Add results file for Qwen2.5-1.5B-Instruct

results/Qwen/Qwen2.5-1.5B-Instruct_results_2025-05-11_19-03-12.json

@@ -0,0 +1,153 @@
+{
+  "results": {
+    "average_score": 4.448936170212766,
+    "speed": 13.245283344579395,
+    "contamination_score": 0,
+    "execution_time": 1252.294841,
+    "errors": [],
+    "scores_by_category": [
+      {
+        "category": "Reading Comprehension",
+        "average_score": 8.823529411764707,
+        "count": 17
+      },
+      {
+        "category": "Coding",
+        "average_score": 8.666666666666666,
+        "count": 3
+      },
+      {
+        "category": "Entity Extraction",
+        "average_score": 7.8,
+        "count": 5
+      },
+      {
+        "category": "Paraphrasing",
+        "average_score": 7.333333333333333,
+        "count": 6
+      },
+      {
+        "category": "Hallucination",
+        "average_score": 7.0,
+        "count": 3
+      },
+      {
+        "category": "Sentiment Analysis",
+        "average_score": 6.666666666666667,
+        "count": 9
+      },
+      {
+        "category": "Function Calling",
+        "average_score": 6.333333333333333,
+        "count": 3
+      },
+      {
+        "category": "Summarization",
+        "average_score": 5.75,
+        "count": 8
+      },
+      {
+        "category": "RAG QA",
+        "average_score": 5.463414634146342,
+        "count": 41
+      },
+      {
+        "category": "Long Context",
+        "average_score": 5.25,
+        "count": 4
+      },
+      {
+        "category": "Writing (incl Dialects)",
+        "average_score": 4.636363636363637,
+        "count": 22
+      },
+      {
+        "category": "MMLU",
+        "average_score": 4.545454545454546,
+        "count": 121
+      },
+      {
+        "category": "Translation (incl Dialects)",
+        "average_score": 4.25,
+        "count": 36
+      },
+      {
+        "category": "General Knowledge",
+        "average_score": 4.238095238095238,
+        "count": 63
+      },
+      {
+        "category": "Trust & Safety",
+        "average_score": 3.933333333333333,
+        "count": 30
+      },
+      {
+        "category": "Structuring",
+        "average_score": 3.3333333333333335,
+        "count": 3
+      },
+      {
+        "category": "Reasoning & Math",
+        "average_score": 3.0232558139534884,
+        "count": 43
+      },
+      {
+        "category": "Diacritization",
+        "average_score": 2.5,
+        "count": 12
+      },
+      {
+        "category": "Instruction Following",
+        "average_score": 2.4285714285714284,
+        "count": 7
+      },
+      {
+        "category": "Transliteration",
+        "average_score": 2.3333333333333335,
+        "count": 6
+      },
+      {
+        "category": "Dialect Detection",
+        "average_score": 2.1818181818181817,
+        "count": 11
+      },
+      {
+        "category": "Arabic Language & Grammar",
+        "average_score": 1.5294117647058822,
+        "count": 17
+      }
+    ],
+    "scores_by_format": [
+      {
+        "format": "MCQ",
+        "average_score": 4.711790393013101,
+        "count": 229
+      },
+      {
+        "format": "Generation",
+        "average_score": 4.2631578947368425,
+        "count": 228
+      },
+      {
+        "format": "Short Answer",
+        "average_score": 4.0,
+        "count": 5
+      },
+      {
+        "format": "Fill-in-the-blank",
+        "average_score": 2.5,
+        "count": 8
+      }
+    ]
+  },
+  "config": {
+    "model": "Qwen/Qwen2.5-1.5B-Instruct",
+    "model_sha": "989aa7980e4cf806f80c7fef2b1adb7bc71aa306",
+    "submitted_time": "2025-05-11T16:49:48Z",
+    "likes": 427,
+    "params": 1.544,
+    "license": "apache-2.0",
+    "model_source": "Hugging Face",
+    "model_category": "Nano"
+  }
+}