Add results file for Llama-3.2-1B-Instruct

results/meta-llama/Llama-3.2-1B-Instruct_results_2025-05-10_20-50-10.json

@@ -0,0 +1,153 @@
+{
+  "results": {
+    "average_score": 3.1404255319148935,
+    "speed": 21.763742973892796,
+    "contamination_score": 0,
+    "execution_time": 1356.660021,
+    "errors": [],
+    "scores_by_category": [
+      {
+        "category": "Paraphrasing",
+        "average_score": 9.666666666666666,
+        "count": 6
+      },
+      {
+        "category": "Coding",
+        "average_score": 8.666666666666666,
+        "count": 3
+      },
+      {
+        "category": "Summarization",
+        "average_score": 7.25,
+        "count": 8
+      },
+      {
+        "category": "Sentiment Analysis",
+        "average_score": 5.555555555555555,
+        "count": 9
+      },
+      {
+        "category": "Trust & Safety",
+        "average_score": 4.9,
+        "count": 30
+      },
+      {
+        "category": "Hallucination",
+        "average_score": 4.0,
+        "count": 3
+      },
+      {
+        "category": "Instruction Following",
+        "average_score": 3.7142857142857144,
+        "count": 7
+      },
+      {
+        "category": "Structuring",
+        "average_score": 3.6666666666666665,
+        "count": 3
+      },
+      {
+        "category": "General Knowledge",
+        "average_score": 3.5873015873015874,
+        "count": 63
+      },
+      {
+        "category": "Reading Comprehension",
+        "average_score": 3.5294117647058822,
+        "count": 17
+      },
+      {
+        "category": "MMLU",
+        "average_score": 3.2231404958677685,
+        "count": 121
+      },
+      {
+        "category": "Entity Extraction",
+        "average_score": 3.2,
+        "count": 5
+      },
+      {
+        "category": "Translation (incl Dialects)",
+        "average_score": 3.0277777777777777,
+        "count": 36
+      },
+      {
+        "category": "Long Context",
+        "average_score": 3.0,
+        "count": 4
+      },
+      {
+        "category": "Reasoning & Math",
+        "average_score": 2.302325581395349,
+        "count": 43
+      },
+      {
+        "category": "Writing (incl Dialects)",
+        "average_score": 2.227272727272727,
+        "count": 22
+      },
+      {
+        "category": "RAG QA",
+        "average_score": 2.1219512195121952,
+        "count": 41
+      },
+      {
+        "category": "Function Calling",
+        "average_score": 1.6666666666666667,
+        "count": 3
+      },
+      {
+        "category": "Arabic Language & Grammar",
+        "average_score": 1.3529411764705883,
+        "count": 17
+      },
+      {
+        "category": "Diacritization",
+        "average_score": 0.6666666666666666,
+        "count": 12
+      },
+      {
+        "category": "Dialect Detection",
+        "average_score": 0.36363636363636365,
+        "count": 11
+      },
+      {
+        "category": "Transliteration",
+        "average_score": 0.0,
+        "count": 6
+      }
+    ],
+    "scores_by_format": [
+      {
+        "format": "Fill-in-the-blank",
+        "average_score": 3.75,
+        "count": 8
+      },
+      {
+        "format": "MCQ",
+        "average_score": 3.5851528384279474,
+        "count": 229
+      },
+      {
+        "format": "Generation",
+        "average_score": 2.6973684210526314,
+        "count": 228
+      },
+      {
+        "format": "Short Answer",
+        "average_score": 2.0,
+        "count": 5
+      }
+    ]
+  },
+  "config": {
+    "model": "meta-llama/Llama-3.2-1B-Instruct",
+    "model_sha": "9213176726f574b556790deb65791e0c5aa438b6",
+    "submitted_time": "2025-05-10T18:35:20Z",
+    "likes": 924,
+    "params": 1.236,
+    "license": "llama3.2",
+    "model_source": "Hugging Face",
+    "model_category": "Nano"
+  }
+}