Commit
·
c985e8b
1
Parent(s):
77d74f4
Update README.md
Browse files
README.md
CHANGED
|
@@ -101,7 +101,6 @@ For specific training settings, please refer to [Baichuan-13B](https://github.co
|
|
| 101 |
| Ziya-LLaMA-13B-Pretrain | 27.6 | 34.4 | 32.0 | 28.6 | 30.0 |
|
| 102 |
| LLaMA-13B | 27.0 | 33.6 | 27.7 | 27.6 | 28.5 |
|
| 103 |
| moss-moon-003-base (16B)| 27.0 | 29.1 | 27.2 | 26.9 | 27.4 |
|
| 104 |
-
| vicuna-13B | 22.8 | 24.8 | 22.3 | 18.5 | 22.2 |
|
| 105 |
| **Baichuan-13B-Base** | **45.9** | **63.5** | **57.2** | **49.3** | **52.4** |
|
| 106 |
| **Baichuan-13B-Chat** | **43.7** | **64.6** | **56.2** | **49.2** | **51.5** |
|
| 107 |
|
|
@@ -115,7 +114,6 @@ For specific training settings, please refer to [Baichuan-13B](https://github.co
|
|
| 115 |
| Ziya-LLaMA-13B-Pretrain | 35.6 | 47.6 | 40.1 | 49.4 | 42.9 |
|
| 116 |
| Baichuan-7B | 35.6 | 48.9 | 38.4 | 48.1 | 42.3 |
|
| 117 |
| Chinese-LLaMA-Plus-13B | 33.1 | 42.8 | 37.0 | 44.6 | 39.2 |
|
| 118 |
-
| vicuna-13B | 24.2 | 24.1 | 24.6 | 26.8 | 24.9 |
|
| 119 |
| moss-moon-003-base (16B)| 22.4 | 22.8 | 24.2 | 24.4 | 23.6 |
|
| 120 |
| **Baichuan-13B-Base** | **41.6** | **60.9** | **47.4** | **58.5** | **51.6** |
|
| 121 |
| **Baichuan-13B-Chat** | **40.9** | **60.9** | **48.8** | **59.0** | **52.1** |
|
|
@@ -131,7 +129,6 @@ For specific training settings, please refer to [Baichuan-13B](https://github.co
|
|
| 131 |
| Ziya-LLaMA-13B-Pretrain | 29.0 | 30.7 | 33.8 | 34.4 | 31.9 | 32.1 |
|
| 132 |
| LLaMA-13B | 29.2 | 30.8 | 31.6 | 33.0 | 30.5 | 31.2 |
|
| 133 |
| moss-moon-003-base (16B)| 27.2 | 30.4 | 28.8 | 32.6 | 28.7 | 29.6 |
|
| 134 |
-
| vicuna-13B | 24.0 | 25.4 | 25.3 | 25.0 | 25.0 | 24.9 |
|
| 135 |
| **Baichuan-13B-Base** | **41.7** | **61.1** | **59.8** | **59.0** | **56.4** | **55.3** |
|
| 136 |
| **Baichuan-13B-Chat** | **42.8** | **62.6** | **59.7** | **59.0** | **56.1** | **55.8** |
|
| 137 |
> 说明：CMMLU 是一个综合性的中文评估基准，专门用于评估语言模型在中文语境下的知识和推理能力。我们采用了其官方的[评测方案](https://github.com/haonan-li/CMMLU)。
|
|
|
|
| 101 |
| Ziya-LLaMA-13B-Pretrain | 27.6 | 34.4 | 32.0 | 28.6 | 30.0 |
|
| 102 |
| LLaMA-13B | 27.0 | 33.6 | 27.7 | 27.6 | 28.5 |
|
| 103 |
| moss-moon-003-base (16B)| 27.0 | 29.1 | 27.2 | 26.9 | 27.4 |
|
|
|
|
| 104 |
| **Baichuan-13B-Base** | **45.9** | **63.5** | **57.2** | **49.3** | **52.4** |
|
| 105 |
| **Baichuan-13B-Chat** | **43.7** | **64.6** | **56.2** | **49.2** | **51.5** |
|
| 106 |
|
|
|
|
| 114 |
| Ziya-LLaMA-13B-Pretrain | 35.6 | 47.6 | 40.1 | 49.4 | 42.9 |
|
| 115 |
| Baichuan-7B | 35.6 | 48.9 | 38.4 | 48.1 | 42.3 |
|
| 116 |
| Chinese-LLaMA-Plus-13B | 33.1 | 42.8 | 37.0 | 44.6 | 39.2 |
|
|
|
|
| 117 |
| moss-moon-003-base (16B)| 22.4 | 22.8 | 24.2 | 24.4 | 23.6 |
|
| 118 |
| **Baichuan-13B-Base** | **41.6** | **60.9** | **47.4** | **58.5** | **51.6** |
|
| 119 |
| **Baichuan-13B-Chat** | **40.9** | **60.9** | **48.8** | **59.0** | **52.1** |
|
|
|
|
| 129 |
| Ziya-LLaMA-13B-Pretrain | 29.0 | 30.7 | 33.8 | 34.4 | 31.9 | 32.1 |
|
| 130 |
| LLaMA-13B | 29.2 | 30.8 | 31.6 | 33.0 | 30.5 | 31.2 |
|
| 131 |
| moss-moon-003-base (16B)| 27.2 | 30.4 | 28.8 | 32.6 | 28.7 | 29.6 |
|
|
|
|
| 132 |
| **Baichuan-13B-Base** | **41.7** | **61.1** | **59.8** | **59.0** | **56.4** | **55.3** |
|
| 133 |
| **Baichuan-13B-Chat** | **42.8** | **62.6** | **59.7** | **59.0** | **56.1** | **55.8** |
|
| 134 |
> 说明：CMMLU 是一个综合性的中文评估基准，专门用于评估语言模型在中文语境下的知识和推理能力。我们采用了其官方的[评测方案](https://github.com/haonan-li/CMMLU)。
|