giganticode / probes Goto Github PK

Thanks a lot for your great work. I met errors when loading CodeT5, PLBART-mtjava and PLBART-large models.
For codet5, I change the code as follows:
tokenizer = RobertaTokenizer.from_pretrained(modelname, cache_dir="~/tmp") model = T5ForConditionalGeneration.from_pretrained(modelname, config=config, cache_dir="~/tmp")

For PLBART-mtjava and PLBART-large models, I found a useful issue

Hello, I have read your article carefully. It is a very interesting work, but I still have some problems.

（1）May I ask which dataset does "the test dataset provided by Ahmad et al. (2021a) consisting of 10k examples of Java functions and methods" refer to?
(2) What do the abbreviations of the datasets in this repo represent and how they are constructed?

Thank you for your time in advance!

How are your AST node taggingextracted into the txt, and what does each column in the AST txt file represent?

Hello, thanks a lot for your great work. When I run probe_classifier.py. There are some errors:
File "probe_classifier.py", line 205, in
train_X, train_y, dev_X, dev_y, test_X, test_y, feat_dim, num_classes, cat2id, id2cat = load_data()
File "probe_classifier.py", line 35, in load_data
feat_jsonl = json.loads(feat_jsonl)
File "/home/fang/anaconda3/envs/probe_env/lib/python3.8/json/init.py", line 357, in loads
return _default_decoder.decode(s)
File "/home/fang/anaconda3/envs/probe_env/lib/python3.8/json/decoder.py", line 337, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "/home/fang/anaconda3/envs/probe_env/lib/python3.8/json/decoder.py", line 355, in raw_decode
raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

And I have no idea how to fix it.