voidful

/

phi4-audio-encoder

like 0

• "torch.distributed.algorithms._checkpoint.checkpoint_wrapper.ActivationWrapper",
• "torch.ao.quantization.stubs.DeQuantStub",
• "torch.nn.modules.conv.Conv2d",
• "transformers_modules.microsoft.Phi-4-multimodal-instruct.0af439b3adb8c23fda473c4f86001dbf9a226021.speech_conformer_encoder.ConvModule",
• "torch.ao.quantization.stubs.QuantStub",
• "torch.nn.modules.activation.ReLU",
• "torch.distributed.algorithms._checkpoint.checkpoint_wrapper.CheckpointImpl",
• "torch.nn.modules.container.ModuleDict",
• "transformers_modules.microsoft.Phi-4-multimodal-instruct.0af439b3adb8c23fda473c4f86001dbf9a226021.speech_conformer_encoder.GLU",
• "torch.nn.modules.linear.Identity",
• "torch.jit._script.Attribute",
• "transformers_modules.microsoft.Phi-4-multimodal-instruct.0af439b3adb8c23fda473c4f86001dbf9a226021.speech_conformer_encoder.DepthWiseSeperableConv1d",
• "typing.Union",
• "torch.nn.modules.activation.Sigmoid",
• "transformers_modules.microsoft.Phi-4-multimodal-instruct.0af439b3adb8c23fda473c4f86001dbf9a226021.speech_conformer_encoder.ConformerEncoderLayer",
• "transformers_modules.microsoft.Phi-4-multimodal-instruct.0af439b3adb8c23fda473c4f86001dbf9a226021.speech_conformer_encoder.ConformerEncoder",
• "transformers_modules.microsoft.Phi-4-multimodal-instruct.0af439b3adb8c23fda473c4f86001dbf9a226021.speech_conformer_encoder.MeanVarianceNormLayer",
• "transformers_modules.microsoft.Phi-4-multimodal-instruct.0af439b3adb8c23fda473c4f86001dbf9a226021.speech_conformer_encoder.T5RelativeAttentionLogitBias",
• "torch.nn.modules.conv.Conv1d",
• "transformers_modules.microsoft.Phi-4-multimodal-instruct.0af439b3adb8c23fda473c4f86001dbf9a226021.speech_conformer_encoder.NemoConvSubsampling",
• "transformers_modules.microsoft.Phi-4-multimodal-instruct.0af439b3adb8c23fda473c4f86001dbf9a226021.configuration_phi4mm.Phi4MMConfig",
• "torch.nn.modules.module._WrappedHook",
• "transformers_modules.microsoft.Phi-4-multimodal-instruct.0af439b3adb8c23fda473c4f86001dbf9a226021.speech_conformer_encoder.FeedForward",
• "transformers_modules.microsoft.Phi-4-multimodal-instruct.0af439b3adb8c23fda473c4f86001dbf9a226021.speech_conformer_encoder._pre_hook",
• "transformers_modules.microsoft.Phi-4-multimodal-instruct.0af439b3adb8c23fda473c4f86001dbf9a226021.speech_conformer_encoder.GLULinear",
• "torch.nn.modules.linear.Linear",
• "transformers_modules.microsoft.Phi-4-multimodal-instruct.0af439b3adb8c23fda473c4f86001dbf9a226021.modeling_phi4mm.Phi4MMAudioEmbedding",
• "transformers_modules.microsoft.Phi-4-multimodal-instruct.0af439b3adb8c23fda473c4f86001dbf9a226021.speech_conformer_encoder.Swish",
• "functools.partial",
• "torch.nn.modules.sparse.Embedding",
• "_operator.getitem",
• "__builtin__.getattr",
• "torch.nn.modules.container.Sequential",
• "torch._utils._rebuild_tensor_v2",
• "torch._utils._rebuild_parameter",
• "torch.FloatStorage",
• "transformers_modules.microsoft.Phi-4-multimodal-instruct.0af439b3adb8c23fda473c4f86001dbf9a226021.speech_conformer_encoder.AbsolutePositionalEncoding",
• "transformers_modules.microsoft.Phi-4-multimodal-instruct.0af439b3adb8c23fda473c4f86001dbf9a226021.speech_conformer_encoder.MultiHeadedAttention",
• "torch.nn.modules.activation.GELU",
• "transformers_modules.microsoft.Phi-4-multimodal-instruct.0af439b3adb8c23fda473c4f86001dbf9a226021.speech_conformer_encoder.GLUPointWiseConv",
• "__builtin__.set",
• "torch.Tensor",
• "__builtin__.type",
• "torch.utils.checkpoint.checkpoint",
• "torch.nn.modules.dropout.Dropout",
• "transformers_modules.microsoft.Phi-4-multimodal-instruct.0af439b3adb8c23fda473c4f86001dbf9a226021.speech_conformer_encoder.MultiSequential",
• "torch.ao.nn.quantized.modules.functional_modules.FloatFunctional",
• "torch.distributed.algorithms._checkpoint.checkpoint_wrapper.CheckpointWrapper",
• "torch.nn.modules.normalization.LayerNorm",
• "collections.OrderedDict"

How to fix it?