From 3467230a77f5444eec9e673ec465a814a0467c8d Mon Sep 17 00:00:00 2001 From: Ikko Ashimine Date: Sat, 31 Dec 2022 02:51:08 +0900 Subject: [PATCH] models : fix typo in convert-h5-to-ggml.py signficant -> significant --- models/convert-h5-to-ggml.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/models/convert-h5-to-ggml.py b/models/convert-h5-to-ggml.py index b882c4d..b06ad23 100644 --- a/models/convert-h5-to-ggml.py +++ b/models/convert-h5-to-ggml.py @@ -56,7 +56,7 @@ 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. """