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 fine-tuned tinybert and mobilebert #209

Merged
merged 1 commit into from
Jan 26, 2025
Merged

support fine-tuned tinybert and mobilebert #209

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
8 changes: 6 additions & 2 deletions llmlingua/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,7 +79,9 @@ def seed_everything(seed: int):


def is_begin_of_new_word(token, model_name, force_tokens, token_map):
if "bert-base-multilingual-cased" in model_name:
if "bert-base-multilingual-cased" in model_name \
or "tinybert" in model_name.lower() \
or "mobilebert" in model_name.lower():
if token.lstrip("##") in force_tokens or token.lstrip("##") in set(
token_map.values()
):
Expand All @@ -104,7 +106,9 @@ def replace_added_token(token, token_map):


def get_pure_token(token, model_name):
if "bert-base-multilingual-cased" in model_name:
if "bert-base-multilingual-cased" in model_name \
or "tinybert" in model_name.lower() \
or "mobilebert" in model_name.lower():
return token.lstrip("##")
elif "xlm-roberta-large" in model_name:
return token.lstrip("▁")
Expand Down
Loading