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
updated evals
Browse files
README.md
CHANGED
|
@@ -46,20 +46,8 @@ model-index:
|
|
| 46 |
num_few_shot: 5
|
| 47 |
metrics:
|
| 48 |
- type: acc
|
| 49 |
-
value: 69.
|
| 50 |
name: acc
|
| 51 |
-
- task:
|
| 52 |
-
type: text-generation
|
| 53 |
-
name: Text Generation
|
| 54 |
-
dataset:
|
| 55 |
-
name: ARC Challenge (25-Shot)
|
| 56 |
-
type: arc_challenge
|
| 57 |
-
args:
|
| 58 |
-
num_few_shot: 25
|
| 59 |
-
metrics:
|
| 60 |
-
- type: acc_norm
|
| 61 |
-
value: 46.25
|
| 62 |
-
name: normalized accuracy
|
| 63 |
- task:
|
| 64 |
type: text-generation
|
| 65 |
name: Text Generation
|
|
@@ -70,7 +58,7 @@ model-index:
|
|
| 70 |
num_few_shot: 5
|
| 71 |
metrics:
|
| 72 |
- type: acc
|
| 73 |
-
value:
|
| 74 |
name: acc
|
| 75 |
- task:
|
| 76 |
type: text-generation
|
|
@@ -82,7 +70,7 @@ model-index:
|
|
| 82 |
num_few_shot: 5
|
| 83 |
metrics:
|
| 84 |
- type: acc
|
| 85 |
-
value:
|
| 86 |
name: acc
|
| 87 |
- task:
|
| 88 |
type: text-generation
|
|
@@ -94,7 +82,7 @@ model-index:
|
|
| 94 |
num_few_shot: 5
|
| 95 |
metrics:
|
| 96 |
- type: acc
|
| 97 |
-
value:
|
| 98 |
name: acc
|
| 99 |
- task:
|
| 100 |
type: text-generation
|
|
@@ -106,7 +94,7 @@ model-index:
|
|
| 106 |
num_few_shot: 5
|
| 107 |
metrics:
|
| 108 |
- type: acc
|
| 109 |
-
value:
|
| 110 |
name: acc
|
| 111 |
- task:
|
| 112 |
type: text-generation
|
|
@@ -118,7 +106,7 @@ model-index:
|
|
| 118 |
num_few_shot: 5
|
| 119 |
metrics:
|
| 120 |
- type: acc
|
| 121 |
-
value:
|
| 122 |
name: acc
|
| 123 |
- task:
|
| 124 |
type: text-generation
|
|
@@ -132,6 +120,18 @@ model-index:
|
|
| 132 |
- type: acc
|
| 133 |
value: 35.76
|
| 134 |
name: acc
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 135 |
- task:
|
| 136 |
type: text-generation
|
| 137 |
name: Text Generation
|
|
@@ -142,7 +142,7 @@ model-index:
|
|
| 142 |
num_few_shot: 5
|
| 143 |
metrics:
|
| 144 |
- type: acc
|
| 145 |
-
value:
|
| 146 |
name: acc
|
| 147 |
- task:
|
| 148 |
type: text-generation
|
|
@@ -154,19 +154,19 @@ model-index:
|
|
| 154 |
num_few_shot: 5
|
| 155 |
metrics:
|
| 156 |
- type: acc
|
| 157 |
-
value:
|
| 158 |
name: acc
|
| 159 |
- task:
|
| 160 |
type: text-generation
|
| 161 |
name: Text Generation
|
| 162 |
dataset:
|
| 163 |
-
name: MMLU
|
| 164 |
type: mmlu
|
| 165 |
args:
|
| 166 |
num_few_shot: 5
|
| 167 |
metrics:
|
| 168 |
- type: acc
|
| 169 |
-
value:
|
| 170 |
name: acc
|
| 171 |
- task:
|
| 172 |
type: text-generation
|
|
|
|
| 46 |
num_few_shot: 5
|
| 47 |
metrics:
|
| 48 |
- type: acc
|
| 49 |
+
value: 69.14
|
| 50 |
name: acc
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
- task:
|
| 52 |
type: text-generation
|
| 53 |
name: Text Generation
|
|
|
|
| 58 |
num_few_shot: 5
|
| 59 |
metrics:
|
| 60 |
- type: acc
|
| 61 |
+
value: 64.58
|
| 62 |
name: acc
|
| 63 |
- task:
|
| 64 |
type: text-generation
|
|
|
|
| 70 |
num_few_shot: 5
|
| 71 |
metrics:
|
| 72 |
- type: acc
|
| 73 |
+
value: 70.32
|
| 74 |
name: acc
|
| 75 |
- task:
|
| 76 |
type: text-generation
|
|
|
|
| 82 |
num_few_shot: 5
|
| 83 |
metrics:
|
| 84 |
- type: acc
|
| 85 |
+
value: 44.00
|
| 86 |
name: acc
|
| 87 |
- task:
|
| 88 |
type: text-generation
|
|
|
|
| 94 |
num_few_shot: 5
|
| 95 |
metrics:
|
| 96 |
- type: acc
|
| 97 |
+
value: 50.25
|
| 98 |
name: acc
|
| 99 |
- task:
|
| 100 |
type: text-generation
|
|
|
|
| 106 |
num_few_shot: 5
|
| 107 |
metrics:
|
| 108 |
- type: acc
|
| 109 |
+
value: 42.16
|
| 110 |
name: acc
|
| 111 |
- task:
|
| 112 |
type: text-generation
|
|
|
|
| 120 |
- type: acc
|
| 121 |
value: 35.76
|
| 122 |
name: acc
|
| 123 |
+
- task:
|
| 124 |
+
type: text-generation
|
| 125 |
+
name: Text Generation
|
| 126 |
+
dataset:
|
| 127 |
+
name: MMLU Conceptual Physics (5-shot)
|
| 128 |
+
type: mmlu
|
| 129 |
+
args:
|
| 130 |
+
num_few_shot: 5
|
| 131 |
+
metrics:
|
| 132 |
+
- type: acc
|
| 133 |
+
value: 53.19
|
| 134 |
+
name: acc
|
| 135 |
- task:
|
| 136 |
type: text-generation
|
| 137 |
name: Text Generation
|
|
|
|
| 142 |
num_few_shot: 5
|
| 143 |
metrics:
|
| 144 |
- type: acc
|
| 145 |
+
value: 53.00
|
| 146 |
name: acc
|
| 147 |
- task:
|
| 148 |
type: text-generation
|
|
|
|
| 154 |
num_few_shot: 5
|
| 155 |
metrics:
|
| 156 |
- type: acc
|
| 157 |
+
value: 61.00
|
| 158 |
name: acc
|
| 159 |
- task:
|
| 160 |
type: text-generation
|
| 161 |
name: Text Generation
|
| 162 |
dataset:
|
| 163 |
+
name: MMLU Astronomy (5-shot)
|
| 164 |
type: mmlu
|
| 165 |
args:
|
| 166 |
num_few_shot: 5
|
| 167 |
metrics:
|
| 168 |
- type: acc
|
| 169 |
+
value: 60.53
|
| 170 |
name: acc
|
| 171 |
- task:
|
| 172 |
type: text-generation
|