Skip to content

Commit da1c78f

Browse files
committed
Added All NusaBERT-v4
1 parent 66b3e22 commit da1c78f

File tree

2 files changed

+30
-9
lines changed

2 files changed

+30
-9
lines changed

README.md

Lines changed: 20 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -61,6 +61,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
6161
| [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/) ||
6262
| [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/) ||
6363
| [all-IndoBERT Base-v4](https://huggingface.co/LazarusNLP/all-indobert-base-v4) | 125M | [IndoBERT Base](https://huggingface.co/indobenchmark/indobert-base-p1) | N/A | See: [README](./training/all/) ||
64+
| [all-NusaBERT Base-v4](https://huggingface.co/LazarusNLP/all-nusabert-base-v4) | 125M | [NusaBERT Base](https://huggingface.co/LazarusNLP/nusabert-base) | N/A | See: [README](./training/all/) ||
6465
| [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/) ||
6566
| [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/) ||
6667
| [all-Indo-e5 Small-v4](https://huggingface.co/LazarusNLP/all-indo-e5-small-v4) | 118M | [multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) | N/A | See: [README](./training/all/) ||
@@ -70,14 +71,17 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
7071
| [multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) | 278M | [XLM-RoBERTa Base](https://huggingface.co/xlm-roberta-base) | See: [arXiv](https://arxiv.org/abs/2212.03533) | See: [🤗](https://huggingface.co/intfloat/multilingual-e5-base) ||
7172
| [multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) | 560M | [XLM-RoBERTa Large](https://huggingface.co/xlm-roberta-large) | See: [arXiv](https://arxiv.org/abs/2212.03533) | See: [🤗](https://huggingface.co/intfloat/multilingual-e5-large) ||
7273

73-
??? example "Deprecated Models"
74+
<details>
75+
<summary>Deprecated Models</summary>
7476

75-
| Model | #params | Base/Student Model | Teacher Model | Train Dataset | Supervised |
76-
| ---------------------------------------------------------------------------------------- | :-----: | --------------------------------------------------------------------------------- | ------------- | ----------------------------------------------------------------------------- | :--------: |
77-
| [SimCSE-IndoBERT Lite Base](https://huggingface.co/LazarusNLP/simcse-indobert-lite-base) | 12M | [IndoBERT Lite Base](https://huggingface.co/indobenchmark/indobert-lite-base-p1) | N/A | [Wikipedia](https://huggingface.co/datasets/LazarusNLP/wikipedia_id_20230520) | |
78-
| [SimCSE-IndoRoBERTa Base](https://huggingface.co/LazarusNLP/simcse-indoroberta-base) | 125M | [IndoRoBERTa Base](https://huggingface.co/flax-community/indonesian-roberta-base) | N/A | [Wikipedia](https://huggingface.co/datasets/LazarusNLP/wikipedia_id_20230520) | |
79-
| [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) | ✅ |
80-
| [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/) | ✅ |
77+
| Model | #params | Base/Student Model | Teacher Model | Train Dataset | Supervised |
78+
| ---------------------------------------------------------------------------------------- | :-----: | --------------------------------------------------------------------------------- | ------------- | ----------------------------------------------------------------------------- | :--------: |
79+
| [SimCSE-IndoBERT Lite Base](https://huggingface.co/LazarusNLP/simcse-indobert-lite-base) | 12M | [IndoBERT Lite Base](https://huggingface.co/indobenchmark/indobert-lite-base-p1) | N/A | [Wikipedia](https://huggingface.co/datasets/LazarusNLP/wikipedia_id_20230520) | |
80+
| [SimCSE-IndoRoBERTa Base](https://huggingface.co/LazarusNLP/simcse-indoroberta-base) | 125M | [IndoRoBERTa Base](https://huggingface.co/flax-community/indonesian-roberta-base) | N/A | [Wikipedia](https://huggingface.co/datasets/LazarusNLP/wikipedia_id_20230520) | |
81+
| [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) ||
82+
| [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/) ||
83+
84+
</details>
8185

8286
## Results
8387

@@ -96,6 +100,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
96100
| [all-IndoBERT Base](https://huggingface.co/LazarusNLP/all-indobert-base) | 73.84 |
97101
| [all-IndoBERT Base-v2](https://huggingface.co/LazarusNLP/all-indobert-base-v2) | 76.03 |
98102
| [all-IndoBERT Base-v4](https://huggingface.co/LazarusNLP/all-indobert-base-v4) | 75.99 |
103+
| [all-NusaBERT Base-v4](https://huggingface.co/LazarusNLP/all-nusabert-base-v4) | 77.65 |
99104
| [all-Indo-e5 Small-v2](https://huggingface.co/LazarusNLP/all-indo-e5-small-v2) | 79.57 |
100105
| [all-Indo-e5 Small-v3](https://huggingface.co/LazarusNLP/all-indo-e5-small-v3) | 79.95 |
101106
| [all-Indo-e5 Small-v4](https://huggingface.co/LazarusNLP/all-indo-e5-small-v4) | 79.85 |
@@ -120,6 +125,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
120125
| [all-IndoBERT Base](https://huggingface.co/LazarusNLP/all-indobert-base) | 65.52 | 75.92 | 70.13 |
121126
| [all-IndoBERT Base-v2](https://huggingface.co/LazarusNLP/all-indobert-base-v2) | 67.18 | 76.59 | 70.16 |
122127
| [all-IndoBERT Base-v4](https://huggingface.co/LazarusNLP/all-indobert-base-v4) | 67.91 | 77.37 | 70.97 |
128+
| [all-NusaBERT Base-v4](https://huggingface.co/LazarusNLP/all-nusabert-base-v4) | 67.08 | 77.47 | 71.24 |
123129
| [all-Indo-e5 Small-v2](https://huggingface.co/LazarusNLP/all-indo-e5-small-v2) | 68.33 | 78.33 | 73.04 |
124130
| [all-Indo-e5 Small-v3](https://huggingface.co/LazarusNLP/all-indo-e5-small-v3) | 68.12 | 78.22 | 73.09 |
125131
| [all-Indo-e5 Small-v4](https://huggingface.co/LazarusNLP/all-indo-e5-small-v4) | 68.33 | 78.41 | 73.23 |
@@ -142,6 +148,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
142148
| [all-IndoBERT Base](https://huggingface.co/LazarusNLP/all-indobert-base) | 88.14 | 91.47 | 92.91 |
143149
| [all-IndoBERT Base-v2](https://huggingface.co/LazarusNLP/all-indobert-base-v2) | 87.61 | 90.91 | 92.31 |
144150
| [all-IndoBERT Base-v4](https://huggingface.co/LazarusNLP/all-indobert-base-v4) | 89.02 | 92.59 | 93.91 |
151+
| [all-NusaBERT Base-v4](https://huggingface.co/LazarusNLP/all-nusabert-base-v4) | 92.74 | 94.95 | 95.73 |
145152
| [all-Indo-e5 Small-v2](https://huggingface.co/LazarusNLP/all-indo-e5-small-v2) | 93.27 | 95.63 | 96.46 |
146153
| [all-Indo-e5 Small-v3](https://huggingface.co/LazarusNLP/all-indo-e5-small-v3) | 93.27 | 95.72 | 96.58 |
147154
| [all-Indo-e5 Small-v4](https://huggingface.co/LazarusNLP/all-indo-e5-small-v4) | 93.45 | 95.66 | 96.43 |
@@ -166,6 +173,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
166173
| [all-IndoBERT Base](https://huggingface.co/LazarusNLP/all-indobert-base) | 58.40 | 57.21 |
167174
| [all-IndoBERT Base-v2](https://huggingface.co/LazarusNLP/all-indobert-base-v2) | 58.31 | 57.11 |
168175
| [all-IndoBERT Base-v4](https://huggingface.co/LazarusNLP/all-indobert-base-v4) | 57.80 | 56.71 |
176+
| [all-NusaBERT Base-v4](https://huggingface.co/LazarusNLP/all-nusabert-base-v4) | 62.10 | 60.38 |
169177
| [all-Indo-e5 Small-v2](https://huggingface.co/LazarusNLP/all-indo-e5-small-v2) | 61.51 | 59.24 |
170178
| [all-Indo-e5 Small-v3](https://huggingface.co/LazarusNLP/all-indo-e5-small-v3) | 61.63 | 59.29 |
171179
| [all-Indo-e5 Small-v4](https://huggingface.co/LazarusNLP/all-indo-e5-small-v4) | 61.38 | 59.07 |
@@ -188,6 +196,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
188196
| [all-IndoBERT Base](https://huggingface.co/LazarusNLP/all-indobert-base) | 66.37 | 66.31 |
189197
| [all-IndoBERT Base-v2](https://huggingface.co/LazarusNLP/all-indobert-base-v2) | 66.02 | 65.97 |
190198
| [all-IndoBERT Base-v4](https://huggingface.co/LazarusNLP/all-indobert-base-v4) | 66.33 | 66.14 |
199+
| [all-NusaBERT Base-v4](https://huggingface.co/LazarusNLP/all-nusabert-base-v4) | 70.17 | 70.18 |
191200
| [all-Indo-e5 Small-v2](https://huggingface.co/LazarusNLP/all-indo-e5-small-v2) | 67.02 | 66.86 |
192201
| [all-Indo-e5 Small-v3](https://huggingface.co/LazarusNLP/all-indo-e5-small-v3) | 67.27 | 67.13 |
193202
| [all-Indo-e5 Small-v4](https://huggingface.co/LazarusNLP/all-indo-e5-small-v4) | 67.33 | 67.24 |
@@ -210,6 +219,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
210219
| [all-IndoBERT Base](https://huggingface.co/LazarusNLP/all-indobert-base) | 57.27 | 57.47 |
211220
| [all-IndoBERT Base-v2](https://huggingface.co/LazarusNLP/all-indobert-base-v2) | 58.86 | 59.31 |
212221
| [all-IndoBERT Base-v4](https://huggingface.co/LazarusNLP/all-indobert-base-v4) | 61.36 | 61.81 |
222+
| [all-NusaBERT Base-v4](https://huggingface.co/LazarusNLP/all-nusabert-base-v4) | 53.18 | 53.01 |
213223
| [all-Indo-e5 Small-v2](https://huggingface.co/LazarusNLP/all-indo-e5-small-v2) | 58.18 | 57.99 |
214224
| [all-Indo-e5 Small-v3](https://huggingface.co/LazarusNLP/all-indo-e5-small-v3) | 56.81 | 56.46 |
215225
| [all-Indo-e5 Small-v4](https://huggingface.co/LazarusNLP/all-indo-e5-small-v4) | 56.94 | 57.04 |
@@ -232,6 +242,7 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
232242
| [all-IndoBERT Base](https://huggingface.co/LazarusNLP/all-indobert-base) | 84.4 | 79.79 |
233243
| [all-IndoBERT Base-v2](https://huggingface.co/LazarusNLP/all-indobert-base-v2) | 83.4 | 79.04 |
234244
| [all-IndoBERT Base-v4](https://huggingface.co/LazarusNLP/all-indobert-base-v4) | 82.4 | 77.82 |
245+
| [all-NusaBERT Base-v4](https://huggingface.co/LazarusNLP/all-nusabert-base-v4) | 84.2 | 78.68 |
235246
| [all-Indo-e5 Small-v2](https://huggingface.co/LazarusNLP/all-indo-e5-small-v2) | 82.0 | 78.15 |
236247
| [all-Indo-e5 Small-v3](https://huggingface.co/LazarusNLP/all-indo-e5-small-v3) | 82.6 | 78.98 |
237248
| [all-Indo-e5 Small-v4](https://huggingface.co/LazarusNLP/all-indo-e5-small-v4) | 82.6 | 79.14 |
@@ -255,7 +266,8 @@ Like SimCSE, [ConGen: Unsupervised Control and Generalization Distillation For S
255266
| [SCT-IndoBERT Base](https://huggingface.co/LazarusNLP/sct-indobert-base) | 59.82 | 53.41 |
256267
| [all-IndoBERT Base](https://huggingface.co/LazarusNLP/all-indobert-base) | 72.01 | 56.79 |
257268
| [all-IndoBERT Base-v2](https://huggingface.co/LazarusNLP/all-indobert-base-v2) | 71.36 | 56.83 |
258-
| [all-IndoBERT Base-v4](https://huggingface.co/LazarusNLP/all-indobert-base-v4) | 70.99 | **58.99** |
269+
| [all-IndoBERT Base-v4](https://huggingface.co/LazarusNLP/all-indobert-base-v4) | 70.99 | 58.99 |
270+
| [all-NusaBERT Base-v4](https://huggingface.co/LazarusNLP/all-nusabert-base-v4) | 73.07 | **59.86** |
259271
| [all-Indo-e5 Small-v2](https://huggingface.co/LazarusNLP/all-indo-e5-small-v2) | **76.29** | 57.05 |
260272
| [all-Indo-e5 Small-v3](https://huggingface.co/LazarusNLP/all-indo-e5-small-v3) | 75.21 | 56.62 |
261273
| [all-Indo-e5 Small-v4](https://huggingface.co/LazarusNLP/all-indo-e5-small-v4) | 75.05 | 57.42 |

0 commit comments

Comments
 (0)