Skip to content
This repository was archived by the owner on Apr 8, 2025. It is now read-only.

CodeBERT support for embeddings #488

Merged
merged 3 commits into from
Aug 31, 2020
Merged

CodeBERT support for embeddings #488

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
70900f9
CodeBERT support
lambdaofgod Aug 9, 2020
61cfe05
exclude mlm codebert model
lambdaofgod Aug 17, 2020
ade64ca
removed automodel support
lambdaofgod Aug 29, 2020
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: 5 additions & 0 deletions farm/modeling/language_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,6 +134,11 @@ def load(cls, pretrained_model_name_or_path, n_added_tokens=0, language_model_cl
language_model_class = 'XLMRoberta'
elif 'roberta' in pretrained_model_name_or_path:
language_model_class = 'Roberta'
elif 'codebert' in pretrained_model_name_or_path.lower():
if "mlm" in pretrained_model_name_or_path.lower():
raise NotImplementedError("MLM part of codebert is currently not supported in FARM")
else:
language_model_class = 'Roberta'
elif 'camembert' in pretrained_model_name_or_path or 'umberto' in pretrained_model_name_or_path:
language_model_class = "Camembert"
elif 'albert' in pretrained_model_name_or_path:
Expand Down
5 changes: 5 additions & 0 deletions farm/modeling/tokenization.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,6 +70,11 @@ def load(cls, pretrained_model_name_or_path, tokenizer_class=None, **kwargs):
tokenizer_class = "XLMRobertaTokenizer"
elif "roberta" in pretrained_model_name_or_path.lower():
tokenizer_class = "RobertaTokenizer"
elif 'codebert' in pretrained_model_name_or_path.lower():
if "mlm" in pretrained_model_name_or_path.lower():
raise NotImplementedError("MLM part of codebert is currently not supported in FARM")
else:
tokenizer_class = "RobertaTokenizer"
elif "camembert" in pretrained_model_name_or_path.lower() or "umberto" in pretrained_model_name_or_path:
tokenizer_class = "CamembertTokenizer"
elif "distilbert" in pretrained_model_name_or_path.lower():
Expand Down