evals
Browse files
README.md
CHANGED
|
@@ -8,6 +8,26 @@ language:
|
|
| 8 |
library_name: transformers
|
| 9 |
license: llama3.1
|
| 10 |
tags:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
- mergekit
|
| 12 |
- merge
|
| 13 |
pipeline_tag: text-generation
|
|
@@ -27,13 +47,148 @@ model-index:
|
|
| 27 |
- type: acc
|
| 28 |
value: 85.00
|
| 29 |
name: acc
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
|
| 31 |
---
|
| 32 |
-
#
|
| 33 |
|
| 34 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 35 |
|
| 36 |
## Merge Details
|
|
|
|
|
|
|
|
|
|
| 37 |
### Merge Method
|
| 38 |
|
| 39 |
This model was merged using the della merge method using [meta-llama/Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct) as a base.
|
|
|
|
| 8 |
library_name: transformers
|
| 9 |
license: llama3.1
|
| 10 |
tags:
|
| 11 |
+
- llama
|
| 12 |
+
- llama3.1
|
| 13 |
+
- llama3
|
| 14 |
+
- meta
|
| 15 |
+
- 70b
|
| 16 |
+
- science
|
| 17 |
+
- physics
|
| 18 |
+
- biology
|
| 19 |
+
- chemistry
|
| 20 |
+
- compsci
|
| 21 |
+
- computer-science
|
| 22 |
+
- engineering
|
| 23 |
+
- logic
|
| 24 |
+
- rationality
|
| 25 |
+
- advanced
|
| 26 |
+
- expert
|
| 27 |
+
- technical
|
| 28 |
+
- conversational
|
| 29 |
+
- chat
|
| 30 |
+
- instruct
|
| 31 |
- mergekit
|
| 32 |
- merge
|
| 33 |
pipeline_tag: text-generation
|
|
|
|
| 47 |
- type: acc
|
| 48 |
value: 85.00
|
| 49 |
name: acc
|
| 50 |
+
- task:
|
| 51 |
+
type: text-generation
|
| 52 |
+
name: Text Generation
|
| 53 |
+
dataset:
|
| 54 |
+
name: ARC Challenge (25-Shot)
|
| 55 |
+
type: arc-challenge
|
| 56 |
+
args:
|
| 57 |
+
num_few_shot: 25
|
| 58 |
+
metrics:
|
| 59 |
+
- type: acc_norm
|
| 60 |
+
value: 67.41
|
| 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: 93.75
|
| 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: 91.94
|
| 85 |
+
name: acc
|
| 86 |
+
- task:
|
| 87 |
+
type: text-generation
|
| 88 |
+
name: Text Generation
|
| 89 |
+
dataset:
|
| 90 |
+
name: MMLU Conceptual Physics (5-Shot)
|
| 91 |
+
type: MMLU
|
| 92 |
+
args:
|
| 93 |
+
num_few_shot: 5
|
| 94 |
+
metrics:
|
| 95 |
+
- type: acc
|
| 96 |
+
value: 82.13
|
| 97 |
+
name: acc
|
| 98 |
+
- task:
|
| 99 |
+
type: text-generation
|
| 100 |
+
name: Text Generation
|
| 101 |
+
dataset:
|
| 102 |
+
name: MMLU College Physics (5-Shot)
|
| 103 |
+
type: MMLU
|
| 104 |
+
args:
|
| 105 |
+
num_few_shot: 5
|
| 106 |
+
metrics:
|
| 107 |
+
- type: acc
|
| 108 |
+
value: 60.78
|
| 109 |
+
name: acc
|
| 110 |
+
- task:
|
| 111 |
+
type: text-generation
|
| 112 |
+
name: Text Generation
|
| 113 |
+
dataset:
|
| 114 |
+
name: MMLU High School Physics (5-Shot)
|
| 115 |
+
type: MMLU
|
| 116 |
+
args:
|
| 117 |
+
num_few_shot: 5
|
| 118 |
+
metrics:
|
| 119 |
+
- type: acc
|
| 120 |
+
value: 62.25
|
| 121 |
+
name: acc
|
| 122 |
+
- task:
|
| 123 |
+
type: text-generation
|
| 124 |
+
name: Text Generation
|
| 125 |
+
dataset:
|
| 126 |
+
name: MMLU College Chemistry (5-Shot)
|
| 127 |
+
type: MMLU
|
| 128 |
+
args:
|
| 129 |
+
num_few_shot: 5
|
| 130 |
+
metrics:
|
| 131 |
+
- type: acc
|
| 132 |
+
value: 56.00
|
| 133 |
+
name: acc
|
| 134 |
+
- task:
|
| 135 |
+
type: text-generation
|
| 136 |
+
name: Text Generation
|
| 137 |
+
dataset:
|
| 138 |
+
name: MMLU High School Chemistry (5-Shot)
|
| 139 |
+
type: MMLU
|
| 140 |
+
args:
|
| 141 |
+
num_few_shot: 5
|
| 142 |
+
metrics:
|
| 143 |
+
- type: acc
|
| 144 |
+
value: 73.40
|
| 145 |
+
name: acc
|
| 146 |
+
- task:
|
| 147 |
+
type: text-generation
|
| 148 |
+
name: Text Generation
|
| 149 |
+
dataset:
|
| 150 |
+
name: MMLU Astronomy (5-Shot)
|
| 151 |
+
type: MMLU
|
| 152 |
+
args:
|
| 153 |
+
num_few_shot: 5
|
| 154 |
+
metrics:
|
| 155 |
+
- type: acc
|
| 156 |
+
value: 89.47
|
| 157 |
+
name: acc
|
| 158 |
+
- task:
|
| 159 |
+
type: text-generation
|
| 160 |
+
name: Text Generation
|
| 161 |
+
dataset:
|
| 162 |
+
name: MMLU College Computer Science (5-Shot)
|
| 163 |
+
type: MMLU
|
| 164 |
+
args:
|
| 165 |
+
num_few_shot: 5
|
| 166 |
+
metrics:
|
| 167 |
+
- type: acc
|
| 168 |
+
value: 64.00
|
| 169 |
+
name: acc
|
| 170 |
+
- task:
|
| 171 |
+
type: text-generation
|
| 172 |
+
name: Text Generation
|
| 173 |
+
dataset:
|
| 174 |
+
name: MMLU High School Computer Science (5-Shot)
|
| 175 |
+
type: MMLU
|
| 176 |
+
args:
|
| 177 |
+
num_few_shot: 5
|
| 178 |
+
metrics:
|
| 179 |
+
- type: acc
|
| 180 |
+
value: 90.00
|
| 181 |
+
name: acc
|
| 182 |
|
| 183 |
---
|
| 184 |
+
# PlumChat 70b
|
| 185 |
|
| 186 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 187 |
|
| 188 |
## Merge Details
|
| 189 |
+
|
| 190 |
+
Shining Valiant 2 + Nemotron for high quality general chat, science-instruct, and complex query performance.
|
| 191 |
+
|
| 192 |
### Merge Method
|
| 193 |
|
| 194 |
This model was merged using the della merge method using [meta-llama/Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct) as a base.
|