Stenpiren

Notebooks and data used for training the model

2

Hi, Is there a possibility to make available the data used for training as well as the notebooks? That way we can generate different model versions, twinkle a little and...

Examples show boolean vectors, what about string vectors?

4

Hi, I was wondering how to use this library for comparing two different Strings that are tokenized into a string vector each. The examples only show boolean vectors which are...

ImportError: cannot import name 'ensure_dir_exists'

4

After cloning the entire repository and doing _docker-compose build_ and then _docker-compose up_ I get I get the following Traceback: Starting scotch_demo_julia_api_1 ... **done** Starting scotch_demo_python_api_1 ... **done** Starting scotch_demo_r_api_1...

Did it take two days to train the model? If so, was it with the 24GB GPU?

Tokenizer tokenizer = ...;

1

What goes in "..." for Tokenizer in the example you wrote in README.md? I would like to replicate the example but I am confused there. Thanks.