yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-10-27 07:49:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update bpe_openai_gpt2.py

Browse Source 
signficant -> significant
This commit is contained in:
Ikko Eltociear Ashimine 2024-01-28 23:26:23 +09:00 committed by GitHub
parent f6e80a376d
commit 3a3a4ac1f1
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ch02/02_bonus_bytepair-encoder/bpe_openai_gpt2.py
View File

@ -48,7 +48,7 @@ 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.
""" """
@ -171,4 +171,4 @@ def download_vocab():
# 1k for chunk_size, since Ethernet packet size is around 1500 bytes # 1k for chunk_size, since Ethernet packet size is around 1500 bytes
for chunk in r.iter_content(chunk_size=chunk_size): for chunk in r.iter_content(chunk_size=chunk_size):
f.write(chunk) f.write(chunk)
pbar.update(chunk_size) pbar.update(chunk_size)