OpenAI GPT
개요
OpenAI GPT 모델은 Alec Radford, Karthik Narasimhan, Tim Salimans, Ilya Sutskever가 작성한 Improving Language Understanding by Generative Pre-Training 논문에서 제안되었습니다. 이는 Toronto Book Corpus와 같은 장기 의존성을 가진 대규모 말뭉치를 사용하여 언어 모델링으로 사전 학습된 인과적(단방향) 트랜스포머입니다.
논문의 초록은 다음과 같습니다:
자연어 이해는 텍스트 함의, 질문 응답, 의미 유사성 평가, 문서 분류와 같은 다양한 작업을 포함합니다. 비록 대규모의 레이블이 없는 텍스트 말뭉치가 풍부하기는 하지만, 이러한 특정 작업에 대한 학습을 위한 레이블된 데이터는 부족하여 판별적으로 학습된 모델이 적절하게 성능을 발휘하기 어렵습니다. 우리는 다양한 레이블이 없는 텍스트 말뭉치에 대한 언어 모델의 생성적 사전 학습을 수행하고, 각 특정 과제에 대한 판별적 미세 조정을 수행함으로써 이러한 과제에서 큰 성과를 달성할 수 있음을 보여줍니다. 이전 접근 방식과 달리, 우리는 모델 아키텍처에 최소한의 변화를 요구하면서 효과적인 전이를 달성하기 위해 미세 조정 중에 과제 인식 입력 변환(task-aware input transformation)을 사용합니다. 우리는 자연어 이해를 위한 다양한 벤치마크에서 우리의 접근 방식의 효과를 입증합니다. 우리의 general task-agnostic 모델은 각 과제에 특별히 설계된 아키텍처를 사용하는 판별적으로 학습된 모델보다 뛰어나며, 연구된 12개 과제 중 9개 부문에서 최첨단 성능(state of the art)을 크게 향상시킵니다.
Write With Transformer는 Hugging Face가 만든 웹 애플리케이션으로, 여러 모델의 생성 능력을 보여주며 그 중에는 GPT도 포함되어 있습니다.
이 모델은 thomwolf에 의해 기여되었으며, 원본 코드는 여기에서 확인할 수 있습니다.
사용 팁
- GPT는 절대 위치 임베딩을 사용하는 모델이므로 입력을 일반적으로 왼쪽보다는 오른쪽에 패딩하는 것이 권장됩니다.
- GPT는 인과 언어 모델링(Causal Language Modeling, CLM) 목표로 학습되었기 때문에 시퀀스에서 다음 토큰을 예측하는 데 강력한 성능을 보여줍니다. 이를 활용하면 run_generation.py 예제 스크립트에서 볼 수 있듯이 GPT-2는 구문적으로 일관된 텍스트를 생성할 수 있습니다.
참고:
OpenAI GPT 논문의 원래 토큰화 과정을 재현하려면 ftfy와 SpaCy를 설치해야 합니다:
pip install spacy ftfy==4.4.3 python -m spacy download en
ftfy와 SpaCy를 설치하지 않으면 OpenAIGPTTokenizer는 기본적으로 BERT의 BasicTokenizer를 사용한 후 Byte-Pair Encoding을 통해 토큰화합니다(대부분의 사용에 문제가 없으니 걱정하지 마세요).
리소스
OpenAI GPT를 시작하는 데 도움이 되는 공식 Hugging Face 및 커뮤니티(🌎 표시) 리소스 목록입니다. 여기에 리소스를 추가하고 싶다면, Pull Request를 열어주시면 검토하겠습니다! 리소스는 기존 리소스를 복제하지 않고 새로운 것을 보여주는 것이 좋습니다.
- SetFit을 사용하여 텍스트 분류에서 OpenAI GPT-3을 능가하는 방법 블로그 게시물.
- 추가 자료: 텍스트 분류 과제 가이드
- Hugging Face와 함께 비영어 GPT-2 모델을 미세 조정하는 방법 블로그.
- GPT-2와 함께 Transformers를 사용한 언어 생성의 다양한 디코딩 방법에 대한 블로그.
- Scratch에서 CodeParrot 🦜을 훈련하는 방법, 대규모 GPT-2 모델에 대한 블로그.
- GPT-2와 함께 TensorFlow 및 XLA를 사용한 더 빠른 텍스트 생성에 대한 블로그.
- Megatron-LM으로 언어 모델을 훈련하는 방법에 대한 블로그.
- 좋아하는 아티스트의 스타일로 가사를 생성하도록 GPT2를 미세 조정하는 방법에 대한 노트북. 🌎
- 좋아하는 트위터 사용자의 스타일로 트윗을 생성하도록 GPT2를 미세 조정하는 방법에 대한 노트북. 🌎
- 🤗 Hugging Face 코스의 인과 언어 모델링 장.
- OpenAIGPTLMHeadModel은 인과 언어 모델링 예제 스크립트, 텍스트 생성 예제 스크립트 및 노트북에 의해 지원됩니다.
- TFOpenAIGPTLMHeadModel은 인과 언어 모델링 예제 스크립트 및 노트북에 의해 지원됩니다.
- 추가 자료: 인과 언어 모델링 과제 가이드
- Byte-Pair Encoding 토큰화에 대한 강의 자료.
OpenAIGPTConfig
class transformers.OpenAIGPTConfig
< source >( vocab_size = 40478 n_positions = 512 n_embd = 768 n_layer = 12 n_head = 12 afn = 'gelu' 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 **kwargs )
Parameters
- vocab_size (
int, optional, defaults to 40478) — Vocabulary size of the GPT-2 model. Defines the number of different tokens that can be represented by theinputs_idspassed when calling OpenAIGPTModel or TFOpenAIGPTModel. - n_positions (
int, optional, defaults to 512) — The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048). - 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. - afn (
strorCallable, optional, defaults to"gelu") — The non-linear activation function (function or string) in the encoder and pooler. If string,"gelu","relu","silu"and"gelu_new"are supported. - 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-05) — 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 (
str, optional, defaults to"cls_index") — Argument used when doing sequence summary, used in the models OpenAIGPTDoubleHeadsModel and OpenAIGPTDoubleHeadsModel.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 OpenAIGPTDoubleHeadsModel and OpenAIGPTDoubleHeadsModel.Whether or not to add a projection after the vector extraction.
- summary_activation (
str, optional) — Argument used when doing sequence summary, used in the models OpenAIGPTDoubleHeadsModel and OpenAIGPTDoubleHeadsModel.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 OpenAIGPTDoubleHeadsModel and OpenAIGPTDoubleHeadsModel.Whether the projection outputs should have
config.num_labelsorconfig.hidden_sizeclasses. - summary_first_dropout (
float, optional, defaults to 0.1) — Argument used when doing sequence summary, used in the models OpenAIGPTDoubleHeadsModel and OpenAIGPTDoubleHeadsModel.The dropout ratio to be used after the projection and activation.
This is the configuration class to store the configuration of a OpenAIGPTModel or a TFOpenAIGPTModel. It is used to instantiate a GPT 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 openai-community/openai-gpt architecture from OpenAI.
Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.
Examples:
>>> from transformers import OpenAIGPTConfig, OpenAIGPTModel
>>> # Initializing a GPT configuration
>>> configuration = OpenAIGPTConfig()
>>> # Initializing a model (with random weights) from the configuration
>>> model = OpenAIGPTModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.configOpenAIGPTTokenizer
class transformers.OpenAIGPTTokenizer
< source >( vocab_file merges_file unk_token = '<unk>' **kwargs )
Construct a GPT Tokenizer. Based on Byte-Pair-Encoding with the following peculiarities:
- lowercases all inputs,
- uses
SpaCytokenizer andftfyfor pre-BPE tokenization if they are installed, fallback to BERT’sBasicTokenizerif not.
This tokenizer inherits from PreTrainedTokenizer which contains most of the main methods. Users should refer to
this superclass for more information regarding those methods.
OpenAIGPTTokenizerFast
class transformers.OpenAIGPTTokenizerFast
< source >( vocab_file = None merges_file = None tokenizer_file = None unk_token = '<unk>' **kwargs )
Construct a “fast” GPT Tokenizer (backed by HuggingFace’s tokenizers library). Based on Byte-Pair-Encoding with the following peculiarities:
- lower case all inputs
- uses BERT’s BasicTokenizer for pre-BPE tokenization
This tokenizer inherits from PreTrainedTokenizerFast which contains most of the main methods. Users should
refer to this superclass for more information regarding those methods.
OpenAI specific outputs
class transformers.models.openai.modeling_openai.OpenAIGPTDoubleHeadsModelOutput
< source >( loss: typing.Optional[torch.FloatTensor] = None mc_loss: typing.Optional[torch.FloatTensor] = None logits: FloatTensor = None mc_logits: FloatTensor = None hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor]] = None )
Parameters
- loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Language modeling loss. - mc_loss (
torch.FloatTensorof shape(1,), optional, returned whenmc_labelsis provided) — Multiple choice classification loss. - logits (
torch.FloatTensorof 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.FloatTensorof shape(batch_size, num_choices)) — Prediction scores of the multiple choice classification head (scores for each choice before SoftMax). - hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis 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=Trueis 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.
Base class for outputs of models predicting if two sentences are consecutive or not.
class transformers.models.openai.modeling_tf_openai.TFOpenAIGPTDoubleHeadsModelOutput
< source >( logits: tf.Tensor = None mc_logits: tf.Tensor = None hidden_states: Tuple[tf.Tensor] | None = None attentions: Tuple[tf.Tensor] | None = None )
Parameters
- logits (
tf.Tensorof 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.Tensorof shape(batch_size, num_choices)) — Prediction scores of the multiple choice classification head (scores for each choice before SoftMax). - hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis 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=Trueis 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.
OpenAIGPTModel
class transformers.OpenAIGPTModel
< source >( config )
Parameters
- config (OpenAIGPTConfig) — 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 OpenAI GPT transformer model 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 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 output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.BaseModelOutput or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof shape(batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.FloatTensorof 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.
- token_type_ids (
torch.LongTensorof 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 (
torch.LongTensorof 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.FloatTensorof 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.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices 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. Seeattentionsunder returned tensors for more detail. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder 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.BaseModelOutput or tuple(torch.FloatTensor)
A transformers.modeling_outputs.BaseModelOutput 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 (OpenAIGPTConfig) and inputs.
-
last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the model. -
hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis 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=Trueis 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 OpenAIGPTModel 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 AutoTokenizer, OpenAIGPTModel
>>> import torch
>>> tokenizer = AutoTokenizer.from_pretrained("openai-community/openai-gpt")
>>> model = OpenAIGPTModel.from_pretrained("openai-community/openai-gpt")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> outputs = model(**inputs)
>>> last_hidden_states = outputs.last_hidden_stateOpenAIGPTLMHeadModel
class transformers.OpenAIGPTLMHeadModel
< source >( config )
Parameters
- config (OpenAIGPTConfig) — 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.
OpenAI GPT 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 attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.CausalLMOutput or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof shape(batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.FloatTensorof 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.
- token_type_ids (
torch.LongTensorof 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 (
torch.LongTensorof 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.FloatTensorof 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.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices 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. Seeattentionsunder returned tensors for more detail. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. - return_dict (
bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - labels (
torch.LongTensorof 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_idsIndices are selected in[-100, 0, ..., config.vocab_size]All labels set to-100are ignored (masked), the loss is only computed for labels in[0, ..., config.vocab_size]
Returns
transformers.modeling_outputs.CausalLMOutput or tuple(torch.FloatTensor)
A transformers.modeling_outputs.CausalLMOutput 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 (OpenAIGPTConfig) and inputs.
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Language modeling loss (for next-token prediction). -
logits (
torch.FloatTensorof 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=Trueis 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=Trueis 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 OpenAIGPTLMHeadModel 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 AutoTokenizer, OpenAIGPTLMHeadModel
>>> tokenizer = AutoTokenizer.from_pretrained("openai-community/openai-gpt")
>>> model = OpenAIGPTLMHeadModel.from_pretrained("openai-community/openai-gpt")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> outputs = model(**inputs, labels=inputs["input_ids"])
>>> loss = outputs.loss
>>> logits = outputs.logitsOpenAIGPTDoubleHeadsModel
class transformers.OpenAIGPTDoubleHeadsModel
< source >( config )
Parameters
- config (OpenAIGPTConfig) — 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.
OpenAI GPT 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 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 output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.models.openai.modeling_openai.OpenAIGPTDoubleHeadsModelOutput or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof shape(batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.FloatTensorof 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.
- token_type_ids (
torch.LongTensorof 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 (
torch.LongTensorof 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.FloatTensorof 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.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices 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. Seeattentionsunder returned tensors for more detail. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder 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.LongTensorof 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.LongTensorof 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_idsIndices are selected in[-1, 0, ..., config.vocab_size]All labels set to-100are ignored (masked), the loss is only computed for labels in[0, ..., config.vocab_size] - mc_labels (
torch.LongTensorof 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.openai.modeling_openai.OpenAIGPTDoubleHeadsModelOutput or tuple(torch.FloatTensor)
A transformers.models.openai.modeling_openai.OpenAIGPTDoubleHeadsModelOutput 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 (OpenAIGPTConfig) and inputs.
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Language modeling loss. -
mc_loss (
torch.FloatTensorof shape(1,), optional, returned whenmc_labelsis provided) — Multiple choice classification loss. -
logits (
torch.FloatTensorof 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.FloatTensorof shape(batch_size, num_choices)) — Prediction scores of the multiple choice classification head (scores for each choice before SoftMax). -
hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis 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=Trueis 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 OpenAIGPTDoubleHeadsModel 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:
>>> from transformers import AutoTokenizer, OpenAIGPTDoubleHeadsModel
>>> import torch
>>> tokenizer = AutoTokenizer.from_pretrained("openai-community/openai-gpt")
>>> model = OpenAIGPTDoubleHeadsModel.from_pretrained("openai-community/openai-gpt")
>>> tokenizer.add_special_tokens(
... {"cls_token": "[CLS]"}
... ) # Add a [CLS] to the vocabulary (we should train it also!)
>>> model.resize_token_embeddings(len(tokenizer))
>>> choices = ["Hello, my dog is cute [CLS]", "Hello, my cat is cute [CLS]"]
>>> input_ids = torch.tensor([tokenizer.encode(s) for s in choices]).unsqueeze(0) # Batch size 1, 2 choices
>>> mc_token_ids = torch.tensor([input_ids.size(-1) - 1, input_ids.size(-1) - 1]).unsqueeze(0) # Batch size 1
>>> outputs = model(input_ids, mc_token_ids=mc_token_ids)
>>> lm_logits = outputs.logits
>>> mc_logits = outputs.mc_logitsOpenAIGPTForSequenceClassification
class transformers.OpenAIGPTForSequenceClassification
< source >( config )
Parameters
- config (OpenAIGPTConfig) — 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 Original OpenAI GPT Model transformer with a sequence classification head on top (linear layer).
OpenAIGPTForSequenceClassification uses the last token in order to do the classification, as other causal
models (e.g. GPT-2) do. Since it does classification on the last token, it requires to know the position of the
last token. If 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 attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.SequenceClassifierOutput or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof shape(batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.FloatTensorof 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.
- token_type_ids (
torch.LongTensorof 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 (
torch.LongTensorof 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.FloatTensorof 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.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices 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. Seeattentionsunder returned tensors for more detail. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. - return_dict (
bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - labels (
torch.LongTensorof shape(batch_size,), optional) — Labels for computing the sequence classification/regression loss. Indices should be in[0, ..., config.num_labels - 1]. Ifconfig.num_labels == 1a regression loss is computed (Mean-Square loss), Ifconfig.num_labels > 1a classification loss is computed (Cross-Entropy).
Returns
transformers.modeling_outputs.SequenceClassifierOutput or tuple(torch.FloatTensor)
A transformers.modeling_outputs.SequenceClassifierOutput 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 (OpenAIGPTConfig) and inputs.
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Classification (or regression if config.num_labels==1) loss. -
logits (
torch.FloatTensorof shape(batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax). -
hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis 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=Trueis 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 OpenAIGPTForSequenceClassification 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 AutoTokenizer, OpenAIGPTForSequenceClassification
>>> tokenizer = AutoTokenizer.from_pretrained("openai-community/openai-gpt")
>>> model = OpenAIGPTForSequenceClassification.from_pretrained("openai-community/openai-gpt")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> with torch.no_grad():
... logits = model(**inputs).logits
>>> predicted_class_id = logits.argmax().item()
>>> # 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 = OpenAIGPTForSequenceClassification.from_pretrained("openai-community/openai-gpt", num_labels=num_labels)
>>> labels = torch.tensor([1])
>>> loss = model(**inputs, labels=labels).lossExample of multi-label classification:
>>> import torch
>>> from transformers import AutoTokenizer, OpenAIGPTForSequenceClassification
>>> tokenizer = AutoTokenizer.from_pretrained("openai-community/openai-gpt")
>>> model = OpenAIGPTForSequenceClassification.from_pretrained("openai-community/openai-gpt", problem_type="multi_label_classification")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> with torch.no_grad():
... logits = model(**inputs).logits
>>> predicted_class_ids = torch.arange(0, logits.shape[-1])[torch.sigmoid(logits).squeeze(dim=0) > 0.5]
>>> # 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 = OpenAIGPTForSequenceClassification.from_pretrained(
... "openai-community/openai-gpt", num_labels=num_labels, problem_type="multi_label_classification"
... )
>>> labels = torch.sum(
... torch.nn.functional.one_hot(predicted_class_ids[None, :].clone(), num_classes=num_labels), dim=1
... ).to(torch.float)
>>> loss = model(**inputs, labels=labels).lossTFOpenAIGPTModel
class transformers.TFOpenAIGPTModel
< source >( config *inputs **kwargs )
Parameters
- config (OpenAIGPTConfig) — 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 OpenAI GPT transformer model outputting raw hidden-states without any specific head on top.
This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.
TensorFlow models and layers in transformers accept two formats as input:
- having all inputs as keyword arguments (like PyTorch models), or
- having all inputs as a list, tuple or dict in the first positional argument.
The reason the second format is supported is that Keras methods prefer this format when passing inputs to models
and layers. Because of this support, when using methods like model.fit() things should “just work” for you - just
pass your inputs and labels in any format that model.fit() supports! If, however, you want to use the second
format outside of Keras methods like fit() and predict(), such as when creating your own layers or models with
the Keras Functional API, there are three possibilities you can use to gather all the input Tensors in the first
positional argument:
- a single Tensor with
input_idsonly 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: TFModelInputType | None = None attention_mask: np.ndarray | tf.Tensor | None = None token_type_ids: np.ndarray | tf.Tensor | None = None position_ids: np.ndarray | tf.Tensor | None = None head_mask: np.ndarray | tf.Tensor | None = None inputs_embeds: np.ndarray | tf.Tensor | None = None output_attentions: Optional[bool] = None output_hidden_states: Optional[bool] = None return_dict: Optional[bool] = None training: Optional[bool] = False ) → transformers.modeling_tf_outputs.TFBaseModelOutput or tuple(tf.Tensor)
Parameters
- input_ids (
Numpy arrayortf.Tensorof shape(batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.call() and PreTrainedTokenizer.encode() for details.
- attention_mask (
tf.TensororNumpy arrayof 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.
- token_type_ids (
tf.TensororNumpy arrayof 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.TensororNumpy arrayof 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 (
tf.TensororNumpy arrayof 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.TensororNumpy arrayof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices 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. Seeattentionsunder 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_statesunder 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).
Returns
transformers.modeling_tf_outputs.TFBaseModelOutput or tuple(tf.Tensor)
A transformers.modeling_tf_outputs.TFBaseModelOutput 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 (OpenAIGPTConfig) and inputs.
-
last_hidden_state (
tf.Tensorof shape(batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the model. -
hidden_states (
tuple(tf.FloatTensor), optional, returned whenoutput_hidden_states=Trueis 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=Trueis 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 TFOpenAIGPTModel 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 AutoTokenizer, TFOpenAIGPTModel
>>> import tensorflow as tf
>>> tokenizer = AutoTokenizer.from_pretrained("openai-community/openai-gpt")
>>> model = TFOpenAIGPTModel.from_pretrained("openai-community/openai-gpt")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="tf")
>>> outputs = model(inputs)
>>> last_hidden_states = outputs.last_hidden_stateTFOpenAIGPTLMHeadModel
class transformers.TFOpenAIGPTLMHeadModel
< source >( config *inputs **kwargs )
Parameters
- config (OpenAIGPTConfig) — 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.
OpenAI GPT 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 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_idsonly 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: TFModelInputType | None = None attention_mask: np.ndarray | tf.Tensor | None = None token_type_ids: np.ndarray | tf.Tensor | None = None position_ids: np.ndarray | tf.Tensor | None = None head_mask: np.ndarray | tf.Tensor | None = None inputs_embeds: np.ndarray | tf.Tensor | None = None output_attentions: Optional[bool] = None output_hidden_states: Optional[bool] = None return_dict: Optional[bool] = None labels: np.ndarray | tf.Tensor | None = None training: Optional[bool] = False ) → transformers.modeling_tf_outputs.TFCausalLMOutput or tuple(tf.Tensor)
Parameters
- input_ids (
Numpy arrayortf.Tensorof shape(batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.call() and PreTrainedTokenizer.encode() for details.
- attention_mask (
tf.TensororNumpy arrayof 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.
- token_type_ids (
tf.TensororNumpy arrayof 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.TensororNumpy arrayof 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 (
tf.TensororNumpy arrayof 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.TensororNumpy arrayof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices 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. Seeattentionsunder 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_statesunder 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.Tensorof 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.TFCausalLMOutput or tuple(tf.Tensor)
A transformers.modeling_tf_outputs.TFCausalLMOutput 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 (OpenAIGPTConfig) and inputs.
-
loss (
tf.Tensorof shape(n,), optional, where n is the number of non-masked labels, returned whenlabelsis provided) — Language modeling loss (for next-token prediction). -
logits (
tf.Tensorof 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=Trueis 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=Trueis 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 TFOpenAIGPTLMHeadModel 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 AutoTokenizer, TFOpenAIGPTLMHeadModel
>>> import tensorflow as tf
>>> tokenizer = AutoTokenizer.from_pretrained("openai-community/openai-gpt")
>>> model = TFOpenAIGPTLMHeadModel.from_pretrained("openai-community/openai-gpt")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="tf")
>>> outputs = model(inputs)
>>> logits = outputs.logitsTFOpenAIGPTDoubleHeadsModel
class transformers.TFOpenAIGPTDoubleHeadsModel
< source >( config *inputs **kwargs )
Parameters
- config (OpenAIGPTConfig) — 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.
OpenAI GPT 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 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_idsonly 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: TFModelInputType | None = None attention_mask: np.ndarray | tf.Tensor | None = None token_type_ids: np.ndarray | tf.Tensor | None = None position_ids: np.ndarray | tf.Tensor | None = None head_mask: np.ndarray | tf.Tensor | None = None inputs_embeds: np.ndarray | tf.Tensor | None = None mc_token_ids: np.ndarray | tf.Tensor | None = None output_attentions: Optional[bool] = None output_hidden_states: Optional[bool] = None return_dict: Optional[bool] = None training: Optional[bool] = False ) → transformers.models.openai.modeling_tf_openai.TFOpenAIGPTDoubleHeadsModelOutput or tuple(tf.Tensor)
Parameters
- input_ids (
Numpy arrayortf.Tensorof shape(batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.call() and PreTrainedTokenizer.encode() for details.
- attention_mask (
tf.TensororNumpy arrayof 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.
- token_type_ids (
tf.TensororNumpy arrayof 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.TensororNumpy arrayof 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 (
tf.TensororNumpy arrayof 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.TensororNumpy arrayof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices 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. Seeattentionsunder 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_statesunder 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.TensororNumpy arrayof 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.openai.modeling_tf_openai.TFOpenAIGPTDoubleHeadsModelOutput or tuple(tf.Tensor)
A transformers.models.openai.modeling_tf_openai.TFOpenAIGPTDoubleHeadsModelOutput 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 (OpenAIGPTConfig) and inputs.
-
logits (
tf.Tensorof 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.Tensorof shape(batch_size, num_choices)) — Prediction scores of the multiple choice classification head (scores for each choice before SoftMax). -
hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis 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=Trueis 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 TFOpenAIGPTDoubleHeadsModel 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 AutoTokenizer, TFOpenAIGPTDoubleHeadsModel
>>> tokenizer = AutoTokenizer.from_pretrained("openai-community/openai-gpt")
>>> model = TFOpenAIGPTDoubleHeadsModel.from_pretrained("openai-community/openai-gpt")
>>> # Add a [CLS] to the vocabulary (we should train it also!)
>>> tokenizer.add_special_tokens({"cls_token": "[CLS]"})
>>> model.resize_token_embeddings(len(tokenizer)) # Update the model embeddings with the new vocabulary size
>>> print(tokenizer.cls_token_id, len(tokenizer)) # The newly token the last token of the vocabulary
>>> choices = ["Hello, my dog is cute [CLS]", "Hello, my cat is cute [CLS]"]
>>> encoding = tokenizer(choices, return_tensors="tf")
>>> inputs = {k: tf.expand_dims(v, 0) for k, v in encoding.items()}
>>> inputs["mc_token_ids"] = tf.constant(
... [inputs["input_ids"].shape[-1] - 1, inputs["input_ids"].shape[-1] - 1]
... )[
... None, :
... ] # Batch size 1
>>> outputs = model(inputs)
>>> lm_prediction_scores, mc_prediction_scores = outputs[:2]TFOpenAIGPTForSequenceClassification
class transformers.TFOpenAIGPTForSequenceClassification
< source >( config *inputs **kwargs )
Parameters
- config (OpenAIGPTConfig) — 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 OpenAI GPT Model transformer with a sequence classification head on top (linear layer).
TFOpenAIGPTForSequenceClassification uses the last token in order to do the classification, as other causal models (e.g. GPT-2) do.
Since it does classification on the last token, it requires to know the position of the last token. If 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 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_idsonly 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: TFModelInputType | None = None attention_mask: np.ndarray | tf.Tensor | None = None token_type_ids: np.ndarray | tf.Tensor | None = None position_ids: np.ndarray | tf.Tensor | None = None head_mask: np.ndarray | tf.Tensor | None = None inputs_embeds: np.ndarray | tf.Tensor | None = None output_attentions: Optional[bool] = None output_hidden_states: Optional[bool] = None return_dict: Optional[bool] = None labels: np.ndarray | tf.Tensor | None = None training: Optional[bool] = False ) → transformers.modeling_tf_outputs.TFSequenceClassifierOutput or tuple(tf.Tensor)
Parameters
- input_ids (
Numpy arrayortf.Tensorof shape(batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.call() and PreTrainedTokenizer.encode() for details.
- attention_mask (
tf.TensororNumpy arrayof 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.
- token_type_ids (
tf.TensororNumpy arrayof 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.TensororNumpy arrayof 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 (
tf.TensororNumpy arrayof 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.TensororNumpy arrayof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices 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. Seeattentionsunder 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_statesunder 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.Tensorof 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.TFSequenceClassifierOutput or tuple(tf.Tensor)
A transformers.modeling_tf_outputs.TFSequenceClassifierOutput 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 (OpenAIGPTConfig) and inputs.
-
loss (
tf.Tensorof shape(batch_size, ), optional, returned whenlabelsis provided) — Classification (or regression if config.num_labels==1) loss. -
logits (
tf.Tensorof shape(batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax). -
hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis 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=Trueis 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 TFOpenAIGPTForSequenceClassification 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 AutoTokenizer, TFOpenAIGPTForSequenceClassification
>>> import tensorflow as tf
>>> tokenizer = AutoTokenizer.from_pretrained("openai-community/openai-gpt")
>>> model = TFOpenAIGPTForSequenceClassification.from_pretrained("openai-community/openai-gpt")
>>> 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])>>> # 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 = TFOpenAIGPTForSequenceClassification.from_pretrained("openai-community/openai-gpt", num_labels=num_labels)
>>> labels = tf.constant(1)
>>> loss = model(**inputs, labels=labels).loss