liwenyun
/
CLIP
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[Minor] Fix typo

This commit is contained in:
Bart Broere 2023-07-17 14:57:03 +02:00 committed by GitHub
parent a1d071733d
commit 2558ec83f8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
clip/simple_tokenizer.py
View File

@ -19,7 +19,7 @@ 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.
""" """