Yijun Yu

Hi, please make sure you are using Python 3.8 on Windows machine. Python 3.9 currently has trouble getting the right version of Tensorflow installed. After successful installation of infercode, please...

I think it is a matter of applying infercode to a number of files multiple times, if your use case the code are as large number of files.

> > Thank you, I can run the program successfully > > Hello, how did you solve this problem? I met the same problem on Linux. Hi, are you importing...

We haven't tested this on Google Collab usage. I guess you need to let the tool install the shared libraries there. If you have command line access, please run `pip...

Looks like you can get it work. Just see if you can get a new version of Visual C++ installed on your computer first.

"parallel" is a GNU utility to launch multiple commands in parallel. If you don't have it. The docker image tries to get installed, but if not, you may need to...

Thanks a lot for the initial import. I was able to run the above script, which loads the original codebert model. However, I am not sure how to load a...

Thanks for the guidance. I will tackle the problem once the conversion can be done. Currently the stack trace is listed below: ``` $ python utils/convert_model.py codeBERT_pl.bin Traceback (most recent...

The main code is listed below: ```python import torch import torch.nn as nn import torch.nn.functional as F from transformers import RobertaConfig, RobertaModel class RobertaClass(torch.nn.Module): def __init__(self): super(RobertaClass, self).__init__() self.codeBert =...

The above conversion works! I can save the model into `rust_model.ot` and load it into the memory using the code fragment you shared: ```rust let model = RobertaForMaskedLM::new(&vs.root(), &config); ```...