|
|
--- |
|
|
license: wtfpl |
|
|
datasets: |
|
|
- cakiki/rosetta-code |
|
|
language: |
|
|
- en |
|
|
metrics: |
|
|
- accuracy |
|
|
library_name: transformers |
|
|
pipeline_tag: text-classification |
|
|
tags: |
|
|
- code |
|
|
- programming-language |
|
|
- code-classification |
|
|
base_model: huggingface/CodeBERTa-small-v1 |
|
|
--- |
|
|
This Model is a fine-tuned version of *huggingface/CodeBERTa-small-v1* on *cakiki/rosetta-code* Dataset for 25 Programming Languages as mentioned below. |
|
|
## Training Details: |
|
|
Model is trained for 25 epochs on Azure for nearly 26000 Datapoints for above Mentioned 25 Programming Languages<br> extracted from Dataset having 1006 of total Programming Language. |
|
|
### Programming Languages this model is able to detect vs Examples used for training |
|
|
<ol> |
|
|
<li>'ARM Assembly': 3,</li> |
|
|
<li>'AppleScript': 17,</li> |
|
|
|
|
|
<li>'C': 22,</li> |
|
|
|
|
|
<li>'C#': 10,</li> |
|
|
|
|
|
<li>'C++': 6,</li> |
|
|
|
|
|
<li>'COBOL': 2,</li> |
|
|
|
|
|
<li>'Erlang': 9,</li> |
|
|
|
|
|
<li>'Fortran': 16,</li> |
|
|
|
|
|
<li>'Go': 8,</li> |
|
|
|
|
|
<li>'Java': 19,</li> |
|
|
|
|
|
<li>'JavaScript': 1,</li> |
|
|
|
|
|
<li>'Kotlin': 24,</li> |
|
|
|
|
|
<li>'Lua': 5,</li> |
|
|
|
|
|
<li>'Mathematica/Wolfram Language': 14,</li> |
|
|
|
|
|
<li>'PHP': 15,</li> |
|
|
|
|
|
<li>'Pascal': 18,</li> |
|
|
|
|
|
<li>'Perl': 23,</li> |
|
|
|
|
|
<li>'PowerShell': 20,</li> |
|
|
|
|
|
<li>'Python': 21,</li> |
|
|
|
|
|
<li>'R': 4</li> |
|
|
|
|
|
<li>'Ruby': 12,</li> |
|
|
|
|
|
<li>'Rust': 11,</li> |
|
|
|
|
|
<li>'Scala': 0,</li> |
|
|
|
|
|
<li>'Swift': 13,</li> |
|
|
|
|
|
<li>'Visual Basic .NET': 7,</li> |
|
|
|
|
|
<li>'jq': 25</li> |
|
|
|
|
|
</ol> |
|
|
<br> |
|
|
Below is the Training Result for 25 epochs. |
|
|
 |
