bridge.models.nemotron_omni.modeling_nemotron_omni#

Module Contents#

Classes#

NemotronOmniModel

Extends NemotronVLModel with sound modality freeze support.

API#

class bridge.models.nemotron_omni.modeling_nemotron_omni.NemotronOmniModel#

Bases: megatron.bridge.models.nemotron_vl.modeling_nemotron_vl.NemotronVLModel

Extends NemotronVLModel with sound modality freeze support.

forward() is inherited from NemotronVLModel (which delegates to LLaVAModel), so sound kwargs (sound_clips, sound_length) pass through automatically when the vlm2 LLaVAModel is used.

freeze(
*,
freeze_language_model: bool = False,
freeze_vision_model: bool = False,
freeze_vision_projection: bool = False,
freeze_sound_model: bool = False,
freeze_sound_projection: bool = False,
) None#