Aamir Syed
Aamir Syed
> > I believe it is best to make sure that the Countvectorizer in Bertopic should be the same as you used to create the dictionary, corpus and tokens. >...
A Finetuning session for the same model does this. A simple workaround is to add ``` import tensorflow as tf tf.reset_default_graph() ``` before your `gpt2.finetune(..)` sample code: ``` def generate(input_file_name,...
@shashank7596 just importing it as `import urllib.request as urllib2` does not work either. :/ It gives me a weird 'list index out of range' error, presumably from the `urllib.request.quote()` I...
> changes: > > * added separate functions for running a list of input strings or a single string > * optimised performance by incorporating nlp.pipe() to form doc, which...