Update README.md
Browse files
README.md
CHANGED
@@ -1,9 +1,25 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
|
4 |
-
-
|
5 |
-
license:
|
6 |
datasets:
|
7 |
- code_search_net
|
8 |
-
|
|
|
9 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- java
|
4 |
+
- code
|
5 |
+
license: apache-2.0
|
6 |
datasets:
|
7 |
- code_search_net
|
8 |
+
widget:
|
9 |
+
- text: 'public [MASK] isOdd(Integer num){if (num % 2 == 0) {return "even";} else {return "odd";}}'
|
10 |
---
|
11 |
+
## JavaRoBERTa-Tara (Name of my baby girl :) )
|
12 |
+
A RoBERTa model pretrained on, code_search_net Java software code.
|
13 |
+
|
14 |
+
### Training Data
|
15 |
+
The model was trained on 10,223,695 Java files retrieved from open source projects on GitHub.
|
16 |
+
|
17 |
+
### Training Objective
|
18 |
+
A MLM (Masked Language Model) objective was used to train this model.
|
19 |
+
|
20 |
+
### Usage
|
21 |
+
```python
|
22 |
+
from transformers import pipeline
|
23 |
+
pipe = pipeline('fill-mask', model='CAUKiel/JavaBERT')
|
24 |
+
output = pipe(CODE) # Replace with Java code; Use '[MASK]' to mask tokens/words in the code.
|
25 |
+
```
|