@@ -57,6 +57,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
57
57
| [ all-IndoBERT Base] ( https://huggingface.co/LazarusNLP/all-indobert-base ) | 125M | [ IndoBERT Base] ( https://huggingface.co/indobenchmark/indobert-base-p1 ) | N/A | See: [ README] ( ./training/all/ ) | ✅ |
58
58
| [ all-IndoBERT Base-v2] ( https://huggingface.co/LazarusNLP/all-indobert-base-v2 ) | 125M | [ IndoBERT Base] ( https://huggingface.co/indobenchmark/indobert-base-p1 ) | N/A | See: [ README] ( ./training/all/ ) | ✅ |
59
59
| [ all-Indo-e5 Small-v2] ( https://huggingface.co/LazarusNLP/all-indo-e5-small-v2 ) | 118M | [ multilingual-e5-small] ( https://huggingface.co/intfloat/multilingual-e5-small ) | N/A | See: [ README] ( ./training/all/ ) | ✅ |
60
+ | [ all-Indo-e5 Small-v3] ( https://huggingface.co/LazarusNLP/all-indo-e5-small-v3 ) | 118M | [ multilingual-e5-small] ( https://huggingface.co/intfloat/multilingual-e5-small ) | N/A | See: [ README] ( ./training/all/ ) | ✅ |
60
61
| [ distiluse-base-multilingual-cased-v2] ( https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2 ) | 134M | [ DistilBERT Base Multilingual] ( https://huggingface.co/distilbert-base-multilingual-cased ) | mUSE | See: [ SBERT] ( https://www.sbert.net/docs/pretrained_models.html#model-overview ) | ✅ |
61
62
| [ paraphrase-multilingual-mpnet-base-v2] ( https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2 ) | 125M | [ XLM-RoBERTa Base] ( https://huggingface.co/xlm-roberta-base ) | [ paraphrase-mpnet-base-v2] ( https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2 ) | See: [ SBERT] ( https://www.sbert.net/docs/pretrained_models.html#model-overview ) | ✅ |
62
63
| [ multilingual-e5-small] ( https://huggingface.co/intfloat/multilingual-e5-small ) | 118M | [ Multilingual-MiniLM-L12-H384] ( https://huggingface.co/microsoft/Multilingual-MiniLM-L12-H384 ) | See: [ arXiv] ( https://arxiv.org/abs/2212.03533 ) | See: [ 🤗] ( https://huggingface.co/intfloat/multilingual-e5-small ) | ✅ |
@@ -89,6 +90,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
89
90
| [ all-IndoBERT Base] ( https://huggingface.co/LazarusNLP/all-indobert-base ) | 73.84 |
90
91
| [ all-IndoBERT Base-v2] ( https://huggingface.co/LazarusNLP/all-indobert-base-v2 ) | 76.03 |
91
92
| [ all-Indo-e5 Small-v2] ( https://huggingface.co/LazarusNLP/all-indo-e5-small-v2 ) | 79.57 |
93
+ | [ all-Indo-e5 Small-v3] ( https://huggingface.co/LazarusNLP/all-indo-e5-small-v3 ) | 79.95 |
92
94
| [ distiluse-base-multilingual-cased-v2] ( https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2 ) | 75.08 |
93
95
| [ paraphrase-multilingual-mpnet-base-v2] ( https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2 ) | ** 83.83** |
94
96
| [ multilingual-e5-small] ( https://huggingface.co/intfloat/multilingual-e5-small ) | 78.89 |
@@ -110,6 +112,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
110
112
| [ all-IndoBERT Base] ( https://huggingface.co/LazarusNLP/all-indobert-base ) | 65.52 | 75.92 | 70.13 |
111
113
| [ all-IndoBERT Base-v2] ( https://huggingface.co/LazarusNLP/all-indobert-base-v2 ) | 67.18 | 76.59 | 70.16 |
112
114
| [ all-Indo-e5 Small-v2] ( https://huggingface.co/LazarusNLP/all-indo-e5-small-v2 ) | 68.33 | 78.33 | 73.04 |
115
+ | [ all-Indo-e5 Small-v3] ( https://huggingface.co/LazarusNLP/all-indo-e5-small-v3 ) | 68.12 | 78.22 | 73.09 |
113
116
| [ distiluse-base-multilingual-cased-v2] ( https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2 ) | 41.35 | 54.93 | 48.79 |
114
117
| [ paraphrase-multilingual-mpnet-base-v2] ( https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2 ) | 52.81 | 65.07 | 57.97 |
115
118
| [ multilingual-e5-small] ( https://huggingface.co/intfloat/multilingual-e5-small ) | 70.20 | 79.61 | 74.80 |
@@ -129,6 +132,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
129
132
| [ all-IndoBERT Base] ( https://huggingface.co/LazarusNLP/all-indobert-base ) | 88.14 | 91.47 | 92.91 |
130
133
| [ all-IndoBERT Base-v2] ( https://huggingface.co/LazarusNLP/all-indobert-base-v2 ) | 87.61 | 90.91 | 92.31 |
131
134
| [ all-Indo-e5 Small-v2] ( https://huggingface.co/LazarusNLP/all-indo-e5-small-v2 ) | 93.27 | 95.63 | 96.46 |
135
+ | [ all-Indo-e5 Small-v3] ( https://huggingface.co/LazarusNLP/all-indo-e5-small-v3 ) | 93.27 | 95.72 | 96.58 |
132
136
| [ distiluse-base-multilingual-cased-v2] ( https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2 ) | 70.44 | 77.94 | 81.56 |
133
137
| [ paraphrase-multilingual-mpnet-base-v2] ( https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2 ) | 81.41 | 87.05 | 89.44 |
134
138
| [ multilingual-e5-small] ( https://huggingface.co/intfloat/multilingual-e5-small ) | 91.50 | 94.34 | 95.39 |
@@ -150,6 +154,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
150
154
| [ all-IndoBERT Base] ( https://huggingface.co/LazarusNLP/all-indobert-base ) | 58.40 | 57.21 |
151
155
| [ all-IndoBERT Base-v2] ( https://huggingface.co/LazarusNLP/all-indobert-base-v2 ) | 58.31 | 57.11 |
152
156
| [ all-Indo-e5 Small-v2] ( https://huggingface.co/LazarusNLP/all-indo-e5-small-v2 ) | 61.51 | 59.24 |
157
+ | [ all-Indo-e5 Small-v3] ( https://huggingface.co/LazarusNLP/all-indo-e5-small-v3 ) | 61.63 | 59.29 |
153
158
| [ distiluse-base-multilingual-cased-v2] ( https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2 ) | 55.99 | 52.44 |
154
159
| [ paraphrase-multilingual-mpnet-base-v2] ( https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2 ) | 65.43 | 63.55 |
155
160
| [ multilingual-e5-small] ( https://huggingface.co/intfloat/multilingual-e5-small ) | 64.16 | 61.33 |
@@ -169,6 +174,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
169
174
| [ all-IndoBERT Base] ( https://huggingface.co/LazarusNLP/all-indobert-base ) | 66.37 | 66.31 |
170
175
| [ all-IndoBERT Base-v2] ( https://huggingface.co/LazarusNLP/all-indobert-base-v2 ) | 66.02 | 65.97 |
171
176
| [ all-Indo-e5 Small-v2] ( https://huggingface.co/LazarusNLP/all-indo-e5-small-v2 ) | 67.02 | 66.86 |
177
+ | [ all-Indo-e5 Small-v3] ( https://huggingface.co/LazarusNLP/all-indo-e5-small-v3 ) | 67.27 | 67.13 |
172
178
| [ distiluse-base-multilingual-cased-v2] ( https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2 ) | 65.25 | 63.45 |
173
179
| [ paraphrase-multilingual-mpnet-base-v2] ( https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2 ) | 70.72 | 70.58 |
174
180
| [ multilingual-e5-small] ( https://huggingface.co/intfloat/multilingual-e5-small ) | 67.92 | 67.23 |
@@ -188,6 +194,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
188
194
| [ all-IndoBERT Base] ( https://huggingface.co/LazarusNLP/all-indobert-base ) | 57.27 | 57.47 |
189
195
| [ all-IndoBERT Base-v2] ( https://huggingface.co/LazarusNLP/all-indobert-base-v2 ) | 58.86 | 59.31 |
190
196
| [ all-Indo-e5 Small-v2] ( https://huggingface.co/LazarusNLP/all-indo-e5-small-v2 ) | 58.18 | 57.99 |
197
+ | [ all-Indo-e5 Small-v3] ( https://huggingface.co/LazarusNLP/all-indo-e5-small-v3 ) | 56.81 | 56.46 |
191
198
| [ distiluse-base-multilingual-cased-v2] ( https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2 ) | 63.63 | 64.13 |
192
199
| [ paraphrase-multilingual-mpnet-base-v2] ( https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2 ) | 63.18 | 63.78 |
193
200
| [ multilingual-e5-small] ( https://huggingface.co/intfloat/multilingual-e5-small ) | 64.54 | 65.04 |
@@ -207,6 +214,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
207
214
| [ all-IndoBERT Base] ( https://huggingface.co/LazarusNLP/all-indobert-base ) | 84.4 | 79.79 |
208
215
| [ all-IndoBERT Base-v2] ( https://huggingface.co/LazarusNLP/all-indobert-base-v2 ) | 83.4 | 79.04 |
209
216
| [ all-Indo-e5 Small-v2] ( https://huggingface.co/LazarusNLP/all-indo-e5-small-v2 ) | 82.0 | 78.15 |
217
+ | [ all-Indo-e5 Small-v3] ( https://huggingface.co/LazarusNLP/all-indo-e5-small-v3 ) | 82.6 | 78.98 |
210
218
| [ distiluse-base-multilingual-cased-v2] ( https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2 ) | 78.8 | 73.64 |
211
219
| [ paraphrase-multilingual-mpnet-base-v2] ( https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2 ) | 89.6 | ** 86.56** |
212
220
| [ multilingual-e5-small] ( https://huggingface.co/intfloat/multilingual-e5-small ) | 83.6 | 79.51 |
@@ -228,6 +236,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
228
236
| [ all-IndoBERT Base] ( https://huggingface.co/LazarusNLP/all-indobert-base ) | 72.01 | 56.79 |
229
237
| [ all-IndoBERT Base-v2] ( https://huggingface.co/LazarusNLP/all-indobert-base-v2 ) | 71.36 | 56.83 |
230
238
| [ all-Indo-e5 Small-v2] ( https://huggingface.co/LazarusNLP/all-indo-e5-small-v2 ) | ** 76.29** | 57.05 |
239
+ | [ all-Indo-e5 Small-v3] ( https://huggingface.co/LazarusNLP/all-indo-e5-small-v3 ) | 75.21 | 56.62 |
231
240
| [ distiluse-base-multilingual-cased-v2] ( https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2 ) | 58.48 | 50.50 |
232
241
| [ paraphrase-multilingual-mpnet-base-v2] ( https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2 ) | 74.87 | ** 57.96** |
233
242
| [ multilingual-e5-small] ( https://huggingface.co/intfloat/multilingual-e5-small ) | 63.97 | 51.85 |
0 commit comments