- value: 90.0
2292
  - type: dot_accuracy
2293
  value: 99.7980198019802
2294
  - type: dot_ap
@@ -2399,7 +2399,7 @@ model-index:
2399
  - type: map_at_5
2400
  value: 0.941
2401
  - type: mrr_at_1
2402
- value: 76.0
2403
  - type: mrr_at_10
2404
  value: 85.85199999999999
2405
  - type: mrr_at_100
@@ -2411,7 +2411,7 @@ model-index:
2411
  - type: mrr_at_5
2412
  value: 85.56700000000001
2413
  - type: ndcg_at_1
2414
- value: 71.0
2415
  - type: ndcg_at_10
2416
  value: 69.60300000000001
2417
  - type: ndcg_at_100
@@ -2423,7 +2423,7 @@ model-index:
2423
  - type: ndcg_at_5
2424
  value: 71.17599999999999
2425
  - type: precision_at_1
2426
- value: 76.0
2427
  - type: precision_at_10
2428
  value: 74.2
2429
  - type: precision_at_100
@@ -2456,13 +2456,13 @@ model-index:
2456
  revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
2457
  metrics:
2458
  - type: accuracy
2459
- value: 8.0
2460
  - type: f1
2461
  value: 6.298401229470593
2462
  - type: precision
2463
  value: 5.916991709050532
2464
  - type: recall
2465
- value: 8.0
2466
  - task:
2467
  type: BitextMining
2468
  dataset:
@@ -2592,13 +2592,13 @@ model-index:
2592
  revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
2593
  metrics:
2594
  - type: accuracy
2595
- value: 22.0
2596
  - type: f1
2597
  value: 17.4576947358322
2598
  - type: precision
2599
  value: 16.261363669827777
2600
  - type: recall
2601
- value: 22.0
2602
  - task:
2603
  type: BitextMining
2604
  dataset:
@@ -2745,13 +2745,13 @@ model-index:
2745
  revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
2746
  metrics:
2747
  - type: accuracy
2748
- value: 0.0
2749
  - type: f1
2750
- value: 0.0
2751
  - type: precision
2752
- value: 0.0
2753
  - type: recall
2754
- value: 0.0
2755
  - task:
2756
  type: BitextMining
2757
  dataset:
@@ -2813,13 +2813,13 @@ model-index:
2813
  revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
2814
  metrics:
2815
  - type: accuracy
2816
- value: 4.0
2817
  - type: f1
2818
  value: 2.3800704501963432
2819
  - type: precision
2820
  value: 2.0919368034607455
2821
  - type: recall
2822
- value: 4.0
2823
  - task:
2824
  type: BitextMining
2825
  dataset:
@@ -2949,13 +2949,13 @@ model-index:
2949
  revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
2950
  metrics:
2951
  - type: accuracy
2952
- value: 21.0
2953
  - type: f1
2954
  value: 18.965901242066018
2955
  - type: precision
2956
  value: 18.381437375171
2957
  - type: recall
2958
- value: 21.0
2959
  - task:
2960
  type: BitextMining
2961
  dataset:
@@ -3119,13 +3119,13 @@ model-index:
3119
  revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
3120
  metrics:
3121
  - type: accuracy
3122
- value: 1.0
3123
  - type: f1
3124
  value: 0.7764001197963462
3125
  - type: precision
3126
  value: 0.7551049317943337
3127
  - type: recall
3128
- value: 1.0
3129
  - task:
3130
  type: BitextMining
3131
  dataset:
@@ -3289,13 +3289,13 @@ model-index:
3289
  revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
3290
  metrics:
3291
  - type: accuracy
3292
- value: 6.0
3293
  - type: f1
3294
  value: 4.58716840215435
3295
  - type: precision
3296
  value: 4.303119297298687
3297
  - type: recall
3298
- value: 6.0
3299
  - task:
3300
  type: BitextMining
3301
  dataset:
@@ -3833,13 +3833,13 @@ model-index:
3833
  revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
3834
  metrics:
3835
  - type: accuracy
3836
- value: 10.0
3837
  - type: f1
3838
  value: 7.351901305737391
3839
  - type: precision
3840
  value: 6.759061952118555
3841
  - type: recall
3842
- value: 10.0
3843
  - task:
3844
  type: BitextMining
3845
  dataset:
@@ -3918,13 +3918,13 @@ model-index:
3918
  revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
3919
  metrics:
3920
  - type: accuracy
3921
- value: 3.0
3922
  - type: f1
3923
  value: 1.5834901411814404
3924
  - type: precision
3925
  value: 1.3894010894944848
3926
  - type: recall
3927
- value: 3.0
3928
  - task:
3929
  type: BitextMining
3930
  dataset:
@@ -4571,6 +4571,7 @@ model-index:
4571
  language:
4572
  - en
4573
  license: mit
 
4574
  ---
4575
  <h1 align="center">GIST Embedding v0</h1>
4576
 
@@ -4648,4 +4649,4 @@ The model was evaluated using the [MTEB Evaluation](https://huggingface.co/mteb)
4648
 
4649
  This work is supported by the "KCP IV - Exploring Data Use in the Development Economics Literature using Large Language Models (AI and LLMs)" project funded by the [Knowledge for Change Program (KCP)](https://www.worldbank.org/en/programs/knowledge-for-change) of the World Bank - RA-P503405-RESE-TF0C3444.
4650
 
4651
- The findings, interpretations, and conclusions expressed in this material are entirely those of the authors. They do not necessarily represent the views of the International Bank for Reconstruction and Development/World Bank and its affiliated organizations, or those of the Executive Directors of the World Bank or the governments they represent.
 
946
  - type: precision_at_10
947
  value: 5.743
948
  - type: precision_at_100
949
+ value: 1
950
  - type: precision_at_1000
951
  value: 0.14300000000000002
952
  - type: precision_at_3
 
2223
  - type: map_at_5
2224
  value: 70.15
2225
  - type: mrr_at_1
2226
+ value: 64
2227
  - type: mrr_at_10
2228
  value: 71.82300000000001
2229
  - type: mrr_at_100
 
2235
  - type: mrr_at_5
2236
  value: 71.11699999999999
2237
  - type: ndcg_at_1
2238
+ value: 64
2239
  - type: ndcg_at_10
2240
  value: 75.286
2241
  - type: ndcg_at_100
 
2247
  - type: ndcg_at_5
2248
  value: 73.36399999999999
2249
  - type: precision_at_1
2250
+ value: 64
2251
  - type: precision_at_10
2252
  value: 9.9
2253
  - type: precision_at_100
 
2288
  - type: cos_sim_precision
2289
  value: 92.3076923076923
2290
  - type: cos_sim_recall
2291
+ value: 90
2292
  - type: dot_accuracy
2293
  value: 99.7980198019802
2294
  - type: dot_ap
 
2399
  - type: map_at_5
2400
  value: 0.941
2401
  - type: mrr_at_1
2402
+ value: 76
2403
  - type: mrr_at_10
2404
  value: 85.85199999999999
2405
  - type: mrr_at_100
 
2411
  - type: mrr_at_5
2412
  value: 85.56700000000001
2413
  - type: ndcg_at_1
2414
+ value: 71
2415
  - type: ndcg_at_10
2416
  value: 69.60300000000001
2417
  - type: ndcg_at_100
 
2423
  - type: ndcg_at_5
2424
  value: 71.17599999999999
2425
  - type: precision_at_1
2426
+ value: 76
2427
  - type: precision_at_10
2428
  value: 74.2
2429
  - type: precision_at_100
 
2456
  revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
2457
  metrics:
2458
  - type: accuracy
2459
+ value: 8
2460
  - type: f1
2461
  value: 6.298401229470593
2462
  - type: precision
2463
  value: 5.916991709050532
2464
  - type: recall
2465
+ value: 8
2466
  - task:
2467
  type: BitextMining
2468
  dataset:
 
2592
  revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
2593
  metrics:
2594
  - type: accuracy
2595
+ value: 22
2596
  - type: f1
2597
  value: 17.4576947358322
2598
  - type: precision
2599
  value: 16.261363669827777
2600
  - type: recall
2601
+ value: 22
2602
  - task:
2603
  type: BitextMining
2604
  dataset:
 
2745
  revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
2746
  metrics:
2747
  - type: accuracy
2748
+ value: 0
2749
  - type: f1
2750
+ value: 0
2751
  - type: precision
2752
+ value: 0
2753
  - type: recall
2754
+ value: 0
2755
  - task:
2756
  type: BitextMining
2757
  dataset:
 
2813
  revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
2814
  metrics:
2815
  - type: accuracy
2816
+ value: 4
2817
  - type: f1
2818
  value: 2.3800704501963432
2819
  - type: precision
2820
  value: 2.0919368034607455
2821
  - type: recall
2822
+ value: 4
2823
  - task:
2824
  type: BitextMining
2825
  dataset:
 
2949
  revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
2950
  metrics:
2951
  - type: accuracy
2952
+ value: 21
2953
  - type: f1
2954
  value: 18.965901242066018
2955
  - type: precision
2956
  value: 18.381437375171
2957
  - type: recall
2958
+ value: 21
2959
  - task:
2960
  type: BitextMining
2961
  dataset:
 
3119
  revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
3120
  metrics:
3121
  - type: accuracy
3122
+ value: 1
3123
  - type: f1
3124
  value: 0.7764001197963462
3125
  - type: precision
3126
  value: 0.7551049317943337
3127
  - type: recall
3128
+ value: 1
3129
  - task:
3130
  type: BitextMining
3131
  dataset:
 
3289
  revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
3290
  metrics:
3291
  - type: accuracy
3292
+ value: 6
3293
  - type: f1
3294
  value: 4.58716840215435
3295
  - type: precision
3296
  value: 4.303119297298687
3297
  - type: recall
3298
+ value: 6
3299
  - task:
3300
  type: BitextMining
3301
  dataset:
 
3833
  revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
3834
  metrics:
3835
  - type: accuracy
3836
+ value: 10
3837
  - type: f1
3838
  value: 7.351901305737391
3839
  - type: precision
3840
  value: 6.759061952118555
3841
  - type: recall
3842
+ value: 10
3843
  - task:
3844
  type: BitextMining
3845
  dataset:
 
3918
  revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
3919
  metrics:
3920
  - type: accuracy
3921
+ value: 3
3922
  - type: f1
3923
  value: 1.5834901411814404
3924
  - type: precision
3925
  value: 1.3894010894944848
3926
  - type: recall
3927
+ value: 3
3928
  - task:
3929
  type: BitextMining
3930
  dataset:
 
4571
  language:
4572
  - en
4573
  license: mit
4574
+ library_name: sentence-transformers
4575
  ---
4576
  <h1 align="center">GIST Embedding v0</h1>
4577
 
 
4649
 
4650
  This work is supported by the "KCP IV - Exploring Data Use in the Development Economics Literature using Large Language Models (AI and LLMs)" project funded by the [Knowledge for Change Program (KCP)](https://www.worldbank.org/en/programs/knowledge-for-change) of the World Bank - RA-P503405-RESE-TF0C3444.
4651
 
4652
+ The findings, interpretations, and conclusions expressed in this material are entirely those of the authors. They do not necessarily represent the views of the International Bank for Reconstruction and Development/World Bank and its affiliated organizations, or those of the Executive Directors of the World Bank or the governments they represent.