Skip to content

Fix Max Token ID for Qwen-VL-Chat #11980

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 2 commits into from
Jan 13, 2025
Merged

Fix Max Token ID for Qwen-VL-Chat #11980

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
73436f7
Fix online qwen models
alex-jw-brooks Jan 13, 2025
7cd1505
Guard against vocab_size attribute to allow other tokenizer types
alex-jw-brooks Jan 13, 2025
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
9 changes: 9 additions & 0 deletions vllm/transformers_utils/tokenizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
import contextlib
import os
import warnings
from pathlib import Path
Expand Down Expand Up @@ -67,7 +68,15 @@ def get_cached_tokenizer(tokenizer: AnyTokenizer) -> AnyTokenizer:
tokenizer.all_special_tokens_extended)
tokenizer_all_special_tokens = set(tokenizer.all_special_tokens)
tokenizer_len = len(tokenizer)

max_token_id = max(tokenizer.get_vocab().values())
# Some tokenizers (e.g., QwenTokenizer) have special tokens that
# are added and included in the implementation of the vocab_size
# property, but not in get_vocab(); if there is an implementation
# of vocab size, we should take the greater value.
if hasattr(tokenizer, "vocab_size"):
with contextlib.suppress(NotImplementedError):
max_token_id = max(max_token_id, tokenizer.vocab_size)

class CachedTokenizer(tokenizer.__class__): # type: ignore

Expand Down
Loading