karimouda commited on
Commit
100def8
·
verified ·
1 Parent(s): 7aa5182

Delete results/Qwen/Qwen3-4B-Thinking-2507_results_2025-08-11_02-12-18.json

Browse files
results/Qwen/Qwen3-4B-Thinking-2507_results_2025-08-11_02-12-18.json DELETED
@@ -1,153 +0,0 @@
1
- {
2
- "results": {
3
- "average_score": 3.425531914893617,
4
- "speed": 34.36978607602766,
5
- "contamination_score": 0,
6
- "execution_time": 7691.086567,
7
- "errors": [],
8
- "scores_by_category": [
9
- {
10
- "category": "Function Calling",
11
- "average_score": 8.333333333333334,
12
- "count": 3
13
- },
14
- {
15
- "category": "Sentiment Analysis",
16
- "average_score": 6.888888888888889,
17
- "count": 9
18
- },
19
- {
20
- "category": "Reading Comprehension",
21
- "average_score": 6.470588235294118,
22
- "count": 17
23
- },
24
- {
25
- "category": "MMLU",
26
- "average_score": 6.041322314049586,
27
- "count": 121
28
- },
29
- {
30
- "category": "Long Context",
31
- "average_score": 4.75,
32
- "count": 4
33
- },
34
- {
35
- "category": "Trust & Safety",
36
- "average_score": 4.333333333333333,
37
- "count": 30
38
- },
39
- {
40
- "category": "General Knowledge",
41
- "average_score": 4.253968253968254,
42
- "count": 63
43
- },
44
- {
45
- "category": "Coding",
46
- "average_score": 3.3333333333333335,
47
- "count": 3
48
- },
49
- {
50
- "category": "Reasoning & Math",
51
- "average_score": 2.883720930232558,
52
- "count": 43
53
- },
54
- {
55
- "category": "RAG QA",
56
- "average_score": 2.073170731707317,
57
- "count": 41
58
- },
59
- {
60
- "category": "Entity Extraction",
61
- "average_score": 1.8,
62
- "count": 5
63
- },
64
- {
65
- "category": "Translation (incl Dialects)",
66
- "average_score": 0.6111111111111112,
67
- "count": 36
68
- },
69
- {
70
- "category": "Arabic Language & Grammar",
71
- "average_score": 0.5882352941176471,
72
- "count": 17
73
- },
74
- {
75
- "category": "Structuring",
76
- "average_score": 0.3333333333333333,
77
- "count": 3
78
- },
79
- {
80
- "category": "Writing (incl Dialects)",
81
- "average_score": 0.18181818181818182,
82
- "count": 22
83
- },
84
- {
85
- "category": "Instruction Following",
86
- "average_score": 0.0,
87
- "count": 7
88
- },
89
- {
90
- "category": "Hallucination",
91
- "average_score": 0.0,
92
- "count": 3
93
- },
94
- {
95
- "category": "Summarization",
96
- "average_score": 0.0,
97
- "count": 8
98
- },
99
- {
100
- "category": "Dialect Detection",
101
- "average_score": 0.0,
102
- "count": 11
103
- },
104
- {
105
- "category": "Transliteration",
106
- "average_score": 0.0,
107
- "count": 6
108
- },
109
- {
110
- "category": "Diacritization",
111
- "average_score": 0.0,
112
- "count": 12
113
- },
114
- {
115
- "category": "Paraphrasing",
116
- "average_score": 0.0,
117
- "count": 6
118
- }
119
- ],
120
- "scores_by_format": [
121
- {
122
- "format": "Short Answer",
123
- "average_score": 6.4,
124
- "count": 5
125
- },
126
- {
127
- "format": "MCQ",
128
- "average_score": 5.847161572052402,
129
- "count": 229
130
- },
131
- {
132
- "format": "Fill-in-the-blank",
133
- "average_score": 1.375,
134
- "count": 8
135
- },
136
- {
137
- "format": "Generation",
138
- "average_score": 1.0,
139
- "count": 228
140
- }
141
- ]
142
- },
143
- "config": {
144
- "model": "Qwen/Qwen3-4B-Thinking-2507",
145
- "model_sha": "768f209d9ea81521153ed38c47d515654e938aea",
146
- "submitted_time": "2025-08-10T22:17:49Z",
147
- "likes": 246,
148
- "params": 4.022,
149
- "license": "apache-2.0",
150
- "model_source": "Hugging Face",
151
- "model_category": "Small"
152
- }
153
- }