o  h٤@sddlmZmZmZddlZddlmZddlm Z ej j Gddde Z ej j Gddde Z ej j Gd d d e Zej j Gd d d e Zej j Gd dde Zej j Gddde Zej j Gddde Zej j Gddde Zej j Gddde Zej j Gddde Zej j Gddde ZeZej j Gddde Zej j Gddde Zej j Gdd d e Zej j Gd!d"d"e Zej j Gd#d$d$e Zej j Gd%d&d&e Zej j Gd'd(d(e Zej j Gd)d*d*e ZdS)+)DictOptionalTupleN) ModelOutputc@PeZdZUdZdZeejed<dZ ee ejed<dZ ee ejed<dS)FlaxBaseModelOutputan Base class for model's outputs, with potential hidden states and attentions. Args: last_hidden_state (`jnp.ndarray` 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(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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. Nlast_hidden_state hidden_states attentions) __name__ __module__ __qualname____doc__r rjnpndarray__annotations__r rr rrv/var/www/html/construction_image-detection-poc/venv/lib/python3.10/site-packages/transformers/modeling_flax_outputs.pyr rc@:eZdZUdZdZeejed<dZ ee ejed<dS)"FlaxBaseModelOutputWithNoAttentiona Base class for model's outputs, with potential hidden states. Args: last_hidden_state (`jnp.ndarray` of shape `(batch_size, num_channels, height, width)`): Sequence of hidden-states at the output of the last layer of the model. hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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 rrr rrrrr rrrrrr0s  rc@sLeZdZUdZdZeejed<dZ eejed<dZ ee ejed<dS),FlaxBaseModelOutputWithPoolingAndNoAttentiona Base class for model's outputs that also contains a pooling of the last hidden states. Args: last_hidden_state (`jnp.ndarray` of shape `(batch_size, num_channels, height, width)`): Sequence of hidden-states at the output of the last layer of the model. pooler_output (`jnp.ndarray` of shape `(batch_size, hidden_size)`): Last layer hidden-state after a pooling operation on the spatial dimensions. hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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 pooler_outputr ) r r rrr rrrrrr rrrrrrBs rc@r)(FlaxImageClassifierOutputWithNoAttentiona Base class for outputs of image classification models. Args: logits (`jnp.ndarray` of shape `(batch_size, config.num_labels)`): Classification (or regression if config.num_labels==1) scores (before SoftMax). hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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. Nlogitsr ) r r rrrrrrrr rrrrrrWs  rc@sjeZdZUdZdZeejed<dZ ee e ejfed<dZ ee ejed<dZee ejed<dS)FlaxBaseModelOutputWithPasta Base class for model's outputs, with potential hidden states and attentions. Args: last_hidden_state (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`): Sequence of hidden-states at the output of the last layer of the model. past_key_values (`Dict[str, jnp.ndarray]`): Dictionary of pre-computed hidden-states (key and values in the attention blocks) that can be used for fast auto-regressive decoding. Pre-computed key and value hidden-states are of shape *[batch_size, max_length]*. hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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 past_key_valuesr r )r r rrr rrrrrrstrr rr rrrrrjs rc@beZdZUdZdZeejed<dZ eejed<dZ ee ejed<dZ ee ejed<dS)FlaxBaseModelOutputWithPoolinga Base class for model's outputs that also contains a pooling of the last hidden states. Args: last_hidden_state (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`): Sequence of hidden-states at the output of the last layer of the model. pooler_output (`jnp.ndarray` 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. hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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 rr r ) r r rrr rrrrrr rr rrrrr s r c@seZdZUdZdZeejed<dZ eejed<dZ ee ejed<dZ ee e ejed<dZ ee ejed<dZee ejed<dS) 0FlaxBaseModelOutputWithPoolingAndCrossAttentionsa Base class for model's outputs that also contains a pooling of the last hidden states. Args: last_hidden_state (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`): Sequence of hidden-states at the output of the last layer of the model. pooler_output (`jnp.ndarray` of shape `(batch_size, hidden_size)`): Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining. hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the optional initial embedding outputs. attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` and `config.add_cross_attention=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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 (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`): Tuple of `tuple(jnp.ndarray)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and optionally if `config.is_encoder_decoder=True` 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`. Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if `config.is_encoder_decoder=True` in the cross-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. Nr rr rr cross_attentions)r r rrr rrrrrr rrr r"rrrrr!s 'r!c@eZdZUdZdZeejed<dZ ee e ejed<dZ ee ejed<dZ ee ejed<dZ ee ejed<dS)-FlaxBaseModelOutputWithPastAndCrossAttentionsa0 Base class for model's outputs that may also contain a past key/values (to speed up sequential decoding). Args: last_hidden_state (`jnp.ndarray` 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 (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`): Tuple of `tuple(jnp.ndarray)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and optionally if `config.is_encoder_decoder=True` 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`. Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if `config.is_encoder_decoder=True` in the cross-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` and `config.add_cross_attention=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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 rr r r")r r rrr rrrrrrr r r"rrrrr$s %r$c@eZdZUdZdZeejed<dZ ee e ejed<dZ ee ejed<dZ ee ejed<dZ ee ejed<dZeejed<dZee ejed <dZee ejed <dS) FlaxSeq2SeqModelOutputa/ Base class for model encoder's outputs that also contains : pre-computed hidden states that can speed up sequential decoding. Args: last_hidden_state (`jnp.ndarray` 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 (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`): Tuple of `tuple(jnp.ndarray)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`. Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. decoder_hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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 (`jnp.ndarray` 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(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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 rdecoder_hidden_statesdecoder_attentionsr"encoder_last_hidden_stateencoder_hidden_statesencoder_attentions)r r rrr rrrrrrr'r(r"r)r*r+rrrrr&s 1r&c@r#)%FlaxCausalLMOutputWithCrossAttentionsa Base class for causal language model (or autoregressive) outputs. Args: logits (`jnp.ndarray` 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(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Cross attentions weights after the attention softmax, used to compute the weighted average in the cross-attention heads. past_key_values (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`): Tuple of `jnp.ndarray` tuples of length `config.n_layers`, with each tuple containing the cached key, value states of the self-attention and the cross-attention layers if model is used in encoder-decoder setting. Only relevant if `config.is_decoder = True`. 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. Nrrr r r")r r rrrrrrrrrr r r"rrrrr,Cs  r,c@r)FlaxMaskedLMOutputaf Base class for masked language models outputs. Args: logits (`jnp.ndarray` 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(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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. Nrr r r r rrrrrrrr rr rrrrr-lrr-c@r%) FlaxSeq2SeqLMOutputa\ Base class for sequence-to-sequence language models outputs. Args: logits (`jnp.ndarray` 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 (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`): Tuple of `tuple(jnp.ndarray)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`. Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. decoder_hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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 (`jnp.ndarray` 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(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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. Nrrr'r(r"r)r*r+r r rrrrrrrrrr'r(r"r)r*r+rrrrr/ -r/c@r)FlaxNextSentencePredictorOutputa Base class for outputs of models predicting if two sentences are consecutive or not. Args: logits (`jnp.ndarray` of shape `(batch_size, 2)`): Prediction scores of the next sequence prediction (classification) head (scores of True/False continuation before SoftMax). hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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. Nrr r r.rrrrr2s r2c@r)FlaxSequenceClassifierOutputaM Base class for outputs of sentence classification models. Args: logits (`jnp.ndarray` of shape `(batch_size, config.num_labels)`): Classification (or regression if config.num_labels==1) scores (before SoftMax). hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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. Nrr r r.rrrrr3rr3c@r%) #FlaxSeq2SeqSequenceClassifierOutputaJ Base class for outputs of sequence-to-sequence sentence classification models. Args: logits (`jnp.ndarray` of shape `(batch_size, config.num_labels)`): Classification (or regression if config.num_labels==1) scores (before SoftMax). past_key_values (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`): Tuple of `tuple(jnp.ndarray)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`. Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. decoder_hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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 (`jnp.ndarray` 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(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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. Nrrr'r(r"r)r*r+r0rrrrr4r1r4c@r)FlaxMultipleChoiceModelOutputay Base class for outputs of multiple choice models. Args: logits (`jnp.ndarray` 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(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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. Nrr r r.rrrrr50s r5c@r)FlaxTokenClassifierOutputa3 Base class for outputs of token classification models. Args: logits (`jnp.ndarray` of shape `(batch_size, sequence_length, config.num_labels)`): Classification scores (before SoftMax). hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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. Nrr r r.rrrrr6Lrr6c@r) FlaxQuestionAnsweringModelOutputa Base class for outputs of question answering models. Args: start_logits (`jnp.ndarray` of shape `(batch_size, sequence_length)`): Span-start scores (before SoftMax). end_logits (`jnp.ndarray` of shape `(batch_size, sequence_length)`): Span-end scores (before SoftMax). hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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 start_logits end_logitsr r ) r r rrr8rrrrr9r rr rrrrr7fs r7c@seZdZUdZdZeejed<dZ eejed<dZ ee e ejed<dZ ee ejed<dZ ee ejed<dZee ejed<dZeejed <dZee ejed <dZee ejed <dS) 'FlaxSeq2SeqQuestionAnsweringModelOutputa Base class for outputs of sequence-to-sequence question answering models. Args: start_logits (`jnp.ndarray` of shape `(batch_size, sequence_length)`): Span-start scores (before SoftMax). end_logits (`jnp.ndarray` of shape `(batch_size, sequence_length)`): Span-end scores (before SoftMax). past_key_values (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`): Tuple of `tuple(jnp.ndarray)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`. Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. decoder_hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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 (`jnp.ndarray` 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(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `jnp.ndarray` (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. Nr8r9rr'r(r"r)r*r+)r r rrr8rrrrr9rrr'r(r"r)r*r+rrrrr:s /r:) typingrrrflax jax.numpynumpyrutilsrstruct dataclassrrrrrr r!r$r&r,r-FlaxCausalLMOutputr/r2r3r4r5r6r7r:rrrrsV   0-<(88