Add results file for AceGPT-v2-8B-Chat

results/FreedomIntelligence/AceGPT-v2-8B-Chat_results_2025-05-03_11-41-24.json

@@ -0,0 +1,153 @@
+{
+  "results": {
+    "average_score": 5.764966740576496,
+    "speed": 11.777341778933428,
+    "contamination_score": -0.30175564012351785,
+    "execution_time": 2568.4064,
+    "errors": [],
+    "scores_by_category": [
+      {
+        "category": "Coding",
+        "average_score": 10.0,
+        "count": 3
+      },
+      {
+        "category": "Paraphrasing",
+        "average_score": 9.5,
+        "count": 6
+      },
+      {
+        "category": "Sentiment Analysis",
+        "average_score": 8.88888888888889,
+        "count": 9
+      },
+      {
+        "category": "Reading Comprehension",
+        "average_score": 8.823529411764707,
+        "count": 17
+      },
+      {
+        "category": "Summarization",
+        "average_score": 8.5,
+        "count": 8
+      },
+      {
+        "category": "RAG QA",
+        "average_score": 7.9523809523809526,
+        "count": 21
+      },
+      {
+        "category": "General Knowledge",
+        "average_score": 7.888888888888889,
+        "count": 63
+      },
+      {
+        "category": "Function Calling",
+        "average_score": 6.333333333333333,
+        "count": 3
+      },
+      {
+        "category": "MMLU",
+        "average_score": 6.115702479338843,
+        "count": 121
+      },
+      {
+        "category": "Trust & Safety",
+        "average_score": 5.266666666666667,
+        "count": 30
+      },
+      {
+        "category": "Reasoning & Math",
+        "average_score": 5.255813953488372,
+        "count": 43
+      },
+      {
+        "category": "Long Context",
+        "average_score": 5.0,
+        "count": 4
+      },
+      {
+        "category": "Writing (incl Dialects)",
+        "average_score": 4.954545454545454,
+        "count": 22
+      },
+      {
+        "category": "Instruction Following",
+        "average_score": 4.571428571428571,
+        "count": 7
+      },
+      {
+        "category": "Translation (incl Dialects)",
+        "average_score": 4.378378378378378,
+        "count": 37
+      },
+      {
+        "category": "Arabic Language & Grammar",
+        "average_score": 3.588235294117647,
+        "count": 17
+      },
+      {
+        "category": "Structuring",
+        "average_score": 1.6666666666666667,
+        "count": 3
+      },
+      {
+        "category": "Entity Extraction",
+        "average_score": 1.6,
+        "count": 5
+      },
+      {
+        "category": "Transliteration",
+        "average_score": 0.8333333333333334,
+        "count": 6
+      },
+      {
+        "category": "Dialect Detection",
+        "average_score": 0.45454545454545453,
+        "count": 11
+      },
+      {
+        "category": "Hallucination",
+        "average_score": 0.3333333333333333,
+        "count": 3
+      },
+      {
+        "category": "Diacritization",
+        "average_score": 0.0,
+        "count": 12
+      }
+    ],
+    "scores_by_format": [
+      {
+        "format": "Short Answer",
+        "average_score": 10.0,
+        "count": 5
+      },
+      {
+        "format": "MCQ",
+        "average_score": 6.567685589519651,
+        "count": 229
+      },
+      {
+        "format": "Fill-in-the-blank",
+        "average_score": 5.0,
+        "count": 8
+      },
+      {
+        "format": "Generation",
+        "average_score": 4.813397129186603,
+        "count": 209
+      }
+    ]
+  },
+  "config": {
+    "model": "FreedomIntelligence/AceGPT-v2-8B-Chat",
+    "model_sha": "562d0998c03c02d315e346f81650a43955711901",
+    "submitted_time": "2025-05-03T10:52:49Z",
+    "likes": 2,
+    "params": 8.03,
+    "license": "apache-2.0",
+    "model_source": "Hugging Face",
+    "model_category": "Small"
+  }
+}