Skip to content

Fix load-hf-weights order #1096

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
ananthsub merged 2 commits into from
Oct 27, 2025
Merged

Fix load-hf-weights order #1096

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
26227d8
fix load-hf-weights order
ananthsub Oct 27, 2025
e69a110
fix test
ananthsub Oct 27, 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
2 changes: 1 addition & 1 deletion src/megatron/bridge/models/conversion/auto_bridge.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -294,7 +294,7 @@ def load_hf_weights(self, model: list[MegatronModelT], hf_path: str | Path | Non
pre_trained = self.hf_pretrained
else:
pre_trained = PreTrainedCausalLM.from_pretrained(hf_path)
self._model_bridge.load_weights_hf_to_megatron(model, pre_trained)
self._model_bridge.load_weights_hf_to_megatron(pre_trained, model)

return model

Expand Down
5 changes: 3 additions & 2 deletions tests/unit_tests/models/test_auto_bridge.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -415,7 +415,7 @@ def test_load_hf_weights(self):
bridge = AutoBridge(mock_hf_model)
bridge.load_hf_weights(mock_megatron_model)

mock_model_bridge.load_weights_hf_to_megatron.assert_called_once_with(mock_megatron_model, mock_hf_model)
mock_model_bridge.load_weights_hf_to_megatron.assert_called_once_with(mock_hf_model, mock_megatron_model)

def test_load_hf_weights_from_path(self):
"""Test loading weights from a different path."""
Expand Down Expand Up @@ -444,7 +444,8 @@ def test_load_hf_weights_from_path(self):

mock_from_pretrained.assert_called_once_with("./custom_model")
mock_model_bridge.load_weights_hf_to_megatron.assert_called_once_with(
mock_megatron_model, mock_loaded_model
mock_loaded_model,
mock_megatron_model,
)

def test_load_hf_weights_no_path_config_only(self):
Expand Down
Loading