karimouda commited on
Commit
75c912f
·
verified ·
1 Parent(s): 5207eb1

Add results file for Llama-3.1-8B-Instruct

Browse files
results/meta-llama/Llama-3.1-8B-Instruct_results_2025-05-01_22-05-13.json ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "average_score": 6.446389496717725,
4
+ "speed": 11.660307769245577,
5
+ "contamination_score": -0.05604882648342041,
6
+ "execution_time": 1583.663173,
7
+ "errors": [],
8
+ "scores_by_category": [
9
+ {
10
+ "category": "Paraphrasing",
11
+ "average_score": 10.0,
12
+ "count": 6
13
+ },
14
+ {
15
+ "category": "Coding",
16
+ "average_score": 9.666666666666666,
17
+ "count": 3
18
+ },
19
+ {
20
+ "category": "Sentiment Analysis",
21
+ "average_score": 8.88888888888889,
22
+ "count": 9
23
+ },
24
+ {
25
+ "category": "Function Calling",
26
+ "average_score": 8.666666666666666,
27
+ "count": 3
28
+ },
29
+ {
30
+ "category": "RAG QA",
31
+ "average_score": 8.523809523809524,
32
+ "count": 21
33
+ },
34
+ {
35
+ "category": "Reading Comprehension",
36
+ "average_score": 8.235294117647058,
37
+ "count": 17
38
+ },
39
+ {
40
+ "category": "Trust & Safety",
41
+ "average_score": 7.0,
42
+ "count": 30
43
+ },
44
+ {
45
+ "category": "Summarization",
46
+ "average_score": 7.0,
47
+ "count": 8
48
+ },
49
+ {
50
+ "category": "Transliteration",
51
+ "average_score": 6.666666666666667,
52
+ "count": 6
53
+ },
54
+ {
55
+ "category": "Hallucination",
56
+ "average_score": 6.666666666666667,
57
+ "count": 3
58
+ },
59
+ {
60
+ "category": "General Knowledge",
61
+ "average_score": 6.396825396825397,
62
+ "count": 63
63
+ },
64
+ {
65
+ "category": "MMLU",
66
+ "average_score": 6.2809917355371905,
67
+ "count": 121
68
+ },
69
+ {
70
+ "category": "Diacritization",
71
+ "average_score": 6.25,
72
+ "count": 12
73
+ },
74
+ {
75
+ "category": "Reasoning & Math",
76
+ "average_score": 6.069767441860465,
77
+ "count": 43
78
+ },
79
+ {
80
+ "category": "Arabic Language & Grammar",
81
+ "average_score": 5.9411764705882355,
82
+ "count": 17
83
+ },
84
+ {
85
+ "category": "Instruction Following",
86
+ "average_score": 5.714285714285714,
87
+ "count": 7
88
+ },
89
+ {
90
+ "category": "Translation (incl Dialects)",
91
+ "average_score": 5.604651162790698,
92
+ "count": 43
93
+ },
94
+ {
95
+ "category": "Long Context",
96
+ "average_score": 5.5,
97
+ "count": 4
98
+ },
99
+ {
100
+ "category": "Writing (incl Dialects)",
101
+ "average_score": 5.5,
102
+ "count": 22
103
+ },
104
+ {
105
+ "category": "Entity Extraction",
106
+ "average_score": 5.0,
107
+ "count": 5
108
+ },
109
+ {
110
+ "category": "Structuring",
111
+ "average_score": 4.333333333333333,
112
+ "count": 3
113
+ },
114
+ {
115
+ "category": "Dialect Detection",
116
+ "average_score": 4.0,
117
+ "count": 11
118
+ }
119
+ ],
120
+ "scores_by_format": [
121
+ {
122
+ "format": "Short Answer",
123
+ "average_score": 8.0,
124
+ "count": 5
125
+ },
126
+ {
127
+ "format": "MCQ",
128
+ "average_score": 6.620087336244541,
129
+ "count": 229
130
+ },
131
+ {
132
+ "format": "Generation",
133
+ "average_score": 6.27906976744186,
134
+ "count": 215
135
+ },
136
+ {
137
+ "format": "Fill-in-the-blank",
138
+ "average_score": 5.0,
139
+ "count": 8
140
+ }
141
+ ]
142
+ },
143
+ "config": {
144
+ "model": "meta-llama/Llama-3.1-8B-Instruct",
145
+ "model_sha": "0e9e39f249a16976918f6564b8830bc894c89659",
146
+ "submitted_time": "2025-05-01T21:24:57Z",
147
+ "likes": 3908,
148
+ "params": 8.03,
149
+ "license": "llama3.1",
150
+ "model_source": "Hugging Face",
151
+ "model_category": "Small"
152
+ }
153
+ }