RoBERTa-PreLayerNorm (original) (raw)

The RoBERTa-PreLayerNorm model was proposed in fairseq: A Fast, Extensible Toolkit for Sequence Modeling by Myle Ott, Sergey Edunov, Alexei Baevski, Angela Fan, Sam Gross, Nathan Ng, David Grangier, Michael Auli. It is identical to using the --encoder-normalize-before flag in fairseq.

fairseq is an open-source sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling, and other text generation tasks. The toolkit is based on PyTorch and supports distributed training across multiple GPUs and machines. We also support fast mixed-precision training and inference on modern GPUs.

class transformers.RobertaPreLayerNormConfig

< source >

( vocab_size = 50265 hidden_size = 768 num_hidden_layers = 12 num_attention_heads = 12 intermediate_size = 3072 hidden_act = 'gelu' hidden_dropout_prob = 0.1 attention_probs_dropout_prob = 0.1 max_position_embeddings = 512 type_vocab_size = 2 initializer_range = 0.02 layer_norm_eps = 1e-12 pad_token_id = 1 bos_token_id = 0 eos_token_id = 2 position_embedding_type = 'absolute' use_cache = True classifier_dropout = None **kwargs )

Parameters

• vocab_size (int, optional, defaults to 50265) — Vocabulary size of the RoBERTa-PreLayerNorm model. Defines the number of different tokens that can be represented by theinputs_ids passed when calling RobertaPreLayerNormModel or TFRobertaPreLayerNormModel.
• hidden_size (int, optional, defaults to 768) — Dimensionality of the encoder layers and the pooler layer.
• num_hidden_layers (int, optional, defaults to 12) — Number of hidden layers in the Transformer encoder.
• num_attention_heads (int, optional, defaults to 12) — Number of attention heads for each attention layer in the Transformer encoder.
• intermediate_size (int, optional, defaults to 3072) — Dimensionality of the “intermediate” (often named feed-forward) layer in the Transformer encoder.
• hidden_act (str or Callable, optional, defaults to "gelu") — The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu","relu", "silu" and "gelu_new" are supported.
• hidden_dropout_prob (float, optional, defaults to 0.1) — The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
• attention_probs_dropout_prob (float, optional, defaults to 0.1) — The dropout ratio for the attention probabilities.
• max_position_embeddings (int, optional, defaults to 512) — The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048).
• type_vocab_size (int, optional, defaults to 2) — The vocabulary size of the token_type_ids passed when calling RobertaPreLayerNormModel or TFRobertaPreLayerNormModel.
• initializer_range (float, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
• layer_norm_eps (float, optional, defaults to 1e-12) — The epsilon used by the layer normalization layers.
• position_embedding_type (str, optional, defaults to "absolute") — Type of position embedding. Choose one of "absolute", "relative_key", "relative_key_query". For positional embeddings use "absolute". For more information on "relative_key", please refer toSelf-Attention with Relative Position Representations (Shaw et al.). For more information on "relative_key_query", please refer to Method 4 in Improve Transformer Models with Better Relative Position Embeddings (Huang et al.).
• is_decoder (bool, optional, defaults to False) — Whether the model is used as a decoder or not. If False, the model is used as an encoder.
• use_cache (bool, optional, defaults to True) — Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if config.is_decoder=True.
• classifier_dropout (float, optional) — The dropout ratio for the classification head.

This is the configuration class to store the configuration of a RobertaPreLayerNormModel or a TFRobertaPreLayerNormModel. It is used to instantiate a RoBERTa-PreLayerNorm model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the RoBERTa-PreLayerNormandreasmadsen/efficient_mlm_m0.40 architecture.

Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.

Examples:

from transformers import RobertaPreLayerNormConfig, RobertaPreLayerNormModel

configuration = RobertaPreLayerNormConfig()

model = RobertaPreLayerNormModel(configuration)

configuration = model.config

RobertaPreLayerNormModel

class transformers.RobertaPreLayerNormModel

< source >

( config add_pooling_layer = True )

Parameters

• config (RobertaPreLayerNormModel) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained() method to load the model weights.
• add_pooling_layer (bool, optional, defaults to True) — Whether to add a pooling layer

The model can behave as an encoder (with only self-attention) as well as a decoder, in which case a layer of cross-attention is added between the self-attention layers, following the architecture described in Attention is all you need_ by Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser and Illia Polosukhin.

To behave as an decoder the model needs to be initialized with the is_decoder argument of the configuration set to True. To be used in a Seq2Seq model, the model needs to initialized with both is_decoder argument andadd_cross_attention set to True; an encoder_hidden_states is then expected as an input to the forward pass.

.. _ Attention is all you need: https://arxiv.org/abs/1706.03762

This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< source >

( input_ids: typing.Optional[torch.Tensor] = None attention_mask: typing.Optional[torch.Tensor] = None token_type_ids: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.Tensor] = None head_mask: typing.Optional[torch.Tensor] = None inputs_embeds: typing.Optional[torch.Tensor] = None encoder_hidden_states: typing.Optional[torch.Tensor] = None encoder_attention_mask: typing.Optional[torch.Tensor] = None past_key_values: typing.Optional[typing.List[torch.FloatTensor]] = None use_cache: typing.Optional[bool] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.BaseModelOutputWithPoolingAndCrossAttentions or tuple(torch.FloatTensor)

Parameters

• input_ids (torch.Tensor of shape (batch_size, sequence_length), optional) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() andPreTrainedTokenizer.call() for details.
  What are input IDs?
• attention_mask (torch.Tensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• token_type_ids (torch.Tensor of shape (batch_size, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0,1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token. This parameter can only be used when the model is initialized with type_vocab_size parameter with value

    = 2. All the value in this tensor should be always < type_vocab_size.
    What are token type IDs?

• position_ids (torch.Tensor of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.n_positions - 1].
  What are position IDs?
• head_mask (torch.Tensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• inputs_embeds (torch.Tensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
• encoder_hidden_states (torch.Tensor of shape (batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder.
• encoder_attention_mask (torch.Tensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
• past_key_values (List[torch.FloatTensor], optional) — Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the past_key_valuesreturned by the model at a previous stage of decoding, when use_cache=True or config.use_cache=True.
  Two formats are allowed:
  • a Cache instance, see our kv cache guide;
  • 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)). This is also known as the legacy cache format.
    The model will output the same cache format that is fed as input. If no past_key_values are passed, the legacy cache format will be returned.
    If past_key_values are used, the user can optionally input only the last input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all input_idsof shape (batch_size, sequence_length).
• use_cache (bool, optional) — If set to True, past_key_values key value states are returned and can be used to speed up decoding (seepast_key_values).
• output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
• output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.

A transformers.modeling_outputs.BaseModelOutputWithPoolingAndCrossAttentions or a tuple oftorch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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 (Cache, optional, returned when use_cache=True is passed or when config.use_cache=True) — It is a Cache instance. For more details, see our kv cache guide.
  Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally ifconfig.is_encoder_decoder=True in the cross-attention blocks) that can be used (see past_key_valuesinput) to speed up sequential decoding.

The RobertaPreLayerNormModel forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

RobertaPreLayerNormForCausalLM

class transformers.RobertaPreLayerNormForCausalLM

< source >

( config )

Parameters

• config (RobertaPreLayerNormForCausalLM) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained() method to load the model weights.

RoBERTa-PreLayerNorm Model with a language modeling head on top for CLM fine-tuning.

This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< source >

( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None encoder_hidden_states: typing.Optional[torch.FloatTensor] = None encoder_attention_mask: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None use_cache: typing.Optional[bool] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None **kwargs ) → transformers.modeling_outputs.CausalLMOutputWithCrossAttentions or tuple(torch.FloatTensor)

Parameters

• input_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() andPreTrainedTokenizer.call() for details.
  What are input IDs?
• attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• token_type_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0,1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token. This parameter can only be used when the model is initialized with type_vocab_size parameter with value

    = 2. All the value in this tensor should be always < type_vocab_size.
    What are token type IDs?

• position_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.n_positions - 1].
  What are position IDs?
• head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
• encoder_hidden_states (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. Used in the cross-attention if the model is configured as a decoder.
• encoder_attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
• labels (torch.LongTensor of shape (batch_size, sequence_length), optional) — Labels for computing the left-to-right language modeling loss (next word prediction). Indices should be in[-100, 0, ..., config.vocab_size] (see input_ids docstring) Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size]
• past_key_values (Tuple[Tuple[torch.FloatTensor]], optional) — Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the past_key_valuesreturned by the model at a previous stage of decoding, when use_cache=True or config.use_cache=True.
  Two formats are allowed:
  • a Cache instance, see our kv cache guide;
  • 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)). This is also known as the legacy cache format.
    The model will output the same cache format that is fed as input. If no past_key_values are passed, the legacy cache format will be returned.
    If past_key_values are used, the user can optionally input only the last input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all input_idsof shape (batch_size, sequence_length).
• use_cache (bool, optional) — If set to True, past_key_values key value states are returned and can be used to speed up decoding (seepast_key_values).
• output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
• output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.

A transformers.modeling_outputs.CausalLMOutputWithCrossAttentions or a tuple oftorch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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 (Cache, optional, returned when use_cache=True is passed or when config.use_cache=True) — It is a Cache instance. For more details, see our kv cache guide.
  Contains pre-computed hidden-states (key and values in the attention blocks) that can be used (seepast_key_values input) to speed up sequential decoding.

The RobertaPreLayerNormForCausalLM forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

from transformers import AutoTokenizer, RobertaPreLayerNormForCausalLM, AutoConfig import torch

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") config = AutoConfig.from_pretrained("andreasmadsen/efficient_mlm_m0.40") config.is_decoder = True model = RobertaPreLayerNormForCausalLM.from_pretrained("andreasmadsen/efficient_mlm_m0.40", config=config)

inputs = tokenizer("Hello, my dog is cute", return_tensors="pt") outputs = model(**inputs)

prediction_logits = outputs.logits

RobertaPreLayerNormForMaskedLM

class transformers.RobertaPreLayerNormForMaskedLM

< source >

( config )

Parameters

• config (RobertaPreLayerNormForMaskedLM) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained() method to load the model weights.

RoBERTa-PreLayerNorm Model with a language modeling head on top.

This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< source >

( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None encoder_hidden_states: typing.Optional[torch.FloatTensor] = None encoder_attention_mask: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.MaskedLMOutput or tuple(torch.FloatTensor)

Parameters

• input_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() andPreTrainedTokenizer.call() for details.
  What are input IDs?
• attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• token_type_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0,1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token. This parameter can only be used when the model is initialized with type_vocab_size parameter with value

    = 2. All the value in this tensor should be always < type_vocab_size.
    What are token type IDs?

• position_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.n_positions - 1].
  What are position IDs?
• head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
• encoder_hidden_states (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. Used in the cross-attention if the model is configured as a decoder.
• encoder_attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
• labels (torch.LongTensor of shape (batch_size, sequence_length), optional) — Labels for computing the masked language modeling loss. Indices should be in [-100, 0, ..., config.vocab_size] (see input_ids docstring) Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size]
• output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
• output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.

A transformers.modeling_outputs.MaskedLMOutput or a tuple oftorch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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.

The RobertaPreLayerNormForMaskedLM forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

from transformers import AutoTokenizer, RobertaPreLayerNormForMaskedLM import torch

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") model = RobertaPreLayerNormForMaskedLM.from_pretrained("andreasmadsen/efficient_mlm_m0.40")

inputs = tokenizer("The capital of France is .", return_tensors="pt")

with torch.no_grad(): ... logits = model(**inputs).logits

mask_token_index = (inputs.input_ids == tokenizer.mask_token_id)[0].nonzero(as_tuple=True)[0]

predicted_token_id = logits[0, mask_token_index].argmax(axis=-1) tokenizer.decode(predicted_token_id) ...

labels = tokenizer("The capital of France is Paris.", return_tensors="pt")["input_ids"]

labels = torch.where(inputs.input_ids == tokenizer.mask_token_id, labels, -100)

outputs = model(**inputs, labels=labels) round(outputs.loss.item(), 2) ...

RobertaPreLayerNormForSequenceClassification

class transformers.RobertaPreLayerNormForSequenceClassification

< source >

( config )

Parameters

• config (RobertaPreLayerNormForSequenceClassification) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained() method to load the model weights.

RoBERTa-PreLayerNorm Model transformer with a sequence classification/regression head on top (a linear layer on top of the pooled output) e.g. for GLUE tasks.

This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< source >

( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.SequenceClassifierOutput or tuple(torch.FloatTensor)

Parameters

• input_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() andPreTrainedTokenizer.call() for details.
  What are input IDs?
• attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• token_type_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0,1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token. This parameter can only be used when the model is initialized with type_vocab_size parameter with value

    = 2. All the value in this tensor should be always < type_vocab_size.
    What are token type IDs?

• position_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.n_positions - 1].
  What are position IDs?
• head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
• labels (torch.LongTensor of shape (batch_size,), optional) — Labels for computing the sequence classification/regression loss. Indices should be in [0, ..., config.num_labels - 1]. If config.num_labels == 1 a regression loss is computed (Mean-Square loss), Ifconfig.num_labels > 1 a classification loss is computed (Cross-Entropy).
• output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
• output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.

A transformers.modeling_outputs.SequenceClassifierOutput or a tuple oftorch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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.

The RobertaPreLayerNormForSequenceClassification forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example of single-label classification:

import torch from transformers import AutoTokenizer, RobertaPreLayerNormForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") model = RobertaPreLayerNormForSequenceClassification.from_pretrained("andreasmadsen/efficient_mlm_m0.40")

inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")

with torch.no_grad(): ... logits = model(**inputs).logits

predicted_class_id = logits.argmax().item() model.config.id2label[predicted_class_id] ...

num_labels = len(model.config.id2label) model = RobertaPreLayerNormForSequenceClassification.from_pretrained("andreasmadsen/efficient_mlm_m0.40", num_labels=num_labels)

labels = torch.tensor([1]) loss = model(**inputs, labels=labels).loss round(loss.item(), 2) ...

Example of multi-label classification:

import torch from transformers import AutoTokenizer, RobertaPreLayerNormForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") model = RobertaPreLayerNormForSequenceClassification.from_pretrained("andreasmadsen/efficient_mlm_m0.40", problem_type="multi_label_classification")

inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")

with torch.no_grad(): ... logits = model(**inputs).logits

predicted_class_ids = torch.arange(0, logits.shape[-1])[torch.sigmoid(logits).squeeze(dim=0) > 0.5]

num_labels = len(model.config.id2label) model = RobertaPreLayerNormForSequenceClassification.from_pretrained( ... "andreasmadsen/efficient_mlm_m0.40", num_labels=num_labels, problem_type="multi_label_classification" ... )

labels = torch.sum( ... torch.nn.functional.one_hot(predicted_class_ids[None, :].clone(), num_classes=num_labels), dim=1 ... ).to(torch.float) loss = model(**inputs, labels=labels).loss

RobertaPreLayerNormForMultipleChoice

class transformers.RobertaPreLayerNormForMultipleChoice

< source >

( config )

Parameters

• config (RobertaPreLayerNormForMultipleChoice) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained() method to load the model weights.

The Roberta Prelayernorm Model with a multiple choice classification head on top (a linear layer on top of the pooled output and a softmax) e.g. for RocStories/SWAG tasks.

This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< source >

( input_ids: typing.Optional[torch.LongTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.MultipleChoiceModelOutput or tuple(torch.FloatTensor)

Parameters

• input_ids (torch.LongTensor of shape (batch_size, num_choices, sequence_length)) — Indices of input sequence tokens in the vocabulary.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() andPreTrainedTokenizer.call() for details.
  What are input IDs?
• token_type_ids (torch.LongTensor of shape (batch_size, num_choices, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0,1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token. This parameter can only be used when the model is initialized with type_vocab_size parameter with value

    = 2. All the value in this tensor should be always < type_vocab_size.
    What are token type IDs?

• attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• labels (torch.LongTensor of shape (batch_size,), optional) — Labels for computing the multiple choice classification loss. Indices should be in [0, ..., num_choices-1] where num_choices is the size of the second dimension of the input tensors. (Seeinput_ids above)
• position_ids (torch.LongTensor of shape (batch_size, num_choices, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].
  What are position IDs?
• head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• inputs_embeds (torch.FloatTensor of shape (batch_size, num_choices, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
• output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
• output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.

A transformers.modeling_outputs.MultipleChoiceModelOutput or a tuple oftorch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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.

The RobertaPreLayerNormForMultipleChoice forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

from transformers import AutoTokenizer, RobertaPreLayerNormForMultipleChoice import torch

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") model = RobertaPreLayerNormForMultipleChoice.from_pretrained("andreasmadsen/efficient_mlm_m0.40")

prompt = "In Italy, pizza served in formal settings, such as at a restaurant, is presented unsliced." choice0 = "It is eaten with a fork and a knife." choice1 = "It is eaten while held in the hand." labels = torch.tensor(0).unsqueeze(0)

encoding = tokenizer([prompt, prompt], [choice0, choice1], return_tensors="pt", padding=True) outputs = model(**{k: v.unsqueeze(0) for k, v in encoding.items()}, labels=labels)

loss = outputs.loss logits = outputs.logits

RobertaPreLayerNormForTokenClassification

class transformers.RobertaPreLayerNormForTokenClassification

< source >

( config )

Parameters

• config (RobertaPreLayerNormForTokenClassification) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained() method to load the model weights.

The Roberta Prelayernorm transformer with a token classification head on top (a linear layer on top of the hidden-states output) e.g. for Named-Entity-Recognition (NER) tasks.

This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< source >

( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.TokenClassifierOutput or tuple(torch.FloatTensor)

Parameters

• input_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() andPreTrainedTokenizer.call() for details.
  What are input IDs?
• attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• token_type_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0,1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token. This parameter can only be used when the model is initialized with type_vocab_size parameter with value

    = 2. All the value in this tensor should be always < type_vocab_size.
    What are token type IDs?

• position_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.n_positions - 1].
  What are position IDs?
• head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
• labels (torch.LongTensor of shape (batch_size, sequence_length), optional) — Labels for computing the token classification loss. Indices should be in [0, ..., config.num_labels - 1].
• output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
• output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.

A transformers.modeling_outputs.TokenClassifierOutput or a tuple oftorch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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.

The RobertaPreLayerNormForTokenClassification forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

from transformers import AutoTokenizer, RobertaPreLayerNormForTokenClassification import torch

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") model = RobertaPreLayerNormForTokenClassification.from_pretrained("andreasmadsen/efficient_mlm_m0.40")

inputs = tokenizer( ... "HuggingFace is a company based in Paris and New York", add_special_tokens=False, return_tensors="pt" ... )

with torch.no_grad(): ... logits = model(**inputs).logits

predicted_token_class_ids = logits.argmax(-1)

predicted_tokens_classes = [model.config.id2label[t.item()] for t in predicted_token_class_ids[0]] predicted_tokens_classes ...

labels = predicted_token_class_ids loss = model(**inputs, labels=labels).loss round(loss.item(), 2) ...

RobertaPreLayerNormForQuestionAnswering

class transformers.RobertaPreLayerNormForQuestionAnswering

< source >

( config )

Parameters

• config (RobertaPreLayerNormForQuestionAnswering) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained() method to load the model weights.

The Roberta Prelayernorm transformer with a span classification head on top for extractive question-answering tasks like SQuAD (a linear layer on top of the hidden-states output to compute span start logits and span end logits).

This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< source >

( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None start_positions: typing.Optional[torch.LongTensor] = None end_positions: typing.Optional[torch.LongTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.QuestionAnsweringModelOutput or tuple(torch.FloatTensor)

Parameters

• input_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() andPreTrainedTokenizer.call() for details.
  What are input IDs?
• attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• token_type_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0,1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token. This parameter can only be used when the model is initialized with type_vocab_size parameter with value

    = 2. All the value in this tensor should be always < type_vocab_size.
    What are token type IDs?

• position_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.n_positions - 1].
  What are position IDs?
• head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
• start_positions (torch.LongTensor of shape (batch_size,), optional) — Labels for position (index) of the start of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length). Position outside of the sequence are not taken into account for computing the loss.
• end_positions (torch.LongTensor of shape (batch_size,), optional) — Labels for position (index) of the end of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length). Position outside of the sequence are not taken into account for computing the loss.
• output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
• output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.

A transformers.modeling_outputs.QuestionAnsweringModelOutput or a tuple oftorch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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.

The RobertaPreLayerNormForQuestionAnswering forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

from transformers import AutoTokenizer, RobertaPreLayerNormForQuestionAnswering import torch

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") model = RobertaPreLayerNormForQuestionAnswering.from_pretrained("andreasmadsen/efficient_mlm_m0.40")

question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"

inputs = tokenizer(question, text, return_tensors="pt") with torch.no_grad(): ... outputs = model(**inputs)

answer_start_index = outputs.start_logits.argmax() answer_end_index = outputs.end_logits.argmax()

predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1] tokenizer.decode(predict_answer_tokens, skip_special_tokens=True) ...

target_start_index = torch.tensor([14]) target_end_index = torch.tensor([15])

outputs = model(**inputs, start_positions=target_start_index, end_positions=target_end_index) loss = outputs.loss round(loss.item(), 2) ...

TFRobertaPreLayerNormModel

class transformers.TFRobertaPreLayerNormModel

< source >

( config *inputs **kwargs )

Parameters

• config (RobertaPreLayerNormConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

The bare RoBERTa-PreLayerNorm Model transformer outputting raw hidden-states without any specific head on top.

This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

TensorFlow models and layers in transformers accept two formats as input:

• having all inputs as keyword arguments (like PyTorch models), or
• having all inputs as a list, tuple or dict in the first positional argument.

The reason the second format is supported is that Keras methods prefer this format when passing inputs to models and layers. Because of this support, when using methods like model.fit() things should “just work” for you - just pass your inputs and labels in any format that model.fit() supports! If, however, you want to use the second format outside of Keras methods like fit() and predict(), such as when creating your own layers or models with the Keras Functional API, there are three possibilities you can use to gather all the input Tensors in the first positional argument:

• a single Tensor with input_ids only and nothing else: model(input_ids)
• a list of varying length with one or several input Tensors IN THE ORDER given in the docstring:model([input_ids, attention_mask]) or model([input_ids, attention_mask, token_type_ids])
• a dictionary with one or several input Tensors associated to the input names given in the docstring:model({"input_ids": input_ids, "token_type_ids": token_type_ids})

Note that when creating models and layers withsubclassing then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function!

call

< source >

( input_ids: TFModelInputType | None = None attention_mask: np.ndarray | tf.Tensor | None = None token_type_ids: np.ndarray | tf.Tensor | None = None position_ids: np.ndarray | tf.Tensor | None = None head_mask: np.ndarray | tf.Tensor | None = None inputs_embeds: np.ndarray | tf.Tensor | None = None encoder_hidden_states: np.ndarray | tf.Tensor | None = None encoder_attention_mask: np.ndarray | tf.Tensor | None = None past_key_values: Optional[Tuple[Tuple[Union[np.ndarray, tf.Tensor]]]] = None use_cache: Optional[bool] = None output_attentions: Optional[bool] = None output_hidden_states: Optional[bool] = None return_dict: Optional[bool] = None training: Optional[bool] = False ) → transformers.modeling_tf_outputs.TFBaseModelOutputWithPoolingAndCrossAttentions or tuple(tf.Tensor)

Parameters

• input_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.call() andPreTrainedTokenizer.encode() for details.
  What are input IDs?
• attention_mask (Numpy array or tf.Tensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• token_type_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token.
    What are token type IDs?
• position_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].
  What are position IDs?
• head_mask (Numpy array or tf.Tensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• inputs_embeds (tf.Tensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
• output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
• output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
• training (bool, optional, defaults to False) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).
• encoder_hidden_states (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. Used in the cross-attention if the model is configured as a decoder.
• encoder_attention_mask (tf.Tensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
• past_key_values (Tuple[Tuple[tf.Tensor]] of length config.n_layers) — contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding. If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of alldecoder_input_ids of shape (batch_size, sequence_length).
• use_cache (bool, optional, defaults to True) — If set to True, past_key_values key value states are returned and can be used to speed up decoding (seepast_key_values). Set to False during training, True during generation

A transformers.modeling_tf_outputs.TFBaseModelOutputWithPoolingAndCrossAttentions or a tuple of tf.Tensor (ifreturn_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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 (seepast_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.

The TFRobertaPreLayerNormModel forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

from transformers import AutoTokenizer, TFRobertaPreLayerNormModel import tensorflow as tf

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") model = TFRobertaPreLayerNormModel.from_pretrained("andreasmadsen/efficient_mlm_m0.40")

inputs = tokenizer("Hello, my dog is cute", return_tensors="tf") outputs = model(inputs)

last_hidden_states = outputs.last_hidden_state

TFRobertaPreLayerNormForCausalLM

class transformers.TFRobertaPreLayerNormForCausalLM

< source >

( config: RobertaPreLayerNormConfig *inputs **kwargs )

call

< source >

( input_ids: TFModelInputType | None = None attention_mask: np.ndarray | tf.Tensor | None = None token_type_ids: np.ndarray | tf.Tensor | None = None position_ids: np.ndarray | tf.Tensor | None = None head_mask: np.ndarray | tf.Tensor | None = None inputs_embeds: np.ndarray | tf.Tensor | None = None encoder_hidden_states: np.ndarray | tf.Tensor | None = None encoder_attention_mask: np.ndarray | tf.Tensor | None = None past_key_values: Optional[Tuple[Tuple[Union[np.ndarray, tf.Tensor]]]] = None use_cache: Optional[bool] = None output_attentions: Optional[bool] = None output_hidden_states: Optional[bool] = None return_dict: Optional[bool] = None labels: np.ndarray | tf.Tensor | None = None training: Optional[bool] = False ) → transformers.modeling_tf_outputs.TFCausalLMOutputWithCrossAttentions or tuple(tf.Tensor)

Parameters

• input_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.call() andPreTrainedTokenizer.encode() for details.
  What are input IDs?
• attention_mask (Numpy array or tf.Tensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• token_type_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token.
    What are token type IDs?
• position_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].
  What are position IDs?
• head_mask (Numpy array or tf.Tensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• inputs_embeds (tf.Tensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
• output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
• output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
• training (bool, optional, defaults to False) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).
• encoder_hidden_states (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. Used in the cross-attention if the model is configured as a decoder.
• encoder_attention_mask (tf.Tensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
• past_key_values (Tuple[Tuple[tf.Tensor]] of length config.n_layers) — contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding. If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of alldecoder_input_ids of shape (batch_size, sequence_length).
• use_cache (bool, optional, defaults to True) — If set to True, past_key_values key value states are returned and can be used to speed up decoding (seepast_key_values). Set to False during training, True during generation
• labels (tf.Tensor or np.ndarray of shape (batch_size, sequence_length), optional) — Labels for computing the cross entropy classification loss. Indices should be in [0, ..., config.vocab_size - 1].

A transformers.modeling_tf_outputs.TFCausalLMOutputWithCrossAttentions or a tuple of tf.Tensor (ifreturn_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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 (seepast_key_values input) to speed up sequential decoding.

The TFRobertaPreLayerNormForCausalLM forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

from transformers import AutoTokenizer, TFRobertaPreLayerNormForCausalLM import tensorflow as tf

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") model = TFRobertaPreLayerNormForCausalLM.from_pretrained("andreasmadsen/efficient_mlm_m0.40")

inputs = tokenizer("Hello, my dog is cute", return_tensors="tf") outputs = model(inputs) logits = outputs.logits

TFRobertaPreLayerNormForMaskedLM

class transformers.TFRobertaPreLayerNormForMaskedLM

< source >

( config *inputs **kwargs )

Parameters

• config (RobertaPreLayerNormConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

RoBERTa-PreLayerNorm Model with a language modeling head on top.

This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

TensorFlow models and layers in transformers accept two formats as input:

• having all inputs as keyword arguments (like PyTorch models), or
• having all inputs as a list, tuple or dict in the first positional argument.

The reason the second format is supported is that Keras methods prefer this format when passing inputs to models and layers. Because of this support, when using methods like model.fit() things should “just work” for you - just pass your inputs and labels in any format that model.fit() supports! If, however, you want to use the second format outside of Keras methods like fit() and predict(), such as when creating your own layers or models with the Keras Functional API, there are three possibilities you can use to gather all the input Tensors in the first positional argument:

• a single Tensor with input_ids only and nothing else: model(input_ids)
• a list of varying length with one or several input Tensors IN THE ORDER given in the docstring:model([input_ids, attention_mask]) or model([input_ids, attention_mask, token_type_ids])
• a dictionary with one or several input Tensors associated to the input names given in the docstring:model({"input_ids": input_ids, "token_type_ids": token_type_ids})

Note that when creating models and layers withsubclassing then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function!

call

< source >

( input_ids: TFModelInputType | None = None attention_mask: np.ndarray | tf.Tensor | None = None token_type_ids: np.ndarray | tf.Tensor | None = None position_ids: np.ndarray | tf.Tensor | None = None head_mask: np.ndarray | tf.Tensor | None = None inputs_embeds: np.ndarray | tf.Tensor | None = None output_attentions: Optional[bool] = None output_hidden_states: Optional[bool] = None return_dict: Optional[bool] = None labels: np.ndarray | tf.Tensor | None = None training: Optional[bool] = False ) → transformers.modeling_tf_outputs.TFMaskedLMOutput or tuple(tf.Tensor)

Parameters

• input_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.call() andPreTrainedTokenizer.encode() for details.
  What are input IDs?
• attention_mask (Numpy array or tf.Tensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• token_type_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token.
    What are token type IDs?
• position_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].
  What are position IDs?
• head_mask (Numpy array or tf.Tensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• inputs_embeds (tf.Tensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
• output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
• output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
• training (bool, optional, defaults to False) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).
• labels (tf.Tensor of shape (batch_size, sequence_length), optional) — Labels for computing the masked language modeling loss. Indices should be in [-100, 0, ..., config.vocab_size] (see input_ids docstring) Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size]

A transformers.modeling_tf_outputs.TFMaskedLMOutput or a tuple of tf.Tensor (ifreturn_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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.

The TFRobertaPreLayerNormForMaskedLM forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

from transformers import AutoTokenizer, TFRobertaPreLayerNormForMaskedLM import tensorflow as tf

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") model = TFRobertaPreLayerNormForMaskedLM.from_pretrained("andreasmadsen/efficient_mlm_m0.40")

inputs = tokenizer("The capital of France is .", return_tensors="tf") logits = model(**inputs).logits

mask_token_index = tf.where((inputs.input_ids == tokenizer.mask_token_id)[0]) selected_logits = tf.gather_nd(logits[0], indices=mask_token_index)

predicted_token_id = tf.math.argmax(selected_logits, axis=-1) tokenizer.decode(predicted_token_id) ' Paris'

labels = tokenizer("The capital of France is Paris.", return_tensors="tf")["input_ids"]

labels = tf.where(inputs.input_ids == tokenizer.mask_token_id, labels, -100)

outputs = model(**inputs, labels=labels) round(float(outputs.loss), 2) 0.69

TFRobertaPreLayerNormForSequenceClassification

class transformers.TFRobertaPreLayerNormForSequenceClassification

< source >

( config *inputs **kwargs )

Parameters

• config (RobertaPreLayerNormConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

RoBERTa-PreLayerNorm Model transformer with a sequence classification/regression head on top (a linear layer on top of the pooled output) e.g. for GLUE tasks.

This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

TensorFlow models and layers in transformers accept two formats as input:

• having all inputs as keyword arguments (like PyTorch models), or
• having all inputs as a list, tuple or dict in the first positional argument.

The reason the second format is supported is that Keras methods prefer this format when passing inputs to models and layers. Because of this support, when using methods like model.fit() things should “just work” for you - just pass your inputs and labels in any format that model.fit() supports! If, however, you want to use the second format outside of Keras methods like fit() and predict(), such as when creating your own layers or models with the Keras Functional API, there are three possibilities you can use to gather all the input Tensors in the first positional argument:

• a single Tensor with input_ids only and nothing else: model(input_ids)
• a list of varying length with one or several input Tensors IN THE ORDER given in the docstring:model([input_ids, attention_mask]) or model([input_ids, attention_mask, token_type_ids])
• a dictionary with one or several input Tensors associated to the input names given in the docstring:model({"input_ids": input_ids, "token_type_ids": token_type_ids})

Note that when creating models and layers withsubclassing then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function!

call

< source >

( input_ids: TFModelInputType | None = None attention_mask: np.ndarray | tf.Tensor | None = None token_type_ids: np.ndarray | tf.Tensor | None = None position_ids: np.ndarray | tf.Tensor | None = None head_mask: np.ndarray | tf.Tensor | None = None inputs_embeds: np.ndarray | tf.Tensor | None = None output_attentions: Optional[bool] = None output_hidden_states: Optional[bool] = None return_dict: Optional[bool] = None labels: np.ndarray | tf.Tensor | None = None training: Optional[bool] = False ) → transformers.modeling_tf_outputs.TFSequenceClassifierOutput or tuple(tf.Tensor)

Parameters

• input_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.call() andPreTrainedTokenizer.encode() for details.
  What are input IDs?
• attention_mask (Numpy array or tf.Tensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• token_type_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token.
    What are token type IDs?
• position_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].
  What are position IDs?
• head_mask (Numpy array or tf.Tensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• inputs_embeds (tf.Tensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
• output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
• output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
• training (bool, optional, defaults to False) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).
• labels (tf.Tensor of shape (batch_size,), optional) — Labels for computing the sequence classification/regression loss. Indices should be in [0, ..., config.num_labels - 1]. If config.num_labels == 1 a regression loss is computed (Mean-Square loss), Ifconfig.num_labels > 1 a classification loss is computed (Cross-Entropy).

A transformers.modeling_tf_outputs.TFSequenceClassifierOutput or a tuple of tf.Tensor (ifreturn_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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.

The TFRobertaPreLayerNormForSequenceClassification forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

from transformers import AutoTokenizer, TFRobertaPreLayerNormForSequenceClassification import tensorflow as tf

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") model = TFRobertaPreLayerNormForSequenceClassification.from_pretrained("andreasmadsen/efficient_mlm_m0.40")

inputs = tokenizer("Hello, my dog is cute", return_tensors="tf")

logits = model(**inputs).logits

predicted_class_id = int(tf.math.argmax(logits, axis=-1)[0])

num_labels = len(model.config.id2label) model = TFRobertaPreLayerNormForSequenceClassification.from_pretrained("andreasmadsen/efficient_mlm_m0.40", num_labels=num_labels)

labels = tf.constant(1) loss = model(**inputs, labels=labels).loss

TFRobertaPreLayerNormForMultipleChoice

class transformers.TFRobertaPreLayerNormForMultipleChoice

< source >

( config *inputs **kwargs )

Parameters

• config (RobertaPreLayerNormConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

RobertaPreLayerNorm Model with a multiple choice classification head on top (a linear layer on top of the pooled output and a softmax) e.g. for RocStories/SWAG tasks.

This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

TensorFlow models and layers in transformers accept two formats as input:

• having all inputs as keyword arguments (like PyTorch models), or
• having all inputs as a list, tuple or dict in the first positional argument.

The reason the second format is supported is that Keras methods prefer this format when passing inputs to models and layers. Because of this support, when using methods like model.fit() things should “just work” for you - just pass your inputs and labels in any format that model.fit() supports! If, however, you want to use the second format outside of Keras methods like fit() and predict(), such as when creating your own layers or models with the Keras Functional API, there are three possibilities you can use to gather all the input Tensors in the first positional argument:

• a single Tensor with input_ids only and nothing else: model(input_ids)
• a list of varying length with one or several input Tensors IN THE ORDER given in the docstring:model([input_ids, attention_mask]) or model([input_ids, attention_mask, token_type_ids])
• a dictionary with one or several input Tensors associated to the input names given in the docstring:model({"input_ids": input_ids, "token_type_ids": token_type_ids})

Note that when creating models and layers withsubclassing then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function!

call

< source >

( input_ids: TFModelInputType | None = None attention_mask: np.ndarray | tf.Tensor | None = None token_type_ids: np.ndarray | tf.Tensor | None = None position_ids: np.ndarray | tf.Tensor | None = None head_mask: np.ndarray | tf.Tensor | None = None inputs_embeds: np.ndarray | tf.Tensor | None = None output_attentions: Optional[bool] = None output_hidden_states: Optional[bool] = None return_dict: Optional[bool] = None labels: np.ndarray | tf.Tensor | None = None training: Optional[bool] = False ) → transformers.modeling_tf_outputs.TFMultipleChoiceModelOutput or tuple(tf.Tensor)

Parameters

• input_ids (Numpy array or tf.Tensor of shape (batch_size, num_choices, sequence_length)) — Indices of input sequence tokens in the vocabulary.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.call() andPreTrainedTokenizer.encode() for details.
  What are input IDs?
• attention_mask (Numpy array or tf.Tensor of shape (batch_size, num_choices, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• token_type_ids (Numpy array or tf.Tensor of shape (batch_size, num_choices, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token.
    What are token type IDs?
• position_ids (Numpy array or tf.Tensor of shape (batch_size, num_choices, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].
  What are position IDs?
• head_mask (Numpy array or tf.Tensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• inputs_embeds (tf.Tensor of shape (batch_size, num_choices, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
• output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
• output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
• training (bool, optional, defaults to False) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).
• labels (tf.Tensor of shape (batch_size,), optional) — Labels for computing the multiple choice classification loss. Indices should be in [0, ..., num_choices]where num_choices is the size of the second dimension of the input tensors. (See input_ids above)

A transformers.modeling_tf_outputs.TFMultipleChoiceModelOutput or a tuple of tf.Tensor (ifreturn_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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.

The TFRobertaPreLayerNormForMultipleChoice forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

from transformers import AutoTokenizer, TFRobertaPreLayerNormForMultipleChoice import tensorflow as tf

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") model = TFRobertaPreLayerNormForMultipleChoice.from_pretrained("andreasmadsen/efficient_mlm_m0.40")

prompt = "In Italy, pizza served in formal settings, such as at a restaurant, is presented unsliced." choice0 = "It is eaten with a fork and a knife." choice1 = "It is eaten while held in the hand."

encoding = tokenizer([prompt, prompt], [choice0, choice1], return_tensors="tf", padding=True) inputs = {k: tf.expand_dims(v, 0) for k, v in encoding.items()} outputs = model(inputs)

logits = outputs.logits

TFRobertaPreLayerNormForTokenClassification

class transformers.TFRobertaPreLayerNormForTokenClassification

< source >

( config *inputs **kwargs )

Parameters

• config (RobertaPreLayerNormConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

RoBERTa-PreLayerNorm Model with a token classification head on top (a linear layer on top of the hidden-states output) e.g. for Named-Entity-Recognition (NER) tasks.

This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

TensorFlow models and layers in transformers accept two formats as input:

• having all inputs as keyword arguments (like PyTorch models), or
• having all inputs as a list, tuple or dict in the first positional argument.

The reason the second format is supported is that Keras methods prefer this format when passing inputs to models and layers. Because of this support, when using methods like model.fit() things should “just work” for you - just pass your inputs and labels in any format that model.fit() supports! If, however, you want to use the second format outside of Keras methods like fit() and predict(), such as when creating your own layers or models with the Keras Functional API, there are three possibilities you can use to gather all the input Tensors in the first positional argument:

• a single Tensor with input_ids only and nothing else: model(input_ids)
• a list of varying length with one or several input Tensors IN THE ORDER given in the docstring:model([input_ids, attention_mask]) or model([input_ids, attention_mask, token_type_ids])
• a dictionary with one or several input Tensors associated to the input names given in the docstring:model({"input_ids": input_ids, "token_type_ids": token_type_ids})

Note that when creating models and layers withsubclassing then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function!

call

< source >

( input_ids: TFModelInputType | None = None attention_mask: np.ndarray | tf.Tensor | None = None token_type_ids: np.ndarray | tf.Tensor | None = None position_ids: np.ndarray | tf.Tensor | None = None head_mask: np.ndarray | tf.Tensor | None = None inputs_embeds: np.ndarray | tf.Tensor | None = None output_attentions: Optional[bool] = None output_hidden_states: Optional[bool] = None return_dict: Optional[bool] = None labels: np.ndarray | tf.Tensor | None = None training: Optional[bool] = False ) → transformers.modeling_tf_outputs.TFTokenClassifierOutput or tuple(tf.Tensor)

Parameters

• input_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.call() andPreTrainedTokenizer.encode() for details.
  What are input IDs?
• attention_mask (Numpy array or tf.Tensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• token_type_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token.
    What are token type IDs?
• position_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].
  What are position IDs?
• head_mask (Numpy array or tf.Tensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• inputs_embeds (tf.Tensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
• output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
• output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
• training (bool, optional, defaults to False) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).
• labels (tf.Tensor of shape (batch_size, sequence_length), optional) — Labels for computing the token classification loss. Indices should be in [0, ..., config.num_labels - 1].

A transformers.modeling_tf_outputs.TFTokenClassifierOutput or a tuple of tf.Tensor (ifreturn_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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.

The TFRobertaPreLayerNormForTokenClassification forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

from transformers import AutoTokenizer, TFRobertaPreLayerNormForTokenClassification import tensorflow as tf

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") model = TFRobertaPreLayerNormForTokenClassification.from_pretrained("andreasmadsen/efficient_mlm_m0.40")

inputs = tokenizer( ... "HuggingFace is a company based in Paris and New York", add_special_tokens=False, return_tensors="tf" ... )

logits = model(**inputs).logits predicted_token_class_ids = tf.math.argmax(logits, axis=-1)

predicted_tokens_classes = [model.config.id2label[t] for t in predicted_token_class_ids[0].numpy().tolist()]

labels = predicted_token_class_ids loss = tf.math.reduce_mean(model(**inputs, labels=labels).loss)

TFRobertaPreLayerNormForQuestionAnswering

class transformers.TFRobertaPreLayerNormForQuestionAnswering

< source >

( config *inputs **kwargs )

Parameters

• config (RobertaPreLayerNormConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

RoBERTa-PreLayerNorm Model with a span classification head on top for extractive question-answering tasks like SQuAD (a linear layers on top of the hidden-states output to compute span start logits and span end logits).

This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

TensorFlow models and layers in transformers accept two formats as input:

• having all inputs as keyword arguments (like PyTorch models), or
• having all inputs as a list, tuple or dict in the first positional argument.

The reason the second format is supported is that Keras methods prefer this format when passing inputs to models and layers. Because of this support, when using methods like model.fit() things should “just work” for you - just pass your inputs and labels in any format that model.fit() supports! If, however, you want to use the second format outside of Keras methods like fit() and predict(), such as when creating your own layers or models with the Keras Functional API, there are three possibilities you can use to gather all the input Tensors in the first positional argument:

• a single Tensor with input_ids only and nothing else: model(input_ids)
• a list of varying length with one or several input Tensors IN THE ORDER given in the docstring:model([input_ids, attention_mask]) or model([input_ids, attention_mask, token_type_ids])
• a dictionary with one or several input Tensors associated to the input names given in the docstring:model({"input_ids": input_ids, "token_type_ids": token_type_ids})

Note that when creating models and layers withsubclassing then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function!

call

< source >

( input_ids: TFModelInputType | None = None attention_mask: np.ndarray | tf.Tensor | None = None token_type_ids: np.ndarray | tf.Tensor | None = None position_ids: np.ndarray | tf.Tensor | None = None head_mask: np.ndarray | tf.Tensor | None = None inputs_embeds: np.ndarray | tf.Tensor | None = None output_attentions: Optional[bool] = None output_hidden_states: Optional[bool] = None return_dict: Optional[bool] = None start_positions: np.ndarray | tf.Tensor | None = None end_positions: np.ndarray | tf.Tensor | None = None training: Optional[bool] = False ) → transformers.modeling_tf_outputs.TFQuestionAnsweringModelOutput or tuple(tf.Tensor)

Parameters

• input_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.call() andPreTrainedTokenizer.encode() for details.
  What are input IDs?
• attention_mask (Numpy array or tf.Tensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• token_type_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token.
    What are token type IDs?
• position_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].
  What are position IDs?
• head_mask (Numpy array or tf.Tensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• inputs_embeds (tf.Tensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
• output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
• output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
• training (bool, optional, defaults to False) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).
• start_positions (tf.Tensor of shape (batch_size,), optional) — Labels for position (index) of the start of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length). Position outside of the sequence are not taken into account for computing the loss.
• end_positions (tf.Tensor of shape (batch_size,), optional) — Labels for position (index) of the end of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length). Position outside of the sequence are not taken into account for computing the loss.

A transformers.modeling_tf_outputs.TFQuestionAnsweringModelOutput or a tuple of tf.Tensor (ifreturn_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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.

The TFRobertaPreLayerNormForQuestionAnswering forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

from transformers import AutoTokenizer, TFRobertaPreLayerNormForQuestionAnswering import tensorflow as tf

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") model = TFRobertaPreLayerNormForQuestionAnswering.from_pretrained("andreasmadsen/efficient_mlm_m0.40")

question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"

inputs = tokenizer(question, text, return_tensors="tf") outputs = model(**inputs)

answer_start_index = int(tf.math.argmax(outputs.start_logits, axis=-1)[0]) answer_end_index = int(tf.math.argmax(outputs.end_logits, axis=-1)[0])

predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1]

target_start_index = tf.constant([14]) target_end_index = tf.constant([15])

outputs = model(**inputs, start_positions=target_start_index, end_positions=target_end_index) loss = tf.math.reduce_mean(outputs.loss)

FlaxRobertaPreLayerNormModel

class transformers.FlaxRobertaPreLayerNormModel

< source >

( config: RobertaPreLayerNormConfig input_shape: typing.Tuple = (1, 1) seed: int = 0 dtype: dtype = <class 'jax.numpy.float32'> _do_init: bool = True gradient_checkpointing: bool = False **kwargs )

Parameters

• config (RobertaPreLayerNormConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

The bare RoBERTa-PreLayerNorm Model transformer outputting raw hidden-states without any specific head on top.

This model inherits from FlaxPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading, saving and converting weights from PyTorch models)

This model is also aflax.linen.Module subclass. Use it as a regular Flax linen Module and refer to the Flax documentation for all matter related to general usage and behavior.

Finally, this model supports inherent JAX features such as:

• Just-In-Time (JIT) compilation
• Automatic Differentiation
• Vectorization
• Parallelization

__call__

< source >

( input_ids attention_mask = None token_type_ids = None position_ids = None head_mask = None encoder_hidden_states = None encoder_attention_mask = None params: typing.Optional[dict] = None dropout_rng: <function PRNGKey at 0x7f69ffb94700> = None train: bool = False output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None past_key_values: typing.Optional[dict] = None ) → transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPooling or tuple(torch.FloatTensor)

Parameters

• input_ids (numpy.ndarray of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() andPreTrainedTokenizer.call() for details.
  What are input IDs?
• attention_mask (numpy.ndarray of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• token_type_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token.
    What are token type IDs?
• position_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].
• head_mask (numpy.ndarray of shape (batch_size, sequence_length), optional) -- Mask to nullify selected heads of the attention modules. Mask values selected in [0, 1]`:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.

A transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPooling or a tuple oftorch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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.

The FlaxRobertaPreLayerNormPreTrainedModel forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

from transformers import AutoTokenizer, FlaxRobertaPreLayerNormModel

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") model = FlaxRobertaPreLayerNormModel.from_pretrained("andreasmadsen/efficient_mlm_m0.40")

inputs = tokenizer("Hello, my dog is cute", return_tensors="jax") outputs = model(**inputs)

last_hidden_states = outputs.last_hidden_state

FlaxRobertaPreLayerNormForCausalLM

class transformers.FlaxRobertaPreLayerNormForCausalLM

< source >

( config: RobertaPreLayerNormConfig input_shape: typing.Tuple = (1, 1) seed: int = 0 dtype: dtype = <class 'jax.numpy.float32'> _do_init: bool = True gradient_checkpointing: bool = False **kwargs )

Parameters

• config (RobertaPreLayerNormConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

RobertaPreLayerNorm Model with a language modeling head on top (a linear layer on top of the hidden-states output) e.g for autoregressive tasks.

This model inherits from FlaxPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading, saving and converting weights from PyTorch models)

This model is also aflax.linen.Module subclass. Use it as a regular Flax linen Module and refer to the Flax documentation for all matter related to general usage and behavior.

Finally, this model supports inherent JAX features such as:

• Just-In-Time (JIT) compilation
• Automatic Differentiation
• Vectorization
• Parallelization

__call__

< source >

( input_ids attention_mask = None token_type_ids = None position_ids = None head_mask = None encoder_hidden_states = None encoder_attention_mask = None params: typing.Optional[dict] = None dropout_rng: <function PRNGKey at 0x7f69ffb94700> = None train: bool = False output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None past_key_values: typing.Optional[dict] = None ) → transformers.modeling_flax_outputs.FlaxCausalLMOutputWithCrossAttentions or tuple(torch.FloatTensor)

Parameters

• input_ids (numpy.ndarray of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() andPreTrainedTokenizer.call() for details.
  What are input IDs?
• attention_mask (numpy.ndarray of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• token_type_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token.
    What are token type IDs?
• position_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].
• head_mask (numpy.ndarray of shape (batch_size, sequence_length), optional) -- Mask to nullify selected heads of the attention modules. Mask values selected in [0, 1]`:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.

A transformers.modeling_flax_outputs.FlaxCausalLMOutputWithCrossAttentions or a tuple oftorch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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 (seepast_key_values input) to speed up sequential decoding.

The FlaxRobertaPreLayerNormPreTrainedModel forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

from transformers import AutoTokenizer, FlaxRobertaPreLayerNormForCausalLM

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") model = FlaxRobertaPreLayerNormForCausalLM.from_pretrained("andreasmadsen/efficient_mlm_m0.40")

inputs = tokenizer("Hello, my dog is cute", return_tensors="np") outputs = model(**inputs)

next_token_logits = outputs.logits[:, -1]

FlaxRobertaPreLayerNormForMaskedLM

class transformers.FlaxRobertaPreLayerNormForMaskedLM

< source >

( config: RobertaPreLayerNormConfig input_shape: typing.Tuple = (1, 1) seed: int = 0 dtype: dtype = <class 'jax.numpy.float32'> _do_init: bool = True gradient_checkpointing: bool = False **kwargs )

Parameters

• config (RobertaPreLayerNormConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

RoBERTa-PreLayerNorm Model with a language modeling head on top.

This model inherits from FlaxPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading, saving and converting weights from PyTorch models)

This model is also aflax.linen.Module subclass. Use it as a regular Flax linen Module and refer to the Flax documentation for all matter related to general usage and behavior.

Finally, this model supports inherent JAX features such as:

• Just-In-Time (JIT) compilation
• Automatic Differentiation
• Vectorization
• Parallelization

__call__

< source >

( input_ids attention_mask = None token_type_ids = None position_ids = None head_mask = None encoder_hidden_states = None encoder_attention_mask = None params: typing.Optional[dict] = None dropout_rng: <function PRNGKey at 0x7f69ffb94700> = None train: bool = False output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None past_key_values: typing.Optional[dict] = None ) → transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPooling or tuple(torch.FloatTensor)

Parameters

• input_ids (numpy.ndarray of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() andPreTrainedTokenizer.call() for details.
  What are input IDs?
• attention_mask (numpy.ndarray of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• token_type_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token.
    What are token type IDs?
• position_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].
• head_mask (numpy.ndarray of shape (batch_size, sequence_length), optional) -- Mask to nullify selected heads of the attention modules. Mask values selected in [0, 1]`:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.

A transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPooling or a tuple oftorch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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.

The FlaxRobertaPreLayerNormPreTrainedModel forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

from transformers import AutoTokenizer, FlaxRobertaPreLayerNormForMaskedLM

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") model = FlaxRobertaPreLayerNormForMaskedLM.from_pretrained("andreasmadsen/efficient_mlm_m0.40")

inputs = tokenizer("The capital of France is [MASK].", return_tensors="jax")

outputs = model(**inputs) logits = outputs.logits

FlaxRobertaPreLayerNormForSequenceClassification

class transformers.FlaxRobertaPreLayerNormForSequenceClassification

< source >

( config: RobertaPreLayerNormConfig input_shape: typing.Tuple = (1, 1) seed: int = 0 dtype: dtype = <class 'jax.numpy.float32'> _do_init: bool = True gradient_checkpointing: bool = False **kwargs )

Parameters

• config (RobertaPreLayerNormConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

RobertaPreLayerNorm Model transformer with a sequence classification/regression head on top (a linear layer on top of the pooled output) e.g. for GLUE tasks.

This model inherits from FlaxPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading, saving and converting weights from PyTorch models)

This model is also aflax.linen.Module subclass. Use it as a regular Flax linen Module and refer to the Flax documentation for all matter related to general usage and behavior.

Finally, this model supports inherent JAX features such as:

• Just-In-Time (JIT) compilation
• Automatic Differentiation
• Vectorization
• Parallelization

__call__

< source >

( input_ids attention_mask = None token_type_ids = None position_ids = None head_mask = None encoder_hidden_states = None encoder_attention_mask = None params: typing.Optional[dict] = None dropout_rng: <function PRNGKey at 0x7f69ffb94700> = None train: bool = False output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None past_key_values: typing.Optional[dict] = None ) → transformers.modeling_flax_outputs.FlaxSequenceClassifierOutput or tuple(torch.FloatTensor)

Parameters

• input_ids (numpy.ndarray of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() andPreTrainedTokenizer.call() for details.
  What are input IDs?
• attention_mask (numpy.ndarray of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• token_type_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token.
    What are token type IDs?
• position_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].
• head_mask (numpy.ndarray of shape (batch_size, sequence_length), optional) -- Mask to nullify selected heads of the attention modules. Mask values selected in [0, 1]`:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.

A transformers.modeling_flax_outputs.FlaxSequenceClassifierOutput or a tuple oftorch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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.

The FlaxRobertaPreLayerNormPreTrainedModel forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

from transformers import AutoTokenizer, FlaxRobertaPreLayerNormForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") model = FlaxRobertaPreLayerNormForSequenceClassification.from_pretrained("andreasmadsen/efficient_mlm_m0.40")

inputs = tokenizer("Hello, my dog is cute", return_tensors="jax")

outputs = model(**inputs) logits = outputs.logits

FlaxRobertaPreLayerNormForMultipleChoice

class transformers.FlaxRobertaPreLayerNormForMultipleChoice

< source >

( config: RobertaPreLayerNormConfig input_shape: typing.Tuple = (1, 1) seed: int = 0 dtype: dtype = <class 'jax.numpy.float32'> _do_init: bool = True gradient_checkpointing: bool = False **kwargs )

Parameters

• config (RobertaPreLayerNormConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

RobertaPreLayerNorm Model with a multiple choice classification head on top (a linear layer on top of the pooled output and a softmax) e.g. for RocStories/SWAG tasks.

This model inherits from FlaxPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading, saving and converting weights from PyTorch models)

This model is also aflax.linen.Module subclass. Use it as a regular Flax linen Module and refer to the Flax documentation for all matter related to general usage and behavior.

Finally, this model supports inherent JAX features such as:

• Just-In-Time (JIT) compilation
• Automatic Differentiation
• Vectorization
• Parallelization

__call__

< source >

( input_ids attention_mask = None token_type_ids = None position_ids = None head_mask = None encoder_hidden_states = None encoder_attention_mask = None params: typing.Optional[dict] = None dropout_rng: <function PRNGKey at 0x7f69ffb94700> = None train: bool = False output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None past_key_values: typing.Optional[dict] = None ) → transformers.modeling_flax_outputs.FlaxMultipleChoiceModelOutput or tuple(torch.FloatTensor)

Parameters

• input_ids (numpy.ndarray of shape (batch_size, num_choices, sequence_length)) — Indices of input sequence tokens in the vocabulary.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() andPreTrainedTokenizer.call() for details.
  What are input IDs?
• attention_mask (numpy.ndarray of shape (batch_size, num_choices, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• token_type_ids (numpy.ndarray of shape (batch_size, num_choices, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token.
    What are token type IDs?
• position_ids (numpy.ndarray of shape (batch_size, num_choices, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].
• head_mask (numpy.ndarray of shape (batch_size, num_choices, sequence_length), optional) -- Mask to nullify selected heads of the attention modules. Mask values selected in [0, 1]`:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.

A transformers.modeling_flax_outputs.FlaxMultipleChoiceModelOutput or a tuple oftorch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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.

The FlaxRobertaPreLayerNormPreTrainedModel forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

from transformers import AutoTokenizer, FlaxRobertaPreLayerNormForMultipleChoice

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") model = FlaxRobertaPreLayerNormForMultipleChoice.from_pretrained("andreasmadsen/efficient_mlm_m0.40")

prompt = "In Italy, pizza served in formal settings, such as at a restaurant, is presented unsliced." choice0 = "It is eaten with a fork and a knife." choice1 = "It is eaten while held in the hand."

encoding = tokenizer([prompt, prompt], [choice0, choice1], return_tensors="jax", padding=True) outputs = model(**{k: v[None, :] for k, v in encoding.items()})

logits = outputs.logits

FlaxRobertaPreLayerNormForTokenClassification

class transformers.FlaxRobertaPreLayerNormForTokenClassification

< source >

( config: RobertaPreLayerNormConfig input_shape: typing.Tuple = (1, 1) seed: int = 0 dtype: dtype = <class 'jax.numpy.float32'> _do_init: bool = True gradient_checkpointing: bool = False **kwargs )

Parameters

• config (RobertaPreLayerNormConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

RobertaPreLayerNorm Model with a token classification head on top (a linear layer on top of the hidden-states output) e.g. for Named-Entity-Recognition (NER) tasks.

This model inherits from FlaxPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading, saving and converting weights from PyTorch models)

This model is also aflax.linen.Module subclass. Use it as a regular Flax linen Module and refer to the Flax documentation for all matter related to general usage and behavior.

Finally, this model supports inherent JAX features such as:

• Just-In-Time (JIT) compilation
• Automatic Differentiation
• Vectorization
• Parallelization

__call__

< source >

( input_ids attention_mask = None token_type_ids = None position_ids = None head_mask = None encoder_hidden_states = None encoder_attention_mask = None params: typing.Optional[dict] = None dropout_rng: <function PRNGKey at 0x7f69ffb94700> = None train: bool = False output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None past_key_values: typing.Optional[dict] = None ) → transformers.modeling_flax_outputs.FlaxTokenClassifierOutput or tuple(torch.FloatTensor)

Parameters

• input_ids (numpy.ndarray of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() andPreTrainedTokenizer.call() for details.
  What are input IDs?
• attention_mask (numpy.ndarray of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• token_type_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token.
    What are token type IDs?
• position_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].
• head_mask (numpy.ndarray of shape (batch_size, sequence_length), optional) -- Mask to nullify selected heads of the attention modules. Mask values selected in [0, 1]`:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.

A transformers.modeling_flax_outputs.FlaxTokenClassifierOutput or a tuple oftorch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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.

The FlaxRobertaPreLayerNormPreTrainedModel forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

from transformers import AutoTokenizer, FlaxRobertaPreLayerNormForTokenClassification

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") model = FlaxRobertaPreLayerNormForTokenClassification.from_pretrained("andreasmadsen/efficient_mlm_m0.40")

inputs = tokenizer("Hello, my dog is cute", return_tensors="jax")

outputs = model(**inputs) logits = outputs.logits

FlaxRobertaPreLayerNormForQuestionAnswering

class transformers.FlaxRobertaPreLayerNormForQuestionAnswering

< source >

( config: RobertaPreLayerNormConfig input_shape: typing.Tuple = (1, 1) seed: int = 0 dtype: dtype = <class 'jax.numpy.float32'> _do_init: bool = True gradient_checkpointing: bool = False **kwargs )

Parameters

• config (RobertaPreLayerNormConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

RobertaPreLayerNorm Model with a span classification head on top for extractive question-answering tasks like SQuAD (a linear layers on top of the hidden-states output to compute span start logits and span end logits).

This model inherits from FlaxPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading, saving and converting weights from PyTorch models)

This model is also aflax.linen.Module subclass. Use it as a regular Flax linen Module and refer to the Flax documentation for all matter related to general usage and behavior.

Finally, this model supports inherent JAX features such as:

• Just-In-Time (JIT) compilation
• Automatic Differentiation
• Vectorization
• Parallelization

__call__

< source >

( input_ids attention_mask = None token_type_ids = None position_ids = None head_mask = None encoder_hidden_states = None encoder_attention_mask = None params: typing.Optional[dict] = None dropout_rng: <function PRNGKey at 0x7f69ffb94700> = None train: bool = False output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None past_key_values: typing.Optional[dict] = None ) → transformers.modeling_flax_outputs.FlaxQuestionAnsweringModelOutput or tuple(torch.FloatTensor)

Parameters

• input_ids (numpy.ndarray of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.
  Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() andPreTrainedTokenizer.call() for details.
  What are input IDs?
• attention_mask (numpy.ndarray of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
    What are attention masks?
• token_type_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:
  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token.
    What are token type IDs?
• position_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].
• head_mask (numpy.ndarray of shape (batch_size, sequence_length), optional) -- Mask to nullify selected heads of the attention modules. Mask values selected in [0, 1]`:
  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.

A transformers.modeling_flax_outputs.FlaxQuestionAnsweringModelOutput or a tuple oftorch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (RobertaPreLayerNormConfig) and inputs.

• 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.

The FlaxRobertaPreLayerNormPreTrainedModel forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

from transformers import AutoTokenizer, FlaxRobertaPreLayerNormForQuestionAnswering

tokenizer = AutoTokenizer.from_pretrained("andreasmadsen/efficient_mlm_m0.40") model = FlaxRobertaPreLayerNormForQuestionAnswering.from_pretrained("andreasmadsen/efficient_mlm_m0.40")

question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet" inputs = tokenizer(question, text, return_tensors="jax")

outputs = model(**inputs) start_scores = outputs.start_logits end_scores = outputs.end_logits