`iF dZddlZddlmZddlmZmZddlZddlmZddl m Z ddl m Z dd l mZdd lmZmZdd lmZmZmZmZmZmZmZmZmZdd lmZd dlmZer ddl m!Z!m"Z"ndZ"dZ!ej#e$Z%dZ&dZ'gdZ(dZ)dZ*eGddeZ+eGddeZ,eGddeZ-Gddej.Z/Gddej.Z0Gd d!ej.Z1dId$ej2d%e3d&e4d'ej2fd(Z5Gd)d*ej.Z6Gd+d,ej.Z7Gd-d.ej.Z8Gd/d0ej.Z9Gd1d2ej.Z:Gd3d4ej.Z;Gd5d6ej.Z<Gd7d8ej.Z=Gd9d:ej.Z>Gd;dZAed?e@Gd@dAe?ZBedBe@GdCdDe?ZCedEe@GdFdGe?eZDgdHZEdS)Jz1PyTorch Neighborhood Attention Transformer model.N) dataclass)OptionalUnion)nn)ACT2FN)BackboneOutput)PreTrainedModel) find_pruneable_heads_and_indicesprune_linear_layer) ModelOutputOptionalDependencyNotAvailableadd_code_sample_docstringsadd_start_docstrings%add_start_docstrings_to_model_forwardis_natten_availableloggingreplace_return_docstringsrequires_backends) BackboneMixin) NatConfig) natten2dav natten2dqkrpbctNrargskwargss /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/deprecated/nat/modeling_nat.pyrr/,...ctrrrs r!rr2r"r#rzshi-labs/nat-mini-in1k-224)rr%iz tiger catceZdZUdZdZeejed<dZ ee ejdfed<dZ ee ejdfed<dZ ee ejdfed<dS)NatEncoderOutputa Nat encoder's outputs, with potential hidden states and attentions. Args: last_hidden_state (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`): Sequence of hidden-states at the output of the last layer of the model. hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `torch.FloatTensor` (one for the output of the embeddings + one for the output of each stage) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the initial embedding outputs. attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `torch.FloatTensor` (one for each stage) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. reshaped_hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `torch.FloatTensor` (one for the output of the embeddings + one for the output of each stage) of shape `(batch_size, hidden_size, height, width)`. Hidden-states of the model at the output of each layer plus the initial embedding outputs reshaped to include the spatial dimensions. Nlast_hidden_state. hidden_states attentionsreshaped_hidden_states) __name__ __module__ __qualname____doc__r(rtorch FloatTensor__annotations__r)tupler*r+r#r!r'r'Gs26:x 12999=AM8E%"3S"89:AAA:>Ju0#567>>>FJHU5+