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

Support GLM Edge and ModernBERT #356

Merged
merged 5 commits into from
Dec 23, 2024
+8 −2
Merged

Support GLM Edge and ModernBERT #356

Changes from 4 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
56ff973
Support GLM Edge
apaniukov Dec 20, 2024
81b7122
Support GLM Edge
apaniukov Dec 20, 2024
254672e
Support GLM Edge
apaniukov Dec 20, 2024
0d31c78
Merge branch 'master' into support-glm-edge
apaniukov Dec 20, 2024
a6173e5
Support ModernBERT
apaniukov Dec 20, 2024
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
3 changes: 2 additions & 1 deletion python/openvino_tokenizers/hf_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -276,6 +276,7 @@ def tokenization_model(self) -> None:
"TemplateProcessing": CombineSegmentsStep.from_hf_json_template_postprocessor,
"BertProcessing": CombineSegmentsStep.from_hf_json_bert_postprocessor,
"RobertaProcessing": CombineSegmentsStep.from_hf_json_roberta_processor,
"ByteLevel": lambda *args: list(), # return no handle for ByteLevel so add_steps skips it
}

def post_tokenization(self) -> None:
Expand Down Expand Up @@ -315,7 +316,7 @@ def post_tokenization(self) -> None:
post_processor_json, self.number_of_inputs, self.add_special_tokens
)

self.num_of_added_tokens += combine_segments_step.number_of_added_tokens
self.num_of_added_tokens += getattr(combine_segments_step, "number_of_added_tokens", 0)

self.add_truncation()
self.pipeline.add_steps(combine_segments_step)
Expand Down
Loading