OpenAI GPT2
Overview
OpenAI GPT-2 model was proposed in Language Models are Unsupervised Multitask Learners by Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei and Ilya Sutskever. It’s a causal (unidirectional) transformer pretrained using language modeling on a very large corpus of ~40 GB of text data.
The abstract from the paper is the following:
GPT-2 is a large transformer-based language model with 1.5 billion parameters, trained on a dataset[1] of 8 million web pages. GPT-2 is trained with a simple objective: predict the next word, given all of the previous words within some text. The diversity of the dataset causes this simple goal to contain naturally occurring demonstrations of many tasks across diverse domains. GPT-2 is a direct scale-up of GPT, with more than 10X the parameters and trained on more than 10X the amount of data.
Tips:
- GPT-2 is a model with absolute position embeddings so it’s usually advised to pad the inputs on the right rather than the left.
- GPT-2 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 GPT-2 to generate syntactically coherent text as it can be observed in the run_generation.py example script.
- The model can take the past_key_values (for PyTorch) or past (for TF) as input, which is the previously computed key/value attention pairs. Using this (past_key_values or past) value prevents the model from re-computing pre-computed values in the context of text generation. For PyTorch, see past_key_values argument of the GPT2Model.forward() method, or for TF the past argument of the TFGPT2Model.call() method for more information on its usage.
- Enabling the scale_attn_by_inverse_layer_idx and reorder_and_upcast_attn flags will apply the training stability improvements from Mistral (for PyTorch only).
Write With Transformer is a webapp created and hosted by Hugging Face showcasing the generative capabilities of several models. GPT-2 is one of them and is available in five different sizes: small, medium, large, xl and a distilled version of the small checkpoint: distilgpt-2.
This model was contributed by thomwolf. The original code can be found here.
GPT2Config
class transformers.GPT2Config
< source >( vocab_size = 50257 n_positions = 1024 n_embd = 768 n_layer = 12 n_head = 12 n_inner = None activation_function = 'gelu_new' resid_pdrop = 0.1 embd_pdrop = 0.1 attn_pdrop = 0.1 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 scale_attn_weights = True use_cache = True bos_token_id = 50256 eos_token_id = 50256 scale_attn_by_inverse_layer_idx = False reorder_and_upcast_attn = False **kwargs )
Parameters
-
vocab_size (
int
, optional, defaults to 50257) — Vocabulary size of the GPT-2 model. Defines the number of different tokens that can be represented by theinputs_ids
passed when calling GPT2Model or TFGPT2Model. -
n_positions (
int
, optional, defaults to 1024) — 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_embd (
int
, optional, defaults to 768) — Dimensionality of the embeddings and hidden states. -
n_layer (
int
, optional, defaults to 12) — Number of hidden layers in the Transformer encoder. -
n_head (
int
, optional, defaults to 12) — Number of attention heads for each attention layer in the Transformer encoder. -
n_inner (
int
, optional, defaults to None) — Dimensionality of the inner feed-forward layers.None
will set it to 4 times n_embd -
activation_function (
str
, optional, defaults to"gelu"
) — Activation function, to be selected in the list["relu", "silu", "gelu", "tanh", "gelu_new"]
. -
resid_pdrop (
float
, optional, defaults to 0.1) — The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. -
embd_pdrop (
int
, optional, defaults to 0.1) — The dropout ratio for the embeddings. -
attn_pdrop (
float
, optional, defaults to 0.1) — The dropout ratio for the attention. -
layer_norm_epsilon (
float
, optional, defaults to 1e-5) — The epsilon to use in the layer normalization layers. -
initializer_range (
float
, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices. -
summary_type (
string
, optional, defaults to"cls_index"
) — Argument used when doing sequence summary, used in the models GPT2DoubleHeadsModel and TFGPT2DoubleHeadsModel.Has to be one of the following options:
"last"
: Take the last token hidden state (like XLNet)."first"
: Take the first token hidden state (like BERT)."mean"
: Take the mean of all tokens hidden states."cls_index"
: Supply a Tensor of classification token position (like GPT/GPT-2)."attn"
: Not implemented now, use multi-head attention.
-
summary_use_proj (
bool
, optional, defaults toTrue
) — Argument used when doing sequence summary, used in the models GPT2DoubleHeadsModel and TFGPT2DoubleHeadsModel.Whether or not to add a projection after the vector extraction.
-
summary_activation (
str
, optional) — Argument used when doing sequence summary. Used in for the multiple choice head in GPT2DoubleHeadsModel.Pass
"tanh"
for a tanh activation to the output, any other value will result in no activation. -
summary_proj_to_labels (
bool
, optional, defaults toTrue
) — Argument used when doing sequence summary, used in the models GPT2DoubleHeadsModel and TFGPT2DoubleHeadsModel.Whether the projection outputs should have
config.num_labels
orconfig.hidden_size
classes. -
summary_first_dropout (
float
, optional, defaults to 0.1) — Argument used when doing sequence summary, used in the models GPT2DoubleHeadsModel and TFGPT2DoubleHeadsModel.The dropout ratio to be used after the projection and activation.
-
scale_attn_weights (
bool
, optional, defaults toTrue
) — Scale attention weights by dividing by sqrt(hidden_size).. -
use_cache (
bool
, optional, defaults toTrue
) — Whether or not the model should return the last key/values attentions (not used by all models). -
scale_attn_by_inverse_layer_idx (
bool
, optional, defaults toFalse
) — Whether to additionally scale attention weights by1 / layer_idx + 1
. -
reorder_and_upcast_attn (
bool
, optional, defaults toFalse
) — Whether to scale keys (K) prior to computing attention (dot-product) and upcast attention dot-product/softmax to float() when training with mixed precision.
This is the configuration class to store the configuration of a GPT2Model or a TFGPT2Model. It is used to instantiate a GPT-2 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 GPT-2 gpt2 architecture.
Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.
GPT2Tokenizer
class transformers.GPT2Tokenizer
< source >( vocab_file merges_file errors = 'replace' unk_token = '<|endoftext|>' bos_token = '<|endoftext|>' eos_token = '<|endoftext|>' pad_token = None add_prefix_space = False add_bos_token = False **kwargs )
Parameters
-
vocab_file (
str
) — Path to the vocabulary file. -
merges_file (
str
) — Path to the merges file. -
errors (
str
, optional, defaults to"replace"
) — Paradigm to follow when decoding bytes to UTF-8. See bytes.decode for more information. -
unk_token (
str
, optional, defaults to<|endoftext|>
) — 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. -
bos_token (
str
, optional, defaults to<|endoftext|>
) — The beginning of sequence token. -
eos_token (
str
, optional, defaults to<|endoftext|>
) — The end of sequence token. -
add_prefix_space (
bool
, optional, defaults toFalse
) — Whether or not to add an initial space to the input. This allows to treat the leading word just as any other word. (GPT2 tokenizer detect beginning of words by the preceding space).
Construct a GPT-2 tokenizer. Based on byte-level Byte-Pair-Encoding.
This tokenizer has been trained to treat spaces like parts of the tokens (a bit like sentencepiece) so a word will
be encoded differently whether it is at the beginning of the sentence (without space) or not:
>>> from transformers import GPT2Tokenizer
>>> tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
>>> tokenizer("Hello world")['input_ids']
[15496, 995]
>>> tokenizer(" Hello world")['input_ids']
[18435, 995]
You can get around that behavior by passing add_prefix_space=True
when instantiating this tokenizer or when you
call it on some text, but since the model was not pretrained this way, it might yield a decrease in performance.
When used with is_split_into_words=True
, this tokenizer will add a space before each word (even the first one).
This tokenizer inherits from PreTrainedTokenizer which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.
GPT2TokenizerFast
class transformers.GPT2TokenizerFast
< source >( vocab_file = None merges_file = None tokenizer_file = None unk_token = '<|endoftext|>' bos_token = '<|endoftext|>' eos_token = '<|endoftext|>' add_prefix_space = False **kwargs )
Parameters
-
vocab_file (
str
) — Path to the vocabulary file. -
merges_file (
str
) — Path to the merges file. -
errors (
str
, optional, defaults to"replace"
) — Paradigm to follow when decoding bytes to UTF-8. See bytes.decode for more information. -
unk_token (
str
, optional, defaults to<|endoftext|>
) — 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. -
bos_token (
str
, optional, defaults to<|endoftext|>
) — The beginning of sequence token. -
eos_token (
str
, optional, defaults to<|endoftext|>
) — The end of sequence token. -
add_prefix_space (
bool
, optional, defaults toFalse
) — Whether or not to add an initial space to the input. This allows to treat the leading word just as any other word. (GPT2 tokenizer detect beginning of words by the preceding space). -
trim_offsets (
bool
, optional, defaults toTrue
) — Whether or not the post-processing step should trim offsets to avoid including whitespaces.
Construct a “fast” GPT-2 tokenizer (backed by HuggingFace’s tokenizers library). Based on byte-level Byte-Pair-Encoding.
This tokenizer has been trained to treat spaces like parts of the tokens (a bit like sentencepiece) so a word will
be encoded differently whether it is at the beginning of the sentence (without space) or not:
>>> from transformers import GPT2TokenizerFast
>>> tokenizer = GPT2TokenizerFast.from_pretrained("gpt2")
>>> tokenizer("Hello world")['input_ids']
[15496, 995]
>>> tokenizer(" Hello world")['input_ids']
[18435, 995]
You can get around that behavior by passing add_prefix_space=True
when instantiating this tokenizer, but since
the model was not pretrained this way, it might yield a decrease in performance.
When used with is_split_into_words=True
, this tokenizer needs to be instantiated with add_prefix_space=True
.
This tokenizer inherits from PreTrainedTokenizerFast which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.
GPT2 specific outputs
class transformers.models.gpt2.modeling_gpt2.GPT2DoubleHeadsModelOutput
< source >( loss: typing.Optional[torch.FloatTensor] = None mc_loss: typing.Optional[torch.FloatTensor] = None logits: FloatTensor = None mc_logits: FloatTensor = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor]] = None )
Parameters
-
loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) — Language modeling loss. -
mc_loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenmc_labels
is provided) — Multiple choice classification loss. -
logits (
torch.FloatTensor
of shape(batch_size, num_choices, sequence_length, config.vocab_size)
) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). -
mc_logits (
torch.FloatTensor
of shape(batch_size, num_choices)
) — Prediction scores of the multiple choice classification head (scores for each choice before SoftMax). -
past_key_values (
Tuple[Tuple[torch.Tensor]]
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) — Tuple of lengthconfig.n_layers
, containing tuples of tensors of shape(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(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — 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
) — Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.GPT2Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
Base class for outputs of models predicting if two sentences are consecutive or not.
class transformers.models.gpt2.modeling_tf_gpt2.TFGPT2DoubleHeadsModelOutput
< source >( logits: Tensor = None mc_logits: Tensor = None past_key_values: typing.Optional[typing.List[tensorflow.python.framework.ops.Tensor]] = None hidden_states: typing.Optional[typing.Tuple[tensorflow.python.framework.ops.Tensor]] = None attentions: typing.Optional[typing.Tuple[tensorflow.python.framework.ops.Tensor]] = None )
Parameters
-
logits (
tf.Tensor
of shape(batch_size, num_choices, sequence_length, config.vocab_size)
) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). -
mc_logits (
tf.Tensor
of shape(batch_size, num_choices)
) — Prediction scores of the multiple choice classification head (scores for each choice before SoftMax). -
past_key_values (
List[tf.Tensor]
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) — 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
) — 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
) — 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.
Base class for outputs of models predicting if two sentences are consecutive or not.
GPT2Model
class transformers.GPT2Model
< source >( config )
Parameters
- config (GPT2Config) — 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 GPT2 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.
forward
< source >(
input_ids: typing.Optional[torch.LongTensor] = None
past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.Tensor]]] = 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.Tensor] = None
encoder_attention_mask: typing.Optional[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.BaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)
Parameters
-
input_ids (
torch.LongTensor
of shape(batch_size, input_ids_length)
) —input_ids_length
=sequence_length
ifpast_key_values
isNone
elsepast_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, onlyinput_ids
that do not have their past calculated should be passed asinput_ids
.Indices can be obtained using GPT2Tokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
-
past_key_values (
Tuple[Tuple[torch.Tensor]]
of lengthconfig.n_layers
) — Contains precomputed 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 asinput_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.
If
past_key_values
is used,attention_mask
needs to contain the masking strategy that was used forpast_key_values
. In other words, theattention_mask
always has to have the length:len(past_key_values) + len(input_ids)
-
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.
-
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]
. -
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 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 model’s internal embedding lookup matrix.If
past_key_values
is used, optionally only the lastinputs_embeds
have to be input (seepast_key_values
). -
use_cache (
bool
, optional) — 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) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
transformers.modeling_outputs.BaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)
A transformers.modeling_outputs.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 (GPT2Config) 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 whenuse_cache=True
is passed or whenconfig.use_cache=True
) — 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
) — Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) — 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.
-
cross_attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
andconfig.add_cross_attention=True
is passed or whenconfig.output_attentions=True
) — Tuple oftorch.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.
The GPT2Model forward method, overrides the __call__
special method.
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.
Example:
>>> from transformers import GPT2Tokenizer, GPT2Model
>>> import torch
>>> tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
>>> model = GPT2Model.from_pretrained("gpt2")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> outputs = model(**inputs)
>>> last_hidden_states = outputs.last_hidden_state
parallelize
< source >( device_map = None )
Parameters
-
device_map (
Dict[int, list]
, optional, defaults to None) — A dictionary that maps attention modules to devices. Note that the embedding module and LMHead are always automatically mapped to the first device (for esoteric reasons). That means that the first device should have fewer attention modules mapped to it than other devices. For reference, the gpt2 models have the following number of attention modules:- gpt2: 12
- gpt2-medium: 24
- gpt2-large: 36
- gpt2-xl: 48
This is an experimental feature and is a subject to change at a moment’s notice.
Uses a device map to distribute attention modules of the model across several devices. If no device map is given, it will evenly distribute blocks across all devices.
Example:
# Here is an example of a device map on a machine with 4 GPUs using gpt2-xl, which has a total of 48 attention modules:
model = GPT2LMHeadModel.from_pretrained("gpt2-xl")
device_map = {
0: [0, 1, 2, 3, 4, 5, 6, 7, 8],
1: [9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21],
2: [22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34],
3: [35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47],
}
model.parallelize(device_map)
Moves the model to cpu from a model parallel state.
Example:
# On a 4 GPU machine with gpt2-large:
model = GPT2LMHeadModel.from_pretrained("gpt2-large")
device_map = {
0: [0, 1, 2, 3, 4, 5, 6, 7],
1: [8, 9, 10, 11, 12, 13, 14, 15],
2: [16, 17, 18, 19, 20, 21, 22, 23],
3: [24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35],
}
model.parallelize(device_map) # Splits the model across several devices
model.deparallelize() # Put the model back on cpu and cleans memory by calling torch.cuda.empty_cache()
GPT2LMHeadModel
class transformers.GPT2LMHeadModel
< source >( config )
Parameters
- config (GPT2Config) — 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 GPT2 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.
forward
< source >(
input_ids: typing.Optional[torch.LongTensor] = None
past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.Tensor]]] = 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.Tensor] = None
encoder_attention_mask: typing.Optional[torch.FloatTensor] = None
labels: typing.Optional[torch.LongTensor] = 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.CausalLMOutputWithCrossAttentions or tuple(torch.FloatTensor)
Parameters
-
input_ids (
torch.LongTensor
of shape(batch_size, input_ids_length)
) —input_ids_length
=sequence_length
ifpast_key_values
isNone
elsepast_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, onlyinput_ids
that do not have their past calculated should be passed asinput_ids
.Indices can be obtained using GPT2Tokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
-
past_key_values (
Tuple[Tuple[torch.Tensor]]
of lengthconfig.n_layers
) — Contains precomputed 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 asinput_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.
If
past_key_values
is used,attention_mask
needs to contain the masking strategy that was used forpast_key_values
. In other words, theattention_mask
always has to have the length:len(past_key_values) + len(input_ids)
-
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.
-
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]
. -
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 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 model’s internal embedding lookup matrix.If
past_key_values
is used, optionally only the lastinputs_embeds
have to be input (seepast_key_values
). -
use_cache (
bool
, optional) — 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) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_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 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
transformers.modeling_outputs.CausalLMOutputWithCrossAttentions or tuple(torch.FloatTensor)
A transformers.modeling_outputs.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 (GPT2Config) and inputs.
-
loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) — 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.
-
cross_attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) — Tuple oftorch.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 whenuse_cache=True
is passed or whenconfig.use_cache=True
) — Tuple oftorch.FloatTensor
tuples of lengthconfig.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 ifconfig.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.
The GPT2LMHeadModel forward method, overrides the __call__
special method.
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.
Example:
>>> import torch
>>> from transformers import GPT2Tokenizer, GPT2LMHeadModel
>>> tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
>>> model = GPT2LMHeadModel.from_pretrained("gpt2")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> outputs = model(**inputs, labels=inputs["input_ids"])
>>> loss = outputs.loss
>>> logits = outputs.logits
parallelize
< source >( device_map = None )
Parameters
-
device_map (
Dict[int, list]
, optional, defaults to None) — A dictionary that maps attention modules to devices. Note that the embedding module and LMHead are always automatically mapped to the first device (for esoteric reasons). That means that the first device should have fewer attention modules mapped to it than other devices. For reference, the gpt2 models have the following number of attention modules:- gpt2: 12
- gpt2-medium: 24
- gpt2-large: 36
- gpt2-xl: 48
This is an experimental feature and is a subject to change at a moment’s notice.
Uses a device map to distribute attention modules of the model across several devices. If no device map is given, it will evenly distribute blocks across all devices.
Example:
# Here is an example of a device map on a machine with 4 GPUs using gpt2-xl, which has a total of 48 attention modules:
model = GPT2LMHeadModel.from_pretrained("gpt2-xl")
device_map = {
0: [0, 1, 2, 3, 4, 5, 6, 7, 8],
1: [9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21],
2: [22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34],
3: [35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47],
}
model.parallelize(device_map)
Moves the model to cpu from a model parallel state.
Example:
# On a 4 GPU machine with gpt2-large:
model = GPT2LMHeadModel.from_pretrained("gpt2-large")
device_map = {
0: [0, 1, 2, 3, 4, 5, 6, 7],
1: [8, 9, 10, 11, 12, 13, 14, 15],
2: [16, 17, 18, 19, 20, 21, 22, 23],
3: [24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35],
}
model.parallelize(device_map) # Splits the model across several devices
model.deparallelize() # Put the model back on cpu and cleans memory by calling torch.cuda.empty_cache()
GPT2DoubleHeadsModel
class transformers.GPT2DoubleHeadsModel
< source >( config )
Parameters
- config (GPT2Config) — 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 GPT2 Model transformer with a language modeling and a multiple-choice classification head on top e.g. for RocStories/SWAG tasks. The two heads are two linear layers. The language modeling head has its weights tied to the input embeddings, the classification head takes as input the input of a specified classification token index in the input sequence).
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
past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.Tensor]]] = 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
mc_token_ids: typing.Optional[torch.LongTensor] = None
labels: typing.Optional[torch.LongTensor] = None
mc_labels: typing.Optional[torch.LongTensor] = 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.models.gpt2.modeling_gpt2.GPT2DoubleHeadsModelOutput or tuple(torch.FloatTensor)
Parameters
-
input_ids (
torch.LongTensor
of shape(batch_size, input_ids_length)
) —input_ids_length
=sequence_length
ifpast_key_values
isNone
elsepast_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, onlyinput_ids
that do not have their past calculated should be passed asinput_ids
.Indices can be obtained using GPT2Tokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
-
past_key_values (
Tuple[Tuple[torch.Tensor]]
of lengthconfig.n_layers
) — Contains precomputed 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 asinput_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.
If
past_key_values
is used,attention_mask
needs to contain the masking strategy that was used forpast_key_values
. In other words, theattention_mask
always has to have the length:len(past_key_values) + len(input_ids)
-
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.
-
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]
. -
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 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 model’s internal embedding lookup matrix.If
past_key_values
is used, optionally only the lastinputs_embeds
have to be input (seepast_key_values
). -
use_cache (
bool
, optional) — 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) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple. -
mc_token_ids (
torch.LongTensor
of shape(batch_size, num_choices)
, optional, default to index of the last token of the input) — Index of the classification token in each input sequence. Selected in the range[0, input_ids.size(-1) - 1]
. -
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 setlabels = input_ids
. Indices are selected in[-100, 0, ..., config.vocab_size - 1]
. All labels set to-100
are ignored (masked), the loss is only computed for labels in[0, ..., config.vocab_size - 1]
-
mc_labels (
torch.LongTensor
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)
Returns
transformers.models.gpt2.modeling_gpt2.GPT2DoubleHeadsModelOutput or tuple(torch.FloatTensor)
A transformers.models.gpt2.modeling_gpt2.GPT2DoubleHeadsModelOutput 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 (GPT2Config) and inputs.
-
loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) — Language modeling loss. -
mc_loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenmc_labels
is provided) — Multiple choice classification loss. -
logits (
torch.FloatTensor
of shape(batch_size, num_choices, sequence_length, config.vocab_size)
) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). -
mc_logits (
torch.FloatTensor
of shape(batch_size, num_choices)
) — Prediction scores of the multiple choice classification head (scores for each choice before SoftMax). -
past_key_values (
Tuple[Tuple[torch.Tensor]]
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) — Tuple of lengthconfig.n_layers
, containing tuples of tensors of shape(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(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — 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
) — Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.GPT2Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
The GPT2DoubleHeadsModel forward method, overrides the __call__
special method.
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.
Example:
>>> import torch
>>> from transformers import GPT2Tokenizer, GPT2DoubleHeadsModel
>>> tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
>>> model = GPT2DoubleHeadsModel.from_pretrained("gpt2")
>>> # Add a [CLS] to the vocabulary (we should train it also!)
>>> num_added_tokens = tokenizer.add_special_tokens({"cls_token": "[CLS]"})
>>> # Update the model embeddings with the new vocabulary size
>>> embedding_layer = model.resize_token_embeddings(len(tokenizer))
>>> choices = ["Hello, my dog is cute [CLS]", "Hello, my cat is cute [CLS]"]
>>> encoded_choices = [tokenizer.encode(s) for s in choices]
>>> cls_token_location = [tokens.index(tokenizer.cls_token_id) for tokens in encoded_choices]
>>> input_ids = torch.tensor(encoded_choices).unsqueeze(0) # Batch size: 1, number of choices: 2
>>> mc_token_ids = torch.tensor([cls_token_location]) # Batch size: 1
>>> outputs = model(input_ids, mc_token_ids=mc_token_ids)
>>> lm_logits = outputs.logits
>>> mc_logits = outputs.mc_logits
GPT2ForSequenceClassification
class transformers.GPT2ForSequenceClassification
< source >( config )
Parameters
- config (GPT2Config) — 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 GPT2 Model transformer with a sequence classification head on top (linear layer).
GPT2ForSequenceClassification 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.
forward
< source >(
input_ids: typing.Optional[torch.LongTensor] = None
past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.Tensor]]] = 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
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.SequenceClassifierOutputWithPast
or tuple(torch.FloatTensor)
Parameters
-
input_ids (
torch.LongTensor
of shape(batch_size, input_ids_length)
) —input_ids_length
=sequence_length
ifpast_key_values
isNone
elsepast_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, onlyinput_ids
that do not have their past calculated should be passed asinput_ids
.Indices can be obtained using GPT2Tokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
-
past_key_values (
Tuple[Tuple[torch.Tensor]]
of lengthconfig.n_layers
) — Contains precomputed 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 asinput_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.
If
past_key_values
is used,attention_mask
needs to contain the masking strategy that was used forpast_key_values
. In other words, theattention_mask
always has to have the length:len(past_key_values) + len(input_ids)
-
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.
-
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]
. -
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 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 model’s internal embedding lookup matrix.If
past_key_values
is used, optionally only the lastinputs_embeds
have to be input (seepast_key_values
). -
use_cache (
bool
, optional) — 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) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_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]
. Ifconfig.num_labels == 1
a regression loss is computed (Mean-Square loss), Ifconfig.num_labels > 1
a classification loss is computed (Cross-Entropy).
Returns
transformers.modeling_outputs.SequenceClassifierOutputWithPast
or tuple(torch.FloatTensor)
A transformers.modeling_outputs.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 (GPT2Config) and inputs.
-
loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
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 whenuse_cache=True
is passed or whenconfig.use_cache=True
) — 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
) — Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) — 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.
The GPT2ForSequenceClassification forward method, overrides the __call__
special method.
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.
Example of single-label classification:
>>> import torch
>>> from transformers import GPT2Tokenizer, GPT2ForSequenceClassification
>>> tokenizer = GPT2Tokenizer.from_pretrained("microsoft/DialogRPT-updown")
>>> model = GPT2ForSequenceClassification.from_pretrained("microsoft/DialogRPT-updown")
>>> 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]
'LABEL_0'
>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = GPT2ForSequenceClassification.from_pretrained("microsoft/DialogRPT-updown", num_labels=num_labels)
>>> labels = torch.tensor([1])
>>> loss = model(**inputs, labels=labels).loss
>>> round(loss.item(), 2)
5.28
Example of multi-label classification:
>>> import torch
>>> from transformers import GPT2Tokenizer, GPT2ForSequenceClassification
>>> tokenizer = GPT2Tokenizer.from_pretrained("microsoft/DialogRPT-updown")
>>> model = GPT2ForSequenceClassification.from_pretrained("microsoft/DialogRPT-updown", 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_id = logits.argmax().item()
>>> model.config.id2label[predicted_class_id]
'LABEL_0'
>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = GPT2ForSequenceClassification.from_pretrained(
... "microsoft/DialogRPT-updown", num_labels=num_labels, problem_type="multi_label_classification"
... )
>>> labels = torch.nn.functional.one_hot(torch.tensor([predicted_class_id]), num_classes=num_labels).to(
... torch.float
... )
>>> loss = model(**inputs, labels=labels).loss
>>> loss.backward()
GPT2ForTokenClassification
class transformers.GPT2ForTokenClassification
< source >( config )
Parameters
- config (GPT2Config) — 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.
GPT2 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 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
past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.Tensor]]] = 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
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.TokenClassifierOutput or tuple(torch.FloatTensor)
Parameters
-
input_ids (
torch.LongTensor
of shape(batch_size, input_ids_length)
) —input_ids_length
=sequence_length
ifpast_key_values
isNone
elsepast_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, onlyinput_ids
that do not have their past calculated should be passed asinput_ids
.Indices can be obtained using GPT2Tokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
-
past_key_values (
Tuple[Tuple[torch.Tensor]]
of lengthconfig.n_layers
) — Contains precomputed 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 asinput_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.
If
past_key_values
is used,attention_mask
needs to contain the masking strategy that was used forpast_key_values
. In other words, theattention_mask
always has to have the length:len(past_key_values) + len(input_ids)
-
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.
-
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]
. -
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 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 model’s internal embedding lookup matrix.If
past_key_values
is used, optionally only the lastinputs_embeds
have to be input (seepast_key_values
). -
use_cache (
bool
, optional) — 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) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_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 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
transformers.modeling_outputs.TokenClassifierOutput or tuple(torch.FloatTensor)
A transformers.modeling_outputs.TokenClassifierOutput 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 (GPT2Config) and inputs.
-
loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) — 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.
The GPT2ForTokenClassification forward method, overrides the __call__
special method.
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.
Example:
>>> from transformers import GPT2Tokenizer, GPT2ForTokenClassification
>>> import torch
>>> tokenizer = GPT2Tokenizer.from_pretrained("brad1141/gpt2-finetuned-comp2")
>>> model = GPT2ForTokenClassification.from_pretrained("brad1141/gpt2-finetuned-comp2")
>>> 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)
>>> # Note that tokens are classified rather then input words which means that
>>> # there might be more predicted token classes than words.
>>> # Multiple token classes might account for the same word
>>> predicted_tokens_classes = [model.config.id2label[t.item()] for t in predicted_token_class_ids[0]]
>>> predicted_tokens_classes
['Lead', 'Lead', 'Lead', 'Position', 'Lead', 'Lead', 'Lead', 'Lead', 'Lead', 'Lead', 'Lead', 'Lead']
TFGPT2Model
class transformers.TFGPT2Model
< source >( *args **kwargs )
Parameters
- config (GPT2Config) — 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 GPT2 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.
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])
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})
Note that when creating models and layers with subclassing 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: typing.Union[typing.List[tensorflow.python.framework.ops.Tensor], typing.List[numpy.ndarray], typing.List[tensorflow.python.keras.engine.keras_tensor.KerasTensor], typing.Dict[str, tensorflow.python.framework.ops.Tensor], typing.Dict[str, numpy.ndarray], typing.Dict[str, tensorflow.python.keras.engine.keras_tensor.KerasTensor], tensorflow.python.framework.ops.Tensor, numpy.ndarray, tensorflow.python.keras.engine.keras_tensor.KerasTensor, NoneType] = None
past: typing.Union[typing.Tuple[typing.Tuple[typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]]], NoneType] = None
attention_mask: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
token_type_ids: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
position_ids: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
head_mask: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
inputs_embeds: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
encoder_hidden_states: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
encoder_attention_mask: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = 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
training: typing.Optional[bool] = False
)
→
transformers.modeling_tf_outputs.TFBaseModelOutputWithPastAndCrossAttentions or tuple(tf.Tensor)
Parameters
-
input_ids (
Numpy array
ortf.Tensor
of shape(batch_size, input_ids_length)
) —input_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 GPT2Tokenizer. See PreTrainedTokenizer.call() and PreTrainedTokenizer.encode() for details.
-
past (
List[tf.Tensor]
of lengthconfig.n_layers
) — 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) — 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.
If
past_key_values
is used,attention_mask
needs to contain the masking strategy that was used forpast_key_values
. In other words, theattention_mask
always has to have the length:len(past_key_values) + len(input_ids)
-
token_type_ids (
tf.Tensor
orNumpy array
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.
-
position_ids (
tf.Tensor
orNumpy array
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 array
ortf.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 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 model’s internal embedding lookup matrix. -
output_attentions (
bool
, optional) — 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) — 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) — 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 toFalse
) — 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 (
Tuple[Tuple[tf.Tensor]]
of lengthconfig.n_layers
) — contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding. Ifpast
are used, the user can optionally input only the lastdecoder_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 toTrue
) — If set toTrue
,past_key_values
key value states are returned and can be used to speed up decoding (seepast
). Set toFalse
during training,True
during generation
Returns
transformers.modeling_tf_outputs.TFBaseModelOutputWithPastAndCrossAttentions or tuple(tf.Tensor)
A transformers.modeling_tf_outputs.TFBaseModelOutputWithPastAndCrossAttentions or a tuple of tf.Tensor
(if
return_dict=False
is passed or when config.return_dict=False
) comprising various elements depending on the
configuration (GPT2Config) 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.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
) — 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.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — 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
) — 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.
-
cross_attentions (
tuple(tf.Tensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) — Tuple oftf.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 TFGPT2Model forward method, overrides the __call__
special method.
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.
Example:
>>> from transformers import GPT2Tokenizer, TFGPT2Model
>>> import tensorflow as tf
>>> tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
>>> model = TFGPT2Model.from_pretrained("gpt2")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="tf")
>>> outputs = model(inputs)
>>> last_hidden_states = outputs.last_hidden_state
TFGPT2LMHeadModel
class transformers.TFGPT2LMHeadModel
< source >( *args **kwargs )
Parameters
- config (GPT2Config) — 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 GPT2 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.
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])
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})
Note that when creating models and layers with subclassing 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: typing.Union[typing.List[tensorflow.python.framework.ops.Tensor], typing.List[numpy.ndarray], typing.List[tensorflow.python.keras.engine.keras_tensor.KerasTensor], typing.Dict[str, tensorflow.python.framework.ops.Tensor], typing.Dict[str, numpy.ndarray], typing.Dict[str, tensorflow.python.keras.engine.keras_tensor.KerasTensor], tensorflow.python.framework.ops.Tensor, numpy.ndarray, tensorflow.python.keras.engine.keras_tensor.KerasTensor, NoneType] = None
past: typing.Union[typing.Tuple[typing.Tuple[typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]]], NoneType] = None
attention_mask: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
token_type_ids: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
position_ids: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
head_mask: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
inputs_embeds: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
encoder_hidden_states: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
encoder_attention_mask: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = 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
labels: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
training: typing.Optional[bool] = False
)
→
transformers.modeling_tf_outputs.TFCausalLMOutputWithCrossAttentions or tuple(tf.Tensor)
Parameters
-
input_ids (
Numpy array
ortf.Tensor
of shape(batch_size, input_ids_length)
) —input_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 GPT2Tokenizer. See PreTrainedTokenizer.call() and PreTrainedTokenizer.encode() for details.
-
past (
List[tf.Tensor]
of lengthconfig.n_layers
) — 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) — 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.
If
past_key_values
is used,attention_mask
needs to contain the masking strategy that was used forpast_key_values
. In other words, theattention_mask
always has to have the length:len(past_key_values) + len(input_ids)
-
token_type_ids (
tf.Tensor
orNumpy array
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.
-
position_ids (
tf.Tensor
orNumpy array
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 array
ortf.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 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 model’s internal embedding lookup matrix. -
output_attentions (
bool
, optional) — 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) — 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) — 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 toFalse
) — 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 (
Tuple[Tuple[tf.Tensor]]
of lengthconfig.n_layers
) — contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding. Ifpast
are used, the user can optionally input only the lastdecoder_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 toTrue
) — If set toTrue
,past_key_values
key value states are returned and can be used to speed up decoding (seepast
). Set toFalse
during training,True
during generation -
labels (
tf.Tensor
of shape(batch_size, sequence_length)
, optional) — Labels for computing the cross entropy classification loss. Indices should be in[0, ..., config.vocab_size - 1]
.
Returns
transformers.modeling_tf_outputs.TFCausalLMOutputWithCrossAttentions or tuple(tf.Tensor)
A transformers.modeling_tf_outputs.TFCausalLMOutputWithCrossAttentions or a tuple of tf.Tensor
(if
return_dict=False
is passed or when config.return_dict=False
) comprising various elements depending on the
configuration (GPT2Config) and inputs.
-
loss (
tf.Tensor
of shape(n,)
, optional, where n is the number of non-masked labels, returned whenlabels
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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — 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
) — 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.
-
cross_attentions (
tuple(tf.Tensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) — Tuple oftf.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 whenuse_cache=True
is passed or whenconfig.use_cache=True
) — 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.
The TFGPT2LMHeadModel forward method, overrides the __call__
special method.
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.
Example:
>>> from transformers import GPT2Tokenizer, TFGPT2LMHeadModel
>>> import tensorflow as tf
>>> tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
>>> model = TFGPT2LMHeadModel.from_pretrained("gpt2")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="tf")
>>> outputs = model(inputs)
>>> logits = outputs.logits
TFGPT2DoubleHeadsModel
class transformers.TFGPT2DoubleHeadsModel
< source >( *args **kwargs )
Parameters
- config (GPT2Config) — 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 GPT2 Model transformer with a language modeling and a multiple-choice classification head on top e.g. for RocStories/SWAG tasks. The two heads are two linear layers. The language modeling head has its weights tied to the input embeddings, the classification head takes as input the input of a specified classification token index in the input sequence).
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.
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])
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})
Note that when creating models and layers with subclassing 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: typing.Union[typing.List[tensorflow.python.framework.ops.Tensor], typing.List[numpy.ndarray], typing.List[tensorflow.python.keras.engine.keras_tensor.KerasTensor], typing.Dict[str, tensorflow.python.framework.ops.Tensor], typing.Dict[str, numpy.ndarray], typing.Dict[str, tensorflow.python.keras.engine.keras_tensor.KerasTensor], tensorflow.python.framework.ops.Tensor, numpy.ndarray, tensorflow.python.keras.engine.keras_tensor.KerasTensor, NoneType] = None
past: typing.Union[typing.Tuple[typing.Tuple[typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]]], NoneType] = None
attention_mask: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
token_type_ids: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
position_ids: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
head_mask: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
inputs_embeds: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
mc_token_ids: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = 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
training: typing.Optional[bool] = False
)
→
transformers.models.gpt2.modeling_tf_gpt2.TFGPT2DoubleHeadsModelOutput or tuple(tf.Tensor)
Parameters
-
input_ids (
Numpy array
ortf.Tensor
of shape(batch_size, input_ids_length)
) —input_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 GPT2Tokenizer. See PreTrainedTokenizer.call() and PreTrainedTokenizer.encode() for details.
-
past (
List[tf.Tensor]
of lengthconfig.n_layers
) — 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) — 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.
If
past_key_values
is used,attention_mask
needs to contain the masking strategy that was used forpast_key_values
. In other words, theattention_mask
always has to have the length:len(past_key_values) + len(input_ids)
-
token_type_ids (
tf.Tensor
orNumpy array
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.
-
position_ids (
tf.Tensor
orNumpy array
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 array
ortf.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 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 model’s internal embedding lookup matrix. -
output_attentions (
bool
, optional) — 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) — 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) — 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 toFalse
) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation). -
mc_token_ids (
tf.Tensor
orNumpy array
of shape(batch_size, num_choices)
, optional, default to index of the last token of the input) — Index of the classification token in each input sequence. Selected in the range[0, input_ids.size(-1) - 1]
.
Returns
transformers.models.gpt2.modeling_tf_gpt2.TFGPT2DoubleHeadsModelOutput or tuple(tf.Tensor)
A transformers.models.gpt2.modeling_tf_gpt2.TFGPT2DoubleHeadsModelOutput or a tuple of tf.Tensor
(if
return_dict=False
is passed or when config.return_dict=False
) comprising various elements depending on the
configuration (GPT2Config) and inputs.
-
logits (
tf.Tensor
of shape(batch_size, num_choices, sequence_length, config.vocab_size)
) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). -
mc_logits (
tf.Tensor
of shape(batch_size, num_choices)
) — Prediction scores of the multiple choice classification head (scores for each choice before SoftMax). -
past_key_values (
List[tf.Tensor]
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) — 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
) — 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
) — 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.
The TFGPT2DoubleHeadsModel forward method, overrides the __call__
special method.
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.
Examples:
>>> import tensorflow as tf
>>> from transformers import GPT2Tokenizer, TFGPT2DoubleHeadsModel
>>> tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
>>> model = TFGPT2DoubleHeadsModel.from_pretrained("gpt2")
>>> # Add a [CLS] to the vocabulary (we should train it also!)
>>> num_added_tokens = tokenizer.add_special_tokens({"cls_token": "[CLS]"})
>>> embedding_layer = model.resize_token_embeddings(
... len(tokenizer)
... ) # Update the model embeddings with the new vocabulary size
>>> choices = ["Hello, my dog is cute [CLS]", "Hello, my cat is cute [CLS]"]
>>> encoded_choices = [tokenizer.encode(s) for s in choices]
>>> cls_token_location = [tokens.index(tokenizer.cls_token_id) for tokens in encoded_choices]
>>> input_ids = tf.constant(encoded_choices)[None, :] # Batch size: 1, number of choices: 2
>>> mc_token_ids = tf.constant([cls_token_location]) # Batch size: 1
>>> outputs = model(input_ids, mc_token_ids=mc_token_ids)
>>> lm_prediction_scores, mc_prediction_scores = outputs[:2]
TFGPT2ForSequenceClassification
class transformers.TFGPT2ForSequenceClassification
< source >( *args **kwargs )
Parameters
- config (GPT2Config) — 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 GPT2 Model transformer with a sequence classification head on top (linear layer).
TFGPT2ForSequenceClassification 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 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.
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])
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})
Note that when creating models and layers with subclassing 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: typing.Union[typing.List[tensorflow.python.framework.ops.Tensor], typing.List[numpy.ndarray], typing.List[tensorflow.python.keras.engine.keras_tensor.KerasTensor], typing.Dict[str, tensorflow.python.framework.ops.Tensor], typing.Dict[str, numpy.ndarray], typing.Dict[str, tensorflow.python.keras.engine.keras_tensor.KerasTensor], tensorflow.python.framework.ops.Tensor, numpy.ndarray, tensorflow.python.keras.engine.keras_tensor.KerasTensor, NoneType] = None
past: typing.Union[typing.Tuple[typing.Tuple[typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]]], NoneType] = None
attention_mask: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
token_type_ids: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
position_ids: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
head_mask: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
inputs_embeds: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = 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
labels: typing.Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor, NoneType] = None
training: typing.Optional[bool] = False
)
→
transformers.modeling_tf_outputs.TFSequenceClassifierOutputWithPast or tuple(tf.Tensor)
Parameters
-
input_ids (
Numpy array
ortf.Tensor
of shape(batch_size, input_ids_length)
) —input_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 GPT2Tokenizer. See PreTrainedTokenizer.call() and PreTrainedTokenizer.encode() for details.
-
past (
List[tf.Tensor]
of lengthconfig.n_layers
) — 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) — 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.
If
past_key_values
is used,attention_mask
needs to contain the masking strategy that was used forpast_key_values
. In other words, theattention_mask
always has to have the length:len(past_key_values) + len(input_ids)
-
token_type_ids (
tf.Tensor
orNumpy array
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.
-
position_ids (
tf.Tensor
orNumpy array
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 array
ortf.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 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 model’s internal embedding lookup matrix. -
output_attentions (
bool
, optional) — 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) — 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) — 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 toFalse
) — 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 cross entropy classification loss. Indices should be in[0, ..., config.vocab_size - 1]
.
Returns
transformers.modeling_tf_outputs.TFSequenceClassifierOutputWithPast or tuple(tf.Tensor)
A transformers.modeling_tf_outputs.TFSequenceClassifierOutputWithPast or a tuple of tf.Tensor
(if
return_dict=False
is passed or when config.return_dict=False
) comprising various elements depending on the
configuration (GPT2Config) and inputs.
-
loss (
tf.Tensor
of shape(batch_size, )
, optional, returned whenlabels
is provided) — Classification (or regression if config.num_labels==1) loss. -
logits (
tf.Tensor
of shape(batch_size, config.num_labels)
) — Classification (or regression if config.num_labels==1) scores (before SoftMax). -
past_key_values (
List[tf.Tensor]
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) — 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
) — 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
) — 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.
The TFGPT2ForSequenceClassification forward method, overrides the __call__
special method.
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.
Example:
>>> from transformers import GPT2Tokenizer, TFGPT2ForSequenceClassification
>>> import tensorflow as tf
>>> tokenizer = GPT2Tokenizer.from_pretrained("microsoft/DialogRPT-updown")
>>> model = TFGPT2ForSequenceClassification.from_pretrained("microsoft/DialogRPT-updown")
>>> 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])
>>> model.config.id2label[predicted_class_id]
>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = TFGPT2ForSequenceClassification.from_pretrained("microsoft/DialogRPT-updown", num_labels=num_labels)
>>> labels = tf.constant(1)
>>> loss = model(**inputs, labels=labels).loss
>>> round(float(loss), 2)
TFSequenceClassifierOutputWithPast
class transformers.modeling_tf_outputs.TFSequenceClassifierOutputWithPast
< source >( loss: typing.Optional[tensorflow.python.framework.ops.Tensor] = None logits: Tensor = None past_key_values: typing.Optional[typing.List[tensorflow.python.framework.ops.Tensor]] = None hidden_states: typing.Optional[typing.Tuple[tensorflow.python.framework.ops.Tensor]] = None attentions: typing.Optional[typing.Tuple[tensorflow.python.framework.ops.Tensor]] = None )
Parameters
-
loss (
tf.Tensor
of shape(batch_size, )
, optional, returned whenlabels
is provided) — Classification (or regression if config.num_labels==1) loss. -
logits (
tf.Tensor
of shape(batch_size, config.num_labels)
) — Classification (or regression if config.num_labels==1) scores (before SoftMax). -
past_key_values (
List[tf.Tensor]
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) — 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
) — 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
) — 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.
Base class for outputs of sentence classification models.
FlaxGPT2Model
class transformers.FlaxGPT2Model
< source >( config: GPT2Config input_shape: typing.Tuple = (1, 1) seed: int = 0 dtype: dtype = <class 'jax.numpy.float32'> _do_init: bool = True **kwargs )
Parameters
- config (GPT2Config) — 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.
-
dtype (
jax.numpy.dtype
, optional, defaults tojax.numpy.float32
) — The data type of the computation. Can be one ofjax.numpy.float32
,jax.numpy.float16
(on GPUs) andjax.numpy.bfloat16
(on TPUs).This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given
dtype
.Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.
If you wish to change the dtype of the model parameters, see to_fp16() and to_bf16().
The bare GPT2 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 or saving, resizing the input embeddings, pruning heads etc.)
This model is also a Flax Linen flax.nn.Module subclass. Use it as a regular Flax 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:
__call__
< source >(
input_ids
attention_mask = None
position_ids = None
encoder_hidden_states: typing.Optional[jax._src.numpy.ndarray.ndarray] = None
encoder_attention_mask: typing.Optional[jax._src.numpy.ndarray.ndarray] = None
params: dict = None
past_key_values: dict = None
dropout_rng: PRNGKey = None
train: bool = False
output_attentions: typing.Optional[bool] = None
output_hidden_states: typing.Optional[bool] = None
return_dict: typing.Optional[bool] = None
)
→
transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)
Parameters
-
input_ids (
numpy.ndarray
of shape(batch_size, input_ids_length)
) —input_ids_length
=sequence_length
. Indices of input sequence tokens in the vocabulary.Indices can be obtained using GPT2Tokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
-
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.
-
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]
. -
past_key_values (
Dict[str, np.ndarray]
, optional, returned byinit_cache
or when passing previouspast_key_values
) — Dictionary of pre-computed hidden-states (key and values in the attention blocks) that can be used for fast auto-regressive decoding. Pre-computed key and value hidden-states are of shape [batch_size, max_length]. -
output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)
A transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions 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 (GPT2Config) 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.If
past_key_values
is used only the last hidden-state of the sequences of shape(batch_size, 1, hidden_size)
is output. -
past_key_values (
tuple(tuple(jnp.ndarray))
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) — Tuple oftuple(jnp.ndarray)
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(jnp.ndarray)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) — Tuple ofjnp.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 whenoutput_attentions=True
andconfig.add_cross_attention=True
is passed or whenconfig.output_attentions=True
) — Tuple ofjnp.ndarray
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
The FlaxGPT2PreTrainedModel
forward method, overrides the __call__
special method.
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.
Example:
>>> from transformers import GPT2Tokenizer, FlaxGPT2Model
>>> tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
>>> model = FlaxGPT2Model.from_pretrained("gpt2")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="jax")
>>> outputs = model(**inputs)
>>> last_hidden_states = outputs.last_hidden_state
FlaxGPT2LMHeadModel
class transformers.FlaxGPT2LMHeadModel
< source >( config: GPT2Config input_shape: typing.Tuple = (1, 1) seed: int = 0 dtype: dtype = <class 'jax.numpy.float32'> _do_init: bool = True **kwargs )
Parameters
- config (GPT2Config) — 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.
-
dtype (
jax.numpy.dtype
, optional, defaults tojax.numpy.float32
) — The data type of the computation. Can be one ofjax.numpy.float32
,jax.numpy.float16
(on GPUs) andjax.numpy.bfloat16
(on TPUs).This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given
dtype
.Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.
If you wish to change the dtype of the model parameters, see to_fp16() and to_bf16().
The GPT2 Model transformer with a language modeling head on top (linear layer with weights tied to the input embeddings).
This model inherits from FlaxPreTrainedModel. 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 Flax Linen flax.nn.Module subclass. Use it as a regular Flax 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:
__call__
< source >(
input_ids
attention_mask = None
position_ids = None
encoder_hidden_states: typing.Optional[jax._src.numpy.ndarray.ndarray] = None
encoder_attention_mask: typing.Optional[jax._src.numpy.ndarray.ndarray] = None
params: dict = None
past_key_values: dict = None
dropout_rng: PRNGKey = None
train: bool = False
output_attentions: typing.Optional[bool] = None
output_hidden_states: typing.Optional[bool] = None
return_dict: typing.Optional[bool] = None
)
→
transformers.modeling_flax_outputs.FlaxCausalLMOutputWithCrossAttentions or tuple(torch.FloatTensor)
Parameters
-
input_ids (
numpy.ndarray
of shape(batch_size, input_ids_length)
) —input_ids_length
=sequence_length
. Indices of input sequence tokens in the vocabulary.Indices can be obtained using GPT2Tokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
-
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.
-
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]
. -
past_key_values (
Dict[str, np.ndarray]
, optional, returned byinit_cache
or when passing previouspast_key_values
) — Dictionary of pre-computed hidden-states (key and values in the attention blocks) that can be used for fast auto-regressive decoding. Pre-computed key and value hidden-states are of shape [batch_size, max_length]. -
output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
transformers.modeling_flax_outputs.FlaxCausalLMOutputWithCrossAttentions or tuple(torch.FloatTensor)
A transformers.modeling_flax_outputs.FlaxCausalLMOutputWithCrossAttentions 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 (GPT2Config) 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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) — Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) — Tuple ofjnp.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 whenuse_cache=True
is passed or whenconfig.use_cache=True
) — Tuple ofjnp.ndarray
tuples of lengthconfig.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 ifconfig.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.
The FlaxGPT2PreTrainedModel
forward method, overrides the __call__
special method.
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.
Example:
>>> from transformers import GPT2Tokenizer, FlaxGPT2LMHeadModel
>>> tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
>>> model = FlaxGPT2LMHeadModel.from_pretrained("gpt2")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="np")
>>> outputs = model(**inputs)
>>> # retrieve logts for next token
>>> next_token_logits = outputs.logits[:, -1]