Skip to content

fix: tiktoken cannot be loaded without internet #12478

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jan 8, 2025
Merged

fix: tiktoken cannot be loaded without internet #12478

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 12 additions & 6 deletions api/core/model_runtime/model_providers/__base/tokenizers/gpt2_tokenzier.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,6 @@
from threading import Lock
from typing import Any

import tiktoken

_tokenizer: Any = None
_lock = Lock()

Expand Down Expand Up @@ -33,9 +31,17 @@ def get_encoder() -> Any:
if _tokenizer is None:
# Try to use tiktoken to get the tokenizer because it is faster
#
_tokenizer = tiktoken.get_encoding("gpt2")
# base_path = abspath(__file__)
# gpt2_tokenizer_path = join(dirname(base_path), "gpt2")
# _tokenizer = TransformerGPT2Tokenizer.from_pretrained(gpt2_tokenizer_path)
try:
import tiktoken

_tokenizer = tiktoken.get_encoding("gpt2")
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
Loading