fix: tiktoken cannot be loaded without internet (#12478)

Signed-off-by: -LAN- <laipz8200@outlook.com>
This commit is contained in:
-LAN-
2025-01-08 14:49:44 +08:00
committed by GitHub
parent 53bb37b749
commit 0a49d3dd52

View File

@@ -1,8 +1,6 @@
from threading import Lock
from typing import Any
import tiktoken
_tokenizer: Any = None
_lock = Lock()
@@ -33,9 +31,17 @@ class GPT2Tokenizer:
if _tokenizer is None:
# Try to use tiktoken to get the tokenizer because it is faster
#
try:
import tiktoken
_tokenizer = tiktoken.get_encoding("gpt2")
# base_path = abspath(__file__)
# gpt2_tokenizer_path = join(dirname(base_path), "gpt2")
# _tokenizer = TransformerGPT2Tokenizer.from_pretrained(gpt2_tokenizer_path)
except Exception:
from os.path import abspath, dirname, join
from transformers import GPT2Tokenizer as TransformerGPT2Tokenizer # type: ignore
base_path = abspath(__file__)
gpt2_tokenizer_path = join(dirname(base_path), "gpt2")
_tokenizer = TransformerGPT2Tokenizer.from_pretrained(gpt2_tokenizer_path)
return _tokenizer