Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# roberta-go
|
2 |
+
---
|
3 |
+
language: Go
|
4 |
+
datasets:
|
5 |
+
- CodeSearchNet
|
6 |
+
---
|
7 |
+
|
8 |
+
This is a [roberta](https://arxiv.org/pdf/1907.11692.pdf) pre-trained version on the [CodeSearchNet dataset](https://github.com/github/CodeSearchNet) for **Golang** Mask Language Model mission.
|
9 |
+
|
10 |
+
To load the model:
|
11 |
+
(necessary packages: !pip install transformers sentencepiece)
|
12 |
+
```python
|
13 |
+
from transformers import AutoTokenizer, AutoModelWithLMHead, pipeline
|
14 |
+
tokenizer = AutoTokenizer.from_pretrained("dbernsohn/roberta-go")
|
15 |
+
model = AutoModelWithLMHead.from_pretrained("dbernsohn/roberta-go")
|
16 |
+
|
17 |
+
fill_mask = pipeline(
|
18 |
+
"fill-mask",
|
19 |
+
model=model,
|
20 |
+
tokenizer=tokenizer
|
21 |
+
)
|
22 |
+
```
|
23 |
+
|
24 |
+
You can then use this model to fill masked words in a Java code.
|
25 |
+
|
26 |
+
```go
|
27 |
+
code = """
|
28 |
+
package main
|
29 |
+
|
30 |
+
import (
|
31 |
+
"fmt"
|
32 |
+
"runtime"
|
33 |
+
)
|
34 |
+
|
35 |
+
func main() {
|
36 |
+
fmt.Print("Go runs on ")
|
37 |
+
switch os := runtime.<mask>; os {
|
38 |
+
case "darwin":
|
39 |
+
fmt.Println("OS X.")
|
40 |
+
case "linux":
|
41 |
+
fmt.Println("Linux.")
|
42 |
+
default:
|
43 |
+
// freebsd, openbsd,
|
44 |
+
// plan9, windows...
|
45 |
+
fmt.Printf("%s.\n", os)
|
46 |
+
}
|
47 |
+
}
|
48 |
+
""".lstrip()
|
49 |
+
|
50 |
+
pred = {x["token_str"].replace("Ġ", ""): x["score"] for x in fill_mask(code)}
|
51 |
+
sorted(pred.items(), key=lambda kv: kv[1], reverse=True)
|
52 |
+
[('GOOS', 0.11810332536697388),
|
53 |
+
('FileInfo', 0.04276798665523529),
|
54 |
+
('Stdout', 0.03572738170623779),
|
55 |
+
('Getenv', 0.025064032524824142),
|
56 |
+
('FileMode', 0.01462600938975811)]
|
57 |
+
```
|
58 |
+
|
59 |
+
The whole training process and hyperparameters are in my [GitHub repo](https://github.com/DorBernsohn/CodeLM/tree/main/CodeMLM)
|
60 |
+
|
61 |
+
> Created by [Dor Bernsohn](https://www.linkedin.com/in/dor-bernsohn-70b2b1146/)
|