Skip to content

[Model] support modernbert #16648

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

Merged
merged 14 commits into from
Apr 16, 2025
+335 −0
Merged

[Model] support modernbert #16648

Show file tree
Hide file tree
Changes from 7 commits
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
2538dc3
support modernbert
Apr 15, 2025
5d0e7e0
fix code style
Apr 15, 2025
17b597b
add model loading test
Apr 15, 2025
9729887
add model loading test
Apr 15, 2025
f53eeb6
add min tf version of modernbert
Apr 15, 2025
0c16ece
remove the dropout
Apr 16, 2025
cfc072b
replace linear with parallel linear
Apr 16, 2025
147b822
update qkv to parallel
Apr 16, 2025
bf40d4b
add modernBert of the doc
Apr 16, 2025
60240e5
remove useless code
Apr 16, 2025
f7dd19b
upgrade to the vllm attention
Apr 16, 2025
7d97c27
remove useless code
Apr 16, 2025
6cd5bba
use torch GELU directly
Apr 16, 2025
8c017bc
add torch compile to the model
Apr 16, 2025
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: 3 additions & 0 deletions tests/models/registry.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -273,6 +273,9 @@ def check_available_online(
"BertForSequenceClassification": _HfExamplesInfo("cross-encoder/ms-marco-MiniLM-L-6-v2"), # noqa: E501
"RobertaForSequenceClassification": _HfExamplesInfo("cross-encoder/quora-roberta-base"), # noqa: E501
"XLMRobertaForSequenceClassification": _HfExamplesInfo("BAAI/bge-reranker-v2-m3"), # noqa: E501
"ModernBertForSequenceClassification":
_HfExamplesInfo("Alibaba-NLP/gte-reranker-modernbert-base",
min_transformers_version="4.49"),
}

_MULTIMODAL_EXAMPLE_MODELS = {
Expand Down
Loading