Update README.md
Browse files
README.md
CHANGED
|
@@ -1,4 +1,185 @@
|
|
| 1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
name: MultiPL-HumanEval (R)
|
| 3 |
metrics:
|
| 4 |
- name: pass@1
|
|
@@ -75,11 +256,9 @@
|
|
| 75 |
type: pass@1
|
| 76 |
value: 0.3229
|
| 77 |
verified: false
|
| 78 |
-
extra_gated_prompt:
|
| 79 |
-
|
| 80 |
-
|
| 81 |
-
agreement before accepting it.
|
| 82 |
-
|
| 83 |
extra_gated_fields:
|
| 84 |
I accept the above license agreement, and will use the Model complying with the set of use restrictions and sharing requirements: checkbox
|
| 85 |
language:
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: text-generation
|
| 3 |
+
inference: true
|
| 4 |
+
widget:
|
| 5 |
+
- text: 'def print_hello_world():'
|
| 6 |
+
example_title: Hello world
|
| 7 |
+
group: Python
|
| 8 |
+
license: bigcode-openrail-m
|
| 9 |
+
datasets:
|
| 10 |
+
- bigcode/the-stack-dedup
|
| 11 |
+
metrics:
|
| 12 |
+
- code_eval
|
| 13 |
+
library_name: transformers
|
| 14 |
+
tags:
|
| 15 |
+
- code
|
| 16 |
+
model-index:
|
| 17 |
+
- name: StarCoder
|
| 18 |
+
results:
|
| 19 |
+
- task:
|
| 20 |
+
type: text-generation
|
| 21 |
+
dataset:
|
| 22 |
+
type: openai_humaneval1
|
| 23 |
+
name: HumanEval1
|
| 24 |
+
metrics:
|
| 25 |
+
- name: pass@1
|
| 26 |
+
type: pass@1
|
| 27 |
+
value: 0.408
|
| 28 |
+
verified: false
|
| 29 |
+
- name: pass@2
|
| 30 |
+
type: pass@2
|
| 31 |
+
value: 0.12345
|
| 32 |
+
verified: false
|
| 33 |
+
- task:
|
| 34 |
+
type: text-generation
|
| 35 |
+
dataset:
|
| 36 |
+
type: openai_humaneval
|
| 37 |
+
name: HumanEval
|
| 38 |
+
metrics:
|
| 39 |
+
- name: pass@1
|
| 40 |
+
type: pass@1
|
| 41 |
+
value:
|
| 42 |
+
dataset:
|
| 43 |
+
type: openai_humaneval
|
| 44 |
+
name: HumanEval
|
| 45 |
+
args: haha
|
| 46 |
+
verified: false
|
| 47 |
+
- name: StarCoder2
|
| 48 |
+
results:
|
| 49 |
+
- task:
|
| 50 |
+
type: text-generation
|
| 51 |
+
dataset:
|
| 52 |
+
type: mbpp
|
| 53 |
+
name: MBPP
|
| 54 |
+
metrics:
|
| 55 |
+
- name: pass@1
|
| 56 |
+
type: pass@1
|
| 57 |
+
value: 0.527
|
| 58 |
+
verified: false
|
| 59 |
+
- task:
|
| 60 |
+
type: text-generation
|
| 61 |
+
dataset:
|
| 62 |
+
type: ds1000
|
| 63 |
+
name: DS-1000 (Overall Completion)
|
| 64 |
+
metrics:
|
| 65 |
+
- name: pass@1
|
| 66 |
+
type: pass@1
|
| 67 |
+
value: 0.26
|
| 68 |
+
verified: false
|
| 69 |
+
- task:
|
| 70 |
+
type: text-generation
|
| 71 |
+
dataset:
|
| 72 |
+
type: nuprl/MultiPL-E
|
| 73 |
+
name: MultiPL-HumanEval (C++)
|
| 74 |
+
metrics:
|
| 75 |
+
- name: pass@1
|
| 76 |
+
type: pass@1
|
| 77 |
+
value: 0.3155
|
| 78 |
+
verified: false
|
| 79 |
+
- task:
|
| 80 |
+
type: text-generation
|
| 81 |
+
dataset:
|
| 82 |
+
type: nuprl/MultiPL-E
|
| 83 |
+
name: MultiPL-HumanEval (C#)
|
| 84 |
+
metrics:
|
| 85 |
+
- name: pass@1
|
| 86 |
+
type: pass@1
|
| 87 |
+
value: 0.2101
|
| 88 |
+
verified: false
|
| 89 |
+
- task:
|
| 90 |
+
type: text-generation
|
| 91 |
+
dataset:
|
| 92 |
+
type: nuprl/MultiPL-E
|
| 93 |
+
name: MultiPL-HumanEval (D)
|
| 94 |
+
metrics:
|
| 95 |
+
- name: pass@1
|
| 96 |
+
type: pass@1
|
| 97 |
+
value: 0.1357
|
| 98 |
+
verified: false
|
| 99 |
+
- task:
|
| 100 |
+
type: text-generation
|
| 101 |
+
dataset:
|
| 102 |
+
type: nuprl/MultiPL-E
|
| 103 |
+
name: MultiPL-HumanEval (Go)
|
| 104 |
+
metrics:
|
| 105 |
+
- name: pass@1
|
| 106 |
+
type: pass@1
|
| 107 |
+
value: 0.1761
|
| 108 |
+
verified: false
|
| 109 |
+
- task:
|
| 110 |
+
type: text-generation
|
| 111 |
+
dataset:
|
| 112 |
+
type: nuprl/MultiPL-E
|
| 113 |
+
name: MultiPL-HumanEval (Java)
|
| 114 |
+
metrics:
|
| 115 |
+
- name: pass@1
|
| 116 |
+
type: pass@1
|
| 117 |
+
value: 0.3022
|
| 118 |
+
verified: false
|
| 119 |
+
- task:
|
| 120 |
+
type: text-generation
|
| 121 |
+
dataset:
|
| 122 |
+
type: nuprl/MultiPL-E
|
| 123 |
+
name: MultiPL-HumanEval (Julia)
|
| 124 |
+
metrics:
|
| 125 |
+
- name: pass@1
|
| 126 |
+
type: pass@1
|
| 127 |
+
value: 0.2302
|
| 128 |
+
verified: false
|
| 129 |
+
- task:
|
| 130 |
+
type: text-generation
|
| 131 |
+
dataset:
|
| 132 |
+
type: nuprl/MultiPL-E
|
| 133 |
+
name: MultiPL-HumanEval (JavaScript)
|
| 134 |
+
metrics:
|
| 135 |
+
- name: pass@1
|
| 136 |
+
type: pass@1
|
| 137 |
+
value: 0.3079
|
| 138 |
+
verified: false
|
| 139 |
+
- task:
|
| 140 |
+
type: text-generation
|
| 141 |
+
dataset:
|
| 142 |
+
type: nuprl/MultiPL-E
|
| 143 |
+
name: MultiPL-HumanEval (Lua)
|
| 144 |
+
metrics:
|
| 145 |
+
- name: pass@1
|
| 146 |
+
type: pass@1
|
| 147 |
+
value: 0.2389
|
| 148 |
+
verified: false
|
| 149 |
+
- task:
|
| 150 |
+
type: text-generation
|
| 151 |
+
dataset:
|
| 152 |
+
type: nuprl/MultiPL-E
|
| 153 |
+
name: MultiPL-HumanEval (PHP)
|
| 154 |
+
metrics:
|
| 155 |
+
- name: pass@1
|
| 156 |
+
type: pass@1
|
| 157 |
+
value: 0.2608
|
| 158 |
+
verified: false
|
| 159 |
+
- task:
|
| 160 |
+
type: text-generation
|
| 161 |
+
dataset:
|
| 162 |
+
type: nuprl/MultiPL-E
|
| 163 |
+
name: MultiPL-HumanEval (Perl)
|
| 164 |
+
metrics:
|
| 165 |
+
- name: pass@1
|
| 166 |
+
type: pass@1
|
| 167 |
+
value: 0.1734
|
| 168 |
+
verified: false
|
| 169 |
+
- task:
|
| 170 |
+
type: text-generation
|
| 171 |
+
dataset:
|
| 172 |
+
type: nuprl/MultiPL-E
|
| 173 |
+
name: MultiPL-HumanEval (Python)
|
| 174 |
+
metrics:
|
| 175 |
+
- name: pass@1
|
| 176 |
+
type: pass@1
|
| 177 |
+
value: 0.3357
|
| 178 |
+
verified: false
|
| 179 |
+
- task:
|
| 180 |
+
type: text-generation
|
| 181 |
+
dataset:
|
| 182 |
+
type: nuprl/MultiPL-E
|
| 183 |
name: MultiPL-HumanEval (R)
|
| 184 |
metrics:
|
| 185 |
- name: pass@1
|
|
|
|
| 256 |
type: pass@1
|
| 257 |
value: 0.3229
|
| 258 |
verified: false
|
| 259 |
+
extra_gated_prompt: "## Model License Agreement Please read the BigCode [OpenRAIL-M\
|
| 260 |
+
\ license](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement)\
|
| 261 |
+
\ agreement before accepting it.\n "
|
|
|
|
|
|
|
| 262 |
extra_gated_fields:
|
| 263 |
I accept the above license agreement, and will use the Model complying with the set of use restrictions and sharing requirements: checkbox
|
| 264 |
language:
|