Hugging Face's logo

Transformers documentation

모델 출력

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v4.46.3).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

모델 출력

모든 모델에는 ModelOutput의 서브클래스의 인스턴스인 모델 출력이 있습니다. 이들은 모델에서 반환되는 모든 정보를 포함하는 데이터 구조이지만 튜플이나 딕셔너리로도 사용할 수 있습니다.

예제를 통해 살펴보겠습니다:

from transformers import BertTokenizer, BertForSequenceClassification
import torch

tokenizer = BertTokenizer.from_pretrained("google-bert/bert-base-uncased")
model = BertForSequenceClassification.from_pretrained("google-bert/bert-base-uncased")

inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
labels = torch.tensor([1]).unsqueeze(0)  # 배치 크기 1
outputs = model(**inputs, labels=labels)

outputs 객체는 SequenceClassifierOutput입니다. 아래 해당 클래스의 문서에서 볼 수 있듯이, loss(선택적), logits, hidden_states(선택적) 및 attentions(선택적) 항목이 있습니다. 여기에서는 labels를 전달했기 때문에 loss가 있지만 hidden_states와 attentions가 없는데, 이는 output_hidden_states=True 또는 output_attentions=True를 전달하지 않았기 때문입니다.

output_hidden_states=True를 전달할 때 outputs.hidden_states[-1]가 outputs.last_hidden_state와 정확히 일치할 것으로 예상할 수 있습니다. 하지만 항상 그런 것은 아닙니다. 일부 모델은 마지막 은닉 상태가 반환될 때 정규화를 적용하거나 다른 후속 프로세스를 적용합니다.

일반적으로 사용할 때와 동일하게 각 속성들에 접근할 수 있으며, 모델이 해당 속성을 반환하지 않은 경우 None이 반환됩니다. 예시에서는 outputs.loss는 모델에서 계산한 손실이고 outputs.attentions는 None입니다.

outputs 객체를 튜플로 간주할 때는 None 값이 없는 속성만 고려합니다. 예시에서는 loss와 logits라는 두 개의 요소가 있습니다. 그러므로,

outputs[:2]

는 (outputs.loss, outputs.logits) 튜플을 반환합니다.

outputs 객체를 딕셔너리로 간주할 때는 None 값이 없는 속성만 고려합니다. 예시에는 loss와 logits라는 두 개의 키가 있습니다.

여기서부터는 두 가지 이상의 모델 유형에서 사용되는 일반 모델 출력을 다룹니다. 구체적인 출력 유형은 해당 모델 페이지에 문서화되어 있습니다.

ModelOutput

class transformers.utils.ModelOutput

< >

( *args **kwargs )

Base class for all model outputs as dataclass. Has a __getitem__ that allows indexing by integer or slice (like a tuple) or strings (like a dictionary) that will ignore the None attributes. Otherwise behaves like a regular python dictionary.

You can’t unpack a ModelOutput directly. Use the to_tuple() method to convert it to a tuple before.

to_tuple

< >

( )

Convert self to a tuple containing all the attributes/keys that are not None.

BaseModelOutput

class transformers.modeling_outputs.BaseModelOutput

< >

( last_hidden_state: FloatTensor = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • 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, 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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.

Base class for model’s outputs, with potential hidden states and attentions.

BaseModelOutputWithPooling

class transformers.modeling_outputs.BaseModelOutputWithPooling

< >

( last_hidden_state: FloatTensor = None pooler_output: FloatTensor = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • 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.
  • pooler_output (torch.FloatTensor 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(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, 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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.

Base class for model’s outputs that also contains a pooling of the last hidden states.

BaseModelOutputWithCrossAttentions

class transformers.modeling_outputs.BaseModelOutputWithCrossAttentions

< >

( last_hidden_state: FloatTensor = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None cross_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • 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, 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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(torch.FloatTensor), optional, returned when output_attentions=True and config.add_cross_attention=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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.

Base class for model’s outputs, with potential hidden states and attentions.

BaseModelOutputWithPoolingAndCrossAttentions

class transformers.modeling_outputs.BaseModelOutputWithPoolingAndCrossAttentions

< >

( last_hidden_state: FloatTensor = None pooler_output: FloatTensor = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None cross_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • 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.
  • pooler_output (torch.FloatTensor 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(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, 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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(torch.FloatTensor), optional, returned when output_attentions=True and config.add_cross_attention=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — Tuple of tuple(torch.FloatTensor) 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.

Base class for model’s outputs that also contains a pooling of the last hidden states.

BaseModelOutputWithPast

class transformers.modeling_outputs.BaseModelOutputWithPast

< >

( last_hidden_state: FloatTensor = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • 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.

    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(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — Tuple of tuple(torch.FloatTensor) 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(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, 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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.

Base class for model’s outputs that may also contain a past key/values (to speed up sequential decoding).

BaseModelOutputWithPastAndCrossAttentions

class transformers.modeling_outputs.BaseModelOutputWithPastAndCrossAttentions

< >

( last_hidden_state: FloatTensor = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None cross_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • 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.

    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(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — Tuple of tuple(torch.FloatTensor) 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(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, 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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(torch.FloatTensor), optional, returned when output_attentions=True and config.add_cross_attention=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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.

Base class for model’s outputs that may also contain a past key/values (to speed up sequential decoding).

Seq2SeqModelOutput

class transformers.modeling_outputs.Seq2SeqModelOutput

< >

( last_hidden_state: FloatTensor = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None decoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None decoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None cross_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_last_hidden_state: typing.Optional[torch.FloatTensor] = None encoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • 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 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(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — Tuple of tuple(torch.FloatTensor) 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(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, 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 decoder at the output of each layer plus the optional initial embedding outputs.

  • decoder_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 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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 (torch.FloatTensor 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(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, 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 encoder at the output of each layer plus the optional initial embedding outputs.

  • encoder_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 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.

Base class for model encoder’s outputs that also contains : pre-computed hidden states that can speed up sequential decoding.

CausalLMOutput

class transformers.modeling_outputs.CausalLMOutput

< >

( loss: typing.Optional[torch.FloatTensor] = None logits: FloatTensor = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Language modeling loss (for next-token prediction).
  • logits (torch.FloatTensor 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(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, 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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.

Base class for causal language model (or autoregressive) outputs.

CausalLMOutputWithCrossAttentions

class transformers.modeling_outputs.CausalLMOutputWithCrossAttentions

< >

( loss: typing.Optional[torch.FloatTensor] = None logits: FloatTensor = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None cross_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Language modeling loss (for next-token prediction).
  • logits (torch.FloatTensor 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(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, 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — Tuple of torch.FloatTensor 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.

Base class for causal language model (or autoregressive) outputs.

CausalLMOutputWithPast

class transformers.modeling_outputs.CausalLMOutputWithPast

< >

( loss: typing.Optional[torch.FloatTensor] = None logits: FloatTensor = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Language modeling loss (for next-token prediction).
  • logits (torch.FloatTensor 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(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head))

    Contains pre-computed hidden-states (key and values in the self-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

  • 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, 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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.

Base class for causal language model (or autoregressive) outputs.

MaskedLMOutput

class transformers.modeling_outputs.MaskedLMOutput

< >

( loss: typing.Optional[torch.FloatTensor] = None logits: FloatTensor = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Masked language modeling (MLM) loss.
  • logits (torch.FloatTensor 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(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, 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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.

Base class for masked language models outputs.

Seq2SeqLMOutput

class transformers.modeling_outputs.Seq2SeqLMOutput

< >

( loss: typing.Optional[torch.FloatTensor] = None logits: FloatTensor = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None decoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None decoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None cross_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_last_hidden_state: typing.Optional[torch.FloatTensor] = None encoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Language modeling loss.
  • logits (torch.FloatTensor 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(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — Tuple of tuple(torch.FloatTensor) 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(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, 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 decoder at the output of each layer plus the initial embedding outputs.

  • decoder_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 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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 (torch.FloatTensor 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(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, 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 encoder at the output of each layer plus the initial embedding outputs.

  • encoder_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 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.

Base class for sequence-to-sequence language models outputs.

NextSentencePredictorOutput

class transformers.modeling_outputs.NextSentencePredictorOutput

< >

( loss: typing.Optional[torch.FloatTensor] = None logits: FloatTensor = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • loss (torch.FloatTensor of shape (1,), optional, returned when next_sentence_label is provided) — Next sequence prediction (classification) loss.
  • logits (torch.FloatTensor of shape (batch_size, 2)) — Prediction scores of the next sequence prediction (classification) head (scores of True/False continuation before SoftMax).
  • 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, 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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.

Base class for outputs of models predicting if two sentences are consecutive or not.

SequenceClassifierOutput

class transformers.modeling_outputs.SequenceClassifierOutput

< >

( loss: typing.Optional[torch.FloatTensor] = None logits: FloatTensor = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Classification (or regression if config.num_labels==1) loss.
  • logits (torch.FloatTensor of shape (batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax).
  • 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, 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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.

Base class for outputs of sentence classification models.

Seq2SeqSequenceClassifierOutput

class transformers.modeling_outputs.Seq2SeqSequenceClassifierOutput

< >

( loss: typing.Optional[torch.FloatTensor] = None logits: FloatTensor = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None decoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None decoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None cross_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_last_hidden_state: typing.Optional[torch.FloatTensor] = None encoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • loss (torch.FloatTensor of shape (1,), optional, returned when label is provided) — Classification (or regression if config.num_labels==1) loss.
  • logits (torch.FloatTensor of shape (batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax).
  • past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — Tuple of tuple(torch.FloatTensor) 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(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, 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 decoder at the output of each layer plus the initial embedding outputs.

  • decoder_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 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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 (torch.FloatTensor 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(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, 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 encoder at the output of each layer plus the initial embedding outputs.

  • encoder_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 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.

Base class for outputs of sequence-to-sequence sentence classification models.

MultipleChoiceModelOutput

class transformers.modeling_outputs.MultipleChoiceModelOutput

< >

( loss: typing.Optional[torch.FloatTensor] = None logits: FloatTensor = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Classification loss.
  • logits (torch.FloatTensor 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(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, 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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.

Base class for outputs of multiple choice models.

TokenClassifierOutput

class transformers.modeling_outputs.TokenClassifierOutput

< >

( loss: typing.Optional[torch.FloatTensor] = None logits: FloatTensor = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Classification loss.
  • logits (torch.FloatTensor of shape (batch_size, sequence_length, config.num_labels)) — Classification scores (before SoftMax).
  • 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, 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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.

Base class for outputs of token classification models.

QuestionAnsweringModelOutput

class transformers.modeling_outputs.QuestionAnsweringModelOutput

< >

( loss: typing.Optional[torch.FloatTensor] = None start_logits: FloatTensor = None end_logits: FloatTensor = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • loss (torch.FloatTensor 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 (torch.FloatTensor of shape (batch_size, sequence_length)) — Span-start scores (before SoftMax).
  • end_logits (torch.FloatTensor of shape (batch_size, sequence_length)) — Span-end scores (before SoftMax).
  • 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, 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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.

Base class for outputs of question answering models.

Seq2SeqQuestionAnsweringModelOutput

class transformers.modeling_outputs.Seq2SeqQuestionAnsweringModelOutput

< >

( loss: typing.Optional[torch.FloatTensor] = None start_logits: FloatTensor = None end_logits: FloatTensor = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None decoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None decoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None cross_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_last_hidden_state: typing.Optional[torch.FloatTensor] = None encoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • loss (torch.FloatTensor 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 (torch.FloatTensor of shape (batch_size, sequence_length)) — Span-start scores (before SoftMax).
  • end_logits (torch.FloatTensor of shape (batch_size, sequence_length)) — Span-end scores (before SoftMax).
  • past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — Tuple of tuple(torch.FloatTensor) 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(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, 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 decoder at the output of each layer plus the initial embedding outputs.

  • decoder_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 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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 (torch.FloatTensor 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(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, 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 encoder at the output of each layer plus the initial embedding outputs.

  • encoder_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 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.

Base class for outputs of sequence-to-sequence question answering models.

Seq2SeqSpectrogramOutput

class transformers.modeling_outputs.Seq2SeqSpectrogramOutput

< >

( loss: typing.Optional[torch.FloatTensor] = None spectrogram: FloatTensor = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None decoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None decoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None cross_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_last_hidden_state: typing.Optional[torch.FloatTensor] = None encoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Spectrogram generation loss.
  • spectrogram (torch.FloatTensor of shape (batch_size, sequence_length, num_bins)) — The predicted spectrogram.
  • past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — Tuple of tuple(torch.FloatTensor) 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(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, 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 decoder at the output of each layer plus the initial embedding outputs.

  • decoder_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 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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 (torch.FloatTensor 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(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, 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 encoder at the output of each layer plus the initial embedding outputs.

  • encoder_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 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.

Base class for sequence-to-sequence spectrogram outputs.

SemanticSegmenterOutput

class transformers.modeling_outputs.SemanticSegmenterOutput

< >

( loss: typing.Optional[torch.FloatTensor] = None logits: FloatTensor = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Classification (or regression if config.num_labels==1) loss.
  • logits (torch.FloatTensor of shape (batch_size, config.num_labels, logits_height, logits_width)) — Classification scores for each pixel.

    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.
  • 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, 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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.

Base class for outputs of semantic segmentation models.

ImageClassifierOutput

class transformers.modeling_outputs.ImageClassifierOutput

< >

( loss: typing.Optional[torch.FloatTensor] = None logits: FloatTensor = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Classification (or regression if config.num_labels==1) loss.
  • logits (torch.FloatTensor of shape (batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax).
  • 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, 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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.

Base class for outputs of image classification models.

ImageClassifierOutputWithNoAttention

class transformers.modeling_outputs.ImageClassifierOutputWithNoAttention

< >

( loss: typing.Optional[torch.FloatTensor] = None logits: FloatTensor = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Classification (or regression if config.num_labels==1) loss.
  • logits (torch.FloatTensor of shape (batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax).
  • 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, 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.

Base class for outputs of image classification models.

DepthEstimatorOutput

class transformers.modeling_outputs.DepthEstimatorOutput

< >

( loss: typing.Optional[torch.FloatTensor] = None predicted_depth: FloatTensor = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Classification (or regression if config.num_labels==1) loss.
  • predicted_depth (torch.FloatTensor of shape (batch_size, height, width)) — Predicted depth for each pixel.
  • 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, 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.

  • 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 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.

Base class for outputs of depth estimation models.

Wav2Vec2BaseModelOutput

class transformers.modeling_outputs.Wav2Vec2BaseModelOutput

< >

( last_hidden_state: FloatTensor = None extract_features: FloatTensor = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • 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.
  • extract_features (torch.FloatTensor of shape (batch_size, sequence_length, conv_dim[-1])) — Sequence of extracted feature vectors of the last convolutional 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 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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.

Base class for models that have been trained with the Wav2Vec2 loss objective.

XVectorOutput

class transformers.modeling_outputs.XVectorOutput

< >

( loss: typing.Optional[torch.FloatTensor] = None logits: FloatTensor = None embeddings: FloatTensor = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )

Parameters

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Classification loss.
  • logits (torch.FloatTensor of shape (batch_size, config.xvector_output_dim)) — Classification hidden states before AMSoftmax.
  • embeddings (torch.FloatTensor of shape (batch_size, config.xvector_output_dim)) — Utterance embeddings used for vector similarity-based retrieval.
  • 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 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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.

Output type of Wav2Vec2ForXVector.

Seq2SeqTSModelOutput

class transformers.modeling_outputs.Seq2SeqTSModelOutput

< >

( last_hidden_state: FloatTensor = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None decoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None decoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None cross_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_last_hidden_state: typing.Optional[torch.FloatTensor] = None encoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None loc: typing.Optional[torch.FloatTensor] = None scale: typing.Optional[torch.FloatTensor] = None static_features: typing.Optional[torch.FloatTensor] = None )

Parameters

  • 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 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(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — Tuple of tuple(torch.FloatTensor) 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(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, 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 decoder at the output of each layer plus the optional initial embedding outputs.

  • decoder_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 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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 (torch.FloatTensor 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(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, 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 encoder at the output of each layer plus the optional initial embedding outputs.

  • encoder_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 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.

  • loc (torch.FloatTensor of shape (batch_size,) or (batch_size, input_size), optional) — Shift values of each time series’ context window which is used to give the model inputs of the same magnitude and then used to shift back to the original magnitude.
  • scale (torch.FloatTensor of shape (batch_size,) or (batch_size, input_size), optional) — Scaling values of each time series’ context window which is used to give the model inputs of the same magnitude and then used to rescale back to the original magnitude.
  • static_features (torch.FloatTensor of shape (batch_size, feature size), optional) — Static features of each time series’ in a batch which are copied to the covariates at inference time.

Base class for time series model’s encoder outputs that also contains pre-computed hidden states that can speed up sequential decoding.

Seq2SeqTSPredictionOutput

class transformers.modeling_outputs.Seq2SeqTSPredictionOutput

< >

( loss: typing.Optional[torch.FloatTensor] = None params: typing.Optional[typing.Tuple[torch.FloatTensor]] = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None decoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None decoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None cross_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_last_hidden_state: typing.Optional[torch.FloatTensor] = None encoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None loc: typing.Optional[torch.FloatTensor] = None scale: typing.Optional[torch.FloatTensor] = None static_features: typing.Optional[torch.FloatTensor] = None )

Parameters

  • loss (torch.FloatTensor of shape (1,), optional, returned when a future_values is provided) — Distributional loss.
  • params (torch.FloatTensor of shape (batch_size, num_samples, num_params)) — Parameters of the chosen distribution.
  • past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — Tuple of tuple(torch.FloatTensor) 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(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, 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 decoder at the output of each layer plus the initial embedding outputs.

  • decoder_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 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(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (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 (torch.FloatTensor 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(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, 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 encoder at the output of each layer plus the initial embedding outputs.

  • encoder_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 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.

  • loc (torch.FloatTensor of shape (batch_size,) or (batch_size, input_size), optional) — Shift values of each time series’ context window which is used to give the model inputs of the same magnitude and then used to shift back to the original magnitude.
  • scale (torch.FloatTensor of shape (batch_size,) or (batch_size, input_size), optional) — Scaling values of each time series’ context window which is used to give the model inputs of the same magnitude and then used to rescale back to the original magnitude.
  • static_features (torch.FloatTensor of shape (batch_size, feature size), optional) — Static features of each time series’ in a batch which are copied to the covariates at inference time.

Base class for time series model’s decoder outputs that also contain the loss as well as the parameters of the chosen distribution.

SampleTSPredictionOutput

class transformers.modeling_outputs.SampleTSPredictionOutput

< >

( sequences: FloatTensor = None )

Parameters

  • sequences (torch.FloatTensor of shape (batch_size, num_samples, prediction_length) or (batch_size, num_samples, prediction_length, input_size)) — Sampled values from the chosen distribution.

Base class for time series model’s predictions outputs that contains the sampled values from the chosen distribution.

TFBaseModelOutput

class transformers.modeling_tf_outputs.TFBaseModelOutput

< >

( last_hidden_state: tf.Tensor = None hidden_states: Tuple[tf.Tensor] | None = None attentions: Tuple[tf.Tensor] | None = None )

Parameters

  • 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.

Base class for model’s outputs, with potential hidden states and attentions.

TFBaseModelOutputWithPooling

class transformers.modeling_tf_outputs.TFBaseModelOutputWithPooling

< >

( last_hidden_state: tf.Tensor = None pooler_output: tf.Tensor = None hidden_states: Tuple[tf.Tensor] | None = None attentions: Tuple[tf.Tensor] | None = None )

Parameters

  • 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.

Base class for model’s outputs that also contains a pooling of the last hidden states.

TFBaseModelOutputWithPoolingAndCrossAttentions

class transformers.modeling_tf_outputs.TFBaseModelOutputWithPoolingAndCrossAttentions

< >

( last_hidden_state: tf.Tensor = None pooler_output: tf.Tensor = None past_key_values: List[tf.Tensor] | None = None hidden_states: Tuple[tf.Tensor] | None = None attentions: Tuple[tf.Tensor] | None = None cross_attentions: Tuple[tf.Tensor] | None = None )

Parameters

  • 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.

Base class for model’s outputs that also contains a pooling of the last hidden states.

TFBaseModelOutputWithPast

class transformers.modeling_tf_outputs.TFBaseModelOutputWithPast

< >

( last_hidden_state: tf.Tensor = None past_key_values: List[tf.Tensor] | None = None hidden_states: Tuple[tf.Tensor] | None = None attentions: Tuple[tf.Tensor] | None = None )

Parameters

  • 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.

Base class for model’s outputs that may also contain a past key/values (to speed up sequential decoding).

TFBaseModelOutputWithPastAndCrossAttentions

class transformers.modeling_tf_outputs.TFBaseModelOutputWithPastAndCrossAttentions

< >

( last_hidden_state: tf.Tensor = None past_key_values: List[tf.Tensor] | None = None hidden_states: Tuple[tf.Tensor] | None = None attentions: Tuple[tf.Tensor] | None = None cross_attentions: Tuple[tf.Tensor] | None = None )

Parameters

  • 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.

Base class for model’s outputs that may also contain a past key/values (to speed up sequential decoding).

TFSeq2SeqModelOutput

class transformers.modeling_tf_outputs.TFSeq2SeqModelOutput

< >

( last_hidden_state: tf.Tensor = None past_key_values: List[tf.Tensor] | None = None decoder_hidden_states: Tuple[tf.Tensor] | None = None decoder_attentions: Tuple[tf.Tensor] | None = None cross_attentions: Tuple[tf.Tensor] | None = None encoder_last_hidden_state: tf.Tensor | None = None encoder_hidden_states: Tuple[tf.Tensor] | None = None encoder_attentions: Tuple[tf.Tensor] | None = None )

Parameters

  • 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.

Base class for model encoder’s outputs that also contains : pre-computed hidden states that can speed up sequential decoding.

TFCausalLMOutput

class transformers.modeling_tf_outputs.TFCausalLMOutput

< >

( loss: tf.Tensor | None = None logits: tf.Tensor = None hidden_states: Tuple[tf.Tensor] | None = None attentions: Tuple[tf.Tensor] | None = None )

Parameters

  • 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.

Base class for causal language model (or autoregressive) outputs.

TFCausalLMOutputWithCrossAttentions

class transformers.modeling_tf_outputs.TFCausalLMOutputWithCrossAttentions

< >

( loss: tf.Tensor | None = None logits: tf.Tensor = None past_key_values: List[tf.Tensor] | None = None hidden_states: Tuple[tf.Tensor] | None = None attentions: Tuple[tf.Tensor] | None = None cross_attentions: Tuple[tf.Tensor] | None = None )

Parameters

  • 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.

Base class for causal language model (or autoregressive) outputs.

TFCausalLMOutputWithPast

class transformers.modeling_tf_outputs.TFCausalLMOutputWithPast

< >

( loss: tf.Tensor | None = None logits: tf.Tensor = None past_key_values: List[tf.Tensor] | None = None hidden_states: Tuple[tf.Tensor] | None = None attentions: Tuple[tf.Tensor] | None = None )

Parameters

  • 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.

Base class for causal language model (or autoregressive) outputs.

TFMaskedLMOutput

class transformers.modeling_tf_outputs.TFMaskedLMOutput

< >

( loss: tf.Tensor | None = None logits: tf.Tensor = None hidden_states: Tuple[tf.Tensor] | None = None attentions: Tuple[tf.Tensor] | None = None )

Parameters

  • 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.

Base class for masked language models outputs.

TFSeq2SeqLMOutput

class transformers.modeling_tf_outputs.TFSeq2SeqLMOutput

< >

( loss: tf.Tensor | None = None logits: tf.Tensor = None past_key_values: List[tf.Tensor] | None = None decoder_hidden_states: Tuple[tf.Tensor] | None = None decoder_attentions: Tuple[tf.Tensor] | None = None cross_attentions: Tuple[tf.Tensor] | None = None encoder_last_hidden_state: tf.Tensor | None = None encoder_hidden_states: Tuple[tf.Tensor] | None = None encoder_attentions: Tuple[tf.Tensor] | None = None )

Parameters

  • 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.

Base class for sequence-to-sequence language models outputs.

TFNextSentencePredictorOutput

class transformers.modeling_tf_outputs.TFNextSentencePredictorOutput

< >

( loss: tf.Tensor | None = None logits: tf.Tensor = None hidden_states: Tuple[tf.Tensor] | None = None attentions: Tuple[tf.Tensor] | None = None )

Parameters

  • 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.

Base class for outputs of models predicting if two sentences are consecutive or not.

TFSequenceClassifierOutput

class transformers.modeling_tf_outputs.TFSequenceClassifierOutput

< >

( loss: tf.Tensor | None = None logits: tf.Tensor = None hidden_states: Tuple[tf.Tensor] | None = None attentions: Tuple[tf.Tensor] | None = None )

Parameters

  • 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.

Base class for outputs of sentence classification models.

TFSeq2SeqSequenceClassifierOutput

class transformers.modeling_tf_outputs.TFSeq2SeqSequenceClassifierOutput

< >

( loss: tf.Tensor | None = None logits: tf.Tensor = None past_key_values: List[tf.Tensor] | None = None decoder_hidden_states: Tuple[tf.Tensor] | None = None decoder_attentions: Tuple[tf.Tensor] | None = None cross_attentions: Tuple[tf.Tensor] | None = None encoder_last_hidden_state: tf.Tensor | None = None encoder_hidden_states: Tuple[tf.Tensor] | None = None encoder_attentions: Tuple[tf.Tensor] | None = None )

Parameters

  • 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.

Base class for outputs of sequence-to-sequence sentence classification models.

TFMultipleChoiceModelOutput

class transformers.modeling_tf_outputs.TFMultipleChoiceModelOutput

< >

( loss: tf.Tensor | None = None logits: tf.Tensor = None hidden_states: Tuple[tf.Tensor] | None = None attentions: Tuple[tf.Tensor] | None = None )

Parameters

  • 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.

Base class for outputs of multiple choice models.

TFTokenClassifierOutput

class transformers.modeling_tf_outputs.TFTokenClassifierOutput

< >

( loss: tf.Tensor | None = None logits: tf.Tensor = None hidden_states: Tuple[tf.Tensor] | None = None attentions: Tuple[tf.Tensor] | None = None )

Parameters

  • 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.

Base class for outputs of token classification models.

TFQuestionAnsweringModelOutput

class transformers.modeling_tf_outputs.TFQuestionAnsweringModelOutput

< >

( loss: tf.Tensor | None = None start_logits: tf.Tensor = None end_logits: tf.Tensor = None hidden_states: Tuple[tf.Tensor] | None = None attentions: Tuple[tf.Tensor] | None = None )

Parameters

  • 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.

Base class for outputs of question answering models.

TFSeq2SeqQuestionAnsweringModelOutput

class transformers.modeling_tf_outputs.TFSeq2SeqQuestionAnsweringModelOutput

< >

( loss: tf.Tensor | None = None start_logits: tf.Tensor = None end_logits: tf.Tensor = None past_key_values: List[tf.Tensor] | None = None decoder_hidden_states: Tuple[tf.Tensor] | None = None decoder_attentions: Tuple[tf.Tensor] | None = None encoder_last_hidden_state: tf.Tensor | None = None encoder_hidden_states: Tuple[tf.Tensor] | None = None encoder_attentions: Tuple[tf.Tensor] | None = None )

Parameters

  • 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.

Base class for outputs of sequence-to-sequence question answering models.

FlaxBaseModelOutput

class transformers.modeling_flax_outputs.FlaxBaseModelOutput

< >

( last_hidden_state: Array = None hidden_states: typing.Optional[typing.Tuple[jax.Array]] = None attentions: typing.Optional[typing.Tuple[jax.Array]] = None )

Parameters

  • 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.

Base class for model’s outputs, with potential hidden states and attentions.

replace

< >

( **updates )

“Returns a new object replacing the specified fields with new values.

FlaxBaseModelOutputWithPast

class transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPast

< >

( last_hidden_state: Array = None past_key_values: typing.Optional[typing.Dict[str, jax.Array]] = None hidden_states: typing.Optional[typing.Tuple[jax.Array]] = None attentions: typing.Optional[typing.Tuple[jax.Array]] = None )

Parameters

  • 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.

Base class for model’s outputs, with potential hidden states and attentions.

replace

< >

( **updates )

“Returns a new object replacing the specified fields with new values.

FlaxBaseModelOutputWithPooling

class transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPooling

< >

( last_hidden_state: Array = None pooler_output: Array = None hidden_states: typing.Optional[typing.Tuple[jax.Array]] = None attentions: typing.Optional[typing.Tuple[jax.Array]] = None )

Parameters

  • 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.

Base class for model’s outputs that also contains a pooling of the last hidden states.

replace

< >

( **updates )

“Returns a new object replacing the specified fields with new values.

FlaxBaseModelOutputWithPastAndCrossAttentions

class transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions

< >

( last_hidden_state: Array = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[jax.Array]]] = None hidden_states: typing.Optional[typing.Tuple[jax.Array]] = None attentions: typing.Optional[typing.Tuple[jax.Array]] = None cross_attentions: typing.Optional[typing.Tuple[jax.Array]] = None )

Parameters

  • 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.

Base class for model’s outputs that may also contain a past key/values (to speed up sequential decoding).

replace

< >

( **updates )

“Returns a new object replacing the specified fields with new values.

FlaxSeq2SeqModelOutput

class transformers.modeling_flax_outputs.FlaxSeq2SeqModelOutput

< >

( last_hidden_state: Array = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[jax.Array]]] = None decoder_hidden_states: typing.Optional[typing.Tuple[jax.Array]] = None decoder_attentions: typing.Optional[typing.Tuple[jax.Array]] = None cross_attentions: typing.Optional[typing.Tuple[jax.Array]] = None encoder_last_hidden_state: typing.Optional[jax.Array] = None encoder_hidden_states: typing.Optional[typing.Tuple[jax.Array]] = None encoder_attentions: typing.Optional[typing.Tuple[jax.Array]] = None )

Parameters

  • 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.

Base class for model encoder’s outputs that also contains : pre-computed hidden states that can speed up sequential decoding.

replace

< >

( **updates )

“Returns a new object replacing the specified fields with new values.

FlaxCausalLMOutputWithCrossAttentions

class transformers.modeling_flax_outputs.FlaxCausalLMOutputWithCrossAttentions

< >

( logits: Array = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[jax.Array]]] = None hidden_states: typing.Optional[typing.Tuple[jax.Array]] = None attentions: typing.Optional[typing.Tuple[jax.Array]] = None cross_attentions: typing.Optional[typing.Tuple[jax.Array]] = None )

Parameters

  • 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.

Base class for causal language model (or autoregressive) outputs.

replace

< >

( **updates )

“Returns a new object replacing the specified fields with new values.

FlaxMaskedLMOutput

class transformers.modeling_flax_outputs.FlaxMaskedLMOutput

< >

( logits: Array = None hidden_states: typing.Optional[typing.Tuple[jax.Array]] = None attentions: typing.Optional[typing.Tuple[jax.Array]] = None )

Parameters

  • 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.

Base class for masked language models outputs.

replace

< >

( **updates )

“Returns a new object replacing the specified fields with new values.

FlaxSeq2SeqLMOutput

class transformers.modeling_flax_outputs.FlaxSeq2SeqLMOutput

< >

( logits: Array = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[jax.Array]]] = None decoder_hidden_states: typing.Optional[typing.Tuple[jax.Array]] = None decoder_attentions: typing.Optional[typing.Tuple[jax.Array]] = None cross_attentions: typing.Optional[typing.Tuple[jax.Array]] = None encoder_last_hidden_state: typing.Optional[jax.Array] = None encoder_hidden_states: typing.Optional[typing.Tuple[jax.Array]] = None encoder_attentions: typing.Optional[typing.Tuple[jax.Array]] = None )

Parameters

  • 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.

Base class for sequence-to-sequence language models outputs.

replace

< >

( **updates )

“Returns a new object replacing the specified fields with new values.

FlaxNextSentencePredictorOutput

class transformers.modeling_flax_outputs.FlaxNextSentencePredictorOutput

< >

( logits: Array = None hidden_states: typing.Optional[typing.Tuple[jax.Array]] = None attentions: typing.Optional[typing.Tuple[jax.Array]] = None )

Parameters

  • 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.

Base class for outputs of models predicting if two sentences are consecutive or not.

replace

< >

( **updates )

“Returns a new object replacing the specified fields with new values.

FlaxSequenceClassifierOutput

class transformers.modeling_flax_outputs.FlaxSequenceClassifierOutput

< >

( logits: Array = None hidden_states: typing.Optional[typing.Tuple[jax.Array]] = None attentions: typing.Optional[typing.Tuple[jax.Array]] = None )

Parameters

  • 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.

Base class for outputs of sentence classification models.

replace

< >

( **updates )

“Returns a new object replacing the specified fields with new values.

FlaxSeq2SeqSequenceClassifierOutput

class transformers.modeling_flax_outputs.FlaxSeq2SeqSequenceClassifierOutput

< >

( logits: Array = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[jax.Array]]] = None decoder_hidden_states: typing.Optional[typing.Tuple[jax.Array]] = None decoder_attentions: typing.Optional[typing.Tuple[jax.Array]] = None cross_attentions: typing.Optional[typing.Tuple[jax.Array]] = None encoder_last_hidden_state: typing.Optional[jax.Array] = None encoder_hidden_states: typing.Optional[typing.Tuple[jax.Array]] = None encoder_attentions: typing.Optional[typing.Tuple[jax.Array]] = None )

Parameters

  • 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.

Base class for outputs of sequence-to-sequence sentence classification models.

replace

< >

( **updates )

“Returns a new object replacing the specified fields with new values.

FlaxMultipleChoiceModelOutput

class transformers.modeling_flax_outputs.FlaxMultipleChoiceModelOutput

< >

( logits: Array = None hidden_states: typing.Optional[typing.Tuple[jax.Array]] = None attentions: typing.Optional[typing.Tuple[jax.Array]] = None )

Parameters

  • 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.

Base class for outputs of multiple choice models.

replace

< >

( **updates )

“Returns a new object replacing the specified fields with new values.

FlaxTokenClassifierOutput

class transformers.modeling_flax_outputs.FlaxTokenClassifierOutput

< >

( logits: Array = None hidden_states: typing.Optional[typing.Tuple[jax.Array]] = None attentions: typing.Optional[typing.Tuple[jax.Array]] = None )

Parameters

  • 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.

Base class for outputs of token classification models.

replace

< >

( **updates )

“Returns a new object replacing the specified fields with new values.

FlaxQuestionAnsweringModelOutput

class transformers.modeling_flax_outputs.FlaxQuestionAnsweringModelOutput

< >

( start_logits: Array = None end_logits: Array = None hidden_states: typing.Optional[typing.Tuple[jax.Array]] = None attentions: typing.Optional[typing.Tuple[jax.Array]] = None )

Parameters

  • 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.

Base class for outputs of question answering models.

replace

< >

( **updates )

“Returns a new object replacing the specified fields with new values.

FlaxSeq2SeqQuestionAnsweringModelOutput

class transformers.modeling_flax_outputs.FlaxSeq2SeqQuestionAnsweringModelOutput

< >

( start_logits: Array = None end_logits: Array = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[jax.Array]]] = None decoder_hidden_states: typing.Optional[typing.Tuple[jax.Array]] = None decoder_attentions: typing.Optional[typing.Tuple[jax.Array]] = None cross_attentions: typing.Optional[typing.Tuple[jax.Array]] = None encoder_last_hidden_state: typing.Optional[jax.Array] = None encoder_hidden_states: typing.Optional[typing.Tuple[jax.Array]] = None encoder_attentions: typing.Optional[typing.Tuple[jax.Array]] = None )

Parameters

  • 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.

Base class for outputs of sequence-to-sequence question answering models.

replace

< >

( **updates )

“Returns a new object replacing the specified fields with new values.

< > Update on GitHub

←모델 출력 (번역중) Processors→