models : fix typo in convert-h5-to-ggml.py

signficant -> significant
This commit is contained in:
Ikko Ashimine 2022-12-31 02:51:08 +09:00 committed by Georgi Gerganov
parent a091581eb3
commit 3467230a77

View File

@ -56,7 +56,7 @@ def bytes_to_unicode():
The reversible bpe codes work on unicode strings. 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. 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. 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. 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. And avoids mapping to whitespace/control characters the bpe code barfs on.
""" """