Commit
•
797d430
1
Parent(s):
068105c
Update README.md
Browse files
README.md
CHANGED
|
@@ -151,6 +151,7 @@ For specific training settings, please refer to [Baichuan-13B](https://github.co
|
|
| 151 |
|-------------------------|:-----:|:---------------:|:----------:|:------:|:-------:|
|
| 152 |
| Baichuan-7B | 38.2 | 52.0 | 46.2 | 39.3 | 42.8 |
|
| 153 |
| Chinese-Alpaca-Plus-13B | 35.2 | 45.6 | 40.0 | 38.2 | 38.8 |
|
|
|
|
| 154 |
| Chinese-LLaMA-Plus-13B | 30.3 | 38.0 | 32.9 | 29.1 | 32.1 |
|
| 155 |
| Ziya-LLaMA-13B-Pretrain | 27.6 | 34.4 | 32.0 | 28.6 | 30.0 |
|
| 156 |
| LLaMA-13B | 27.0 | 33.6 | 27.7 | 27.6 | 28.5 |
|
|
@@ -158,11 +159,11 @@ For specific training settings, please refer to [Baichuan-13B](https://github.co
|
|
| 158 |
| **Baichuan-13B-Base** | **45.9** | **63.5** | **57.2** | **49.3** | **52.4** |
|
| 159 |
| **Baichuan-13B-Chat** | **43.7** | **64.6** | **56.2** | **49.2** | **51.5** |
|
| 160 |
|
| 161 |
-
|
| 162 |
## [MMLU](https://arxiv.org/abs/2009.03300)
|
| 163 |
|
| 164 |
| Model 5-shot | STEM | Social Sciences | Humanities | Others | Average |
|
| 165 |
|-------------------------|:-----:|:---------------:|:----------:|:------:|:-------:|
|
|
|
|
| 166 |
| LLaMA-13B | 36.1 | 53.0 | 44.0 | 52.8 | 46.3 |
|
| 167 |
| Chinese-Alpaca-Plus-13B | 36.9 | 48.9 | 40.5 | 50.5 | 43.9 |
|
| 168 |
| Ziya-LLaMA-13B-Pretrain | 35.6 | 47.6 | 40.1 | 49.4 | 42.9 |
|
|
@@ -178,6 +179,7 @@ For specific training settings, please refer to [Baichuan-13B](https://github.co
|
|
| 178 |
| Model 5-shot | STEM | Humanities | Social Sciences | Others | China Specific | Average |
|
| 179 |
|-------------------------|:-----:|:----------:|:---------------:|:------:|:--------------:|:-------:|
|
| 180 |
| Baichuan-7B | 34.4 | 47.5 | 47.6 | 46.6 | 44.3 | 44.0 |
|
|
|
|
| 181 |
| Chinese-Alpaca-Plus-13B | 29.8 | 33.4 | 33.2 | 37.9 | 32.1 | 33.4 |
|
| 182 |
| Chinese-LLaMA-Plus-13B | 28.1 | 33.1 | 35.4 | 35.1 | 33.5 | 33.0 |
|
| 183 |
| Ziya-LLaMA-13B-Pretrain | 29.0 | 30.7 | 33.8 | 34.4 | 31.9 | 32.1 |
|
|
|
|
| 151 |
|-------------------------|:-----:|:---------------:|:----------:|:------:|:-------:|
|
| 152 |
| Baichuan-7B | 38.2 | 52.0 | 46.2 | 39.3 | 42.8 |
|
| 153 |
| Chinese-Alpaca-Plus-13B | 35.2 | 45.6 | 40.0 | 38.2 | 38.8 |
|
| 154 |
+
| Vicuna-13B | 30.5 | 38.2 | 32.5 | 32.5 | 32.8 |
|
| 155 |
| Chinese-LLaMA-Plus-13B | 30.3 | 38.0 | 32.9 | 29.1 | 32.1 |
|
| 156 |
| Ziya-LLaMA-13B-Pretrain | 27.6 | 34.4 | 32.0 | 28.6 | 30.0 |
|
| 157 |
| LLaMA-13B | 27.0 | 33.6 | 27.7 | 27.6 | 28.5 |
|
|
|
|
| 159 |
| **Baichuan-13B-Base** | **45.9** | **63.5** | **57.2** | **49.3** | **52.4** |
|
| 160 |
| **Baichuan-13B-Chat** | **43.7** | **64.6** | **56.2** | **49.2** | **51.5** |
|
| 161 |
|
|
|
|
| 162 |
## [MMLU](https://arxiv.org/abs/2009.03300)
|
| 163 |
|
| 164 |
| Model 5-shot | STEM | Social Sciences | Humanities | Others | Average |
|
| 165 |
|-------------------------|:-----:|:---------------:|:----------:|:------:|:-------:|
|
| 166 |
+
| Vicuna-13B | 40.4 | 60.5 | 49.5 | 58.4 | 52.0 |
|
| 167 |
| LLaMA-13B | 36.1 | 53.0 | 44.0 | 52.8 | 46.3 |
|
| 168 |
| Chinese-Alpaca-Plus-13B | 36.9 | 48.9 | 40.5 | 50.5 | 43.9 |
|
| 169 |
| Ziya-LLaMA-13B-Pretrain | 35.6 | 47.6 | 40.1 | 49.4 | 42.9 |
|
|
|
|
| 179 |
| Model 5-shot | STEM | Humanities | Social Sciences | Others | China Specific | Average |
|
| 180 |
|-------------------------|:-----:|:----------:|:---------------:|:------:|:--------------:|:-------:|
|
| 181 |
| Baichuan-7B | 34.4 | 47.5 | 47.6 | 46.6 | 44.3 | 44.0 |
|
| 182 |
+
| Vicuna-13B | 31.8 | 36.2 | 37.6 | 39.5 | 34.3 | 36.3 |
|
| 183 |
| Chinese-Alpaca-Plus-13B | 29.8 | 33.4 | 33.2 | 37.9 | 32.1 | 33.4 |
|
| 184 |
| Chinese-LLaMA-Plus-13B | 28.1 | 33.1 | 35.4 | 35.1 | 33.5 | 33.0 |
|
| 185 |
| Ziya-LLaMA-13B-Pretrain | 29.0 | 30.7 | 33.8 | 34.4 | 31.9 | 32.1 |
|