leaderboard

app.py

@@ -12,6 +12,7 @@ from spellchecker import SpellChecker
 import difflib
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
+import hashlib
 
 # ======================== 新增：WAC-GEC导入 ========================
 try:
@@ -423,6 +424,13 @@ def load_leaderboard_data():
     try:
         with open(json_path, 'r', encoding='utf-8') as f:
             data = json.load(f)
+
+        # Replace ID with hash based on Benchmark
+        for item in data:
+            benchmark = item['Benchmark']
+            hash_object = hashlib.md5(benchmark.encode())
+            item['ID'] = hash_object.hexdigest()[:8]  # Use first 8 hex digits for brevity
+
         return pd.DataFrame(data)
     except Exception as e:
         print(f"Error loading leaderboard: {e}")
@@ -774,8 +782,8 @@ with demo:
             gr.Markdown("## BD-toolkit轻量化Demo展示")
             
             # 模型可用性提示
-            model_status = "✅ DeepSeek-R1: " + ("已配置" if DEEPSEEK_API_KEY else "未配置API密钥")
-            model_status += " | ✅ WAC-GEC: " + ("可用" if WAC_GEC_AVAILABLE else "未安装")
+            model_status = "✅ WAC-GEC: " + ("可用" if WAC_GEC_AVAILABLE else "未安装")
+            model_status += " | ✅ DeepSeek-R1: " + ("已配置" if DEEPSEEK_API_KEY else "未配置API密钥")
             gr.Markdown(f"**模型状态**: {model_status}")
             
             with gr.Row():
@@ -792,8 +800,8 @@ with demo:
                     )
                     
                     model_choice = gr.Dropdown(
-                        choices=["deepseek-r1-distill-llama-8b", "WAC-GEC"],
-                        value="deepseek-r1-distill-llama-8b",
+                        choices=["WAC-GEC", "deepseek-r1-distill-llama-8b"],
+                        value="WAC-GEC",
                         label="🤖 选择模型",
                         info="DeepSeek: 全面纠错 | WAC-GEC: 语法+空白符纠正(本地模型)"
                     )
@@ -804,7 +812,8 @@ with demo:
                         value=0.1,
                         step=0.1,
                         label="🌡️ Temperature",
-                        info="仅对DeepSeek生效"
+                        info="仅对DeepSeek生效",
+                        interactive=False  # 默认不可交互（因为默认选择WAC-GEC）
                     )
                     
                     max_samples = gr.Slider(
@@ -826,6 +835,19 @@ with demo:
                     
                     download_file = gr.File(label="📥 下载去噪后的数据集")
             
+            # 添加交互逻辑：根据模型选择动态启用/禁用temperature滑块
+            def update_temperature_interactive(model):
+                if model == "deepseek-r1-distill-llama-8b":
+                    return gr.update(interactive=True, info="调整生成的随机性")
+                else:
+                    return gr.update(interactive=False, info="WAC-GEC模型不支持temperature参数")
+            
+            model_choice.change(
+                fn=update_temperature_interactive,
+                inputs=[model_choice],
+                outputs=[temperature]
+            )
+            
             # 颜色对比预览区域
             gr.Markdown("### 🎨 去噪效果对比预览")
             gr.Markdown("""

leaderboard.json

@@ -3,7 +3,7 @@
         "ID": 1,
         "Category": "RA",
         "Benchmark": "ARC_deepseek_r1_denoising",
-        "WAR": 0.02,
+        "WAR": 0.00,
         "SED": 0.67,
         "Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/ARC/arc_deepseek_r1_denoising)"
     },