karimouda commited on
Commit
1d35062
·
verified ·
1 Parent(s): 7ee5194

Add results file for Qwen2.5-14B-Instruct

Browse files
results/Qwen/Qwen2.5-14B-Instruct_results_2025-06-03_12-06-14.json ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "average_score": 7.772340425531915,
4
+ "speed": 6.536370837042747,
5
+ "contamination_score": 0,
6
+ "execution_time": 2982.541916,
7
+ "errors": [],
8
+ "scores_by_category": [
9
+ {
10
+ "category": "Paraphrasing",
11
+ "average_score": 10.0,
12
+ "count": 6
13
+ },
14
+ {
15
+ "category": "Sentiment Analysis",
16
+ "average_score": 10.0,
17
+ "count": 9
18
+ },
19
+ {
20
+ "category": "Coding",
21
+ "average_score": 10.0,
22
+ "count": 3
23
+ },
24
+ {
25
+ "category": "Reading Comprehension",
26
+ "average_score": 10.0,
27
+ "count": 17
28
+ },
29
+ {
30
+ "category": "Function Calling",
31
+ "average_score": 9.333333333333334,
32
+ "count": 3
33
+ },
34
+ {
35
+ "category": "Instruction Following",
36
+ "average_score": 9.285714285714286,
37
+ "count": 7
38
+ },
39
+ {
40
+ "category": "MMLU",
41
+ "average_score": 8.760330578512397,
42
+ "count": 121
43
+ },
44
+ {
45
+ "category": "Summarization",
46
+ "average_score": 8.75,
47
+ "count": 8
48
+ },
49
+ {
50
+ "category": "Trust & Safety",
51
+ "average_score": 8.333333333333334,
52
+ "count": 30
53
+ },
54
+ {
55
+ "category": "Long Context",
56
+ "average_score": 8.25,
57
+ "count": 4
58
+ },
59
+ {
60
+ "category": "General Knowledge",
61
+ "average_score": 7.857142857142857,
62
+ "count": 63
63
+ },
64
+ {
65
+ "category": "RAG QA",
66
+ "average_score": 7.853658536585366,
67
+ "count": 41
68
+ },
69
+ {
70
+ "category": "Dialect Detection",
71
+ "average_score": 7.636363636363637,
72
+ "count": 11
73
+ },
74
+ {
75
+ "category": "Reasoning & Math",
76
+ "average_score": 7.232558139534884,
77
+ "count": 43
78
+ },
79
+ {
80
+ "category": "Writing (incl Dialects)",
81
+ "average_score": 6.954545454545454,
82
+ "count": 22
83
+ },
84
+ {
85
+ "category": "Hallucination",
86
+ "average_score": 6.666666666666667,
87
+ "count": 3
88
+ },
89
+ {
90
+ "category": "Entity Extraction",
91
+ "average_score": 6.6,
92
+ "count": 5
93
+ },
94
+ {
95
+ "category": "Transliteration",
96
+ "average_score": 6.5,
97
+ "count": 6
98
+ },
99
+ {
100
+ "category": "Structuring",
101
+ "average_score": 5.666666666666667,
102
+ "count": 3
103
+ },
104
+ {
105
+ "category": "Translation (incl Dialects)",
106
+ "average_score": 5.083333333333333,
107
+ "count": 36
108
+ },
109
+ {
110
+ "category": "Diacritization",
111
+ "average_score": 4.833333333333333,
112
+ "count": 12
113
+ },
114
+ {
115
+ "category": "Arabic Language & Grammar",
116
+ "average_score": 4.823529411764706,
117
+ "count": 17
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": 8.40174672489083,
129
+ "count": 229
130
+ },
131
+ {
132
+ "format": "Generation",
133
+ "average_score": 7.18859649122807,
134
+ "count": 228
135
+ },
136
+ {
137
+ "format": "Fill-in-the-blank",
138
+ "average_score": 5.0,
139
+ "count": 8
140
+ }
141
+ ]
142
+ },
143
+ "config": {
144
+ "model": "Qwen/Qwen2.5-14B-Instruct",
145
+ "model_sha": "cf98f3b3bbb457ad9e2bb7baf9a0125b6b88caa8",
146
+ "submitted_time": "2025-06-03T11:09:44Z",
147
+ "likes": 234,
148
+ "params": 14.77,
149
+ "license": "apache-2.0",
150
+ "model_source": "Hugging Face",
151
+ "model_category": "Medium"
152
+ }
153
+ }