karimouda commited on
Commit
9aca0f5
·
verified ·
1 Parent(s): 97a0299

Add results file for Qwen2.5-0.5B-Instruct

Browse files
results/Qwen/Qwen2.5-0.5B-Instruct_results_2025-05-11_18-00-04.json ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "average_score": 3.078723404255319,
4
+ "speed": 17.28472479297938,
5
+ "contamination_score": 0,
6
+ "execution_time": 1583.536928,
7
+ "errors": [],
8
+ "scores_by_category": [
9
+ {
10
+ "category": "Paraphrasing",
11
+ "average_score": 8.833333333333334,
12
+ "count": 6
13
+ },
14
+ {
15
+ "category": "Reading Comprehension",
16
+ "average_score": 7.647058823529412,
17
+ "count": 17
18
+ },
19
+ {
20
+ "category": "Entity Extraction",
21
+ "average_score": 7.2,
22
+ "count": 5
23
+ },
24
+ {
25
+ "category": "Function Calling",
26
+ "average_score": 6.333333333333333,
27
+ "count": 3
28
+ },
29
+ {
30
+ "category": "Long Context",
31
+ "average_score": 6.25,
32
+ "count": 4
33
+ },
34
+ {
35
+ "category": "Sentiment Analysis",
36
+ "average_score": 5.555555555555555,
37
+ "count": 9
38
+ },
39
+ {
40
+ "category": "Coding",
41
+ "average_score": 4.666666666666667,
42
+ "count": 3
43
+ },
44
+ {
45
+ "category": "Summarization",
46
+ "average_score": 4.25,
47
+ "count": 8
48
+ },
49
+ {
50
+ "category": "RAG QA",
51
+ "average_score": 3.951219512195122,
52
+ "count": 41
53
+ },
54
+ {
55
+ "category": "Trust & Safety",
56
+ "average_score": 3.933333333333333,
57
+ "count": 30
58
+ },
59
+ {
60
+ "category": "Writing (incl Dialects)",
61
+ "average_score": 3.4545454545454546,
62
+ "count": 22
63
+ },
64
+ {
65
+ "category": "Structuring",
66
+ "average_score": 3.3333333333333335,
67
+ "count": 3
68
+ },
69
+ {
70
+ "category": "Translation (incl Dialects)",
71
+ "average_score": 2.861111111111111,
72
+ "count": 36
73
+ },
74
+ {
75
+ "category": "Reasoning & Math",
76
+ "average_score": 2.627906976744186,
77
+ "count": 43
78
+ },
79
+ {
80
+ "category": "Arabic Language & Grammar",
81
+ "average_score": 2.4705882352941178,
82
+ "count": 17
83
+ },
84
+ {
85
+ "category": "General Knowledge",
86
+ "average_score": 2.238095238095238,
87
+ "count": 63
88
+ },
89
+ {
90
+ "category": "MMLU",
91
+ "average_score": 2.231404958677686,
92
+ "count": 121
93
+ },
94
+ {
95
+ "category": "Dialect Detection",
96
+ "average_score": 2.1818181818181817,
97
+ "count": 11
98
+ },
99
+ {
100
+ "category": "Instruction Following",
101
+ "average_score": 2.142857142857143,
102
+ "count": 7
103
+ },
104
+ {
105
+ "category": "Hallucination",
106
+ "average_score": 1.0,
107
+ "count": 3
108
+ },
109
+ {
110
+ "category": "Transliteration",
111
+ "average_score": 0.8333333333333334,
112
+ "count": 6
113
+ },
114
+ {
115
+ "category": "Diacritization",
116
+ "average_score": 0.3333333333333333,
117
+ "count": 12
118
+ }
119
+ ],
120
+ "scores_by_format": [
121
+ {
122
+ "format": "Fill-in-the-blank",
123
+ "average_score": 5.0,
124
+ "count": 8
125
+ },
126
+ {
127
+ "format": "MCQ",
128
+ "average_score": 3.1397379912663754,
129
+ "count": 229
130
+ },
131
+ {
132
+ "format": "Generation",
133
+ "average_score": 2.973684210526316,
134
+ "count": 228
135
+ },
136
+ {
137
+ "format": "Short Answer",
138
+ "average_score": 2.0,
139
+ "count": 5
140
+ }
141
+ ]
142
+ },
143
+ "config": {
144
+ "model": "Qwen/Qwen2.5-0.5B-Instruct",
145
+ "model_sha": "7ae557604adf67be50417f59c2c2f167def9a775",
146
+ "submitted_time": "2025-05-11T16:49:08Z",
147
+ "likes": 315,
148
+ "params": 0.494,
149
+ "license": "apache-2.0",
150
+ "model_source": "Hugging Face",
151
+ "model_category": "Nano"
152
+ }
153
+ }