mirror of
https://github.com/RYDE-WORK/MiniCPM.git
synced 2026-01-31 20:03:13 +08:00
Update README.md
This commit is contained in:
parent
8dcf68fa61
commit
ecb090ad80
@ -82,9 +82,7 @@ XXXXXX
|
|||||||
|
|
||||||
在具体评测时,我们以两种评测方式得分的最高者为最终结果,以此保证对比的公平性。
|
在具体评测时,我们以两种评测方式得分的最高者为最终结果,以此保证对比的公平性。
|
||||||
|
|
||||||
#### 评测结果
|
#### 文本评测
|
||||||
|
|
||||||
* 文本评测
|
|
||||||
|
|
||||||
|模型|英文均分|中文均分|CEval|CMMLU|MMLU|HumanEval|MBPP|GSM8K|MATH|BBH|Arc-e|ARC-c|HellaSwag|
|
|模型|英文均分|中文均分|CEval|CMMLU|MMLU|HumanEval|MBPP|GSM8K|MATH|BBH|Arc-e|ARC-c|HellaSwag|
|
||||||
|-|-|-|-|-|-|-|-|-|-|-|-|-|-|
|
|-|-|-|-|-|-|-|-|-|-|-|-|-|-|
|
||||||
@ -105,7 +103,7 @@ XXXXXX
|
|||||||
|Phi-2-2B|48.84|54.41|23.775|23.37|24.18|52.66|47.56|55.04|57.16|3.5|43.39|86.11|71.25|73.07*|
|
|Phi-2-2B|48.84|54.41|23.775|23.37|24.18|52.66|47.56|55.04|57.16|3.5|43.39|86.11|71.25|73.07*|
|
||||||
|MiniCPM-2B|52.33|52.6|51.1|51.13|51.07|53.46|50.00|47.31|53.83|10.24|36.87|85.44|68.00|68.25|
|
|MiniCPM-2B|52.33|52.6|51.1|51.13|51.07|53.46|50.00|47.31|53.83|10.24|36.87|85.44|68.00|68.25|
|
||||||
|
|
||||||
* 多模态评测
|
#### 多模态评测
|
||||||
|
|
||||||
|模型|MME(P)|MMB-dev(en)|MMB-dev(zh)|MMMU-val|CMMMU-val|
|
|模型|MME(P)|MMB-dev(en)|MMB-dev(zh)|MMMU-val|CMMMU-val|
|
||||||
|-|-|-|-|-|-|
|
|-|-|-|-|-|-|
|
||||||
@ -115,7 +113,7 @@ XXXXXX
|
|||||||
|Qwen-VL-Chat|**1487**|60.6|56.7|**35.9**|30.7
|
|Qwen-VL-Chat|**1487**|60.6|56.7|**35.9**|30.7
|
||||||
|**MiniCPM-V**|1446|**67.3**|**61.9**|34.7|**32.1**|
|
|**MiniCPM-V**|1446|**67.3**|**61.9**|34.7|**32.1**|
|
||||||
|
|
||||||
* DPO评测
|
#### DPO评测
|
||||||
|
|
||||||
|模型|MT-bench|
|
|模型|MT-bench|
|
||||||
|---|---|
|
|---|---|
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user