github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-27 22:37:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

issue#4082 base_language had wrong code comment that it was using gpt… (#4084)

Browse Source 
…3 to tokenize text instead of gpt-2

Co-authored-by: Pulkit <pulkit.mehta@catylex.com>
This commit is contained in:
Pulkit Mehta
2023-05-04 10:28:29 +05:30
committed by GitHub
parent 6caba8e759
commit bbbca10704
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
langchain/base_language.py
View File

@@ -25,7 +25,7 @@ def _get_num_tokens_default_method(text: str) -> int:
# create a GPT-2 tokenizer instance
tokenizer = GPT2TokenizerFast.from_pretrained("gpt2")
# tokenize the text using the GPT-3 tokenizer
# tokenize the text using the GPT-2 tokenizer
tokenized_text = tokenizer.tokenize(text)
# calculate the number of tokens in the tokenized text