GPT2ForLatentConnector

[Bila12]

Hello, great work there !

Everything is fine with the docker env, and the code works amazingly. However I would like to compute the code in my own conda environement, and it seems that the version of pytorch-transformers (1.2.0) in your requirement file doesn't have GPT2ForLatentConnector and BertForLatentConnector, and I couldn't find it in other versions.

Could you give me the actual version that is used in your code ? Or even the source code for these classes.

Thanks a lot !
Romain

[Bila12]

Oh actually that was provided sorry ! I just shouldn't have worried about the requirement.txt file provided in the repository where pytorch-transformers version 1.2.0 is installed and use the custom model. Then run everything from the folder code.

[kevinfd]

Thanks Bila, this helped me solve a similar issue. In case it's helpful for anyone else (or me in the future when I inevitably forget), modifying my PYTHONPATH variable fixed the issue. (line 1 in fine-tuning script):

export PYTHONPATH="${PYTHONPATH}:/workspace/code"