File size: 3,007 Bytes
a9979f5 9f5e4f0 1930b02 bc528bd b9434c2 8953341 4d6cc9b bc528bd eab57b7 4d6cc9b eab57b7 4b4843c ac48d25 4b4843c 5d5ca4b 748090d d17eb4a 748090d 4d6cc9b ac48d25 bc528bd ac48d25 1577cef ac48d25 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 |
---
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 26 Programming Languages as mentioned below.
## Training Details:
Model is trained for 25 epochs on Azure for nearly 26000 Datapoints for above Mentioned 26 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':</li>
<li>'AppleScript'</li>
<li>'C'</li>
<li>'C#'</li>
<li>'C++'</li>
<li>'COBOL'</li>
<li>'Erlang'</li>
<li>'Fortran'</li>
<li>'Go'</li>
<li>'Java'</li>
<li>'JavaScript'</li>
<li>'Kotlin'</li>
<li>'Lua</li>
<li>'Mathematica/Wolfram Language'</li>
<li>'PHP'</li>
<li>'Pascal'</li>
<li>'Perl'</li>
<li>'PowerShell'</li>
<li>'Python'</li>
<li>'R</li>
<li>'Ruby'</li>
<li>'Rust'</li>
<li>'Scala'</li>
<li>'Swift'</li>
<li>'Visual Basic .NET'</li>
<li>'jq'</li>
</ol>
<br>
## Below is the Training Result for 25 epochs.
<ul>
<li>Training Computer Configuration: <ul>
<li>GPU:1xNvidia Tesla T4, </li>
<li>VRam: 16GB,</li>
<li>Ram:112GB,</li>
<li>Cores:6 Cores </li>
</ul></li>
<li>Training Time taken: exactly 7 hours for 25 epochs</li>
<li>Training Hyper-parameters: </li>
</ul>
## Inference Code
```python
import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification, TextClassificationPipeline
model_name = 'philomath-1209/programming-language-identification'
loaded_tokenizer = AutoTokenizer.from_pretrained(model_name)
loaded_model = AutoModelForSequenceClassification.from_pretrained(model_name)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
text = """
PROGRAM Triangle
IMPLICIT NONE
REAL :: a, b, c, Area
PRINT *, 'Welcome, please enter the&
&lengths of the 3 sides.'
READ *, a, b, c
PRINT *, 'Triangle''s area: ', Area(a,b,c)
END PROGRAM Triangle
FUNCTION Area(x,y,z)
IMPLICIT NONE
REAL :: Area ! function type
REAL, INTENT( IN ) :: x, y, z
REAL :: theta, height
theta = ACOS((x**2+y**2-z**2)/(2.0*x*y))
height = x*SIN(theta); Area = 0.5*y*height
END FUNCTION Area
"""
inputs = loaded_tokenizer(text, return_tensors="pt",truncation=True)
with torch.no_grad():
logits = loaded_model(**inputs).logits
predicted_class_id = logits.argmax().item()
loaded_model.config.id2label[predicted_class_id]
``` |