From 2558ec83f8fdfd5b500bf0c7255d1f53b5dbf588 Mon Sep 17 00:00:00 2001 From: Bart Broere Date: Mon, 17 Jul 2023 14:57:03 +0200 Subject: [PATCH] [Minor] Fix typo --- clip/simple_tokenizer.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/clip/simple_tokenizer.py b/clip/simple_tokenizer.py index 0a66286..341fb61 100644 --- a/clip/simple_tokenizer.py +++ b/clip/simple_tokenizer.py @@ -19,7 +19,7 @@ def bytes_to_unicode(): The reversible bpe codes work on unicode strings. This means you need a large # of unicode characters in your vocab if you want to avoid UNKs. When you're at something like a 10B token dataset you end up needing around 5K for decent coverage. - This is a signficant percentage of your normal, say, 32K bpe vocab. + This is a significant percentage of your normal, say, 32K bpe vocab. To avoid that, we want lookup tables between utf-8 bytes and unicode strings. And avoids mapping to whitespace/control characters the bpe code barfs on. """