Hugging Face's logo

Transformers documentation

BioGPT

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

BioGPT

개요

BioGPT는 Renqian Luo, Liai Sun, Yingce Xia, Tao Qin, Sheng Zhang, Hoifung Poon, Tie-Yan Liu에 의해 BioGPT: generative pre-trained transformer for biomedical text generation and mining 에서 제안된 모델입니다. BioGPT는 생물의학 텍스트 생성과 마이닝을 위해 도메인에 특화된 생성형 사전 학습 트랜스포머 언어 모델입니다. BioGPT는 트랜스포머 언어 모델 구조를 따르며, 1,500만 개의 PubMed 초록을 이용해 처음부터 학습되었습니다.

논문의 초록은 다음과 같습니다:

생물의학 분야에서 사전 학습된 언어 모델은 일반 자연어 처리 분야에서의 성공에 영감을 받아 점점 더 많은 주목을 받고 있습니다. 일반 언어 분야에서 사전 학습된 언어 모델의 두 가지 주요 계통인 BERT(및 그 변형)와 GPT(및 그 변형) 중 첫 번째는 생물의학 분야에서 BioBERT와 PubMedBERT와 같이 광범위하게 연구되었습니다. 이들은 다양한 분류 기반의 생물의학 작업에서 큰 성공을 거두었지만, 생성 능력의 부족은 그들의 적용 범위를 제한했습니다. 본 논문에서는 대규모 생물의학 문헌을 사전 학습한 도메인 특화 생성형 트랜스포머 언어 모델인 BioGPT를 제안합니다. 우리는 6개의 생물의학 자연어 처리 작업에서 BioGPT를 평가한 결과, 대부분의 작업에서 이전 모델보다 우수한 성능을 보였습니다. 특히, BC5CDR, KD-DTI, DDI 엔드-투-엔드 관계 추출 작업에서 각각 44.98%, 38.42%, 40.76%의 F1 점수를 기록하였으며, PubMedQA에서 78.2%의 정확도를 달성해 새로운 기록을 세웠습니다. 또한 텍스트 생성에 대한 사례 연구는 생물의학 용어에 대한 유창한 설명을 생성하는 데 있어 BioGPT의 장점을 더욱 입증했습니다.

이 모델은 kamalkraj에 의해 기여되었습니다. 원본 코드는 여기에서 찾을 수 있습니다.

사용 팁

  • BioGPT는 절대적 위치 임베딩(absolute position embedding)을 사용하므로, 입력을 왼쪽이 아닌 오른쪽에서 패딩하는 것이 권장됩니다.
  • BioGPT는 인과적 언어 모델링(Casual Langague Modeling, CLM) 목표로 학습되었기 때문에, 다음 토큰을 예측하는 데 강력한 성능을 보입니다. 이 기능을 활용하여 BioGPT는 구문적으로 일관된 텍스트를 생성할 수 있으며, 예시 스크립트 run_generation.py에서 이를 확인할 수 있습니다.
  • 이 모델은 past_key_values(PyTorch 용)를 입력으로 받을 수 있는데, 이는 이전에 계산된 키/값 어텐션 쌍입니다. 이 값을 사용하면 텍스트 생성 중 이미 계산된 값을 다시 계산하지 않도록 할 수 있습니다. PyTorch에서 past_key_values 인수는 BioGptForCausalLM.forward() 메소드에서 자세히 설명되어 있습니다.

Scaled Dot Product Attention(SDPA) 사용

PyTorch는 torch.nn.functional의 일부로 스케일된 점곱 어텐션(SDPA) 연산자를 기본적으로 포함합니다. 이 함수는 입력과 사용 중인 하드웨어에 따라 여러 구현을 적용할 수 있습니다. 자세한 내용은 공식 문서 또는 GPU 추론 페이지를 참조하세요.

torch>=2.1.1에서 구현이 가능한 경우 SDPA는 기본적으로 사용되며, attn_implementation="sdpa"를 from_pretrained()에서 설정하여 SDPA 사용을 명시적으로 요청할 수 있습니다.

from transformers import BioGptForCausalLM
model = BioGptForCausalLM.from_pretrained("microsoft/biogpt", attn_implementation="sdpa", torch_dtype=torch.float16)

NVIDIA GeForce RTX 2060-8GB, PyTorch 2.3.1, Ubuntu 20.04 환경에서 float16 및 CausalLM 헤드가 있는 microsoft/biogpt 모델로 로컬 벤치마크를 수행한 결과, 훈련 중 다음과 같은 속도 향상을 확인했습니다.

최적의 속도 향상을 위해 모델을 반정밀도(예: torch.float16 또는 torch.bfloat16)로 로드하는 것이 좋습니다.

num_training_steps batch_size seq_len is cuda Time per batch (eager - s) Time per batch (sdpa - s) Speedup (%) Eager peak mem (MB) sdpa peak mem (MB) Mem saving (%)
100 1 128 False 0.038 0.031 21.301 1601.862 1601.497 0.023
100 1 256 False 0.039 0.034 15.084 1624.944 1625.296 -0.022
100 2 128 False 0.039 0.033 16.820 1624.567 1625.296 -0.045
100 2 256 False 0.065 0.059 10.255 1672.164 1672.164 0.000
100 4 128 False 0.062 0.058 6.998 1671.435 1672.164 -0.044
100 4 256 False 0.113 0.100 13.316 2350.179 1848.435 27.144
100 8 128 False 0.107 0.098 9.883 2098.521 1848.435 13.530
100 8 256 False 0.222 0.196 13.413 3989.980 2986.492 33.601

NVIDIA GeForce RTX 2060-8GB, PyTorch 2.3.1, Ubuntu 20.04 환경에서 float16 및 AutoModel 헤드가 있는 microsoft/biogpt 모델로 추론 중 다음과 같은 속도 향상을 확인했습니다.

num_batches batch_size seq_len is cuda is half use mask Per token latency eager (ms) Per token latency SDPA (ms) Speedup (%) Mem eager (MB) Mem BT (MB) Mem saved (%)
50 1 64 True True True 0.115 0.098 17.392 716.998 716.998 0.000
50 1 128 True True True 0.115 0.093 24.640 730.916 730.916 0.000
50 2 64 True True True 0.114 0.096 19.204 730.900 730.900 0.000
50 2 128 True True True 0.117 0.095 23.529 759.262 759.262 0.000
50 4 64 True True True 0.113 0.096 18.325 759.229 759.229 0.000
50 4 128 True True True 0.186 0.178 4.289 816.478 816.478 0.000

리소스

BioGptConfig

class transformers.BioGptConfig

< >

( vocab_size = 42384 hidden_size = 1024 num_hidden_layers = 24 num_attention_heads = 16 intermediate_size = 4096 hidden_act = 'gelu' hidden_dropout_prob = 0.1 attention_probs_dropout_prob = 0.1 max_position_embeddings = 1024 initializer_range = 0.02 layer_norm_eps = 1e-12 scale_embedding = True use_cache = True layerdrop = 0.0 activation_dropout = 0.0 pad_token_id = 1 bos_token_id = 0 eos_token_id = 2 **kwargs )

Parameters

  • vocab_size (int, optional, defaults to 42384) — Vocabulary size of the BioGPT model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling BioGptModel.
  • hidden_size (int, optional, defaults to 1024) — Dimension of the encoder layers and the pooler layer.
  • num_hidden_layers (int, optional, defaults to 24) — Number of hidden layers in the Transformer encoder.
  • num_attention_heads (int, optional, defaults to 16) — Number of attention heads for each attention layer in the Transformer encoder.
  • intermediate_size (int, optional, defaults to 4096) — Dimension of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder.
  • hidden_act (str or function, optional, defaults to "gelu") — The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu", "relu", "selu" and "gelu_new" are supported.
  • hidden_dropout_prob (float, optional, defaults to 0.1) — The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
  • attention_probs_dropout_prob (float, optional, defaults to 0.1) — The dropout ratio for the attention probabilities.
  • max_position_embeddings (int, optional, defaults to 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).
  • initializer_range (float, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
  • layer_norm_eps (float, optional, defaults to 1e-12) — The epsilon used by the layer normalization layers.
  • scale_embedding (bool, optional, defaults to True) — Scale embeddings by diving by sqrt(d_model).
  • use_cache (bool, optional, defaults to True) — Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if config.is_decoder=True.
  • layerdrop (float, optional, defaults to 0.0) — Please refer to the paper about LayerDrop: https://arxiv.org/abs/1909.11556 for further details
  • activation_dropout (float, optional, defaults to 0.0) — The dropout ratio for activations inside the fully connected layer.
  • pad_token_id (int, optional, defaults to 1) — Padding token id.
  • bos_token_id (int, optional, defaults to 0) — Beginning of stream token id.
  • eos_token_id (int, optional, defaults to 2) — End of stream token id.

This is the configuration class to store the configuration of a BioGptModel. It is used to instantiate an BioGPT 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 BioGPT microsoft/biogpt architecture.

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

Example:

>>> from transformers import BioGptModel, BioGptConfig

>>> # Initializing a BioGPT microsoft/biogpt style configuration
>>> configuration = BioGptConfig()

>>> # Initializing a model from the microsoft/biogpt style configuration
>>> model = BioGptModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config

BioGptTokenizer

class transformers.BioGptTokenizer

< >

( vocab_file merges_file unk_token = '<unk>' bos_token = '<s>' eos_token = '</s>' sep_token = '</s>' pad_token = '<pad>' **kwargs )

Parameters

  • vocab_file (str) — Path to the vocabulary file.
  • merges_file (str) — Merges file.
  • unk_token (str, optional, defaults to "<unk>") — 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 "<s>") — The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.

    When building a sequence using special tokens, this is not the token that is used for the beginning of sequence. The token used is the cls_token.
  • eos_token (str, optional, defaults to "</s>") — The end of sequence token.

    When building a sequence using special tokens, this is not the token that is used for the end of sequence. The token used is the sep_token.
  • sep_token (str, optional, defaults to "</s>") — The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for sequence classification or for a text and a question for question answering. It is also used as the last token of a sequence built with special tokens.
  • pad_token (str, optional, defaults to "<pad>") — The token used for padding, for example when batching sequences of different lengths.

Construct an FAIRSEQ Transformer tokenizer. Moses tokenization followed by Byte-Pair Encoding.

This tokenizer inherits from PreTrainedTokenizer which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.

save_vocabulary

< >

( save_directory: str filename_prefix: Optional = None )

BioGptModel

class transformers.BioGptModel

< >

( config: BioGptConfig )

Parameters

  • config (~BioGptConfig) — 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 BioGPT Model transformer outputting raw hidden-states without any specific head on top. This model is a PyTorch torch.nn.Module sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< >

( input_ids: Optional = None attention_mask: Optional = None head_mask: Optional = None inputs_embeds: Optional = None past_key_values: Optional = None use_cache: Optional = None output_attentions: Optional = None output_hidden_states: Optional = None return_dict: Optional = None ) → transformers.modeling_outputs.BaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)

Parameters

  • input_ids (torch.LongTensor of 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.

    What are input IDs?

  • attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:

    • 1 for tokens that are not masked,
    • 0 for tokens that are masked.

    What are attention masks?

  • head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:

    • 1 indicates the head is not masked,
    • 0 indicates the head is masked.
  • inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
  • past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 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 in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

    If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all decoder_input_ids of shape (batch_size, sequence_length).

  • inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
  • use_cache (bool, optional) — If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).
  • output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
  • output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
  • return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.

Returns

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 (BioGptConfig) and inputs.

  • last_hidden_state (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the model.

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

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

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

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

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

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

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

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

    Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.

The BioGptModel 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, BioGptModel
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("microsoft/biogpt")
>>> model = BioGptModel.from_pretrained("microsoft/biogpt")

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

>>> last_hidden_states = outputs.last_hidden_state

BioGptForCausalLM

class transformers.BioGptForCausalLM

< >

( config )

Parameters

  • config (~BioGptConfig) — 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.

BioGPT Model with a language modeling head on top for CLM fine-tuning. This model is a PyTorch torch.nn.Module sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< >

( input_ids: Optional = None attention_mask: Optional = None head_mask: Optional = None inputs_embeds: Optional = None past_key_values: Optional = None labels: Optional = None use_cache: Optional = None output_attentions: Optional = None output_hidden_states: Optional = None return_dict: Optional = None ) → transformers.modeling_outputs.CausalLMOutputWithCrossAttentions or tuple(torch.FloatTensor)

Parameters

  • input_ids (torch.LongTensor of 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.

    What are input IDs?

  • attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:

    • 1 for tokens that are not masked,
    • 0 for tokens that are masked.

    What are attention masks?

  • head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:

    • 1 indicates the head is not masked,
    • 0 indicates the head is masked.
  • inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
  • past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 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 in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

    If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all decoder_input_ids of shape (batch_size, sequence_length).

  • inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
  • use_cache (bool, optional) — If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).
  • output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
  • output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
  • return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
  • labels (torch.LongTensor of shape (batch_size, sequence_length), optional) — Labels for language modeling. Note that the labels are shifted inside the model, i.e. you can set labels = input_ids Indices are selected in [-100, 0, ..., config.vocab_size] All labels set to -100 are ignored (masked), the loss is only computed for labels in [0, ..., config.vocab_size]

Returns

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 (BioGptConfig) and inputs.

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Language modeling loss (for next-token prediction).

  • logits (torch.FloatTensor of shape (batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).

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

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

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

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

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

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

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

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

The BioGptForCausalLM 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, BioGptForCausalLM

>>> tokenizer = AutoTokenizer.from_pretrained("microsoft/biogpt")
>>> model = BioGptForCausalLM.from_pretrained("microsoft/biogpt")

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

BioGptForTokenClassification

class transformers.BioGptForTokenClassification

< >

( config )

Parameters

  • config (~BioGptConfig) — 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.

BioGPT 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 is a PyTorch torch.nn.Module sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< >

( input_ids: Optional = None token_type_ids: Optional = None attention_mask: Optional = None head_mask: Optional = None past_key_values: Optional = None inputs_embeds: Optional = None labels: Optional = None use_cache: Optional = None output_attentions: Optional = None output_hidden_states: Optional = None return_dict: Optional = None ) → transformers.modeling_outputs.TokenClassifierOutput or tuple(torch.FloatTensor)

Parameters

  • input_ids (torch.LongTensor of shape ({0})) — Indices of input sequence tokens in the vocabulary.

    Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

    What are input IDs?

  • attention_mask (torch.FloatTensor of shape ({0}), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:

    • 1 for tokens that are not masked,
    • 0 for tokens that are masked.

    What are attention masks?

  • 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 ({0}, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
  • past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 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 in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

    If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all decoder_input_ids of shape (batch_size, sequence_length).

  • inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
  • use_cache (bool, optional) — If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).
  • output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
  • output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
  • return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
  • labels (torch.LongTensor of shape (batch_size,), optional) — Labels for computing the sequence classification/regression loss. Indices should be in [0, ..., config.num_labels - 1]. If config.num_labels == 1 a regression loss is computed (Mean-Square loss), If config.num_labels > 1 a classification loss is computed (Cross-Entropy).

Returns

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 (BioGptConfig) and inputs.

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Classification loss.

  • logits (torch.FloatTensor of shape (batch_size, sequence_length, config.num_labels)) — Classification scores (before SoftMax).

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

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

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

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

The BioGptForTokenClassification 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, BioGptForTokenClassification
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("microsoft/biogpt")
>>> model = BioGptForTokenClassification.from_pretrained("microsoft/biogpt")

>>> 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]]

>>> labels = predicted_token_class_ids
>>> loss = model(**inputs, labels=labels).loss

BioGptForSequenceClassification

class transformers.BioGptForSequenceClassification

< >

( config: BioGptConfig )

Parameters

  • config (~BioGptConfig) — 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 BioGpt Model transformer with a sequence classification head on top (linear layer).

BioGptForSequenceClassification 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 is required 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 is a PyTorch torch.nn.Module sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< >

( input_ids: Optional = None attention_mask: Optional = None head_mask: Optional = None past_key_values: Optional = None inputs_embeds: Optional = None labels: Optional = None use_cache: Optional = None output_attentions: Optional = None output_hidden_states: Optional = None return_dict: Optional = None ) → transformers.modeling_outputs.SequenceClassifierOutputWithPast or tuple(torch.FloatTensor)

Parameters

  • input_ids (torch.LongTensor of shape ({0})) — Indices of input sequence tokens in the vocabulary.

    Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

    What are input IDs?

  • attention_mask (torch.FloatTensor of shape ({0}), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:

    • 1 for tokens that are not masked,
    • 0 for tokens that are masked.

    What are attention masks?

  • 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 ({0}, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
  • past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 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 in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

    If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all decoder_input_ids of shape (batch_size, sequence_length).

  • inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
  • use_cache (bool, optional) — If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).
  • output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
  • output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
  • return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
  • labels (torch.LongTensor of shape (batch_size,), optional) — Labels for computing the sequence classification/regression loss. Indices should be in [0, ..., config.num_labels - 1]. If config.num_labels == 1 a regression loss is computed (Mean-Square loss), If config.num_labels > 1 a classification loss is computed (Cross-Entropy).

Returns

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 (BioGptConfig) and inputs.

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Classification (or regression if config.num_labels==1) loss.

  • logits (torch.FloatTensor of shape (batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax).

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

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

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

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

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

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

The BioGptForSequenceClassification 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, BioGptForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("microsoft/biogpt")
>>> model = BioGptForSequenceClassification.from_pretrained("microsoft/biogpt")

>>> 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 = BioGptForSequenceClassification.from_pretrained("microsoft/biogpt", num_labels=num_labels)

>>> labels = torch.tensor([1])
>>> loss = model(**inputs, labels=labels).loss

Example of multi-label classification:

>>> import torch
>>> from transformers import AutoTokenizer, BioGptForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("microsoft/biogpt")
>>> model = BioGptForSequenceClassification.from_pretrained("microsoft/biogpt", 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 = BioGptForSequenceClassification.from_pretrained(
...     "microsoft/biogpt", num_labels=num_labels, problem_type="multi_label_classification"
... )

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

←(번역중) BigBirdPegasus (번역중) Blenderbot→