@@ -58,6 +58,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
58
58
| [ SCT-IndoBERT Base] ( https://huggingface.co/LazarusNLP/sct-indobert-base ) | 125M | [ IndoBERT Base] ( https://huggingface.co/indobenchmark/indobert-base-p1 ) | [ paraphrase-multilingual-mpnet-base-v2] ( https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2 ) | [ Wikipedia] ( https://huggingface.co/datasets/LazarusNLP/wikipedia_id_20230520 ) | |
59
59
| [ S-IndoBERT Base mMARCO] ( https://huggingface.co/LazarusNLP/s-indobert-base-mmarco ) | 125M | [ IndoBERT Base] ( https://huggingface.co/indobenchmark/indobert-base-p1 ) | N/A | [ mMARCO] ( https://huggingface.co/datasets/unicamp-dl/mmarco ) | ✅ |
60
60
| [ 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/ ) | ✅ |
61
+ | [ 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/ ) | ✅ |
61
62
| [ all-IndoBERT Base p2] ( https://huggingface.co/LazarusNLP/all-indobert-base-p2 ) | 125M | [ IndoBERT Base p2] ( https://huggingface.co/indobenchmark/indobert-base-p2 ) | N/A | See: [ README] ( ./training/all/ ) | ✅ |
62
63
| [ 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 ) | ✅ |
63
64
| [ 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 ) | ✅ |
@@ -83,6 +84,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
83
84
| [ SCT-IndoBERT Base] ( https://huggingface.co/LazarusNLP/sct-indobert-base ) | 74.56 |
84
85
| [ S-IndoBERT Base mMARCO] ( https://huggingface.co/LazarusNLP/s-indobert-base-mmarco ) | 72.95 |
85
86
| [ all-IndoBERT Base] ( https://huggingface.co/LazarusNLP/all-indobert-base ) | 73.84 |
87
+ | [ all-IndoBERT Base-v2] ( https://huggingface.co/LazarusNLP/all-indobert-base-v2 ) | 76.03 |
86
88
| [ all-IndoBERT Base p2] ( https://huggingface.co/LazarusNLP/all-indobert-base-p2 ) | 73.45 |
87
89
| [ distiluse-base-multilingual-cased-v2] ( https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2 ) | 75.08 |
88
90
| [ paraphrase-multilingual-mpnet-base-v2] ( https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2 ) | ** 83.83** |
@@ -103,6 +105,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
103
105
| [ ConGen-Indo-e5 Small] ( https://huggingface.co/LazarusNLP/congen-indo-e5-small ) | 55.00 | 66.74 | 58.95 |
104
106
| [ SCT-IndoBERT Base] ( https://huggingface.co/LazarusNLP/sct-indobert-base ) | 40.41 | 47.29 | 40.68 |
105
107
| [ all-IndoBERT Base] ( https://huggingface.co/LazarusNLP/all-indobert-base ) | 65.52 | 75.92 | 70.13 |
108
+ | [ all-IndoBERT Base-v2] ( https://huggingface.co/LazarusNLP/all-indobert-base-v2 ) | 67.18 | 76.59 | 70.16 |
106
109
| [ all-IndoBERT Base p2] ( https://huggingface.co/LazarusNLP/all-indobert-base-p2 ) | 60.62 | 71.95 | 66.31 |
107
110
| [ distiluse-base-multilingual-cased-v2] ( https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2 ) | 41.35 | 54.93 | 48.79 |
108
111
| [ paraphrase-multilingual-mpnet-base-v2] ( https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2 ) | 52.81 | 65.07 | 57.97 |
@@ -121,6 +124,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
121
124
| [ ConGen-Indo-e5 Small] ( https://huggingface.co/LazarusNLP/congen-indo-e5-small ) | 84.60 | 89.30 | 91.27 |
122
125
| [ SCT-IndoBERT Base] ( https://huggingface.co/LazarusNLP/sct-indobert-base ) | 76.81 | 83.16 | 85.87 |
123
126
| [ all-IndoBERT Base] ( https://huggingface.co/LazarusNLP/all-indobert-base ) | 88.14 | 91.47 | 92.91 |
127
+ | [ all-IndoBERT Base-v2] ( https://huggingface.co/LazarusNLP/all-indobert-base-v2 ) | 87.61 | 90.91 | 92.31 |
124
128
| [ all-IndoBERT Base p2] ( https://huggingface.co/LazarusNLP/all-indobert-base-p2 ) | 87.78 | 91.14 | 92.58 |
125
129
| [ distiluse-base-multilingual-cased-v2] ( https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2 ) | 70.44 | 77.94 | 81.56 |
126
130
| [ paraphrase-multilingual-mpnet-base-v2] ( https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2 ) | 81.41 | 87.05 | 89.44 |
@@ -141,6 +145,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
141
145
| [ ConGen-Indo-e5 Small] ( https://huggingface.co/LazarusNLP/congen-indo-e5-small ) | 62.92 | 60.18 |
142
146
| [ SCT-IndoBERT Base] ( https://huggingface.co/LazarusNLP/sct-indobert-base ) | 55.66 | 54.48 |
143
147
| [ all-IndoBERT Base] ( https://huggingface.co/LazarusNLP/all-indobert-base ) | 58.40 | 57.21 |
148
+ | [ all-IndoBERT Base-v2] ( https://huggingface.co/LazarusNLP/all-indobert-base-v2 ) | 58.31 | 57.11 |
144
149
| [ all-IndoBERT Base p2] ( https://huggingface.co/LazarusNLP/all-indobert-base-p2 ) | 60.36 | 59.29 |
145
150
| [ distiluse-base-multilingual-cased-v2] ( https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2 ) | 55.99 | 52.44 |
146
151
| [ paraphrase-multilingual-mpnet-base-v2] ( https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2 ) | 65.43 | 63.55 |
@@ -159,6 +164,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
159
164
| [ ConGen-Indo-e5 Small] ( https://huggingface.co/LazarusNLP/congen-indo-e5-small ) | 66.92 | 66.29 |
160
165
| [ SCT-IndoBERT Base] ( https://huggingface.co/LazarusNLP/sct-indobert-base ) | 61.89 | 60.97 |
161
166
| [ all-IndoBERT Base] ( https://huggingface.co/LazarusNLP/all-indobert-base ) | 66.37 | 66.31 |
167
+ | [ all-IndoBERT Base-v2] ( https://huggingface.co/LazarusNLP/all-indobert-base-v2 ) | 66.02 | 65.s97 |
162
168
| [ all-IndoBERT Base p2] ( https://huggingface.co/LazarusNLP/all-indobert-base-p2 ) | 68.90 | 68.88 |
163
169
| [ distiluse-base-multilingual-cased-v2] ( https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2 ) | 65.25 | 63.45 |
164
170
| [ paraphrase-multilingual-mpnet-base-v2] ( https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2 ) | 70.72 | 70.58 |
@@ -177,6 +183,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
177
183
| [ ConGen-Indo-e5 Small] ( https://huggingface.co/LazarusNLP/congen-indo-e5-small ) | 60.00 | 60.52 |
178
184
| [ SCT-IndoBERT Base] ( https://huggingface.co/LazarusNLP/sct-indobert-base ) | 61.13 | 61.70 |
179
185
| [ all-IndoBERT Base] ( https://huggingface.co/LazarusNLP/all-indobert-base ) | 57.27 | 57.47 |
186
+ | [ all-IndoBERT Base-v2] ( https://huggingface.co/LazarusNLP/all-indobert-base-v2 ) | 58.86 | 59.31 |
180
187
| [ all-IndoBERT Base p2] ( https://huggingface.co/LazarusNLP/all-indobert-base-p2 ) | 57.04 | 57.14 |
181
188
| [ distiluse-base-multilingual-cased-v2] ( https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2 ) | 63.63 | 64.13 |
182
189
| [ paraphrase-multilingual-mpnet-base-v2] ( https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2 ) | 63.18 | 63.78 |
@@ -195,6 +202,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
195
202
| [ ConGen-Indo-e5 Small] ( https://huggingface.co/LazarusNLP/congen-indo-e5-small ) | 84.2 | 80.21 |
196
203
| [ SCT-IndoBERT Base] ( https://huggingface.co/LazarusNLP/sct-indobert-base ) | 82.0 | 76.92 |
197
204
| [ all-IndoBERT Base] ( https://huggingface.co/LazarusNLP/all-indobert-base ) | 84.4 | 79.79 |
205
+ | [ all-IndoBERT Base-v2] ( https://huggingface.co/LazarusNLP/all-indobert-base-v2 ) | 83.4 | 79.04 |
198
206
| [ all-IndoBERT Base p2] ( https://huggingface.co/LazarusNLP/all-indobert-base-p2 ) | 84.8 | 80.03 |
199
207
| [ distiluse-base-multilingual-cased-v2] ( https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2 ) | 78.8 | 73.64 |
200
208
| [ paraphrase-multilingual-mpnet-base-v2] ( https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2 ) | 89.6 | ** 86.56** |
@@ -215,6 +223,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
215
223
| [ ConGen-Indo-e5 Small] ( https://huggingface.co/LazarusNLP/congen-indo-e5-small ) | 70.51 | 55.67 |
216
224
| [ SCT-IndoBERT Base] ( https://huggingface.co/LazarusNLP/sct-indobert-base ) | 59.82 | 53.41 |
217
225
| [ all-IndoBERT Base] ( https://huggingface.co/LazarusNLP/all-indobert-base ) | 72.01 | 56.79 |
226
+ | [ all-IndoBERT Base-v2] ( https://huggingface.co/LazarusNLP/all-indobert-base-v2 ) | 71.36 | 56.83 |
218
227
| [ all-IndoBERT Base p2] ( https://huggingface.co/LazarusNLP/all-indobert-base-p2 ) | 69.32 | 54.76 |
219
228
| [ distiluse-base-multilingual-cased-v2] ( https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2 ) | 58.48 | 50.50 |
220
229
| [ paraphrase-multilingual-mpnet-base-v2] ( https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2 ) | ** 74.87** | ** 57.96** |
0 commit comments