Skip to content

[Fix] Support cls pooling in ModernBertPooler #20067

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 4 commits into from
Jun 25, 2025
Merged

[Fix] Support cls pooling in ModernBertPooler #20067

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
d79c485
Adapt cls and mean pooling in
lsz05 Jun 25, 2025
bf343f9
reformat
lsz05 Jun 25, 2025
cbfa28d
reformat
lsz05 Jun 25, 2025
643b090
reformat
lsz05 Jun 25, 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
9 changes: 8 additions & 1 deletion vllm/model_executor/models/modernbert.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -258,14 +258,21 @@ def __init__(self, config: ModernBertConfig):
super().__init__()
self.dense = nn.Linear(config.hidden_size, config.hidden_size,
config.classifier_bias)
self.pooling_type = config.classifier_pooling
Copy link
Contributor

Choose a reason for hiding this comment

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

medium

It's good to see that the pooling type is being loaded from the model config. However, ensure that config.classifier_pooling is validated elsewhere to prevent unexpected values from being used. If not, consider adding a validation step here or in the config definition to ensure it's one of the supported types (cls or mean).

self.act = nn.GELU()
self.norm = nn.LayerNorm(config.hidden_size,
eps=config.norm_eps,
bias=config.norm_bias)

def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
pooled_output = hidden_states
pooled_output = pooled_output.mean(dim=0, keepdim=False)
if self.pooling_type == "mean":
pooled_output = pooled_output.mean(dim=0, keepdim=False)
elif self.pooling_type == "cls":
pooled_output = pooled_output[0, :]
else:
raise ValueError("Pooling type should be either `cls` or `mean`, "
f"but got {self.pooling_type}")
pooled_output = self.norm(self.act(self.dense(pooled_output)))
return pooled_output

Expand Down