Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
This model is funetune version of Codebert in robert. On CodeSearchNet.
|
| 2 |
+
###
|
| 3 |
+
Quick start:
|
| 4 |
+
|
| 5 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
| 6 |
+
|
| 7 |
+
tokenizer = AutoTokenizer.from_pretrained("addy88/programming-lang-identifier")
|
| 8 |
+
|
| 9 |
+
model = AutoModelForSequenceClassification.from_pretrained("addy88/programming-lang-identifier")
|
| 10 |
+
|
| 11 |
+
input_ids = tokenizer.encode(CODE_TO_IDENTIFY)
|
| 12 |
+
logits = model(input_ids)[0]
|
| 13 |
+
|
| 14 |
+
language_idx = logits.argmax() # index for the resulting label
|
| 15 |
+
###
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
CodeSearchNet citation
|
| 19 |
+
Details
|
| 20 |
+
@article{husain_codesearchnet_2019,
|
| 21 |
+
title = {{CodeSearchNet} {Challenge}: {Evaluating} the {State} of {Semantic} {Code} {Search}},
|
| 22 |
+
shorttitle = {{CodeSearchNet} {Challenge}},
|
| 23 |
+
url = {http://arxiv.org/abs/1909.09436},
|
| 24 |
+
urldate = {2020-03-12},
|
| 25 |
+
journal = {arXiv:1909.09436 [cs, stat]},
|
| 26 |
+
author = {Husain, Hamel and Wu, Ho-Hsiang and Gazit, Tiferet and Allamanis, Miltiadis and Brockschmidt, Marc},
|
| 27 |
+
month = sep,
|
| 28 |
+
year = {2019},
|
| 29 |
+
note = {arXiv: 1909.09436},
|
| 30 |
+
}
|