Text Generation
Safetensors
English
llama
shining-valiant
shining-valiant-2
valiant
valiant-labs
llama-3.2
llama-3.2-instruct
llama-3.2-instruct-3b
llama-3
llama-3-instruct
llama-3-instruct-3b
3b
science
physics
biology
chemistry
compsci
computer-science
engineering
technical
conversational
chat
instruct
Eval Results
eval
Browse files
README.md
CHANGED
@@ -59,6 +59,114 @@ model-index:
|
|
59 |
- type: acc_norm
|
60 |
value: 46.25
|
61 |
name: normalized accuracy
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
- task:
|
63 |
type: text-generation
|
64 |
name: Text Generation
|
|
|
59 |
- type: acc_norm
|
60 |
value: 46.25
|
61 |
name: normalized accuracy
|
62 |
+
- task:
|
63 |
+
type: text-generation
|
64 |
+
name: Text Generation
|
65 |
+
dataset:
|
66 |
+
name: MMLU College Biology (5-shot)
|
67 |
+
type: mmlu
|
68 |
+
args:
|
69 |
+
num_few_shot: 5
|
70 |
+
metrics:
|
71 |
+
- type: acc
|
72 |
+
value: 56.25
|
73 |
+
name: acc
|
74 |
+
- task:
|
75 |
+
type: text-generation
|
76 |
+
name: Text Generation
|
77 |
+
dataset:
|
78 |
+
name: MMLU High School Biology (5-shot)
|
79 |
+
type: mmlu
|
80 |
+
args:
|
81 |
+
num_few_shot: 5
|
82 |
+
metrics:
|
83 |
+
- type: acc
|
84 |
+
value: 63.55
|
85 |
+
name: acc
|
86 |
+
- task:
|
87 |
+
type: text-generation
|
88 |
+
name: Text Generation
|
89 |
+
dataset:
|
90 |
+
name: MMLU College Chemistry (5-shot)
|
91 |
+
type: mmlu
|
92 |
+
args:
|
93 |
+
num_few_shot: 5
|
94 |
+
metrics:
|
95 |
+
- type: acc
|
96 |
+
value: 41.0
|
97 |
+
name: acc
|
98 |
+
- task:
|
99 |
+
type: text-generation
|
100 |
+
name: Text Generation
|
101 |
+
dataset:
|
102 |
+
name: MMLU High School Chemistry (5-shot)
|
103 |
+
type: mmlu
|
104 |
+
args:
|
105 |
+
num_few_shot: 5
|
106 |
+
metrics:
|
107 |
+
- type: acc
|
108 |
+
value: 41.38
|
109 |
+
name: acc
|
110 |
+
- task:
|
111 |
+
type: text-generation
|
112 |
+
name: Text Generation
|
113 |
+
dataset:
|
114 |
+
name: MMLU College Physics (5-shot)
|
115 |
+
type: mmlu
|
116 |
+
args:
|
117 |
+
num_few_shot: 5
|
118 |
+
metrics:
|
119 |
+
- type: acc
|
120 |
+
value: 34.31
|
121 |
+
name: acc
|
122 |
+
- task:
|
123 |
+
type: text-generation
|
124 |
+
name: Text Generation
|
125 |
+
dataset:
|
126 |
+
name: MMLU High School Physics (5-shot)
|
127 |
+
type: mmlu
|
128 |
+
args:
|
129 |
+
num_few_shot: 5
|
130 |
+
metrics:
|
131 |
+
- type: acc
|
132 |
+
value: 35.76
|
133 |
+
name: acc
|
134 |
+
- task:
|
135 |
+
type: text-generation
|
136 |
+
name: Text Generation
|
137 |
+
dataset:
|
138 |
+
name: MMLU College Computer Science (5-shot)
|
139 |
+
type: mmlu
|
140 |
+
args:
|
141 |
+
num_few_shot: 5
|
142 |
+
metrics:
|
143 |
+
- type: acc
|
144 |
+
value: 48.0
|
145 |
+
name: acc
|
146 |
+
- task:
|
147 |
+
type: text-generation
|
148 |
+
name: Text Generation
|
149 |
+
dataset:
|
150 |
+
name: MMLU High School Computer Science (5-shot)
|
151 |
+
type: mmlu
|
152 |
+
args:
|
153 |
+
num_few_shot: 5
|
154 |
+
metrics:
|
155 |
+
- type: acc
|
156 |
+
value: 58.0
|
157 |
+
name: acc
|
158 |
+
- task:
|
159 |
+
type: text-generation
|
160 |
+
name: Text Generation
|
161 |
+
dataset:
|
162 |
+
name: MMLU STEM (5-shot)
|
163 |
+
type: mmlu
|
164 |
+
args:
|
165 |
+
num_few_shot: 5
|
166 |
+
metrics:
|
167 |
+
- type: acc
|
168 |
+
value: 45.54
|
169 |
+
name: acc
|
170 |
- task:
|
171 |
type: text-generation
|
172 |
name: Text Generation
|