This model is funetune version of Codebert in robert. On CodeSearchNet. ### Quick start:
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("addy88/programming-lang-identifier")
model = AutoModelForSequenceClassification.from_pretrained("addy88/programming-lang-identifier")
input_ids = tokenizer.encode(CODE_TO_IDENTIFY) logits = model(input_ids)[0]
language_idx = logits.argmax() # index for the resulting label ###
CodeSearchNet citation Details @article{husain_codesearchnet_2019, title = {{CodeSearchNet} {Challenge}: {Evaluating} the {State} of {Semantic} {Code} {Search}}, shorttitle = {{CodeSearchNet} {Challenge}}, url = {http://arxiv.org/abs/1909.09436}, urldate = {2020-03-12}, journal = {arXiv:1909.09436 [cs, stat]}, author = {Husain, Hamel and Wu, Ho-Hsiang and Gazit, Tiferet and Allamanis, Miltiadis and Brockschmidt, Marc}, month = sep, year = {2019}, note = {arXiv: 1909.09436}, }