increase datasets for testing

README.md

@@ -42,6 +42,13 @@ pip install opencompass*
 pip install -e .
 ```
 
+安装humaneval(可选)
+```shell
+git clone https://github.com/open-compass/human-eval.git
+cd human-eval
+pip install -e .
+```
+
 
 #### 注意事项
 + 若使用 pip install 下载安装过慢，可添加源：-i https://pypi.tuna.tsinghua.edu.cn/simple/

configs/vllm/eval_baichuan2_chat_vllm.py

@@ -4,6 +4,7 @@ with read_base():
     from ..datasets.ARC_c.ARC_c_gen_1e0de5 import ARC_c_datasets 
     from ..datasets.ARC_e.ARC_e_gen_1e0de5 import ARC_e_datasets
     from ..datasets.ceval.ceval_gen_5f30c7 import ceval_datasets
+    from ..datasets.SuperGLUE_BoolQ.SuperGLUE_BoolQ_gen_883d50 import BoolQ_datasets
     from ..summarizers.example import summarizer
 
 datasets = sum([v for k, v in locals().items() if k.endswith("_datasets") or k == 'datasets'], [])

configs/vllm/eval_chatglm3_vllm.py

@@ -3,6 +3,7 @@ from mmengine.config import read_base
 with read_base():
     from ..datasets.ARC_c.ARC_c_gen_1e0de5 import ARC_c_datasets 
     from ..datasets.ARC_e.ARC_e_gen_1e0de5 import ARC_e_datasets
+    from ..datasets.SuperGLUE_BoolQ.SuperGLUE_BoolQ_gen_883d50 import BoolQ_datasets
     from ..summarizers.example import summarizer
 
 datasets = sum([v for k, v in locals().items() if k.endswith("_datasets") or k == 'datasets'], [])

configs/vllm/eval_qwen1.5_chat_vllm.py

 from mmengine.config import read_base
 
 with read_base():
-    from ..datasets.ARC_c.ARC_c_gen_1e0de5 import ARC_c_datasets 
-    from ..datasets.ARC_e.ARC_e_gen_1e0de5 import ARC_e_datasets
+    # from ..datasets.ARC_c.ARC_c_gen_1e0de5 import ARC_c_datasets 
+    # from ..datasets.ARC_e.ARC_e_gen_1e0de5 import ARC_e_datasets
     from ..datasets.ceval.ceval_gen_5f30c7 import ceval_datasets
+    from ..datasets.SuperGLUE_BoolQ.SuperGLUE_BoolQ_gen_883d50 import BoolQ_datasets
+    from ..datasets.humaneval.humaneval_gen_8e312c import humaneval_datasets
     from ..summarizers.example import summarizer
 
 datasets = sum([v for k, v in locals().items() if k.endswith("_datasets") or k == 'datasets'], [])

configs/vllm/eval_qwen1.5_int4_chat_vllm.py

 from mmengine.config import read_base
 
 with read_base():
-    from ..datasets.ARC_c.ARC_c_gen_1e0de5 import ARC_c_datasets 
-    from ..datasets.ARC_e.ARC_e_gen_1e0de5 import ARC_e_datasets
+    # from ..datasets.ARC_c.ARC_c_gen_1e0de5 import ARC_c_datasets 
+    # from ..datasets.ARC_e.ARC_e_gen_1e0de5 import ARC_e_datasets
     from ..datasets.ceval.ceval_gen_5f30c7 import ceval_datasets
+    from ..datasets.SuperGLUE_BoolQ.SuperGLUE_BoolQ_gen_883d50 import BoolQ_datasets
+    from ..datasets.humaneval.humaneval_gen_8e312c import humaneval_datasets
     from ..summarizers.example import summarizer
 
 datasets = sum([v for k, v in locals().items() if k.endswith("_datasets") or k == 'datasets'], [])

configs/vllm/eval_qwen1.5_vllm.py

 from mmengine.config import read_base
 
 with read_base():
-    from ..datasets.ARC_c.ARC_c_gen_1e0de5 import ARC_c_datasets 
-    from ..datasets.ARC_e.ARC_e_gen_1e0de5 import ARC_e_datasets
+    # from ..datasets.ARC_c.ARC_c_gen_1e0de5 import ARC_c_datasets 
+    # from ..datasets.ARC_e.ARC_e_gen_1e0de5 import ARC_e_datasets
     from ..datasets.ceval.ceval_gen_5f30c7 import ceval_datasets
+    from ..datasets.SuperGLUE_BoolQ.SuperGLUE_BoolQ_gen_883d50 import BoolQ_datasets
+    from ..datasets.humaneval.humaneval_gen_8e312c import humaneval_datasets
     from ..summarizers.example import summarizer
 
 datasets = sum([v for k, v in locals().items() if k.endswith("_datasets") or k == 'datasets'], [])

configs/vllm/eval_qwen_chat_vllm.py

 from mmengine.config import read_base
 
 with read_base():
-    from ..datasets.ARC_c.ARC_c_gen_1e0de5 import ARC_c_datasets 
-    from ..datasets.ARC_e.ARC_e_gen_1e0de5 import ARC_e_datasets
+    # from ..datasets.ARC_c.ARC_c_gen_1e0de5 import ARC_c_datasets 
+    # from ..datasets.ARC_e.ARC_e_gen_1e0de5 import ARC_e_datasets
+    from ..datasets.ceval.ceval_gen_5f30c7 import ceval_datasets
+    from ..datasets.SuperGLUE_BoolQ.SuperGLUE_BoolQ_gen_883d50 import BoolQ_datasets
+    from ..datasets.humaneval.humaneval_gen_8e312c import humaneval_datasets
     from ..summarizers.example import summarizer
 
 datasets = sum([v for k, v in locals().items() if k.endswith("_datasets") or k == 'datasets'], [])

configs/vllm/eval_qwen_int4_chat_vllm.py

 from mmengine.config import read_base
 
 with read_base():
-    from ..datasets.ARC_c.ARC_c_gen_1e0de5 import ARC_c_datasets 
-    from ..datasets.ARC_e.ARC_e_gen_1e0de5 import ARC_e_datasets
+    # from ..datasets.ARC_c.ARC_c_gen_1e0de5 import ARC_c_datasets 
+    # from ..datasets.ARC_e.ARC_e_gen_1e0de5 import ARC_e_datasets
+    from ..datasets.ceval.ceval_gen_5f30c7 import ceval_datasets
+    from ..datasets.SuperGLUE_BoolQ.SuperGLUE_BoolQ_gen_883d50 import BoolQ_datasets
+    from ..datasets.humaneval.humaneval_gen_8e312c import humaneval_datasets
     from ..summarizers.example import summarizer
 
 datasets = sum([v for k, v in locals().items() if k.endswith("_datasets") or k == 'datasets'], [])