chenning-tao / c4 Goto Github PK

I would like to ask how you applied the dataset from C4 to CLCDSA. When I used the Antlr tool in CLCDSA to parse code, I was unable to correctly obtain the feature values required by the CLCDSA model (due to the lack of line breaks in the code in the dataset)

Hi, I am trying to build a Python code clone classifier and your dataset is very useful. But it seems that those datasets files can't be downloaded anymore due to lack of data quota:

Downloading dataset/pair_test.jsonl (33 MB)
Error downloading object: dataset/pair_test.jsonl (1101894): Smudge error: Error downloading dataset/pair_test.jsonl (1101894e6b66d1dfe3ae9d889eac781a9a549a03d9c3466fb4b3bc9671d85358): batch response: This repository is over its data quota. Account responsible for LFS bandwidth should purchase more data packs to restore access.

It will be appreciated if you could fix this or provide any other access to the dataset!

Hi. I'm quite interested in your work and was trying to replicate the experiments with the released code, but something goes wrong :(

The script announces that model and bleu are not found. It seems that the necesarry files model.py and bleu.py are missing? Could you please supplement these two files (and any other files necessary yet missing)?

Btw, can you also tell the necessary python libraries and their versions to run the released codes?

Thx a lot.

Dear author, when I read the code in the test part, I found the following problems:
there is a 'break ' at run_con.py 441rows, I am confused by this. I want to ask you if there is an error here?

thank you very much!

Is it possible for you to share the trained model so that it can be used on other datasets?