
    sg
                       d dl mZ d dlZd dlmZ d dlmZmZmZ d dl	Z
ddlmZ e G d de             Ze G d	 d
e             Ze G d de             Ze G d de             Ze G d de             Ze G d de             Ze G d de             Ze G d de             Ze G d de             Ze G d de             Ze G d de             Ze G d de             Ze G d d e             Ze G d! d"e             Ze G d# d$e             Ze G d% d&e             Ze G d' d(e             Ze G d) d*e             Ze G d+ d,e             Ze G d- d.e             Z e G d/ d0e             Z!e G d1 d2e             Z"e G d3 d4e             Z#e G d5 d6e             Z$e G d7 d8e             Z%e G d9 d:e             Z&e G d; d<e             Z'y)=    )annotationsN)	dataclass)ListOptionalTuple   )ModelOutputc                  <    e Zd ZU dZdZded<   dZded<   dZded<   y)TFBaseModelOutputai  
    Base class for model's outputs, with potential hidden states and attentions.

    Args:
        last_hidden_state (`tf.Tensor` 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(tf.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) 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(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) 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.
    N	tf.Tensorlast_hidden_stateTuple[tf.Tensor] | Nonehidden_states
attentions)__name__
__module____qualname____doc__r   __annotations__r   r        S/var/www/html/venv/lib/python3.12/site-packages/transformers/modeling_tf_outputs.pyr   r      s*    & $(y'-1M*1*.J'.r   r   c                  .    e Zd ZU dZdZded<   dZded<   y) TFBaseModelOutputWithNoAttentiona  
    Base class for model's outputs, with potential hidden states.

    Args:
        last_hidden_state (`tf.Tensor` shape `(batch_size, num_channels, height, width)`):
            Sequence of hidden-states at the output of the last layer of the model.
        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings, if the model has an embedding layer, + one for
            the output of each layer) of shape `(batch_size, num_channels, height, width)`.

            Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
    Nr   r   Optional[Tuple[tf.Tensor, ...]]r   )r   r   r   r   r   r   r   r   r   r   r   r   4   s     $(y'59M29r   r   c                  J    e Zd ZU dZdZded<   dZded<   dZded<   dZded<   y)	TFBaseModelOutputWithPoolinga  
    Base class for model's outputs that also contains a pooling of the last hidden states.

    Args:
        last_hidden_state (`tf.Tensor` of shape `(batch_size, sequence_length, hidden_size)`):
            Sequence of hidden-states at the output of the last layer of the model.
        pooler_output (`tf.Tensor` of shape `(batch_size, hidden_size)`):
            Last layer hidden-state of the first token of the sequence (classification token) further processed by a
            Linear layer and a Tanh activation function. The Linear layer weights are trained from the next sentence
            prediction (classification) objective during pretraining.

            This output is usually *not* a good summary of the semantic content of the input, you're often better with
            averaging or pooling the sequence of hidden-states for the whole input sequence.
        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) 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(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) 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.
    Nr   r   pooler_outputr   r   r   )	r   r   r   r   r   r   r   r   r   r   r   r   r   r   G   s4    4 $(y'#M9#-1M*1*.J'.r   r   c                  <    e Zd ZU dZdZded<   dZded<   dZded<   y)*TFBaseModelOutputWithPoolingAndNoAttentiona  
    Base class for model's outputs that also contains a pooling of the last hidden states.

    Args:
        last_hidden_state (`tf.Tensor` of shape `(batch_size, num_channels, height, width)`):
            Sequence of hidden-states at the output of the last layer of the model.
        pooler_output (`tf.Tensor` of shape `(batch_size, hidden_size)`):
            Last layer hidden-state after a pooling operation on the spatial dimensions.
        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings, if the model has an embedding layer, + one for
            the output of each layer) of shape `(batch_size, num_channels, height, width)`.

            Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
    Nr   r   r   r   r   )r   r   r   r   r   r   r   r   r   r   r   r    r    i   s)     $(y'#M9#59M29r   r    c                  f    e Zd ZU dZdZded<   dZded<   dZded<   dZded	<   dZ	ded
<   dZ
ded<   y).TFBaseModelOutputWithPoolingAndCrossAttentionsao
  
    Base class for model's outputs that also contains a pooling of the last hidden states.

    Args:
        last_hidden_state (`tf.Tensor` of shape `(batch_size, sequence_length, hidden_size)`):
            Sequence of hidden-states at the output of the last layer of the model.
        pooler_output (`tf.Tensor` of shape `(batch_size, hidden_size)`):
            Last layer hidden-state of the first token of the sequence (classification token) further processed by a
            Linear layer and a Tanh activation function. The Linear layer weights are trained from the next sentence
            prediction (classification) objective during pretraining.

            This output is usually *not* a good summary of the semantic content of the input, you're often better with
            averaging or pooling the sequence of hidden-states for the whole input sequence.
        past_key_values (`List[tf.Tensor]`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
            List of `tf.Tensor` of length `config.n_layers`, with each tensor of shape `(2, batch_size, num_heads,
            sequence_length, embed_size_per_head)`).

            Contains pre-computed hidden-states (key and values in the attention blocks) that can be used (see
            `past_key_values` input) to speed up sequential decoding.
        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) 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(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) 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.
        cross_attentions (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
            sequence_length)`.

            Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the
            weighted average in the cross-attention heads.
    Nr   r   r   List[tf.Tensor] | Nonepast_key_valuesr   r   r   cross_attentions)r   r   r   r   r   r   r   r$   r   r   r%   r   r   r   r"   r"      sL    $L $(y'#M9#.2O+2-1M*1*.J'.04-4r   r"   c                  J    e Zd ZU dZdZded<   dZded<   dZded<   dZded	<   y)
TFBaseModelOutputWithPasta  
    Base class for model's outputs that may also contain a past key/values (to speed up sequential decoding).

    Args:
        last_hidden_state (`tf.Tensor` of shape `(batch_size, sequence_length, hidden_size)`):
            Sequence of hidden-states at the output of the last layer of the model.

            If `past_key_values` is used only the last hidden-state of the sequences of shape `(batch_size, 1,
            hidden_size)` is output.
        past_key_values (`List[tf.Tensor]`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
            List of `tf.Tensor` of length `config.n_layers`, with each tensor of shape `(2, batch_size, num_heads,
            sequence_length, embed_size_per_head)`).

            Contains pre-computed hidden-states (key and values in the attention blocks) that can be used (see
            `past_key_values` input) to speed up sequential decoding.
        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) 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(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) 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.
    Nr   r   r#   r$   r   r   r   )	r   r   r   r   r   r   r$   r   r   r   r   r   r'   r'      s5    8 $(y'.2O+2-1M*1*.J'.r   r'   c                  J    e Zd ZU dZdZded<   dZded<   dZded<   dZded<   y)	$TFBaseModelOutputWithCrossAttentionsa:  
    Base class for model's outputs, with potential hidden states and attentions.

    Args:
        last_hidden_state (`tf.Tensor` 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(tf.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) 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(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) 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.
        cross_attentions (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
            sequence_length)`.

            Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the
            weighted average in the cross-attention heads.
    Nr   r   r   r   r   r%   )	r   r   r   r   r   r   r   r   r%   r   r   r   r)   r)      s6    2 $(y'-1M*1*.J'.04-4r   r)   c                  X    e Zd ZU dZdZded<   dZded<   dZded<   dZded	<   dZ	ded
<   y)+TFBaseModelOutputWithPastAndCrossAttentionsa  
    Base class for model's outputs that may also contain a past key/values (to speed up sequential decoding).

    Args:
        last_hidden_state (`tf.Tensor` of shape `(batch_size, sequence_length, hidden_size)`):
            Sequence of hidden-states at the output of the last layer of the model.

            If `past_key_values` is used only the last hidden-state of the sequences of shape `(batch_size, 1,
            hidden_size)` is output.
        past_key_values (`List[tf.Tensor]`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
            List of `tf.Tensor` of length `config.n_layers`, with each tensor of shape `(2, batch_size, num_heads,
            sequence_length, embed_size_per_head)`).

            Contains pre-computed hidden-states (key and values in the attention blocks) that can be used (see
            `past_key_values` input) to speed up sequential decoding.
        hidden_states (`tuple(tf.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) 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(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) 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.
        cross_attentions (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
            sequence_length)`.

            Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the
            weighted average in the cross-attention heads.
    Nr   r   r#   r$   r   r   r   r%   )
r   r   r   r   r   r   r$   r   r   r%   r   r   r   r+   r+      sB     D $(y'.2O+2-1M*1*.J'.04-4r   r+   c                      e Zd ZU dZdZded<   dZded<   dZded<   dZded	<   dZ	ded
<   dZ
ded<   dZded<   dZded<   y)TFSeq2SeqModelOutputah  
    Base class for model encoder's outputs that also contains : pre-computed hidden states that can speed up sequential
    decoding.

    Args:
        last_hidden_state (`tf.Tensor` of shape `(batch_size, sequence_length, hidden_size)`):
            Sequence of hidden-states at the output of the last layer of the decoder of the model.

            If `past_key_values` is used only the last hidden-state of the sequences of shape `(batch_size, 1,
            hidden_size)` is output.
        past_key_values (`List[tf.Tensor]`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
            List of `tf.Tensor` of length `config.n_layers`, with each tensor of shape `(2, batch_size, num_heads,
            sequence_length, embed_size_per_head)`).

            Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be
            used (see `past_key_values` input) to speed up sequential decoding.
        decoder_hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape
            `(batch_size, sequence_length, hidden_size)`.

            Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
        decoder_attentions (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
            sequence_length)`.

            Attentions weights of the decoder, after the attention softmax, used to compute the weighted average in the
            self-attention heads.
        cross_attentions (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
            sequence_length)`.

            Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the
            weighted average in the cross-attention heads.
        encoder_last_hidden_state (`tf.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
            Sequence of hidden-states at the output of the last layer of the encoder of the model.
        encoder_hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape
            `(batch_size, sequence_length, hidden_size)`.

            Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
        encoder_attentions (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
            sequence_length)`.

            Attentions weights of the encoder, after the attention softmax, used to compute the weighted average in the
            self-attention heads.
    Nr   r   r#   r$   r   decoder_hidden_statesdecoder_attentionsr%   tf.Tensor | Noneencoder_last_hidden_stateencoder_hidden_statesencoder_attentions)r   r   r   r   r   r   r$   r.   r/   r%   r1   r2   r3   r   r   r   r-   r-     sh    .` $(y'.2O+2592926/604-426/6592926/6r   r-   c                  J    e Zd ZU dZdZded<   dZded<   dZded<   dZded	<   y)
TFCausalLMOutputa7  
    Base class for causal language model (or autoregressive) outputs.

    Args:
        loss (`tf.Tensor` of shape `(n,)`, *optional*, where n is the number of non-masked labels, returned when `labels` is provided):
            Language modeling loss (for next-token prediction).
        logits (`tf.Tensor` of shape `(batch_size, sequence_length, config.vocab_size)`):
            Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) 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(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) 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.
    Nr0   lossr   logitsr   r   r   	r   r   r   r   r6   r   r7   r   r   r   r   r   r5   r5   [  4    * "D
!FI-1M*1*.J'.r   r5   c                  X    e Zd ZU dZdZded<   dZded<   dZded<   dZd	ed
<   dZ	d	ed<   y)TFCausalLMOutputWithPasta  
    Base class for causal language model (or autoregressive) outputs.

    Args:
        loss (`tf.Tensor` of shape `(n,)`, *optional*, where n is the number of non-masked labels, returned when `labels` is provided):
            Language modeling loss (for next-token prediction).
        logits (`tf.Tensor` of shape `(batch_size, sequence_length, config.vocab_size)`):
            Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
        past_key_values (`List[tf.Tensor]`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
            List of `tf.Tensor` of length `config.n_layers`, with each tensor of shape `(2, batch_size, num_heads,
            sequence_length, embed_size_per_head)`).

            Contains pre-computed hidden-states (key and values in the attention blocks) that can be used (see
            `past_key_values` input) to speed up sequential decoding.
        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) 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(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) 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.
    Nr0   r6   r   r7   r#   r$   r   r   r   
r   r   r   r   r6   r   r7   r$   r   r   r   r   r   r;   r;   x  ?    6 "D
!FI.2O+2-1M*1*.J'.r   r;   c                  f    e Zd ZU dZdZded<   dZded<   dZded<   dZd	ed
<   dZ	d	ed<   dZ
d	ed<   y)#TFCausalLMOutputWithCrossAttentionsa  
    Base class for causal language model (or autoregressive) outputs.

    Args:
        loss (`tf.Tensor` of shape `(n,)`, *optional*, where n is the number of non-masked labels, returned when `labels` is provided):
            Language modeling loss (for next-token prediction).
        logits (`tf.Tensor` of shape `(batch_size, sequence_length, config.vocab_size)`):
            Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) 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(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) 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.
        cross_attentions (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
            sequence_length)`.

            Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the
            weighted average in the cross-attention heads.
        past_key_values (`List[tf.Tensor]`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
            List of `tf.Tensor` of length `config.n_layers`, with each tensor of shape `(2, batch_size, num_heads,
            sequence_length, embed_size_per_head)`).

            Contains pre-computed hidden-states (key and values in the attention blocks) that can be used (see
            `past_key_values` input) to speed up sequential decoding.
    Nr0   r6   r   r7   r#   r$   r   r   r   r%   )r   r   r   r   r6   r   r7   r$   r   r   r%   r   r   r   r?   r?     sL    B "D
!FI.2O+2-1M*1*.J'.04-4r   r?   c                  J    e Zd ZU dZdZded<   dZded<   dZded<   dZded	<   y)
TFMaskedLMOutputa  
    Base class for masked language models outputs.

    Args:
        loss (`tf.Tensor` of shape `(n,)`, *optional*, where n is the number of non-masked labels, returned when `labels` is provided):
            Masked language modeling (MLM) loss.
        logits (`tf.Tensor` of shape `(batch_size, sequence_length, config.vocab_size)`):
            Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) 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(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) 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.
    Nr0   r6   r   r7   r   r   r   r8   r   r   r   rA   rA     r9   r   rA   c                      e Zd ZU dZdZded<   dZded<   dZded<   dZd	ed
<   dZ	d	ed<   dZ
d	ed<   dZded<   dZd	ed<   dZd	ed<   y)TFSeq2SeqLMOutputaA  
    Base class for sequence-to-sequence language models outputs.

    Args:
        loss (`tf.Tensor` of shape `(n,)`, *optional*, where n is the number of non-masked labels, returned when `labels` is provided):
            Language modeling loss.
        logits (`tf.Tensor` of shape `(batch_size, sequence_length, config.vocab_size)`):
            Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
        past_key_values (`List[tf.Tensor]`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
            List of `tf.Tensor` of length `config.n_layers`, with each tensor of shape `(2, batch_size, num_heads,
            sequence_length, embed_size_per_head)`).

            Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be
            used (see `past_key_values` input) to speed up sequential decoding.
        decoder_hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape
            `(batch_size, sequence_length, hidden_size)`.

            Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
        decoder_attentions (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
            sequence_length)`.

            Attentions weights of the decoder, after the attention softmax, used to compute the weighted average in the
            self-attention heads.
        cross_attentions (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
            sequence_length)`.

            Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the
            weighted average in the cross-attention heads.
        encoder_last_hidden_state (`tf.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
            Sequence of hidden-states at the output of the last layer of the encoder of the model.
        encoder_hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape
            `(batch_size, sequence_length, hidden_size)`.

            Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
        encoder_attentions (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
            sequence_length)`.

            Attentions weights of the encoder, after the attention softmax, used to compute the weighted average in the
            self-attention heads.
    Nr0   r6   r   r7   r#   r$   r   r.   r/   r%   r1   r2   r3   r   r   r   r   r6   r   r7   r$   r.   r/   r%   r1   r2   r3   r   r   r   rC   rC     sr    ,\ "D
!FI.2O+2592926/604-426/6592926/6r   rC   c                  J    e Zd ZU dZdZded<   dZded<   dZded<   dZded	<   y)
TFNextSentencePredictorOutputaF  
    Base class for outputs of models predicting if two sentences are consecutive or not.

    Args:
        loss (`tf.Tensor` of shape `(n,)`, *optional*, where n is the number of non-masked labels, returned when `next_sentence_label` is provided):
            Next sentence prediction loss.
        logits (`tf.Tensor` of shape `(batch_size, 2)`):
            Prediction scores of the next sequence prediction (classification) head (scores of True/False continuation
            before SoftMax).
        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) 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(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) 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.
    Nr0   r6   r   r7   r   r   r   r8   r   r   r   rF   rF     s4    , "D
!FI-1M*1*.J'.r   rF   c                  J    e Zd ZU dZdZded<   dZded<   dZded<   dZded	<   y)
TFSequenceClassifierOutputa  
    Base class for outputs of sentence classification models.

    Args:
        loss (`tf.Tensor` of shape `(batch_size, )`, *optional*, returned when `labels` is provided):
            Classification (or regression if config.num_labels==1) loss.
        logits (`tf.Tensor` of shape `(batch_size, config.num_labels)`):
            Classification (or regression if config.num_labels==1) scores (before SoftMax).
        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) 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(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) 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.
    Nr0   r6   r   r7   r   r   r   r8   r   r   r   rH   rH   =  r9   r   rH   c                      e Zd ZU dZdZded<   dZded<   dZded<   dZd	ed
<   dZ	d	ed<   dZ
d	ed<   dZded<   dZd	ed<   dZd	ed<   y)!TFSeq2SeqSequenceClassifierOutputar  
    Base class for outputs of sequence-to-sequence sentence classification models.

    Args:
        loss (`tf.Tensor` of shape `(1,)`, *optional*, returned when `label` is provided):
            Classification (or regression if config.num_labels==1) loss.
        logits (`tf.Tensor` of shape `(batch_size, config.num_labels)`):
            Classification (or regression if config.num_labels==1) scores (before SoftMax).
        past_key_values (`List[tf.Tensor]`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
            List of `tf.Tensor` of length `config.n_layers`, with each tensor of shape `(2, batch_size, num_heads,
            sequence_length, embed_size_per_head)`).

            Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be
            used (see `past_key_values` input) to speed up sequential decoding.
        decoder_hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape
            `(batch_size, sequence_length, hidden_size)`.

            Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
        decoder_attentions (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
            sequence_length)`.

            Attentions weights of the decoder, after the attention softmax, used to compute the weighted average in the
            self-attention heads.
        cross_attentions (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
            sequence_length)`
        encoder_last_hidden_state (`tf.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
            Sequence of hidden-states at the output of the last layer of the encoder of the model.
        encoder_hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape
            `(batch_size, sequence_length, hidden_size)`.

            Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
        encoder_attentions (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
            sequence_length)`.

            Attentions weights of the encoder, after the attention softmax, used to compute the weighted average in the
            self-attention heads.
    Nr0   r6   r   r7   r#   r$   r   r.   r/   r%   r1   r2   r3   rD   r   r   r   rJ   rJ   Z  sr    )V "D
!FI.2O+2592926/604-426/6592926/6r   rJ   c                  J    e Zd ZU dZdZded<   dZded<   dZded<   dZded	<   y)
TFSemanticSegmenterOutputa  
    Base class for outputs of semantic segmentation models.

    Args:
        loss (`tf.Tensor` of shape `(1,)`, *optional*, returned when `labels` is provided):
            Classification (or regression if config.num_labels==1) loss.
        logits (`tf.Tensor` of shape `(batch_size, config.num_labels, logits_height, logits_width)`):
            Classification scores for each pixel.

            <Tip warning={true}>

            The logits returned do not necessarily have the same size as the `pixel_values` passed as inputs. This is
            to avoid doing two interpolations and lose some quality when a user needs to resize the logits to the
            original image size as post-processing. You should always check your logits shape and resize as needed.

            </Tip>

        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings, if the model has an embedding layer, + one for
            the output of each layer) of shape `(batch_size, patch_size, hidden_size)`.

            Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
        attentions (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, patch_size, sequence_length)`.

            Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
            heads.
    Nr0   r6   r   r7   r   r   r   r8   r   r   r   rL   rL     s4    : "D
!FI-1M*1*.J'.r   rL   c                  <    e Zd ZU dZdZded<   dZded<   dZded<   y)	(TFSemanticSegmenterOutputWithNoAttentiona  
    Base class for outputs of semantic segmentation models that do not output attention scores.

    Args:
        loss (`tf.Tensor` of shape `(1,)`, *optional*, returned when `labels` is provided):
            Classification (or regression if config.num_labels==1) loss.
        logits (`tf.Tensor` of shape `(batch_size, config.num_labels, logits_height, logits_width)`):
            Classification scores for each pixel.

            <Tip warning={true}>

            The logits returned do not necessarily have the same size as the `pixel_values` passed as inputs. This is
            to avoid doing two interpolations and lose some quality when a user needs to resize the logits to the
            original image size as post-processing. You should always check your logits shape and resize as needed.

            </Tip>

        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings, if the model has an embedding layer, + one for
            the output of each layer) of shape `(batch_size, patch_size, hidden_size)`.

            Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
    Nr0   r6   r   r7   r   r   r   r   r   r   r6   r   r7   r   r   r   r   rN   rN     s)    0 "D
!FI-1M*1r   rN   c                  J    e Zd ZU dZdZded<   dZded<   dZded<   dZded	<   y)
TFImageClassifierOutputa  
    Base class for outputs of image classification models.

    Args:
        loss (`tf.Tensor` of shape `(1,)`, *optional*, returned when `labels` is provided):
            Classification (or regression if config.num_labels==1) loss.
        logits (`tf.Tensor` of shape `(batch_size, config.num_labels)`):
            Classification (or regression if config.num_labels==1) scores (before SoftMax).
        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings, if the model has an embedding layer, + one for
            the output of each stage) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states (also called
            feature maps) of the model at the output of each stage.
        attentions (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, patch_size, sequence_length)`.

            Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
            heads.
    Nr0   r6   r   r7   r   r   r   r8   r   r   r   rQ   rQ     s4    & "D
!FI-1M*1*.J'.r   rQ   c                  J    e Zd ZU dZdZded<   dZded<   dZded<   dZded	<   y)
TFMultipleChoiceModelOutputa  
    Base class for outputs of multiple choice models.

    Args:
        loss (`tf.Tensor` of shape *(batch_size, )*, *optional*, returned when `labels` is provided):
            Classification loss.
        logits (`tf.Tensor` of shape `(batch_size, num_choices)`):
            *num_choices* is the second dimension of the input tensors. (see *input_ids* above).

            Classification scores (before SoftMax).
        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) 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(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) 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.
    Nr0   r6   r   r7   r   r   r   r8   r   r   r   rS   rS     s4    . "D
!FI-1M*1*.J'.r   rS   c                  J    e Zd ZU dZdZded<   dZded<   dZded<   dZded	<   y)
TFTokenClassifierOutputa  
    Base class for outputs of token classification models.

    Args:
        loss (`tf.Tensor` of shape `(n,)`, *optional*, where n is the number of unmasked labels, returned when `labels` is provided) :
            Classification loss.
        logits (`tf.Tensor` of shape `(batch_size, sequence_length, config.num_labels)`):
            Classification scores (before SoftMax).
        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) 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(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) 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.
    Nr0   r6   r   r7   r   r   r   r8   r   r   r   rU   rU     r9   r   rU   c                  X    e Zd ZU dZdZded<   dZded<   dZded<   dZded	<   dZ	ded
<   y)TFQuestionAnsweringModelOutputay  
    Base class for outputs of question answering models.

    Args:
        loss (`tf.Tensor` of shape `(batch_size, )`, *optional*, returned when `start_positions` and `end_positions` are provided):
            Total span extraction loss is the sum of a Cross-Entropy for the start and end positions.
        start_logits (`tf.Tensor` of shape `(batch_size, sequence_length)`):
            Span-start scores (before SoftMax).
        end_logits (`tf.Tensor` of shape `(batch_size, sequence_length)`):
            Span-end scores (before SoftMax).
        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) 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(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) 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.
    Nr0   r6   r   start_logits
end_logitsr   r   r   )
r   r   r   r   r6   r   rX   rY   r   r   r   r   r   rW   rW   -  s>    . "D
!"L)" J	 -1M*1*.J'.r   rW   c                      e Zd ZU dZdZded<   dZded<   dZded<   dZded	<   dZ	d
ed<   dZ
d
ed<   dZded<   dZd
ed<   dZd
ed<   y)%TFSeq2SeqQuestionAnsweringModelOutputa  
    Base class for outputs of sequence-to-sequence question answering models.

    Args:
        loss (`tf.Tensor` of shape `(1,)`, *optional*, returned when `labels` is provided):
            Total span extraction loss is the sum of a Cross-Entropy for the start and end positions.
        start_logits (`tf.Tensor` of shape `(batch_size, sequence_length)`):
            Span-start scores (before SoftMax).
        end_logits (`tf.Tensor` of shape `(batch_size, sequence_length)`):
            Span-end scores (before SoftMax).
        past_key_values (`List[tf.Tensor]`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
            List of `tf.Tensor` of length `config.n_layers`, with each tensor of shape `(2, batch_size, num_heads,
            sequence_length, embed_size_per_head)`).

            Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be
            used (see `past_key_values` input) to speed up sequential decoding.
        decoder_hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape
            `(batch_size, sequence_length, hidden_size)`.

            Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
        decoder_attentions (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
            sequence_length)`.

            Attentions weights of the decoder, after the attention softmax, used to compute the weighted average in the
            self-attention heads.
        encoder_last_hidden_state (`tf.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
            Sequence of hidden-states at the output of the last layer of the encoder of the model.
        encoder_hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape
            `(batch_size, sequence_length, hidden_size)`.

            Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
        encoder_attentions (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
            sequence_length)`.

            Attentions weights of the encoder, after the attention softmax, used to compute the weighted average in the
            self-attention heads.
    Nr0   r6   r   rX   rY   r#   r$   r   r.   r/   r1   r2   r3   )r   r   r   r   r6   r   rX   rY   r$   r.   r/   r1   r2   r3   r   r   r   r[   r[   M  sp    (T "D
!"L)" J	 .2O+2592926/626/6592926/6r   r[   c                  X    e Zd ZU dZdZded<   dZded<   dZded<   dZd	ed
<   dZ	d	ed<   y)"TFSequenceClassifierOutputWithPasta  
    Base class for outputs of sentence classification models.

    Args:
        loss (`tf.Tensor` of shape `(batch_size, )`, *optional*, returned when `labels` is provided):
            Classification (or regression if config.num_labels==1) loss.
        logits (`tf.Tensor` of shape `(batch_size, config.num_labels)`):
            Classification (or regression if config.num_labels==1) scores (before SoftMax).
        past_key_values (`List[tf.Tensor]`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
            List of `tf.Tensor` of length `config.n_layers`, with each tensor of shape `(2, batch_size, num_heads,
            sequence_length, embed_size_per_head)`).

            Contains pre-computed hidden-states (key and values in the attention blocks) that can be used (see
            `past_key_values` input) to speed up sequential decoding.
        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) 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(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) 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.
    Nr0   r6   r   r7   r#   r$   r   r   r   r<   r   r   r   r]   r]     r=   r   r]   c                  <    e Zd ZU dZdZded<   dZded<   dZded<   y)	&TFImageClassifierOutputWithNoAttentiona_  
    Base class for outputs of image classification models.

    Args:
        loss (`tf.Tensor` of shape `(1,)`, *optional*, returned when `labels` is provided):
            Classification (or regression if config.num_labels==1) loss.
        logits (`tf.Tensor` of shape `(batch_size, config.num_labels)`):
            Classification (or regression if config.num_labels==1) scores (before SoftMax).
        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings, if the model has an embedding layer, + one for
            the output of each stage) of shape `(batch_size, num_channels, height, width)`. Hidden-states (also called
            feature maps) of the model at the output of each stage.
    Nr0   r6   r   r7   r   r   rO   r   r   r   r_   r_     s)     "D
!FI59M29r   r_   c                  Z    e Zd ZU dZdZded<   dZded<   dZded<   dZded	<   e	d
        Z
y)TFMaskedImageModelingOutputa  
    Base class for outputs of masked image completion / in-painting models.

    Args:
        loss (`tf.Tensor` of shape `(1,)`, *optional*, returned when `bool_masked_pos` is provided):
            Reconstruction loss.
        reconstruction (`tf.Tensor` of shape `(batch_size, num_channels, height, width)`):
           Reconstructed / completed images.
        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when
        `config.output_hidden_states=True`):
            Tuple of `tf.Tensor` (one for the output of the embeddings, if the model has an embedding layer, + one for
            the output of each stage) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states (also called
            feature maps) of the model at the output of each stage.
        attentions (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when
        `config.output_attentions=True`):
            Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, patch_size, sequence_length)`.
            Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
            heads.
    Nr0   r6   r   reconstructionr   r   r   c                N    t        j                  dt               | j                  S )Nzlogits attribute is deprecated and will be removed in version 5 of Transformers. Please use the reconstruction attribute to retrieve the final output instead.)warningswarnFutureWarningrb   )selfs    r   r7   z"TFMaskedImageModelingOutput.logits  s%    ]	

 """r   )r   r   r   r   r6   r   rb   r   r   propertyr7   r   r   r   ra   ra     sF    ( "D
! $NI$-1M*1*.J'.# #r   ra   )(
__future__r   rd   dataclassesr   typingr   r   r   
tensorflowtfutilsr	   r   r   r   r    r"   r'   r)   r+   r-   r5   r;   r?   rA   rC   rF   rH   rJ   rL   rN   rQ   rS   rU   rW   r[   r]   r_   ra   r   r   r   <module>ro      s   #  ! ( (   / / /2 :{ : :$ /; / /B : : :* ,5[ ,5 ,5^  /  /  /F 5; 5 5@ '5+ '5 '5T 87; 87 87v /{ / /8  /{  /  /F '5+ '5 '5T /{ / /8 77 77 77t /K / /: / / /8 47 47 47n !/ !/ !/H 2{ 2 2< /k / /4 /+ / /< /k / /8 /[ / /> 37K 37 37l  /  /  /F :[ : :( !#+ !# !#r   