File tree 1 file changed +7
-6
lines changed
1 file changed +7
-6
lines changed Original file line number Diff line number Diff line change @@ -57,12 +57,13 @@ ChatGLM2-6B 开源模型旨在与开源社区一起推动大模型技术发展
57
57
58
58
### C-Eval
59
59
60
- | Model | Average | STEM | Social Sciences | Humanities | Others |
61
- | ----- | ---- | ---- | ----- | ------------| --------|
62
- | ChatGLM-6B | 38.9 | 33.3 | 48.3 | 41.3 | 38.0 |
63
- | ChatGLM2-6B (base) | 51.7 | 48.6 | 60.5 | 51.3 | 49.8 |
64
- | ChatGLM2-6B | 50.1 | 46.4 | 60.4 | 50.6 | 46.9 |
65
- | ChatGLM2-12B (base) | 61.6 | 55.4 | 73.7 | 64.2 | 59.4 |
60
+ | Model | Average | STEM | Social Sciences | Humanities | Others |
61
+ | ----- | ---------| -------| ----- | ------------| --------|
62
+ | ChatGLM-6B | 38.9 | 33.3 | 48.3 | 41.3 | 38.0 |
63
+ | ChatGLM2-6B (base) | 51.7 | 48.6 | 60.5 | 51.3 | 49.8 |
64
+ | ChatGLM2-6B | 50.1 | 46.4 | 60.4 | 50.6 | 46.9 |
65
+ | ChatGLM2-12B (base) | 61.6 | 55.4 | 73.7 | 64.2 | 59.4 |
66
+ | ChatGLM2-12B | 57.0 | 52.1 | 69.3 | 58.5 | 53.2 |
66
67
67
68
> Chat 模型使用 zero-shot CoT 的方法测试,Base 模型使用 few-shot answer only 的方法测试
68
69
You can’t perform that action at this time.
0 commit comments