Add results file for ALLaM-7B-Instruct-preview
Browse files
results/ALLaM-AI/ALLaM-7B-Instruct-preview_results_2025-05-10_16-35-34.json
ADDED
@@ -0,0 +1,153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"results": {
|
3 |
+
"average_score": 7.176595744680851,
|
4 |
+
"speed": 15.572252842874866,
|
5 |
+
"contamination_score": 0,
|
6 |
+
"execution_time": 806.94811,
|
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": "Reading Comprehension",
|
21 |
+
"average_score": 10.0,
|
22 |
+
"count": 17
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"category": "Coding",
|
26 |
+
"average_score": 9.333333333333334,
|
27 |
+
"count": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"category": "MMLU",
|
31 |
+
"average_score": 8.264462809917354,
|
32 |
+
"count": 121
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"category": "Summarization",
|
36 |
+
"average_score": 8.25,
|
37 |
+
"count": 8
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"category": "Entity Extraction",
|
41 |
+
"average_score": 8.0,
|
42 |
+
"count": 5
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"category": "Function Calling",
|
46 |
+
"average_score": 8.0,
|
47 |
+
"count": 3
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"category": "General Knowledge",
|
51 |
+
"average_score": 7.857142857142857,
|
52 |
+
"count": 63
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"category": "Trust & Safety",
|
56 |
+
"average_score": 7.666666666666667,
|
57 |
+
"count": 30
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"category": "Writing (incl Dialects)",
|
61 |
+
"average_score": 7.090909090909091,
|
62 |
+
"count": 22
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"category": "Translation (incl Dialects)",
|
66 |
+
"average_score": 6.638888888888889,
|
67 |
+
"count": 36
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"category": "Reasoning & Math",
|
71 |
+
"average_score": 6.186046511627907,
|
72 |
+
"count": 43
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"category": "Dialect Detection",
|
76 |
+
"average_score": 6.090909090909091,
|
77 |
+
"count": 11
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"category": "Instruction Following",
|
81 |
+
"average_score": 5.857142857142857,
|
82 |
+
"count": 7
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"category": "Arabic Language & Grammar",
|
86 |
+
"average_score": 5.764705882352941,
|
87 |
+
"count": 17
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"category": "Structuring",
|
91 |
+
"average_score": 5.333333333333333,
|
92 |
+
"count": 3
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"category": "RAG QA",
|
96 |
+
"average_score": 4.609756097560975,
|
97 |
+
"count": 41
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"category": "Diacritization",
|
101 |
+
"average_score": 4.416666666666667,
|
102 |
+
"count": 12
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"category": "Long Context",
|
106 |
+
"average_score": 4.0,
|
107 |
+
"count": 4
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"category": "Hallucination",
|
111 |
+
"average_score": 3.3333333333333335,
|
112 |
+
"count": 3
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"category": "Transliteration",
|
116 |
+
"average_score": 3.1666666666666665,
|
117 |
+
"count": 6
|
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": 8.08296943231441,
|
129 |
+
"count": 229
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"format": "Generation",
|
133 |
+
"average_score": 6.324561403508772,
|
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": "ALLaM-AI/ALLaM-7B-Instruct-preview",
|
145 |
+
"model_sha": "09279909eca600d150b3e6c83a4ef1400abfcdb6",
|
146 |
+
"submitted_time": "2025-05-10T14:56:04Z",
|
147 |
+
"likes": 111,
|
148 |
+
"params": 7.001,
|
149 |
+
"license": "apache-2.0",
|
150 |
+
"model_source": "Hugging Face",
|
151 |
+
"model_category": "Small"
|
152 |
+
}
|
153 |
+
}
|