Thomas Dimson

Haha, it does sometimes pluralize in interesting ways. The way I'm doing the example rejection is really naive: https://github.com/turtlesoupy/this-word-does-not-exist/blob/7b11b616f3b9b6ed75637aec1cd4d17f1e0e083d/title_maker_pro/datasets.py#L482 basically I'm checking if "terezi" is in the example ignoring word...

Hello there -- what version of python are you using here? This looks like it might be related to an older version

Can potentially downsample

@JonLaliberte I didn't actually find anything good -- it is easy enough to do dynamic lookups but it gets expensive since the code is designed with a master list in...

@desegura what version of Python are you using? For reference, I pickled the file on Python 3.7

(and for reference, you do need to un-gzip before trying to load it in)

@desegura I think this has to do with your network set-up on that machine, I'm able to access that URL without any issue: https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-config.json

@desegura that error is in the transformers library, it looks like the GPT-2 base model archive it is trying to load is corrupt in some way; perhaps the download was...

It's definitely possible, but hosting costs can be pretty expensive for inference queries. @duncte123 can you tell me a bit more about your use case?

@duncte123 sweet, that's very cachable. I cached 100,000 words for the website in this file: https://github.com/turtlesoupy/this-word-does-not-exist/blob/master/website/data/words.json.gz The JSON format should be pretty obvious once unzipping. Maybe load it in and...