GPT NeoΒΆ

OverviewΒΆ

The GPTNeo model was released in the EleutherAI/gpt-neo repository by Sid Black, Stella Biderman, Leo Gao, Phil Wang and Connor Leahy. It is a GPT2 like causal language model trained on the Pile dataset.

The architecture is similar to GPT2 except that GPT Neo uses local attention in every other layer with a window size of 256 tokens.

This model was contributed by valhalla.

GenerationΒΆ

The generate() method can be used to generate text using GPT Neo model.

>>> from transformers import GPTNeoForCausalLM, GPT2Tokenizer
>>> model = GPTNeoForCausalLM.from_pretrained("EleutherAI/gpt-neo-1.3B")
>>> tokenizer = GPT2Tokenizer.from_pretrained("EleutherAI/gpt-neo-1.3B")

>>> prompt = "In a shocking finding, scientists discovered a herd of unicorns living in a remote, " \
...          "previously unexplored valley, in the Andes Mountains. Even more surprising to the " \
...          "researchers was the fact that the unicorns spoke perfect English."

>>> input_ids = tokenizer(prompt, return_tensors="pt").input_ids

>>> gen_tokens = model.generate(input_ids, do_sample=True, temperature=0.9, max_length=100,)
>>> gen_text = tokenizer.batch_decode(gen_tokens)[0]

GPTNeoConfigΒΆ

class transformers.GPTNeoConfig(vocab_size=50257, max_position_embeddings=2048, hidden_size=2048, num_layers=24, attention_types=[[['global', 'local'], 12]], num_heads=16, intermediate_size=None, window_size=256, activation_function='gelu_new', resid_dropout=0.0, embed_dropout=0.0, attention_dropout=0.0, layer_norm_epsilon=1e-05, initializer_range=0.02, summary_type='cls_index', summary_use_proj=True, summary_activation=None, summary_proj_to_labels=True, summary_first_dropout=0.1, gradient_checkpointing=False, use_cache=True, bos_token_id=50256, eos_token_id=50256, **kwargs)[source]ΒΆ

This is the configuration class to store the configuration of a GPTNeoModel. It is used to instantiate a GPT Neo 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 GPTNeo gpt-neo-1.3B architecture.

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

Parameters
  • vocab_size (int, optional, defaults to 50257) – Vocabulary size of the GPT Neo model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling GPTNeoModel. Vocabulary size of the model. Defines the different tokens that can be represented by the inputs_ids passed to the forward method of GPTNeoModel.

  • attention_types (List, optional, defaults to [[["global", "local"], 12]]) – The type of attention for each layer in a List of the following format [[["attention_type"], num_layerss]] e.g. for a 24 layer model [[["global"], 24]] or [[["global", "local"], 12]] Choose the value of attention_type from ["global", "local"]

  • hidden_size (int, optional, defaults to 2048) – Dimensionality of the encoder layers and the pooler layer.

  • num_layers (int, optional, defaults to 24) – Number of hidden layers in the Transformer encoder.

  • num_heads (int, optional, defaults to 16) – Number of attention heads for each attention layer in the Transformer encoder.

  • intermediate_size (int, optional, defaults to 8192) – Dimensionality of the β€œintermediate” (i.e., feed-forward) layer in the Transformer encoder.

  • activation_function (str or function, optional, defaults to "gelu_new") – The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu", "relu", "selu" and "gelu_new" are supported.

  • embed_dropout (float, optional, defaults to 0.0) – The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.

  • attention_dropout (float, optional, defaults to 0.0) – The dropout ratio for the attention probabilities.

  • max_position_embeddings (int, optional, defaults to 2048) – 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 GPTNeoModel.

  • initializer_range (float, optional, defaults to 0.02) – The standard deviation of the truncated_normal_initializer for initializing all weight matrices.

  • layer_norm_epsilon (float, optional, defaults to 1e-5) – The epsilon used by the layer normalization layers.

  • 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.

  • gradient_checkpointing (bool, optional, defaults to False) – If True, use gradient checkpointing to save memory at the expense of slower backward pass.

  • Example:: –

    >>> from transformers import GPTNeoModel, GPTNeoConfig
    
    >>> # Initializing a GPTNeo EleutherAI/gpt-neo-1.3B style configuration
    >>> configuration = GPTNeoConfig()
    
    >>> # Initializing a model from the EleutherAI/gpt-neo-1.3B style configuration
    >>> model = GPTNeoModel(configuration)
    
    >>> # Accessing the model configuration
    >>> configuration = model.config
    

GPTNeoModelΒΆ

class transformers.GPTNeoModel(config)[source]ΒΆ

The bare GPT Neo Model transformer outputting raw hidden-states without any specific 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.

Parameters

config (GPTNeoConfig) – 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.

forward(input_ids=None, past_key_values=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]ΒΆ

The GPTNeoModel forward method, overrides the __call__() special method.

Note

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

Parameters
  • input_ids (torch.LongTensor of shape (batch_size, input_ids_length)) –

    input_ids_length = sequence_length if past_key_values is None else past_key_values[0][0].shape[-2] (sequence_length of input past key value states). Indices of input sequence tokens in the vocabulary.

    If past_key_values is used, only input_ids that do not have their past calculated should be passed as input_ids.

    Indices can be obtained using GPTNeoTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

    What are input IDs?

  • past_key_values (Tuple[Tuple[torch.Tensor]] of length config.num_layers) – Contains precomputed hidden-states (key and values in the attention blocks) as computed by the model (see past_key_values output below). Can be used to speed up sequential decoding. The input_ids which have their past given to this model should not be passed as input_ids as they have already been computed.

  • 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, input_ids_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 (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.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, 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.

    If past_key_values is used, optionally only the last inputs_embeds have to be input (see past_key_values).

  • use_cache (bool, optional) – If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_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.

Returns

A BaseModelOutputWithPastAndCrossAttentions or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (GPTNeoConfig) 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.

    If past_key_values is used only the last hidden-state of the sequences of shape (batch_size, 1, hidden_size) is output.

  • past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) – Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and optionally if config.is_encoder_decoder=True 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

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

  • hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of torch.FloatTensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

    Hidden-states of the model at the output of each layer plus the initial embedding outputs.

  • attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

    Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

  • 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.

Return type

BaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)

Example:

>>> from transformers import GPT2Tokenizer, GPTNeoModel
>>> import torch

>>> tokenizer = GPT2Tokenizer.from_pretrained('EleutherAI/gpt-neo-1.3B')
>>> model = GPTNeoModel.from_pretrained('EleutherAI/gpt-neo-1.3B')

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

>>> last_hidden_states = outputs.last_hidden_state

GPTNeoForCausalLMΒΆ

class transformers.GPTNeoForCausalLM(config)[source]ΒΆ

The GPT Neo Model transformer with a language modeling head on top (linear layer with weights tied to the input embeddings).

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.

Parameters

config (GPTNeoConfig) – 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.

forward(input_ids=None, past_key_values=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, labels=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]ΒΆ

The GPTNeoForCausalLM forward method, overrides the __call__() special method.

Note

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

Parameters
  • input_ids (torch.LongTensor of shape (batch_size, input_ids_length)) –

    input_ids_length = sequence_length if past_key_values is None else past_key_values[0][0].shape[-2] (sequence_length of input past key value states). Indices of input sequence tokens in the vocabulary.

    If past_key_values is used, only input_ids that do not have their past calculated should be passed as input_ids.

    Indices can be obtained using GPTNeoTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

    What are input IDs?

  • past_key_values (Tuple[Tuple[torch.Tensor]] of length config.num_layers) – Contains precomputed hidden-states (key and values in the attention blocks) as computed by the model (see past_key_values output below). Can be used to speed up sequential decoding. The input_ids which have their past given to this model should not be passed as input_ids as they have already been computed.

  • 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, input_ids_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 (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.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, 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.

    If past_key_values is used, optionally only the last inputs_embeds have to be input (see past_key_values).

  • use_cache (bool, optional) – If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_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.

  • labels (torch.LongTensor of shape (batch_size, sequence_length), optional) – Labels for language modeling. Note that the labels are shifted inside the model, i.e. you can set labels = input_ids Indices are selected in [-100, 0, ..., config.vocab_size] All labels set to -100 are ignored (masked), the loss is only computed for labels in [0, ..., config.vocab_size]

Returns

A CausalLMOutputWithCrossAttentions or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (GPTNeoConfig) 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 + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

    Hidden-states of the model at the output of each layer plus the initial embedding outputs.

  • attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

    Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

  • cross_attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

    Cross attentions weights after the attention softmax, used to compute the weighted average in the cross-attention heads.

  • past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) – Tuple of torch.FloatTensor tuples of length config.n_layers, with each tuple containing the cached key, value states of the self-attention and the cross-attention layers if model is used in encoder-decoder setting. Only relevant if config.is_decoder = True.

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

Return type

CausalLMOutputWithCrossAttentions or tuple(torch.FloatTensor)

Example:

>>> import torch
>>> from transformers import GPT2Tokenizer, GPTNeoForCausalLM

>>> tokenizer = GPT2Tokenizer.from_pretrained('EleutherAI/gpt-neo-1.3B')
>>> model = GPTNeoForCausalLM.from_pretrained('EleutherAI/gpt-neo-1.3B')

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> outputs = model(**inputs, labels=inputs["input_ids"])
>>> loss = outputs.loss
>>> logits = outputs.logits

GPTNeoForSequenceClassificationΒΆ

class transformers.GPTNeoForSequenceClassification(config)[source]ΒΆ

The GPTNeo Model transformer with a sequence classification head on top (linear layer).

GPTNeoForSequenceClassification uses the last token in order to do the classification, as other causal models (e.g. GPT-1) do.

Since it does classification on the last token, it requires to know the position of the last token. If a pad_token_id is defined in the configuration, it finds the last token that is not a padding token in each row. If no pad_token_id is defined, it simply takes the last value in each row of the batch. Since it cannot guess the padding tokens when inputs_embeds are passed instead of input_ids, it does the same (take the last value in each row of the batch).

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.

Parameters

config (GPTNeoConfig) – 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.

forward(input_ids=None, past_key_values=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, labels=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]ΒΆ

The GPTNeoForSequenceClassification forward method, overrides the __call__() special method.

Note

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

Parameters
  • input_ids (torch.LongTensor of shape (batch_size, input_ids_length)) –

    input_ids_length = sequence_length if past_key_values is None else past_key_values[0][0].shape[-2] (sequence_length of input past key value states). Indices of input sequence tokens in the vocabulary.

    If past_key_values is used, only input_ids that do not have their past calculated should be passed as input_ids.

    Indices can be obtained using GPTNeoTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

    What are input IDs?

  • past_key_values (Tuple[Tuple[torch.Tensor]] of length config.num_layers) – Contains precomputed hidden-states (key and values in the attention blocks) as computed by the model (see past_key_values output below). Can be used to speed up sequential decoding. The input_ids which have their past given to this model should not be passed as input_ids as they have already been computed.

  • 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, input_ids_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 (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.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, 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.

    If past_key_values is used, optionally only the last inputs_embeds have to be input (see past_key_values).

  • use_cache (bool, optional) – If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_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.

  • 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), If config.num_labels > 1 a classification loss is computed (Cross-Entropy).

Returns

A SequenceClassifierOutputWithPast or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (GPTNeoConfig) 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).

  • past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) – Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head))

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

  • hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of torch.FloatTensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

    Hidden-states of the model at the output of each layer plus the initial embedding outputs.

  • attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

    Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

Return type

SequenceClassifierOutputWithPast or tuple(torch.FloatTensor)

Example:

>>> from transformers import GPT2Tokenizer, GPTNeoForSequenceClassification
>>> import torch

>>> tokenizer = GPT2Tokenizer.from_pretrained('EleutherAI/gpt-neo-1.3B')
>>> model = GPTNeoForSequenceClassification.from_pretrained('EleutherAI/gpt-neo-1.3B')

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> labels = torch.tensor([1]).unsqueeze(0)  # Batch size 1
>>> outputs = model(**inputs, labels=labels)
>>> loss = outputs.loss
>>> logits = outputs.logits