CTRLΒΆ
OverviewΒΆ
CTRL model was proposed in CTRL: A Conditional Transformer Language Model for Controllable Generation by Nitish Shirish Keskar*, Bryan McCann*, Lav R. Varshney, Caiming Xiong and Richard Socher. Itβs a causal (unidirectional) transformer pre-trained using language modeling on a very large corpus of ~140 GB of text data with the first token reserved as a control code (such as Links, Books, Wikipedia etc.).
The abstract from the paper is the following:
Large-scale language models show promising text generation capabilities, but users cannot easily control particular aspects of the generated text. We release CTRL, a 1.63 billion-parameter conditional transformer language model, trained to condition on control codes that govern style, content, and task-specific behavior. Control codes were derived from structure that naturally co-occurs with raw text, preserving the advantages of unsupervised learning while providing more explicit control over text generation. These codes also allow CTRL to predict which parts of the training data are most likely given a sequence. This provides a potential method for analyzing large amounts of data via model-based source attribution.
Tips:
CTRL makes use of control codes to generate text: it requires generations to be started by certain words, sentences or links to generate coherent text. Refer to the original implementation for more information.
CTRL is a model with absolute position embeddings so itβs usually advised to pad the inputs on the right rather than the left.
CTRL was trained with a causal language modeling (CLM) objective and is therefore powerful at predicting the next token in a sequence. Leveraging this feature allows CTRL to generate syntactically coherent text as it can be observed in the run_generation.py example script.
The PyTorch models can take the past as input, which is the previously computed key/value attention pairs. Using this past value prevents the model from re-computing pre-computed values in the context of text generation. See reusing the past in generative models for more information on the usage of this argument.
This model was contributed by keskarnitishr. The original code can be found here.
CTRLConfigΒΆ
-
class
transformers.
CTRLConfig
(vocab_size=246534, n_positions=256, n_ctx=256, n_embd=1280, dff=8192, n_layer=48, n_head=16, resid_pdrop=0.1, embd_pdrop=0.1, attn_pdrop=0.1, layer_norm_epsilon=1e-06, 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, use_cache=True, **kwargs)[source]ΒΆ This is the configuration class to store the configuration of a
CTRLModel
or aTFCTRLModel
. It is used to instantiate a CTRL 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 ctrl architecture from SalesForce.Configuration objects inherit from
PretrainedConfig
and can be used to control the model outputs. Read the documentation fromPretrainedConfig
for more information.- Parameters
vocab_size (
int
, optional, defaults to 246534) β Vocabulary size of the CTRL model. Defines the number of different tokens that can be represented by theinputs_ids
passed when callingCTRLModel
orTFCTRLModel
.n_positions (
int
, optional, defaults to 256) β 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).n_ctx (
int
, optional, defaults to 256) β Dimensionality of the causal mask (usually same as n_positions).n_embd (
int
, optional, defaults to 1280) β Dimensionality of the embeddings and hidden states.dff (
int
, optional, defaults to 8192) β Dimensionality of the inner dimension of the feed forward networks (FFN).n_layer (
int
, optional, defaults to 48) β Number of hidden layers in the Transformer encoder.n_head (
int
, optional, defaults to 16) β Number of attention heads for each attention layer in the Transformer encoder.resid_pdrop (
float
, optional, defaults to 0.1) β The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.embd_pdrop (
int
, optional, defaults to 0.1) β The dropout ratio for the embeddings.attn_pdrop (
float
, optional, defaults to 0.1) β The dropout ratio for the attention.layer_norm_epsilon (
float
, optional, defaults to 1e-6) β The epsilon to use in the layer normalization layersinitializer_range (
float
, optional, defaults to 0.02) β The standard deviation of the truncated_normal_initializer for initializing all weight matrices.use_cache (
bool
, optional, defaults toTrue
) β Whether or not the model should return the last key/values attentions (not used by all models).
Examples:
>>> from transformers import CTRLModel, CTRLConfig >>> # Initializing a CTRL configuration >>> configuration = CTRLConfig() >>> # Initializing a model from the configuration >>> model = CTRLModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config
CTRLTokenizerΒΆ
-
class
transformers.
CTRLTokenizer
(vocab_file, merges_file, unk_token='<unk>', **kwargs)[source]ΒΆ Construct a CTRL tokenizer. Based on Byte-Pair-Encoding.
This tokenizer inherits from
PreTrainedTokenizer
which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.- Parameters
vocab_file (
str
) β Path to the vocabulary file.merges_file (
str
) β Path to the merges file.unk_token (
str
, optional, defaults to"<unk>"
) β The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead.
-
save_vocabulary
(save_directory: str, filename_prefix: Optional[str] = None) → Tuple[str][source]ΒΆ Save only the vocabulary of the tokenizer (vocabulary + added tokens).
This method wonβt save the configuration and special token mappings of the tokenizer. Use
_save_pretrained()
to save the whole state of the tokenizer.- Parameters
save_directory (
str
) β The directory in which to save the vocabulary.filename_prefix (
str
, optional) β An optional prefix to add to the named of the saved files.
- Returns
Paths to the files saved.
- Return type
Tuple(str)
CTRLModelΒΆ
-
class
transformers.
CTRLModel
(config)[source]ΒΆ The bare CTRL 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 (
CTRLConfig
) β 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.
-
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
CTRLModel
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, sequence_length)
) βinput_ids_length
=sequence_length
ifpast_key_values
isNone
elsepast_key_values[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 asinput_ids
.Indices can be obtained using
CTRLTokenizer
. Seetransformers.PreTrainedTokenizer.__call__()
andtransformers.PreTrainedTokenizer.encode()
for details.past_key_values (
Tuple[Tuple[torch.FloatTensor]]
of lengthconfig.n_layers
) β Contains pre-computed hidden-states (key and values in the attention blocks) as computed by the model (seepast_key_values
output below). Can be used to speed up sequential decoding. Theinput_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) βMask 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.
token_type_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) βSegment 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.
position_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) βIndices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) βMask 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) β Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_ids
indices into associated vectors than the modelβs internal embedding lookup matrix.use_cache (
bool
, optional) β If set toTrue
,past_key_values
key value states are returned and can be used to speed up decoding (seepast_key_values
).output_attentions (
bool
, optional) β Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail.output_hidden_states (
bool
, optional) β Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) β Whether or not to return aModelOutput
instead of a plain tuple.
- Returns
A
BaseModelOutputWithPast
or a tuple oftorch.FloatTensor
(ifreturn_dict=False
is passed or whenconfig.return_dict=False
) comprising various elements depending on the configuration (CTRLConfig
) and inputs.last_hidden_state (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
) β 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 whenuse_cache=True
is passed or whenconfig.use_cache=True
) β Tuple oftuple(torch.FloatTensor)
of lengthconfig.n_layers
, with each tuple having 2 tensors of shape(batch_size, num_heads, sequence_length, embed_size_per_head)
) and optionally ifconfig.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 (seepast_key_values
input) to speed up sequential decoding.hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.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
BaseModelOutputWithPast
ortuple(torch.FloatTensor)
Example:
>>> from transformers import CTRLTokenizer, CTRLModel >>> import torch >>> tokenizer = CTRLTokenizer.from_pretrained('ctrl') >>> model = CTRLModel.from_pretrained('ctrl') >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt") >>> outputs = model(**inputs) >>> last_hidden_states = outputs.last_hidden_state
CTRLLMHeadModelΒΆ
-
class
transformers.
CTRLLMHeadModel
(config)[source]ΒΆ The CTRL 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 (
CTRLConfig
) β 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.
-
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
CTRLLMHeadModel
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, sequence_length)
) βinput_ids_length
=sequence_length
ifpast_key_values
isNone
elsepast_key_values[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 asinput_ids
.Indices can be obtained using
CTRLTokenizer
. Seetransformers.PreTrainedTokenizer.__call__()
andtransformers.PreTrainedTokenizer.encode()
for details.past_key_values (
Tuple[Tuple[torch.FloatTensor]]
of lengthconfig.n_layers
) β Contains pre-computed hidden-states (key and values in the attention blocks) as computed by the model (seepast_key_values
output below). Can be used to speed up sequential decoding. Theinput_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) βMask 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.
token_type_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) βSegment 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.
position_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) βIndices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) βMask 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) β Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_ids
indices into associated vectors than the modelβs internal embedding lookup matrix.use_cache (
bool
, optional) β If set toTrue
,past_key_values
key value states are returned and can be used to speed up decoding (seepast_key_values
).output_attentions (
bool
, optional) β Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail.output_hidden_states (
bool
, optional) β Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) β Whether or not to return aModelOutput
instead of a plain tuple.labels (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) β Labels for language modeling. Note that the labels are shifted inside the model, i.e. you can setlabels = 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
CausalLMOutputWithPast
or a tuple oftorch.FloatTensor
(ifreturn_dict=False
is passed or whenconfig.return_dict=False
) comprising various elements depending on the configuration (CTRLConfig
) and inputs.loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) β Language modeling loss (for next-token prediction).logits (
torch.FloatTensor
of shape(batch_size, sequence_length, config.vocab_size)
) β Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).past_key_values (
tuple(tuple(torch.FloatTensor))
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) β Tuple oftuple(torch.FloatTensor)
of lengthconfig.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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.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
CausalLMOutputWithPast
ortuple(torch.FloatTensor)
Example:
>>> import torch >>> from transformers import CTRLTokenizer, CTRLLMHeadModel >>> tokenizer = CTRLTokenizer.from_pretrained('ctrl') >>> model = CTRLLMHeadModel.from_pretrained('ctrl') >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt") >>> outputs = model(**inputs, labels=inputs["input_ids"]) >>> loss = outputs.loss >>> logits = outputs.logits
CTRLForSequenceClassificationΒΆ
-
class
transformers.
CTRLForSequenceClassification
(config)[source]ΒΆ The CTRL Model transformer with a sequence classification head on top (linear layer).
CTRLForSequenceClassification
uses the last token in order to do the classification, as other causal models (e.g. GPT-2) do. Since it does classification on the last token, it requires to know the position of the last token. If apad_token_id
is defined in the configuration, it finds the last token that is not a padding token in each row. If nopad_token_id
is defined, it simply takes the last value in each row of the batch. Since it cannot guess the padding tokens wheninputs_embeds
are passed instead ofinput_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 (
CTRLConfig
) β 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.
-
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
CTRLForSequenceClassification
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, sequence_length)
) βinput_ids_length
=sequence_length
ifpast_key_values
isNone
elsepast_key_values[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 asinput_ids
.Indices can be obtained using
CTRLTokenizer
. Seetransformers.PreTrainedTokenizer.__call__()
andtransformers.PreTrainedTokenizer.encode()
for details.past_key_values (
Tuple[Tuple[torch.FloatTensor]]
of lengthconfig.n_layers
) β Contains pre-computed hidden-states (key and values in the attention blocks) as computed by the model (seepast_key_values
output below). Can be used to speed up sequential decoding. Theinput_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) βMask 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.
token_type_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) βSegment 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.
position_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) βIndices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) βMask 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) β Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_ids
indices into associated vectors than the modelβs internal embedding lookup matrix.use_cache (
bool
, optional) β If set toTrue
,past_key_values
key value states are returned and can be used to speed up decoding (seepast_key_values
).output_attentions (
bool
, optional) β Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail.output_hidden_states (
bool
, optional) β Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) β Whether or not to return aModelOutput
instead of a plain tuple.labels (
torch.LongTensor
of shape(batch_size,)
, optional) β Labels for computing the sequence classification/regression loss. Indices should be in[0, ..., config.num_labels - 1]
. Ifconfig.num_labels == 1
a regression loss is computed (Mean-Square loss), Ifconfig.num_labels > 1
a classification loss is computed (Cross-Entropy).
- Returns
A
SequenceClassifierOutput
or a tuple oftorch.FloatTensor
(ifreturn_dict=False
is passed or whenconfig.return_dict=False
) comprising various elements depending on the configuration (CTRLConfig
) and inputs.loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) β Classification (or regression if config.num_labels==1) loss.logits (
torch.FloatTensor
of shape(batch_size, config.num_labels)
) β Classification (or regression if config.num_labels==1) scores (before SoftMax).hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.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
SequenceClassifierOutput
ortuple(torch.FloatTensor)
Example:
>>> from transformers import CTRLTokenizer, CTRLForSequenceClassification >>> import torch >>> tokenizer = CTRLTokenizer.from_pretrained('ctrl') >>> model = CTRLForSequenceClassification.from_pretrained('ctrl') >>> 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
TFCTRLModelΒΆ
-
class
transformers.
TFCTRLModel
(*args, **kwargs)[source]ΒΆ The bare CTRL 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 tf.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.
Note
TF 2.0 models accepts two formats as inputs:
having all inputs as keyword arguments (like PyTorch models), or
having all inputs as a list, tuple or dict in the first positional arguments.
This second option is useful when using
tf.keras.Model.fit()
method which currently requires having all the tensors in the first argument of the model call function:model(inputs)
.If you choose this second option, 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(inputs_ids)
a list of varying length with one or several input Tensors IN THE ORDER given in the docstring:
model([input_ids, attention_mask])
ormodel([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})
- Parameters
config (
CTRLConfig
) β 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.
-
call
(input_ids=None, past=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, training=False, **kwargs)[source]ΒΆ The
TFCTRLModel
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 (
Numpy array
ortf.Tensor
of shape(batch_size, input_ids_length)
) βinput_ids_length
=sequence_length
ifpast
isNone
elsepast[0].shape[-2]
(sequence_length
of input past key value states).Indices of input sequence tokens in the vocabulary.
If
past
is used, only input IDs that do not have their past calculated should be passed asinput_ids
.Indices can be obtained using
CTRLTokenizer
. Seetransformers.PreTrainedTokenizer.__call__()
andtransformers.PreTrainedTokenizer.encode()
for details.past (
List[tf.Tensor]
of lengthconfig.n_layers
) β Contains pre-computed hidden-states (key and values in the attention blocks) as computed by the model (seepast
output below). Can be used to speed up sequential decoding. The token ids which have their past given to this model should not be passed as input ids as they have already been computed.attention_mask (
tf.Tensor
orNumpy array
of shape(batch_size, sequence_length)
, optional) βMask 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.
token_type_ids (
tf.Tensor
orNumpy array
of shape(batch_size, sequence_length)
, optional) βSegment 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.
position_ids (
tf.Tensor
orNumpy array
of shape(batch_size, sequence_length)
, optional) βIndices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) βMask 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
orNumpy array
of shape(batch_size, sequence_length, hidden_size)
, optional) β Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_ids
indices into associated vectors than the modelβs internal embedding lookup matrix.use_cache (
bool
, optional) β If set toTrue
,past
key value states are returned and can be used to speed up decoding (seepast
).output_attentions (
bool
, optional) β Whether or not to return the attentions tensors of all attention layers. Seeattentions
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) β Whether or not to return the hidden states of all layers. Seehidden_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) β Whether or not to return aModelOutput
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 toFalse
) β Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).
- Returns
A
TFBaseModelOutputWithPast
or a tuple oftf.Tensor
(ifreturn_dict=False
is passed or whenconfig.return_dict=False
) comprising various elements depending on the configuration (CTRLConfig
) and inputs.last_hidden_state (
tf.Tensor
of shape(batch_size, sequence_length, hidden_size)
) β Sequence of hidden-states at the output of the last layer of the model.If
past_key_values
is used only the last hidden-state of the sequences of shape(batch_size, 1, hidden_size)
is output.past_key_values (
List[tf.Tensor]
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) β List oftf.Tensor
of lengthconfig.n_layers
, with each tensor of shape(2, batch_size, num_heads, sequence_length, embed_size_per_head)
).Contains pre-computed hidden-states (key and values in the attention blocks) that can be used (see
past_key_values
input) to speed up sequential decoding.hidden_states (
tuple(tf.Tensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftf.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftf.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.
- Return type
TFBaseModelOutputWithPast
ortuple(tf.Tensor)
Example:
>>> from transformers import CTRLTokenizer, TFCTRLModel >>> import tensorflow as tf >>> tokenizer = CTRLTokenizer.from_pretrained('ctrl') >>> model = TFCTRLModel.from_pretrained('ctrl') >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="tf") >>> outputs = model(inputs) >>> last_hidden_states = outputs.last_hidden_state
TFCTRLLMHeadModelΒΆ
-
class
transformers.
TFCTRLLMHeadModel
(*args, **kwargs)[source]ΒΆ The CTRL Model transformer with a language modeling head on top (linear layer with weights tied to the input embeddings).
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 tf.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.
Note
TF 2.0 models accepts two formats as inputs:
having all inputs as keyword arguments (like PyTorch models), or
having all inputs as a list, tuple or dict in the first positional arguments.
This second option is useful when using
tf.keras.Model.fit()
method which currently requires having all the tensors in the first argument of the model call function:model(inputs)
.If you choose this second option, 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(inputs_ids)
a list of varying length with one or several input Tensors IN THE ORDER given in the docstring:
model([input_ids, attention_mask])
ormodel([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})
- Parameters
config (
CTRLConfig
) β 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.
-
call
(input_ids=None, past=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, labels=None, training=False, **kwargs)[source]ΒΆ The
TFCTRLLMHeadModel
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 (
Numpy array
ortf.Tensor
of shape(batch_size, input_ids_length)
) βinput_ids_length
=sequence_length
ifpast
isNone
elsepast[0].shape[-2]
(sequence_length
of input past key value states).Indices of input sequence tokens in the vocabulary.
If
past
is used, only input IDs that do not have their past calculated should be passed asinput_ids
.Indices can be obtained using
CTRLTokenizer
. Seetransformers.PreTrainedTokenizer.__call__()
andtransformers.PreTrainedTokenizer.encode()
for details.past (
List[tf.Tensor]
of lengthconfig.n_layers
) β Contains pre-computed hidden-states (key and values in the attention blocks) as computed by the model (seepast
output below). Can be used to speed up sequential decoding. The token ids which have their past given to this model should not be passed as input ids as they have already been computed.attention_mask (
tf.Tensor
orNumpy array
of shape(batch_size, sequence_length)
, optional) βMask 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.
token_type_ids (
tf.Tensor
orNumpy array
of shape(batch_size, sequence_length)
, optional) βSegment 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.
position_ids (
tf.Tensor
orNumpy array
of shape(batch_size, sequence_length)
, optional) βIndices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) βMask 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
orNumpy array
of shape(batch_size, sequence_length, hidden_size)
, optional) β Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_ids
indices into associated vectors than the modelβs internal embedding lookup matrix.use_cache (
bool
, optional) β If set toTrue
,past
key value states are returned and can be used to speed up decoding (seepast
).output_attentions (
bool
, optional) β Whether or not to return the attentions tensors of all attention layers. Seeattentions
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) β Whether or not to return the hidden states of all layers. Seehidden_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) β Whether or not to return aModelOutput
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 toFalse
) β 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) β Labels for computing the cross entropy classification loss. Indices should be in[0, ..., config.vocab_size - 1]
.
- Returns
A
TFCausalLMOutputWithPast
or a tuple oftf.Tensor
(ifreturn_dict=False
is passed or whenconfig.return_dict=False
) comprising various elements depending on the configuration (CTRLConfig
) and inputs.loss (
tf.Tensor
of shape(n,)
, optional, where n is the number of non-masked labels, returned whenlabels
is provided) β Language modeling loss (for next-token prediction).logits (
tf.Tensor
of shape(batch_size, sequence_length, config.vocab_size)
) β Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).past_key_values (
List[tf.Tensor]
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) β List oftf.Tensor
of lengthconfig.n_layers
, with each tensor of shape(2, batch_size, num_heads, sequence_length, embed_size_per_head)
).Contains pre-computed hidden-states (key and values in the attention blocks) that can be used (see
past_key_values
input) to speed up sequential decoding.hidden_states (
tuple(tf.Tensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftf.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftf.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.
- Return type
TFCausalLMOutputWithPast
ortuple(tf.Tensor)
Example:
>>> from transformers import CTRLTokenizer, TFCTRLLMHeadModel >>> import tensorflow as tf >>> tokenizer = CTRLTokenizer.from_pretrained('ctrl') >>> model = TFCTRLLMHeadModel.from_pretrained('ctrl') >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="tf") >>> outputs = model(inputs) >>> logits = outputs.logits
TFCTRLForSequenceClassificationΒΆ
-
class
transformers.
TFCTRLForSequenceClassification
(*args, **kwargs)[source]ΒΆ The CTRL Model transformer with a sequence classification head on top (linear layer).
TFCTRLForSequenceClassification
uses the last token in order to do the classification, as other causal models (e.g. GPT-1, GPT-2) 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 nopad_token_id
is defined, it simply takes the last value in each row of the batch. Since it cannot guess the padding tokens wheninputs_embeds
are passed instead ofinput_ids
, it does the same (take the last value in each row of the batch).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 tf.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.
Note
TF 2.0 models accepts two formats as inputs:
having all inputs as keyword arguments (like PyTorch models), or
having all inputs as a list, tuple or dict in the first positional arguments.
This second option is useful when using
tf.keras.Model.fit()
method which currently requires having all the tensors in the first argument of the model call function:model(inputs)
.If you choose this second option, 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(inputs_ids)
a list of varying length with one or several input Tensors IN THE ORDER given in the docstring:
model([input_ids, attention_mask])
ormodel([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})
- Parameters
config (
CTRLConfig
) β 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.
-
call
(input_ids=None, past=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, labels=None, training=False, **kwargs)[source]ΒΆ The
TFCTRLForSequenceClassification
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 (
Numpy array
ortf.Tensor
of shape(batch_size, input_ids_length)
) βinput_ids_length
=sequence_length
ifpast
isNone
elsepast[0].shape[-2]
(sequence_length
of input past key value states).Indices of input sequence tokens in the vocabulary.
If
past
is used, only input IDs that do not have their past calculated should be passed asinput_ids
.Indices can be obtained using
CTRLTokenizer
. Seetransformers.PreTrainedTokenizer.__call__()
andtransformers.PreTrainedTokenizer.encode()
for details.past (
List[tf.Tensor]
of lengthconfig.n_layers
) β Contains pre-computed hidden-states (key and values in the attention blocks) as computed by the model (seepast
output below). Can be used to speed up sequential decoding. The token ids which have their past given to this model should not be passed as input ids as they have already been computed.attention_mask (
tf.Tensor
orNumpy array
of shape(batch_size, sequence_length)
, optional) βMask 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.
token_type_ids (
tf.Tensor
orNumpy array
of shape(batch_size, sequence_length)
, optional) βSegment 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.
position_ids (
tf.Tensor
orNumpy array
of shape(batch_size, sequence_length)
, optional) βIndices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) βMask 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
orNumpy array
of shape(batch_size, sequence_length, hidden_size)
, optional) β Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_ids
indices into associated vectors than the modelβs internal embedding lookup matrix.use_cache (
bool
, optional) β If set toTrue
,past
key value states are returned and can be used to speed up decoding (seepast
).output_attentions (
bool
, optional) β Whether or not to return the attentions tensors of all attention layers. Seeattentions
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) β Whether or not to return the hidden states of all layers. Seehidden_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) β Whether or not to return aModelOutput
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 toFalse
) β 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) β Labels for computing the cross entropy classification loss. Indices should be in[0, ..., config.vocab_size - 1]
.
- Returns
A
TFSequenceClassifierOutput
or a tuple oftf.Tensor
(ifreturn_dict=False
is passed or whenconfig.return_dict=False
) comprising various elements depending on the configuration (CTRLConfig
) and inputs.loss (
tf.Tensor
of shape(batch_size, )
, optional, returned whenlabels
is provided) β Classification (or regression if config.num_labels==1) loss.logits (
tf.Tensor
of shape(batch_size, config.num_labels)
) β Classification (or regression if config.num_labels==1) scores (before SoftMax).hidden_states (
tuple(tf.Tensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftf.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftf.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.
- Return type
TFSequenceClassifierOutput
ortuple(tf.Tensor)
Example:
>>> from transformers import CTRLTokenizer, TFCTRLForSequenceClassification >>> import tensorflow as tf >>> tokenizer = CTRLTokenizer.from_pretrained('ctrl') >>> model = TFCTRLForSequenceClassification.from_pretrained('ctrl') >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="tf") >>> inputs["labels"] = tf.reshape(tf.constant(1), (-1, 1)) # Batch size 1 >>> outputs = model(inputs) >>> loss = outputs.loss >>> logits = outputs.logits