karimouda commited on
Commit
5de98af
·
verified ·
1 Parent(s): d8e0a66

Add results file for c4ai-command-r7b-arabic-02-2025

Browse files
results/CohereLabs/c4ai-command-r7b-arabic-02-2025_results_2025-05-10_23-22-16.json ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "average_score": 6.914893617021277,
4
+ "speed": 9.65201056743635,
5
+ "contamination_score": 0,
6
+ "execution_time": 2158.099585,
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": 9.411764705882353,
27
+ "count": 17
28
+ },
29
+ {
30
+ "category": "Entity Extraction",
31
+ "average_score": 9.0,
32
+ "count": 5
33
+ },
34
+ {
35
+ "category": "Function Calling",
36
+ "average_score": 9.0,
37
+ "count": 3
38
+ },
39
+ {
40
+ "category": "Summarization",
41
+ "average_score": 8.375,
42
+ "count": 8
43
+ },
44
+ {
45
+ "category": "Long Context",
46
+ "average_score": 7.75,
47
+ "count": 4
48
+ },
49
+ {
50
+ "category": "MMLU",
51
+ "average_score": 7.520661157024794,
52
+ "count": 121
53
+ },
54
+ {
55
+ "category": "General Knowledge",
56
+ "average_score": 7.015873015873016,
57
+ "count": 63
58
+ },
59
+ {
60
+ "category": "RAG QA",
61
+ "average_score": 6.853658536585366,
62
+ "count": 41
63
+ },
64
+ {
65
+ "category": "Dialect Detection",
66
+ "average_score": 6.818181818181818,
67
+ "count": 11
68
+ },
69
+ {
70
+ "category": "Trust & Safety",
71
+ "average_score": 6.666666666666667,
72
+ "count": 30
73
+ },
74
+ {
75
+ "category": "Translation (incl Dialects)",
76
+ "average_score": 6.527777777777778,
77
+ "count": 36
78
+ },
79
+ {
80
+ "category": "Writing (incl Dialects)",
81
+ "average_score": 6.454545454545454,
82
+ "count": 22
83
+ },
84
+ {
85
+ "category": "Instruction Following",
86
+ "average_score": 6.428571428571429,
87
+ "count": 7
88
+ },
89
+ {
90
+ "category": "Structuring",
91
+ "average_score": 6.0,
92
+ "count": 3
93
+ },
94
+ {
95
+ "category": "Diacritization",
96
+ "average_score": 5.666666666666667,
97
+ "count": 12
98
+ },
99
+ {
100
+ "category": "Arabic Language & Grammar",
101
+ "average_score": 5.176470588235294,
102
+ "count": 17
103
+ },
104
+ {
105
+ "category": "Reasoning & Math",
106
+ "average_score": 4.906976744186046,
107
+ "count": 43
108
+ },
109
+ {
110
+ "category": "Transliteration",
111
+ "average_score": 4.166666666666667,
112
+ "count": 6
113
+ },
114
+ {
115
+ "category": "Hallucination",
116
+ "average_score": 0.0,
117
+ "count": 3
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": 7.17467248908297,
129
+ "count": 229
130
+ },
131
+ {
132
+ "format": "Generation",
133
+ "average_score": 6.697368421052632,
134
+ "count": 228
135
+ },
136
+ {
137
+ "format": "Fill-in-the-blank",
138
+ "average_score": 3.75,
139
+ "count": 8
140
+ }
141
+ ]
142
+ },
143
+ "config": {
144
+ "model": "CohereLabs/c4ai-command-r7b-arabic-02-2025",
145
+ "model_sha": "567c7224870f92b22a83525d2c7fb545cdffb948",
146
+ "submitted_time": "2025-05-10T18:37:06Z",
147
+ "likes": 105,
148
+ "params": 8.028,
149
+ "license": "cc-by-nc-4.0",
150
+ "model_source": "Hugging Face",
151
+ "model_category": "Small"
152
+ }
153
+ }