Keywords are all lowercase

Question

secsilm opened this issue 7 months ago · comments

Hi, great project first.

I would prefer to keep the original form instead of all lowercase. How can I do that? Thanks.

Maarten Grootendorst · Answer 1 · Tue Oct 17 2023 15:03:42 GMT+0800 (China Standard Time)

That is a result of the underlying tokenizer. You can find more about that here.

Alan Lee · Answer 2 · Mon Oct 23 2023 11:34:10 GMT+0800 (China Standard Time)

That is a result of the underlying tokenizer. You can find more about that here.

OK, I found it. It's a CountVectorizer config. Thanks.