Add results file for gemma-2-9b-it
Browse files
results/google/gemma-2-9b-it_results_2025-04-29_19-56-50.json
ADDED
@@ -0,0 +1,153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"results": {
|
3 |
+
"average_score": 7.568965517241379,
|
4 |
+
"speed": 6.819987941810345,
|
5 |
+
"contamination_score": -0.0801562041360131,
|
6 |
+
"execution_time": 3164.474405,
|
7 |
+
"errors": [],
|
8 |
+
"scores_by_category": [
|
9 |
+
{
|
10 |
+
"category": "Sentiment Analysis",
|
11 |
+
"average_score": 10.0,
|
12 |
+
"count": 9
|
13 |
+
},
|
14 |
+
{
|
15 |
+
"category": "Reading Comprehension",
|
16 |
+
"average_score": 10.0,
|
17 |
+
"count": 17
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"category": "Paraphrasing",
|
21 |
+
"average_score": 9.666666666666666,
|
22 |
+
"count": 6
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"category": "Function Calling",
|
26 |
+
"average_score": 9.666666666666666,
|
27 |
+
"count": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"category": "RAG QA",
|
31 |
+
"average_score": 9.571428571428571,
|
32 |
+
"count": 21
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"category": "MMLU",
|
36 |
+
"average_score": 8.347107438016529,
|
37 |
+
"count": 121
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"category": "General Knowledge",
|
41 |
+
"average_score": 8.17910447761194,
|
42 |
+
"count": 67
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"category": "Entity Extraction",
|
46 |
+
"average_score": 7.6,
|
47 |
+
"count": 5
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"category": "Writing (incl Dialects)",
|
51 |
+
"average_score": 7.5,
|
52 |
+
"count": 22
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"category": "Transliteration",
|
56 |
+
"average_score": 7.333333333333333,
|
57 |
+
"count": 6
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"category": "Summarization",
|
61 |
+
"average_score": 7.111111111111111,
|
62 |
+
"count": 9
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"category": "Translation (incl Dialects)",
|
66 |
+
"average_score": 6.681818181818182,
|
67 |
+
"count": 44
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"category": "Coding",
|
71 |
+
"average_score": 6.666666666666667,
|
72 |
+
"count": 3
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"category": "Trust & Safety",
|
76 |
+
"average_score": 6.666666666666667,
|
77 |
+
"count": 30
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"category": "Arabic Language & Grammar",
|
81 |
+
"average_score": 6.647058823529412,
|
82 |
+
"count": 17
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"category": "Dialect Detection",
|
86 |
+
"average_score": 6.181818181818182,
|
87 |
+
"count": 11
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"category": "Reasoning & Math",
|
91 |
+
"average_score": 6.116279069767442,
|
92 |
+
"count": 43
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"category": "Structuring",
|
96 |
+
"average_score": 5.333333333333333,
|
97 |
+
"count": 3
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"category": "Instruction Following",
|
101 |
+
"average_score": 5.0,
|
102 |
+
"count": 7
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"category": "Diacritization",
|
106 |
+
"average_score": 4.5,
|
107 |
+
"count": 12
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"category": "Hallucination",
|
111 |
+
"average_score": 4.333333333333333,
|
112 |
+
"count": 3
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"category": "Long Context",
|
116 |
+
"average_score": 3.8,
|
117 |
+
"count": 5
|
118 |
+
}
|
119 |
+
],
|
120 |
+
"scores_by_format": [
|
121 |
+
{
|
122 |
+
"format": "Short Answer",
|
123 |
+
"average_score": 10.0,
|
124 |
+
"count": 5
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"format": "MCQ",
|
128 |
+
"average_score": 8.025751072961373,
|
129 |
+
"count": 233
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"format": "Generation",
|
133 |
+
"average_score": 7.256880733944954,
|
134 |
+
"count": 218
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"format": "Fill-in-the-blank",
|
138 |
+
"average_score": 1.25,
|
139 |
+
"count": 8
|
140 |
+
}
|
141 |
+
]
|
142 |
+
},
|
143 |
+
"config": {
|
144 |
+
"model": "google/gemma-2-9b-it",
|
145 |
+
"model_sha": "11c9b309abf73637e4b6f9a3fa1e92e615547819",
|
146 |
+
"submitted_time": "2025-04-29 19:00:47",
|
147 |
+
"likes": 700,
|
148 |
+
"params": 9.2,
|
149 |
+
"license": "gemma",
|
150 |
+
"model_source": "Hugging Face",
|
151 |
+
"model_category": "Small"
|
152 |
+
}
|
153 |
+
}
|