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.

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

Convert tokenizers with openvino_tokenizers #500

Closed
wants to merge 2 commits into from
Closed
Changes from 1 commit
Commits
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
27 changes: 27 additions & 0 deletions optimum/exporters/openvino/__main__.py
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@

from requests.exceptions import ConnectionError as RequestsConnectionError
from transformers import AutoConfig, AutoTokenizer
from openvino import save_model

from optimum.exporters import TasksManager
from optimum.exporters.onnx import __main__ as optimum_main
Expand Down Expand Up @@ -46,6 +47,24 @@
logger = logging.getLogger(__name__)


def tokenizer_export(
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it should be in convert.py file together with other conversion functions.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Moved.

tokenizer,
output: Union[str, Path],
suffix: Optional[str] = ""
):
try:
from openvino_tokenizers import convert_tokenizer
ov_tokenizer, ov_detokenizer = convert_tokenizer(tokenizer, with_detokenizer=True)
if isinstance(output, str):
output = Path(output)
tokenizer_path = output.joinpath("openvino_tokenizer" + suffix + ".xml")
detokenizer_path = output.joinpath("openvino_detokenizer" + suffix + ".xml")
save_model(ov_tokenizer, tokenizer_path)
save_model(ov_detokenizer, detokenizer_path)
except Exception as exception:
print("[ WARNING ] OpenVINO tokenizer/detokenizer models couldn't be exported because of exception:", exception)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
print("[ WARNING ] OpenVINO tokenizer/detokenizer models couldn't be exported because of exception:", exception)
logger.warning(OpenVINO tokenizer/detokenizer models couldn't be exported because of exception:", exception)

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Fixed.



def main_export(
model_name_or_path: str,
output: Union[str, Path],
Expand Down Expand Up @@ -328,6 +347,12 @@ class StoreAttr(object):
if generation_config is not None:
generation_config.save_pretrained(output)
maybe_save_preprocessors(model_name_or_path, output)
try:
# Avoid loding it for the second time if loaded before
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
tokenizer_export(tokenizer, output)
except:
print("[ WARNING ] Could not load tokenizer using specified model ID or path. OpenVINO tokenizer/detokenizer models won't be generated.")

if model.config.is_encoder_decoder and task.startswith("text-generation"):
raise ValueError(
Expand Down Expand Up @@ -358,10 +383,12 @@ class StoreAttr(object):
tokenizer = getattr(model, "tokenizer", None)
if tokenizer is not None:
tokenizer.save_pretrained(output.joinpath("tokenizer"))
tokenizer_export(tokenizer, output)

tokenizer_2 = getattr(model, "tokenizer_2", None)
if tokenizer_2 is not None:
tokenizer_2.save_pretrained(output.joinpath("tokenizer_2"))
tokenizer_export(tokenizer, output, "_2")

model.save_config(output)

Expand Down