Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,10 @@
|
|
| 1 |
---
|
| 2 |
pipeline_tag: text-generation
|
| 3 |
inference: true
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
| 5 |
license: bigcode-openrail-m
|
| 6 |
datasets:
|
| 7 |
- shailja/Verilog_GitHub
|
|
@@ -15,227 +18,7 @@ model-index:
|
|
| 15 |
type: text-generation
|
| 16 |
dataset:
|
| 17 |
type: openai_humaneval
|
| 18 |
-
name:
|
| 19 |
-
metrics:
|
| 20 |
-
- name: pass@1
|
| 21 |
-
type: pass@1
|
| 22 |
-
value:
|
| 23 |
-
verified: false
|
| 24 |
-
- task:
|
| 25 |
-
type: text-generation
|
| 26 |
-
dataset:
|
| 27 |
-
type: openai_humaneval
|
| 28 |
-
name: HumanEval
|
| 29 |
-
metrics:
|
| 30 |
-
- name: pass@1
|
| 31 |
-
type: pass@1
|
| 32 |
-
value:
|
| 33 |
-
verified: false
|
| 34 |
-
- task:
|
| 35 |
-
type: text-generation
|
| 36 |
-
dataset:
|
| 37 |
-
type: mbpp
|
| 38 |
-
name: MBPP
|
| 39 |
-
metrics:
|
| 40 |
-
- name: pass@1
|
| 41 |
-
type: pass@1
|
| 42 |
-
value:
|
| 43 |
-
verified: false
|
| 44 |
-
- task:
|
| 45 |
-
type: text-generation
|
| 46 |
-
dataset:
|
| 47 |
-
type: ds1000
|
| 48 |
-
name: DS-1000 (Overall Completion)
|
| 49 |
-
metrics:
|
| 50 |
-
- name: pass@1
|
| 51 |
-
type: pass@1
|
| 52 |
-
value:
|
| 53 |
-
verified: false
|
| 54 |
-
- task:
|
| 55 |
-
type: text-generation
|
| 56 |
-
dataset:
|
| 57 |
-
type: nuprl/MultiPL-E
|
| 58 |
-
name: MultiPL-HumanEval (C++)
|
| 59 |
-
metrics:
|
| 60 |
-
- name: pass@1
|
| 61 |
-
type: pass@1
|
| 62 |
-
value:
|
| 63 |
-
verified: false
|
| 64 |
-
- task:
|
| 65 |
-
type: text-generation
|
| 66 |
-
dataset:
|
| 67 |
-
type: nuprl/MultiPL-E
|
| 68 |
-
name: MultiPL-HumanEval (C#)
|
| 69 |
-
metrics:
|
| 70 |
-
- name: pass@1
|
| 71 |
-
type: pass@1
|
| 72 |
-
value:
|
| 73 |
-
verified: false
|
| 74 |
-
- task:
|
| 75 |
-
type: text-generation
|
| 76 |
-
dataset:
|
| 77 |
-
type: nuprl/MultiPL-E
|
| 78 |
-
name: MultiPL-HumanEval (D)
|
| 79 |
-
metrics:
|
| 80 |
-
- name: pass@1
|
| 81 |
-
type: pass@1
|
| 82 |
-
value: 0.1357
|
| 83 |
-
verified: false
|
| 84 |
-
- task:
|
| 85 |
-
type: text-generation
|
| 86 |
-
dataset:
|
| 87 |
-
type: nuprl/MultiPL-E
|
| 88 |
-
name: MultiPL-HumanEval (Go)
|
| 89 |
-
metrics:
|
| 90 |
-
- name: pass@1
|
| 91 |
-
type: pass@1
|
| 92 |
-
value:
|
| 93 |
-
verified: false
|
| 94 |
-
- task:
|
| 95 |
-
type: text-generation
|
| 96 |
-
dataset:
|
| 97 |
-
type: nuprl/MultiPL-E
|
| 98 |
-
name: MultiPL-HumanEval (Java)
|
| 99 |
-
metrics:
|
| 100 |
-
- name: pass@1
|
| 101 |
-
type: pass@1
|
| 102 |
-
value:
|
| 103 |
-
verified: false
|
| 104 |
-
- task:
|
| 105 |
-
type: text-generation
|
| 106 |
-
dataset:
|
| 107 |
-
type: nuprl/MultiPL-E
|
| 108 |
-
name: MultiPL-HumanEval (Julia)
|
| 109 |
-
metrics:
|
| 110 |
-
- name: pass@1
|
| 111 |
-
type: pass@1
|
| 112 |
-
value:
|
| 113 |
-
verified: false
|
| 114 |
-
- task:
|
| 115 |
-
type: text-generation
|
| 116 |
-
dataset:
|
| 117 |
-
type: nuprl/MultiPL-E
|
| 118 |
-
name: MultiPL-HumanEval (JavaScript)
|
| 119 |
-
metrics:
|
| 120 |
-
- name: pass@1
|
| 121 |
-
type: pass@1
|
| 122 |
-
value:
|
| 123 |
-
verified: false
|
| 124 |
-
- task:
|
| 125 |
-
type: text-generation
|
| 126 |
-
dataset:
|
| 127 |
-
type: nuprl/MultiPL-E
|
| 128 |
-
name: MultiPL-HumanEval (Lua)
|
| 129 |
-
metrics:
|
| 130 |
-
- name: pass@1
|
| 131 |
-
type: pass@1
|
| 132 |
-
value:
|
| 133 |
-
verified: false
|
| 134 |
-
- task:
|
| 135 |
-
type: text-generation
|
| 136 |
-
dataset:
|
| 137 |
-
type: nuprl/MultiPL-E
|
| 138 |
-
name: MultiPL-HumanEval (PHP)
|
| 139 |
-
metrics:
|
| 140 |
-
- name: pass@1
|
| 141 |
-
type: pass@1
|
| 142 |
-
value:
|
| 143 |
-
verified: false
|
| 144 |
-
- task:
|
| 145 |
-
type: text-generation
|
| 146 |
-
dataset:
|
| 147 |
-
type: nuprl/MultiPL-E
|
| 148 |
-
name: MultiPL-HumanEval (Perl)
|
| 149 |
-
metrics:
|
| 150 |
-
- name: pass@1
|
| 151 |
-
type: pass@1
|
| 152 |
-
value:
|
| 153 |
-
verified: false
|
| 154 |
-
- task:
|
| 155 |
-
type: text-generation
|
| 156 |
-
dataset:
|
| 157 |
-
type: nuprl/MultiPL-E
|
| 158 |
-
name: MultiPL-HumanEval (Python)
|
| 159 |
-
metrics:
|
| 160 |
-
- name: pass@1
|
| 161 |
-
type: pass@1
|
| 162 |
-
value:
|
| 163 |
-
verified: false
|
| 164 |
-
- task:
|
| 165 |
-
type: text-generation
|
| 166 |
-
dataset:
|
| 167 |
-
type: nuprl/MultiPL-E
|
| 168 |
-
name: MultiPL-HumanEval (R)
|
| 169 |
-
metrics:
|
| 170 |
-
- name: pass@1
|
| 171 |
-
type: pass@1
|
| 172 |
-
value:
|
| 173 |
-
verified: false
|
| 174 |
-
- task:
|
| 175 |
-
type: text-generation
|
| 176 |
-
dataset:
|
| 177 |
-
type: nuprl/MultiPL-E
|
| 178 |
-
name: MultiPL-HumanEval (Ruby)
|
| 179 |
-
metrics:
|
| 180 |
-
- name: pass@1
|
| 181 |
-
type: pass@1
|
| 182 |
-
value:
|
| 183 |
-
verified: false
|
| 184 |
-
- task:
|
| 185 |
-
type: text-generation
|
| 186 |
-
dataset:
|
| 187 |
-
type: nuprl/MultiPL-E
|
| 188 |
-
name: MultiPL-HumanEval (Racket)
|
| 189 |
-
metrics:
|
| 190 |
-
- name: pass@1
|
| 191 |
-
type: pass@1
|
| 192 |
-
value:
|
| 193 |
-
verified: false
|
| 194 |
-
- task:
|
| 195 |
-
type: text-generation
|
| 196 |
-
dataset:
|
| 197 |
-
type: nuprl/MultiPL-E
|
| 198 |
-
name: MultiPL-HumanEval (Rust)
|
| 199 |
-
metrics:
|
| 200 |
-
- name: pass@1
|
| 201 |
-
type: pass@1
|
| 202 |
-
value:
|
| 203 |
-
verified: false
|
| 204 |
-
- task:
|
| 205 |
-
type: text-generation
|
| 206 |
-
dataset:
|
| 207 |
-
type: nuprl/MultiPL-E
|
| 208 |
-
name: MultiPL-HumanEval (Scala)
|
| 209 |
-
metrics:
|
| 210 |
-
- name: pass@1
|
| 211 |
-
type: pass@1
|
| 212 |
-
value:
|
| 213 |
-
verified: false
|
| 214 |
-
- task:
|
| 215 |
-
type: text-generation
|
| 216 |
-
dataset:
|
| 217 |
-
type: nuprl/MultiPL-E
|
| 218 |
-
name: MultiPL-HumanEval (Bash)
|
| 219 |
-
metrics:
|
| 220 |
-
- name: pass@1
|
| 221 |
-
type: pass@1
|
| 222 |
-
value:
|
| 223 |
-
verified: false
|
| 224 |
-
- task:
|
| 225 |
-
type: text-generation
|
| 226 |
-
dataset:
|
| 227 |
-
type: nuprl/MultiPL-E
|
| 228 |
-
name: MultiPL-HumanEval (Swift)
|
| 229 |
-
metrics:
|
| 230 |
-
- name: pass@1
|
| 231 |
-
type: pass@1
|
| 232 |
-
value:
|
| 233 |
-
verified: false
|
| 234 |
-
- task:
|
| 235 |
-
type: text-generation
|
| 236 |
-
dataset:
|
| 237 |
-
type: nuprl/MultiPL-E
|
| 238 |
-
name: MultiPL-HumanEval (TypeScript)
|
| 239 |
metrics:
|
| 240 |
- name: pass@1
|
| 241 |
type: pass@1
|
|
@@ -267,7 +50,7 @@ extra_gated_fields:
|
|
| 267 |
|
| 268 |
## Model Summary
|
| 269 |
|
| 270 |
-
The
|
| 271 |
|
| 272 |
- **Repository:** [shailja-thakur/VGen](https://github.com/shailja-thakur/VGen)
|
| 273 |
- **Baseline LLM** [SalesForce/CodeGen](https://github.com/salesforce/CodeGen)
|
|
|
|
| 1 |
---
|
| 2 |
pipeline_tag: text-generation
|
| 3 |
inference: true
|
| 4 |
+
widget:
|
| 5 |
+
- text: module display_hello_word
|
| 6 |
+
example_title: Hello world
|
| 7 |
+
group: Verilog
|
| 8 |
license: bigcode-openrail-m
|
| 9 |
datasets:
|
| 10 |
- shailja/Verilog_GitHub
|
|
|
|
| 18 |
type: text-generation
|
| 19 |
dataset:
|
| 20 |
type: openai_humaneval
|
| 21 |
+
name: VeriEval (Prompted)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: pass@1
|
| 24 |
type: pass@1
|
|
|
|
| 50 |
|
| 51 |
## Model Summary
|
| 52 |
|
| 53 |
+
The CodeGen models are 15.5B parameter models trained on 80+ programming languages from [The Stack (v1.2)](https://huggingface.co/datasets/bigcode/the-stack), with opt-out requests excluded. The model uses [Multi Query Attention](https://arxiv.org/abs/1911.02150), [a context window of 8192 tokens](https://arxiv.org/abs/2205.14135), and was trained using the [Fill-in-the-Middle objective](https://arxiv.org/abs/2207.14255) on 1 trillion tokens.
|
| 54 |
|
| 55 |
- **Repository:** [shailja-thakur/VGen](https://github.com/shailja-thakur/VGen)
|
| 56 |
- **Baseline LLM** [SalesForce/CodeGen](https://github.com/salesforce/CodeGen)
|