Skip to content
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

Jump to bottom

[Transformers] Add an argument trust_remote_code on transformers pipeline initialization. #1173

Merged
merged 1 commit into from
Aug 8, 2023
Merged

[Transformers] Add an argument trust_remote_code on transformers pipeline initialization. #1173

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
10 changes: 9 additions & 1 deletion src/deepsparse/transformers/pipelines/pipeline.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,16 +66,22 @@ class TransformersPipeline(Pipeline, Bucketable):
If a list of lengths is provided, then for each length, a model and
tokenizer will be compiled capable of handling that sequence length
(also known as a bucket). Default is 128
:param trust_remote_code: if True, will trust remote code. This option
should only be set to `True` for repositories you trust and in which
you have read the code, as it will execute possibly unsafe code
on your local machine. Default is False
"""

def __init__(
self,
*,
sequence_length: Union[int, List[int]] = 128,
trust_remote_code: bool = False,
**kwargs,
):

self._sequence_length = sequence_length
self._trust_remote_code = trust_remote_code

self.config = None
self.tokenizer = None
Expand Down Expand Up @@ -111,7 +117,9 @@ def setup_onnx_file_path(self) -> str:
)

self.config = AutoConfig.from_pretrained(
config_path, finetuning_task=self.task if hasattr(self, "task") else None
config_path,
trust_remote_code=self._trust_remote_code,
finetuning_task=self.task if hasattr(self, "task") else None,
)
self.tokenizer = AutoTokenizer.from_pretrained(
tokenizer_path, model_max_length=self.sequence_length
Expand Down
Loading