hongfu_update_20250701

.idea/workspace.xml

@@ -0,0 +1,58 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ChangeListManager">
+    <list default="true" id="60da6b73-38f4-48aa-bd78-5731d35b3a7c" name="Changes" comment="" />
+    <option name="SHOW_DIALOG" value="false" />
+    <option name="HIGHLIGHT_CONFLICTS" value="true" />
+    <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
+    <option name="LAST_RESOLUTION" value="IGNORE" />
+  </component>
+  <component name="Git.Settings">
+    <option name="RECENT_GIT_ROOT_PATH" value="$PROJECT_DIR$" />
+  </component>
+  <component name="MarkdownSettingsMigration">
+    <option name="stateVersion" value="1" />
+  </component>
+  <component name="ProjectColorInfo">{
+  &quot;customColor&quot;: &quot;&quot;,
+  &quot;associatedIndex&quot;: 2
+}</component>
+  <component name="ProjectId" id="2zGmpeKAt5GZlNtHRIRD45uRoxd" />
+  <component name="ProjectViewState">
+    <option name="hideEmptyMiddlePackages" value="true" />
+    <option name="showLibraryContents" value="true" />
+  </component>
+  <component name="PropertiesComponent"><![CDATA[{
+  "keyToString": {
+    "RunOnceActivity.OpenProjectViewOnStart": "true",
+    "RunOnceActivity.ShowReadmeOnStart": "true",
+    "git-widget-placeholder": "pr/18",
+    "last_opened_file_path": "E:/pythonProject/ChineseSafe-Benchmark",
+    "nodejs_package_manager_path": "npm",
+    "vue.rearranger.settings.migration": "true"
+  }
+}]]></component>
+  <component name="SharedIndexes">
+    <attachedChunks>
+      <set>
+        <option value="bundled-python-sdk-67fca87a943a-c986f194a52a-com.jetbrains.pycharm.pro.sharedIndexes.bundled-PY-233.11799.259" />
+      </set>
+    </attachedChunks>
+  </component>
+  <component name="SpellCheckerSettings" RuntimeDictionaries="0" Folders="0" CustomDictionaries="0" DefaultDictionary="application-level" UseSingleDictionary="true" transferred="true" />
+  <component name="TaskManager">
+    <task active="true" id="Default" summary="Default task">
+      <changelist id="60da6b73-38f4-48aa-bd78-5731d35b3a7c" name="Changes" comment="" />
+      <created>1751365967779</created>
+      <option name="number" value="Default" />
+      <option name="presentableId" value="Default" />
+      <updated>1751365967779</updated>
+      <workItem from="1751365968934" duration="39000" />
+      <workItem from="1751366116696" duration="54000" />
+    </task>
+    <servers />
+  </component>
+  <component name="TypeScriptGeneratedFilesManager">
+    <option name="version" value="3" />
+  </component>
+</project>

app.py

@@ -6,11 +6,13 @@ import pandas as pd
 from assets.text import INTRODUCTION_TEXT, METRICS_TEXT, EVALUTION_TEXT, ACKNOWLEDGEMENTS_TEXT, REFERENCE_TEXT
 
 
-ORIGINAL_DF = pd.read_csv("./data/chinese_benchmark_gen.csv", sep='\t') # space separated values
-ORIGINAL_DF_PER = pd.read_csv("./data/chinese_benchmark_per.csv", sep='\t') #
+ORIGINAL_DF = pd.read_csv("./data/chinese_benchmark_gen.csv", encoding='utf-8') # space separated values
+ORIGINAL_DF_PER = pd.read_csv("./data/chinese_benchmark_per.csv", encoding='utf-8') #
+
+
+ORIGINAL_DF_SUB_GEN = pd.read_csv("./data/subclass_gen.csv", encoding='utf-8') #
+ORIGINAL_DF_SUB_PER = pd.read_csv("./data/subclass_per.csv", encoding='utf-8')
 
-ORIGINAL_DF_SUB_GEN = pd.read_csv("./data/subclass_gen.csv", sep=',') #
-ORIGINAL_DF_SUB_PER = pd.read_csv("./data/subclass_per.csv", sep=',')
 
 METRICS = ["Accuracy", "Precision_Unsafe", "Recall_Unsafe", "Precision_Safe", "Recall_Safe", "None"]
 
@@ -28,7 +30,7 @@ CLASSIFICATION = {
         "5B~10B",
         "API",
     ]
-    
+
 }
 
 
@@ -36,13 +38,13 @@ CLASSIFICATION = {
 
 _BIBTEX = """
 @misc{zhang2024chinesesafechinesebenchmarkevaluating,
-      title={ChineseSafe: A Chinese Benchmark for Evaluating Safety in Large Language Models}, 
+      title={ChineseSafe: A Chinese Benchmark for Evaluating Safety in Large Language Models},
       author={Hengxiang Zhang and Hongfu Gao and Qiang Hu and Guanhua Chen and Lili Yang and Bingyi Jing and Hongxin Wei and Bing Wang and Haifeng Bai and Lei Yang},
       year={2024},
       eprint={2410.18491},
       archivePrefix={arXiv},
       primaryClass={cs.CL},
-      url={https://arxiv.org/abs/2410.18491}, 
+      url={https://arxiv.org/abs/2410.18491},
 }
 """
 
@@ -62,8 +64,8 @@ def format_csv_numbers(text):
 
 def format_csv_numbers_second(text):
     return text.split()
-    
-    
+
+
 def format_number(x):
     return float(f"{x:.3}")
 
@@ -73,7 +75,7 @@ def get_dataset_csv(
 ):
     df = ORIGINAL_DF[ORIGINAL_DF['Size'].isin(model_size)]
     df = df.drop(columns="Size")
-    
+
     leaderboard_table = gr.components.Dataframe(
         value=df,
         interactive=False,
@@ -101,11 +103,11 @@ def get_dataset_csv_sub_gen(
 ):
     df = ORIGINAL_DF_SUB_GEN[ORIGINAL_DF_SUB_GEN['Size'].isin(model_size)]
     df = df.drop(columns="Size")
-    
+
     # get subclass
     subclass_choice_label = ["Model", subclass_choice+"_Accuracy", subclass_choice+"_Precision", subclass_choice+"_Recall"]
     df = df[subclass_choice_label]
-    
+
     leaderboard_table = gr.components.Dataframe(
         value=df,
         interactive=False,
@@ -120,11 +122,11 @@ def get_dataset_csv_sub_per(
 ):
     df = ORIGINAL_DF_SUB_PER[ORIGINAL_DF_SUB_PER['Size'].isin(model_size)]
     df = df.drop(columns="Size")
-    
+
     # get subclass
     subclass_choice_label = ["Model", subclass_choice+"_Accuracy", subclass_choice+"_Precision", subclass_choice+"_Recall"]
     df = df[subclass_choice_label]
-    
+
     leaderboard_table = gr.components.Dataframe(
         value=df,
         interactive=False,
@@ -143,7 +145,7 @@ def get_dataset_classfier_gen(
         subclass_choice = main_choice
         leaderboard_table = get_dataset_csv_sub_gen(model_size, subclass_choice)
     return leaderboard_table
-        
+
 def get_dataset_classfier_per(
     model_size: List[str],
     main_choice: List[str],
@@ -164,10 +166,10 @@ with gr.Blocks() as demo:
 
     with gr.Row():
         gr.Markdown(METRICS_TEXT, elem_classes="markdown-text")
-    
+
     with gr.Row():
         gr.Markdown(EVALUTION_TEXT, elem_classes="markdown-text")
-        
+
     with gr.Row():
         with gr.Column(scale=0.8):
             main_choice = gr.Dropdown(
@@ -176,8 +178,8 @@ with gr.Blocks() as demo:
                 label="Type",
                 info="Please choose the type to display.",
             )
-            
-        with gr.Column(scale=10): 
+
+        with gr.Column(scale=10):
             model_choice = gr.CheckboxGroup(
                 choices=CLASSIFICATION["model_size"],
                 value=CLASSIFICATION["model_size"],  # all be choosed
@@ -188,12 +190,12 @@ with gr.Blocks() as demo:
     #👉 this part is for csv table generatived
     with gr.Tabs(elem_classes="tab-buttons") as tabs:
         # ----------------- modify text -----------------
-        
+
         with gr.TabItem("🏅 Generation", elem_id="od-benchmark-tab-table", id=6):
             dataframe_all_gen = gr.components.Dataframe(
                 elem_id="leaderboard-table",
             )
-            
+
         with gr.TabItem("🏅 Perplexity", elem_id="od-benchmark-tab-table", id=5):
             dataframe_all_per = gr.components.Dataframe(
                 elem_id="leaderboard-table",
@@ -202,10 +204,10 @@ with gr.Blocks() as demo:
     # ----------------- modify text -----------------
     with gr.Row():
         gr.Markdown(ACKNOWLEDGEMENTS_TEXT, elem_classes="markdown-text")
-    
+
     with gr.Row():
         gr.Markdown(REFERENCE_TEXT, elem_classes="markdown-text")
-    
+
     # 👉 this part is for citation
     with gr.Row():
         with gr.Accordion("📙 Citation", open=True):
@@ -216,18 +218,18 @@ with gr.Blocks() as demo:
                 elem_id="citation-button",
                 show_copy_button=True
             )
-    
+
     gr.Markdown(f"Last updated on **{_LAST_UPDATED}**", elem_classes="markdown-text")
-    
+
     # --------------------------- all --------------------------------
     # this is  all result Perplexity
-    
+
     main_choice.change(
         get_dataset_classfier_per,
         inputs=[model_choice, main_choice],
         outputs=dataframe_all_per,
     )
-        
+
     model_choice.change(
         get_dataset_classfier_per,
         inputs=[model_choice, main_choice],
@@ -239,26 +241,26 @@ with gr.Blocks() as demo:
         inputs=[model_choice, main_choice],
         outputs=dataframe_all_per,
     )
-    
+
     # this is all result generatived
     main_choice.change(
         get_dataset_classfier_gen,
         inputs=[model_choice, main_choice],
         outputs=dataframe_all_gen,
     )
-        
+
     model_choice.change(
         get_dataset_classfier_gen,
         inputs=[model_choice, main_choice],
         outputs=dataframe_all_gen,
     )
-    
+
     demo.load(
         fn=get_dataset_classfier_gen,
         inputs=[model_choice, main_choice],
         outputs=dataframe_all_gen,
     )
-    
-    
+
+
 demo.launch(share=True)
 

data/chinese_benchmark_per.csv

@@ -43,4 +43,4 @@ Opt-6.7B,5B~10B,48.54/0.43,49.24/0.31,86.62/1.03,43.40/1.18,10.30/0.55
 Mistral-7B-Instruct-v0.3,5B~10B,42.99/0.06,39.54/0.47,26.01/0.69,44.69/0.11,60.05/0.50
 Llama3-ChatQA-1.5-8B,5B~10B,42.11/0.29,37.46/0.85,23.20/0.89,44.20/0.09,61.11/0.57
 Qwen3-4B,5B~10B,46.04/0.00,47.79/0.00,85.94/0.00,30.39/0.00,6.14/0.00
-Gemma-3-4B-it,5B~10B,50.00/0.00,0.00/0.00,0.00/0.00,50.00/0.00,100.00/0.00
+Gemma-3-4B-it,5B~10B,50.00/0.00,0.00/0.00,0.00/0.00,50.00/0.00,100.00/0.00

data/subclass_gen.csv

@@ -48,4 +48,4 @@ Opt-30B,~30B,0.4672,0.4683,0.6648,0.5002,0.5082,0.7109,0.5044,0.4987,0.7354,0.53
 QwQ-32B-Preview,~30B,0.6837,0.7403,0.547,0.812,0.8219,0.8084,0.606,0.6749,0.3914,0.7516,0.8198,0.6977,0.8121,0.823,0.8081,0.847,0.8208,0.8801,0.6113,0.6736,0.3973,0.605,0.67,0.3873,0.7492,0.7768,0.6783,0.4656,0.3791,0.1124
 Qwen3-32B,~30B,0.5416,0.5902,0.2095,0.5495,0.6557,0.2531,0.477,0.3724,0.0843,0.6293,0.66,0.6114,0.8339,0.7311,0.6644,0.9577,0.3309,0.2379,0.1626,0.6958,0.6204,0.8741,0.2629,0.9049,0.9606,0.8489,0.5103,0.547,0.0453,0.8192
 Gemma-3-27b-it,~30B,0.66,0.6114,0.8339,0.7311,0.6644,0.9577,0.3309,0.2379,0.1626,0.6958,0.6204,0.8741,0.2629,0.9049,0.9606,0.8489,0.5103,0.547,0.0453,0.8192,0.4672,0.4683,0.6648,0.5002,0.5082,0.7109,0.5044,0.4987,0.7354,0.5314
-OpenThinker2-32B,~30B,0.6204,0.8741,0.2629,0.9049,0.9606,0.8489,0.5103,0.547,0.0453,0.8192,0.4672,0.4683,0.6648,0.5002,0.5082,0.7109,0.5044,0.4987,0.7354,0.5314,0.6837,0.7403,0.547,0.812,0.8219,0.8084,0.606,0.6749,0.3914,0.7516
+OpenThinker2-32B,~30B,0.6204,0.8741,0.2629,0.9049,0.9606,0.8489,0.5103,0.547,0.0453,0.8192,0.4672,0.4683,0.6648,0.5002,0.5082,0.7109,0.5044,0.4987,0.7354,0.5314,0.6837,0.7403,0.547,0.812,0.8219,0.8084,0.606,0.6749,0.3914,0.7516

data/subclass_per.csv

@@ -41,4 +41,4 @@ Opt-30B,~30B,0.5831,0.5754,0.5565,0.3952,0.338,0.1915,0.6784,0.6507,0.7506,0.579
 QwQ-32B-Preview,~30B,0.5231,0.5061,0.9839,0.5519,0.5328,1,0.4141,0.4443,0.7537,0.5814,0.565,0.9989,0.5529,0.534,0.9993,0.5318,0.5111,0.9993,0.5083,0.4978,0.9542,0.4392,0.4593,0.808,0.5238,0.5042,0.9922,0.5269,0.5128,0.9743
 Mistral-Small-24B-Instruct-2501,~30B,0.5897,0.5714,0.6393,0.7706,0.6931,0.9888,0.3109,0.1339,0.0727,0.7308,0.6984,0.8887,0.7454,0.683,0.9385,0.7584,0.6732,0.9835,0.585,0.5671,0.6297,0.3646,0.2744,0.1803,0.7088,0.645,0.8855,0.3839,0.3257,0.2233
 OpenThinker2-32B,~30B,0.7139 ,0.8341 ,0.5176 ,0.7722 ,0.8735 ,0.6482 ,0.4750 ,0.2581 ,0.0357 ,0.7162 ,0.6749 ,0.6366 ,0.7789 ,0.7893 ,0.7099 ,0.9938 ,0.4372 ,0.4025 ,0.2943 ,0.7921 ,0.5831 ,0.5754 ,0.5565 ,0.3952 ,0.3380 ,0.1915 ,0.6784 ,0.6507 ,0.7506 ,0.5798 
-Qwen3-32B,~30B,0.6749 ,0.6366 ,0.7789 ,0.7893 ,0.7099 ,0.9938 ,0.4372 ,0.4025 ,0.2943 ,0.7921 ,0.5831 ,0.5754 ,0.5565 ,0.3952 ,0.3380 ,0.1915 ,0.6784 ,0.6507 ,0.7506 ,0.5798 ,0.5231 ,0.5061 ,0.9839 ,0.5519 ,0.5328 ,1.0000 ,0.4141 ,0.4443 ,0.7537 ,0.5814 
+Qwen3-32B,~30B,0.6749 ,0.6366 ,0.7789 ,0.7893 ,0.7099 ,0.9938 ,0.4372 ,0.4025 ,0.2943 ,0.7921 ,0.5831 ,0.5754 ,0.5565 ,0.3952 ,0.3380 ,0.1915 ,0.6784 ,0.6507 ,0.7506 ,0.5798 ,0.5231 ,0.5061 ,0.9839 ,0.5519 ,0.5328 ,1.0000 ,0.4141 ,0.4443 ,0.7537 ,0.5814