Skip to content

Prevent add_special_tokens overwrite for BART #12

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

Open
carlesonielfa wants to merge 1 commit into
base: master
Choose a base branch
from
+4 −1
Open

Prevent add_special_tokens overwrite for BART #12

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
5 changes: 4 additions & 1 deletion vllm_bart_plugin/bart.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1041,6 +1041,9 @@ def _call_hf_processor(
has_encoder_data = mm_data is not None and "texts" in mm_data
result = {}

# vLLM may pass add_special_tokens in tok_kwargs; we set it ourselves
tok_kwargs = {k: v for k, v in tok_kwargs.items() if k != "add_special_tokens"}

if has_encoder_data:
# Tokenize the encoder text from mm_data
encoder_texts = mm_data["texts"]
Expand Down Expand Up @@ -1379,4 +1382,4 @@ def load_weights(self, weights: Iterable[tuple[str, torch.Tensor]]) -> set[str]:
for key in self.keys_to_ignore_on_load_missing:
loaded_params.add(key)

return loaded_params
return loaded_params