Text Generation
Safetensors
English
llama
shining-valiant
shining-valiant-2
valiant
valiant-labs
llama-3.1
llama-3.1-instruct
llama-3.1-instruct-8b
llama-3
llama-3-instruct
llama-3-instruct-8b
8b
science
physics
biology
chemistry
compsci
computer-science
engineering
technical
conversational
chat
instruct
Eval Results
updated evals
Browse files
README.md
CHANGED
|
@@ -45,7 +45,7 @@ model-index:
|
|
| 45 |
num_few_shot: 5
|
| 46 |
metrics:
|
| 47 |
- type: acc
|
| 48 |
-
value:
|
| 49 |
name: acc
|
| 50 |
- task:
|
| 51 |
type: text-generation
|
|
@@ -57,7 +57,7 @@ model-index:
|
|
| 57 |
num_few_shot: 5
|
| 58 |
metrics:
|
| 59 |
- type: acc
|
| 60 |
-
value:
|
| 61 |
name: acc
|
| 62 |
- task:
|
| 63 |
type: text-generation
|
|
@@ -69,7 +69,7 @@ model-index:
|
|
| 69 |
num_few_shot: 5
|
| 70 |
metrics:
|
| 71 |
- type: acc
|
| 72 |
-
value:
|
| 73 |
name: acc
|
| 74 |
- task:
|
| 75 |
type: text-generation
|
|
@@ -81,7 +81,7 @@ model-index:
|
|
| 81 |
num_few_shot: 5
|
| 82 |
metrics:
|
| 83 |
- type: acc
|
| 84 |
-
value:
|
| 85 |
name: acc
|
| 86 |
- task:
|
| 87 |
type: text-generation
|
|
@@ -93,7 +93,19 @@ model-index:
|
|
| 93 |
num_few_shot: 5
|
| 94 |
metrics:
|
| 95 |
- type: acc
|
| 96 |
-
value:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 97 |
name: acc
|
| 98 |
- task:
|
| 99 |
type: text-generation
|
|
@@ -105,7 +117,7 @@ model-index:
|
|
| 105 |
num_few_shot: 5
|
| 106 |
metrics:
|
| 107 |
- type: acc
|
| 108 |
-
value:
|
| 109 |
name: acc
|
| 110 |
- task:
|
| 111 |
type: text-generation
|
|
@@ -129,7 +141,7 @@ model-index:
|
|
| 129 |
num_few_shot: 5
|
| 130 |
metrics:
|
| 131 |
- type: acc
|
| 132 |
-
value:
|
| 133 |
name: acc
|
| 134 |
- task:
|
| 135 |
type: text-generation
|
|
@@ -141,19 +153,19 @@ model-index:
|
|
| 141 |
num_few_shot: 5
|
| 142 |
metrics:
|
| 143 |
- type: acc
|
| 144 |
-
value:
|
| 145 |
name: acc
|
| 146 |
- task:
|
| 147 |
type: text-generation
|
| 148 |
name: Text Generation
|
| 149 |
dataset:
|
| 150 |
-
name: MMLU
|
| 151 |
type: MMLU
|
| 152 |
args:
|
| 153 |
num_few_shot: 5
|
| 154 |
metrics:
|
| 155 |
- type: acc
|
| 156 |
-
value:
|
| 157 |
name: acc
|
| 158 |
- task:
|
| 159 |
type: text-generation
|
|
|
|
| 45 |
num_few_shot: 5
|
| 46 |
metrics:
|
| 47 |
- type: acc
|
| 48 |
+
value: 75.85
|
| 49 |
name: acc
|
| 50 |
- task:
|
| 51 |
type: text-generation
|
|
|
|
| 57 |
num_few_shot: 5
|
| 58 |
metrics:
|
| 59 |
- type: acc
|
| 60 |
+
value: 68.75
|
| 61 |
name: acc
|
| 62 |
- task:
|
| 63 |
type: text-generation
|
|
|
|
| 69 |
num_few_shot: 5
|
| 70 |
metrics:
|
| 71 |
- type: acc
|
| 72 |
+
value: 73.23
|
| 73 |
name: acc
|
| 74 |
- task:
|
| 75 |
type: text-generation
|
|
|
|
| 81 |
num_few_shot: 5
|
| 82 |
metrics:
|
| 83 |
- type: acc
|
| 84 |
+
value: 46.00
|
| 85 |
name: acc
|
| 86 |
- task:
|
| 87 |
type: text-generation
|
|
|
|
| 93 |
num_few_shot: 5
|
| 94 |
metrics:
|
| 95 |
- type: acc
|
| 96 |
+
value: 44.33
|
| 97 |
+
name: acc
|
| 98 |
+
- task:
|
| 99 |
+
type: text-generation
|
| 100 |
+
name: Text Generation
|
| 101 |
+
dataset:
|
| 102 |
+
name: MMLU Conceptual Physics (5-Shot)
|
| 103 |
+
type: MMLU
|
| 104 |
+
args:
|
| 105 |
+
num_few_shot: 5
|
| 106 |
+
metrics:
|
| 107 |
+
- type: acc
|
| 108 |
+
value: 53.19
|
| 109 |
name: acc
|
| 110 |
- task:
|
| 111 |
type: text-generation
|
|
|
|
| 117 |
num_few_shot: 5
|
| 118 |
metrics:
|
| 119 |
- type: acc
|
| 120 |
+
value: 37.25
|
| 121 |
name: acc
|
| 122 |
- task:
|
| 123 |
type: text-generation
|
|
|
|
| 141 |
num_few_shot: 5
|
| 142 |
metrics:
|
| 143 |
- type: acc
|
| 144 |
+
value: 56.00
|
| 145 |
name: acc
|
| 146 |
- task:
|
| 147 |
type: text-generation
|
|
|
|
| 153 |
num_few_shot: 5
|
| 154 |
metrics:
|
| 155 |
- type: acc
|
| 156 |
+
value: 63.00
|
| 157 |
name: acc
|
| 158 |
- task:
|
| 159 |
type: text-generation
|
| 160 |
name: Text Generation
|
| 161 |
dataset:
|
| 162 |
+
name: MMLU Astronomy (5-shot)
|
| 163 |
type: MMLU
|
| 164 |
args:
|
| 165 |
num_few_shot: 5
|
| 166 |
metrics:
|
| 167 |
- type: acc
|
| 168 |
+
value: 63.16
|
| 169 |
name: acc
|
| 170 |
- task:
|
| 171 |
type: text-generation
|