Update README.md
Browse files
README.md
CHANGED
@@ -64,6 +64,15 @@ avoiding problems in commonly used large generative models such as FLAN. It not
|
|
64 |
| [UniMC-RoBERTa-330M](https://huggingface.co/IDEA-CCNL/Erlangshen-UniMC-RoBERTa-330M-Chinese) | 87.5 | 30.4 | 47.6 | 31.5 | 69.9 | 75.9 | 78.17 | 49.5 | 60.55 | 59.01 |
|
65 |
| [UniMC-MegatronBERT-1.3B](https://huggingface.co/IDEA-CCNL/Erlangshen-UniMC-MegatronBERT-1.3B-Chinese) | **88.79** | 42.06 | 55.21 | 33.93 | **75.57** | **79.5** | **89.4** | 50.25 | **66.67** | **64.53** |
|
66 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
|
68 |
## 使用 Usage
|
69 |
```shell
|
|
|
64 |
| [UniMC-RoBERTa-330M](https://huggingface.co/IDEA-CCNL/Erlangshen-UniMC-RoBERTa-330M-Chinese) | 87.5 | 30.4 | 47.6 | 31.5 | 69.9 | 75.9 | 78.17 | 49.5 | 60.55 | 59.01 |
|
65 |
| [UniMC-MegatronBERT-1.3B](https://huggingface.co/IDEA-CCNL/Erlangshen-UniMC-MegatronBERT-1.3B-Chinese) | **88.79** | 42.06 | 55.21 | 33.93 | **75.57** | **79.5** | **89.4** | 50.25 | **66.67** | **64.53** |
|
66 |
|
67 |
+
**Full dataset**
|
68 |
+
|
69 |
+
| Model | AFQMC | TNEWS1.1 | IFLYTEK | OCNLI | CMNLI | WSC1.1 | CSL | CHID | C3 |
|
70 |
+
|--------------------------------------------|-------|----------|---------|-------|-------|--------|-------|-------|-------|
|
71 |
+
| RoBERTa-Base | 74.06 | 57.5 | 60.36 | 74.3 | 79.73 | 83.48 | 85.37 | - | - |
|
72 |
+
| RoBERTa-Large | 74.88 | 58.79 | 61.52 | 77.7 | 81.4 | 89.14 | 86 | - | - |
|
73 |
+
| [Erlangshen-MegatronBert-1.3B](https://huggingface.co/IDEA-CCNL/Erlangshen-MegatronBert-1.3B) 「Finetuning」 | 76.08 | 59.38 | 62.34 | 79.14 | 81 | 92.43 | 87.2 | 84.65 | 86.77 |
|
74 |
+
| [Erlangshen-UniMC-MegatronBERT-1.3B-Chinese](https://huggingface.co/IDEA-CCNL/Erlangshen-UniMC-MegatronBERT-1.3B-Chinese) | 77.09 | 60.4 | 62.67 | 83.05 | 84.76 | 93.74 | 87.67 | 85.93 | 86.54 |
|
75 |
+
|
76 |
|
77 |
## 使用 Usage
|
78 |
```shell
|