Update olmpiadBench

configs/eval_OlympiadBench.py

@@ -5,7 +5,7 @@ with read_base():
 
     # from opencompass.configs.models.qwen2_5.hf_qwen2_5_7b_instruct import models as hf_qwen2_5_7b_instruct_model
     from opencompass.configs.models.qwen2_5.lmdeploy_qwen2_5_7b_instruct import models as lmdeploy_qwen2_5_7b_instruct_model
-    from opencompass.configs.models.hf_llama.lmdeploy_llama3_8b_instruct import models as lmdeploy_llama3_8b_instruct_model
+    # from opencompass.configs.models.hf_llama.lmdeploy_llama3_8b_instruct import models as lmdeploy_llama3_8b_instruct_model
 
     from opencompass.configs.summarizers.OlympiadBench import summarizer
 

opencompass/configs/datasets/OlympiadBench/OlympiadBench_0shot_gen_be8b13.py

@@ -1,8 +1,6 @@
 from mmengine.config import read_base
-from opencompass.openicl.icl_prompt_template import PromptTemplate
 from opencompass.openicl.icl_retriever import ZeroRetriever
 from opencompass.openicl.icl_inferencer import GenInferencer
-# from opencompass.datasets import MATHDataset, MATHEvaluator, math_postprocess_v2, normalize_final_answer
 from opencompass.datasets import OlympiadBenchDataset, OlympiadBenchEvaluator, olympiadbench_postprocess_v2
 
 

opencompass/utils/datasets_info.py

@@ -398,9 +398,18 @@ DATASETS_MAPPING = {
         "hf_id": "THUDM/LongBench-v2",
         "local": "./data/longbenchv2/data.json",
     },
+    "opencompass/OlympiadBench": {
+        "ms_id": "",
+        "hf_id": "",
+        "local": "./data/OlympiadBench",
+    },
 }
 
 DATASETS_URL = {
+    "/OlympiadBench": {
+        "url": "http://opencompass.oss-cn-shanghai.aliyuncs.com/datasets/data/OlympiadBench.zip",
+        "md5": "97e8b1ae7f6170d94817288a8930ef00",
+    },
     "/longbenchv2":{
         "url": "http://opencompass.oss-cn-shanghai.aliyuncs.com/datasets/data/longbenchv2.zip",
         "md5": "09b7e06e6f98c5cca8ad597b3d7b42f0",

requirements/extra.txt

@@ -1,5 +1,7 @@
 # Alpaca-eval
 alpaca-eval==0.6
+# OlympiadBench
+antlr4-python3-runtime==4.11
 cn2an
 # Dingo
 dingo-python==1.1.2