# BigBird ## Overview BigBird モデルは、[Big Bird: Transformers for Longer Sequences](https://huggingface.co/papers/2007.14062) で提案されました。 ザヒール、マンジルとグルガネシュ、グルとダベイ、クマール・アヴィナヴァとエインズリー、ジョシュアとアルベルティ、クリスとオンタノン、 サンティアゴとファム、フィリップとラブラ、アニルードとワン、キーファンとヤン、リーなど。 BigBird は注目度が低い BERT などの Transformer ベースのモデルをさらに長いシーケンスに拡張する、Transformer ベースのモデル。まばらに加えて アテンションと同様に、BigBird は入力シーケンスにランダム アテンションだけでなくグローバル アテンションも適用します。理論的には、 まばらで全体的でランダムな注意を適用すると、完全な注意に近づくことが示されていますが、 長いシーケンスでは計算効率が大幅に向上します。より長いコンテキストを処理できる機能の結果として、 BigBird は、質問応答や BERT または RoBERTa と比較した要約。 論文の要約は次のとおりです。 *BERT などのトランスフォーマーベースのモデルは、NLP で最も成功した深層学習モデルの 1 つです。 残念ながら、それらの中核的な制限の 1 つは、シーケンスに対する二次依存性 (主にメモリに関する) です。 完全な注意メカニズムによる長さです。これを解決するために、BigBird は、まばらな注意メカニズムを提案します。 この二次依存関係を線形に削減します。 BigBird がシーケンス関数の汎用近似器であることを示します。 チューリングは完全であるため、二次完全注意モデルのこれらの特性が保存されます。途中、私たちの 理論分析により、O(1) 個のグローバル トークン (CLS など) を持つ利点の一部が明らかになり、 スパース注意メカニズムの一部としてのシーケンス。提案されたスパース アテンションは、次の長さのシーケンスを処理できます。 同様のハードウェアを使用して以前に可能であったものの 8 倍。より長いコンテキストを処理できる機能の結果として、 BigBird は、質問応答や要約などのさまざまな NLP タスクのパフォーマンスを大幅に向上させます。私達も ゲノミクスデータへの新しいアプリケーションを提案します。* チップ： - BigBird の注意がどのように機能するかについての詳細な説明については、[このブログ投稿](https://huggingface.co/blog/big-bird) を参照してください。 - BigBird には、**original_full** と **block_sparse** の 2 つの実装が付属しています。シーケンス長が 1024 未満の場合、次を使用します。 **block_sparse** を使用してもメリットがないため、**original_full** を使用することをお勧めします。 - コードは現在、3 ブロックと 2 グローバル ブロックのウィンドウ サイズを使用しています。 - シーケンスの長さはブロック サイズで割り切れる必要があります。 - 現在の実装では **ITC** のみがサポートされています。 - 現在の実装では **num_random_blocks = 0** はサポートされていません - BigBird は絶対位置埋め込みを備えたモデルであるため、通常は入力を右側にパディングすることをお勧めします。 左。 このモデルは、[vasudevgupta](https://huggingface.co/vasudevgupta) によって提供されました。元のコードが見つかる [こちら](https://github.com/google-research/bigbird)。 ## ドキュメント リソース - [テキスト分類タスクガイド(英語版)](../../en/tasks/sequence_classification) - [トークン分類タスクガイド](../tasks/token_classification) - [質問回答タスク ガイド](../tasks/question_answering) - [因果言語モデリング タスク ガイド](../tasks/language_modeling) - [マスクされた言語モデリング タスク ガイド](../tasks/masked_lang_modeling) - [多肢選択タスク ガイド](../tasks/multiple_choice) ## BigBirdConfig[[transformers.BigBirdConfig]]
class transformers.BigBirdConfigtransformers.BigBirdConfighttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/configuration_big_bird.py#L28[{"name": "vocab_size", "val": " = 50358"}, {"name": "hidden_size", "val": " = 768"}, {"name": "num_hidden_layers", "val": " = 12"}, {"name": "num_attention_heads", "val": " = 12"}, {"name": "intermediate_size", "val": " = 3072"}, {"name": "hidden_act", "val": " = 'gelu_new'"}, {"name": "hidden_dropout_prob", "val": " = 0.1"}, {"name": "attention_probs_dropout_prob", "val": " = 0.1"}, {"name": "max_position_embeddings", "val": " = 4096"}, {"name": "type_vocab_size", "val": " = 2"}, {"name": "initializer_range", "val": " = 0.02"}, {"name": "layer_norm_eps", "val": " = 1e-12"}, {"name": "use_cache", "val": " = True"}, {"name": "pad_token_id", "val": " = 0"}, {"name": "bos_token_id", "val": " = 1"}, {"name": "eos_token_id", "val": " = 2"}, {"name": "sep_token_id", "val": " = 66"}, {"name": "attention_type", "val": " = 'block_sparse'"}, {"name": "use_bias", "val": " = True"}, {"name": "rescale_embeddings", "val": " = False"}, {"name": "block_size", "val": " = 64"}, {"name": "num_random_blocks", "val": " = 3"}, {"name": "classifier_dropout", "val": " = None"}, {"name": "**kwargs", "val": ""}]- **vocab_size** (`int`, *optional*, defaults to 50358) -- Vocabulary size of the BigBird model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [BigBirdModel](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdModel). - **hidden_size** (`int`, *optional*, defaults to 768) -- Dimension of the encoder layers and the pooler layer. - **num_hidden_layers** (`int`, *optional*, defaults to 12) -- Number of hidden layers in the Transformer encoder. - **num_attention_heads** (`int`, *optional*, defaults to 12) -- Number of attention heads for each attention layer in the Transformer encoder. - **intermediate_size** (`int`, *optional*, defaults to 3072) -- Dimension of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. - **hidden_act** (`str` or `function`, *optional*, defaults to `"gelu_new"`) -- The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. - **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 4096) -- The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 1024 or 2048 or 4096). - **type_vocab_size** (`int`, *optional*, defaults to 2) -- The vocabulary size of the `token_type_ids` passed when calling [BigBirdModel](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdModel). - **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. - **is_decoder** (`bool`, *optional*, defaults to `False`) -- Whether the model is used as a decoder or not. If `False`, the model is used as an encoder. - **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`. - **attention_type** (`str`, *optional*, defaults to `"block_sparse"`) -- Whether to use block sparse attention (with n complexity) as introduced in paper or original attention layer (with n^2 complexity). Possible values are `"original_full"` and `"block_sparse"`. - **use_bias** (`bool`, *optional*, defaults to `True`) -- Whether to use bias in query, key, value. - **rescale_embeddings** (`bool`, *optional*, defaults to `False`) -- Whether to rescale embeddings with (hidden_size ** 0.5). - **block_size** (`int`, *optional*, defaults to 64) -- Size of each block. Useful only when `attention_type == "block_sparse"`. - **num_random_blocks** (`int`, *optional*, defaults to 3) -- Each query is going to attend these many number of random blocks. Useful only when `attention_type == "block_sparse"`. - **classifier_dropout** (`float`, *optional*) -- The dropout ratio for the classification head.0 This is the configuration class to store the configuration of a [BigBirdModel](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdModel). It is used to instantiate an BigBird 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 BigBird [google/bigbird-roberta-base](https://huggingface.co/google/bigbird-roberta-base) architecture. Configuration objects inherit from [PretrainedConfig](/docs/transformers/v4.57.0/ja/main_classes/configuration#transformers.PretrainedConfig) and can be used to control the model outputs. Read the documentation from [PretrainedConfig](/docs/transformers/v4.57.0/ja/main_classes/configuration#transformers.PretrainedConfig) for more information. Example: ```python >>> from transformers import BigBirdConfig, BigBirdModel >>> # Initializing a BigBird google/bigbird-roberta-base style configuration >>> configuration = BigBirdConfig() >>> # Initializing a model (with random weights) from the google/bigbird-roberta-base style configuration >>> model = BigBirdModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```
## BigBirdTokenizer[[transformers.BigBirdTokenizer]]
class transformers.BigBirdTokenizertransformers.BigBirdTokenizerhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/tokenization_big_bird.py#L35[{"name": "vocab_file", "val": ""}, {"name": "unk_token", "val": " = ''"}, {"name": "bos_token", "val": " = ''"}, {"name": "eos_token", "val": " = ''"}, {"name": "pad_token", "val": " = ''"}, {"name": "sep_token", "val": " = '[SEP]'"}, {"name": "mask_token", "val": " = '[MASK]'"}, {"name": "cls_token", "val": " = '[CLS]'"}, {"name": "sp_model_kwargs", "val": ": typing.Optional[dict[str, typing.Any]] = None"}, {"name": "**kwargs", "val": ""}]- **vocab_file** (`str`) -- [SentencePiece](https://github.com/google/sentencepiece) file (generally has a *.spm* extension) that contains the vocabulary necessary to instantiate a tokenizer. - **unk_token** (`str`, *optional*, defaults to `""`) -- 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 `""`) -- The begin of sequence token. - **eos_token** (`str`, *optional*, defaults to `""`) -- The end of sequence token. - **pad_token** (`str`, *optional*, defaults to `""`) -- The token used for padding, for example when batching sequences of different lengths. - **sep_token** (`str`, *optional*, defaults to `"[SEP]"`) -- 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. - **mask_token** (`str`, *optional*, defaults to `"[MASK]"`) -- The token used for masking values. This is the token used when training this model with masked language modeling. This is the token which the model will try to predict. - **cls_token** (`str`, *optional*, defaults to `"[CLS]"`) -- The classifier token which is used when doing sequence classification (classification of the whole sequence instead of per-token classification). It is the first token of the sequence when built with special tokens. - **sp_model_kwargs** (`dict`, *optional*) -- Will be passed to the `SentencePieceProcessor.__init__()` method. The [Python wrapper for SentencePiece](https://github.com/google/sentencepiece/tree/master/python) can be used, among other things, to set: - `enable_sampling`: Enable subword regularization. - `nbest_size`: Sampling parameters for unigram. Invalid for BPE-Dropout. - `nbest_size = {0,1}`: No sampling is performed. - `nbest_size > 1`: samples from the nbest_size results. - `nbest_size < 0`: assuming that nbest_size is infinite and samples from the all hypothesis (lattice) using forward-filtering-and-backward-sampling algorithm. - `alpha`: Smoothing parameter for unigram sampling, and dropout probability of merge operations for BPE-dropout.0 Construct a BigBird tokenizer. Based on [SentencePiece](https://github.com/google/sentencepiece). This tokenizer inherits from [PreTrainedTokenizer](/docs/transformers/v4.57.0/ja/main_classes/tokenizer#transformers.PreTrainedTokenizer) which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.
build_inputs_with_special_tokenstransformers.BigBirdTokenizer.build_inputs_with_special_tokenshttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/tokenization_big_bird.py#L250[{"name": "token_ids_0", "val": ": list"}, {"name": "token_ids_1", "val": ": typing.Optional[list[int]] = None"}]- **token_ids_0** (`List[int]`) -- List of IDs to which the special tokens will be added. - **token_ids_1** (`List[int]`, *optional*) -- Optional second list of IDs for sequence pairs.0`List[int]`List of [input IDs](../glossary#input-ids) with the appropriate special tokens. Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. A Big Bird sequence has the following format: - single sequence: `[CLS] X [SEP]` - pair of sequences: `[CLS] A [SEP] B [SEP]`
get_special_tokens_masktransformers.BigBirdTokenizer.get_special_tokens_maskhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/tokenization_big_bird.py#L275[{"name": "token_ids_0", "val": ": list"}, {"name": "token_ids_1", "val": ": typing.Optional[list[int]] = None"}, {"name": "already_has_special_tokens", "val": ": bool = False"}]- **token_ids_0** (`List[int]`) -- List of IDs. - **token_ids_1** (`List[int]`, *optional*) -- Optional second list of IDs for sequence pairs. - **already_has_special_tokens** (`bool`, *optional*, defaults to `False`) -- Whether or not the token list is already formatted with special tokens for the model.0`List[int]`A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token. Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the tokenizer `prepare_for_model` method.
create_token_type_ids_from_sequencestransformers.BigBirdTokenizer.create_token_type_ids_from_sequenceshttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/tokenization_utils_base.py#L3459[{"name": "token_ids_0", "val": ": list"}, {"name": "token_ids_1", "val": ": typing.Optional[list[int]] = None"}]- **token_ids_0** (`list[int]`) -- The first tokenized sequence. - **token_ids_1** (`list[int]`, *optional*) -- The second tokenized sequence.0`list[int]`The token type ids. Create the token type IDs corresponding to the sequences passed. [What are token type IDs?](../glossary#token-type-ids) Should be overridden in a subclass if the model has a special way of building those.
save_vocabularytransformers.BigBirdTokenizer.save_vocabularyhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/tokenization_big_bird.py#L233[{"name": "save_directory", "val": ": str"}, {"name": "filename_prefix", "val": ": typing.Optional[str] = None"}]
## BigBirdTokenizerFast[[transformers.BigBirdTokenizerFast]]
class transformers.BigBirdTokenizerFasttransformers.BigBirdTokenizerFasthttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/tokenization_big_bird_fast.py#L38[{"name": "vocab_file", "val": " = None"}, {"name": "tokenizer_file", "val": " = None"}, {"name": "unk_token", "val": " = ''"}, {"name": "bos_token", "val": " = ''"}, {"name": "eos_token", "val": " = ''"}, {"name": "pad_token", "val": " = ''"}, {"name": "sep_token", "val": " = '[SEP]'"}, {"name": "mask_token", "val": " = '[MASK]'"}, {"name": "cls_token", "val": " = '[CLS]'"}, {"name": "**kwargs", "val": ""}]- **vocab_file** (`str`) -- [SentencePiece](https://github.com/google/sentencepiece) file (generally has a *.spm* extension) that contains the vocabulary necessary to instantiate a tokenizer. - **bos_token** (`str`, *optional*, defaults to `""`) -- 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 `""`) -- The end of sequence token. .. note:: 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`. - **unk_token** (`str`, *optional*, defaults to `""`) -- 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. - **sep_token** (`str`, *optional*, defaults to `"[SEP]"`) -- 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 `""`) -- The token used for padding, for example when batching sequences of different lengths. - **cls_token** (`str`, *optional*, defaults to `"[CLS]"`) -- The classifier token which is used when doing sequence classification (classification of the whole sequence instead of per-token classification). It is the first token of the sequence when built with special tokens. - **mask_token** (`str`, *optional*, defaults to `"[MASK]"`) -- The token used for masking values. This is the token used when training this model with masked language modeling. This is the token which the model will try to predict.0 Construct a "fast" BigBird tokenizer (backed by HuggingFace's *tokenizers* library). Based on [Unigram](https://huggingface.co/docs/tokenizers/python/latest/components.html?highlight=unigram#models). This tokenizer inherits from [PreTrainedTokenizerFast](/docs/transformers/v4.57.0/ja/main_classes/tokenizer#transformers.PreTrainedTokenizerFast) which contains most of the main methods. Users should refer to this superclass for more information regarding those methods
build_inputs_with_special_tokenstransformers.BigBirdTokenizerFast.build_inputs_with_special_tokenshttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/tokenization_big_bird_fast.py#L122[{"name": "token_ids_0", "val": ": list"}, {"name": "token_ids_1", "val": ": typing.Optional[list[int]] = None"}]- **token_ids_0** (`List[int]`) -- List of IDs to which the special tokens will be added - **token_ids_1** (`List[int]`, *optional*) -- Optional second list of IDs for sequence pairs.0`List[int]`list of [input IDs](../glossary#input-ids) with the appropriate special tokens. Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. An BigBird sequence has the following format: - single sequence: `[CLS] X [SEP]` - pair of sequences: `[CLS] A [SEP] B [SEP]`
get_special_tokens_masktransformers.BigBirdTokenizerFast.get_special_tokens_maskhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/tokenization_big_bird_fast.py#L147[{"name": "token_ids_0", "val": ": list"}, {"name": "token_ids_1", "val": ": typing.Optional[list[int]] = None"}, {"name": "already_has_special_tokens", "val": ": bool = False"}]- **token_ids_0** (`List[int]`) -- List of ids. - **token_ids_1** (`List[int]`, *optional*) -- Optional second list of IDs for sequence pairs. - **already_has_special_tokens** (`bool`, *optional*, defaults to `False`) -- Set to True if the token list is already formatted with special tokens for the model0`List[int]`A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token. Retrieves sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the tokenizer `prepare_for_model` method.
## BigBird specific outputs[[transformers.models.big_bird.modeling_big_bird.BigBirdForPreTrainingOutput]]
class transformers.models.big_bird.modeling_big_bird.BigBirdForPreTrainingOutputtransformers.models.big_bird.modeling_big_bird.BigBirdForPreTrainingOutputhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_big_bird.py#L1740[{"name": "loss", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "prediction_logits", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "seq_relationship_logits", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "hidden_states", "val": ": typing.Optional[tuple[torch.FloatTensor]] = None"}, {"name": "attentions", "val": ": typing.Optional[tuple[torch.FloatTensor]] = None"}]- **loss** (`*optional*`, returned when `labels` is provided, `torch.FloatTensor` of shape `(1,)`) -- Total loss as the sum of the masked language modeling loss and the next sequence prediction (classification) loss. - **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). - **seq_relationship_logits** (`torch.FloatTensor` of shape `(batch_size, 2)`) -- Prediction scores of the next sequence prediction (classification) head (scores of True/False continuation 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.0 Output type of [BigBirdForPreTraining](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdForPreTraining).
## BigBirdModel[[transformers.BigBirdModel]]
class transformers.BigBirdModeltransformers.BigBirdModelhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_big_bird.py#L1782[{"name": "config", "val": ""}, {"name": "add_pooling_layer", "val": " = True"}]- **config** ([BigBirdModel](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdModel)) -- 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()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. - **add_pooling_layer** (`bool`, *optional*, defaults to `True`) -- Whether to add a pooling layer0 The bare Big Bird Model outputting raw hidden-states without any specific head on top. This model inherits from [PreTrainedModel](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.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](https://pytorch.org/docs/stable/nn.html#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.
forwardtransformers.BigBirdModel.forwardhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_big_bird.py#L1843[{"name": "input_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "attention_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "token_type_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "position_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "head_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "inputs_embeds", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "encoder_hidden_states", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "encoder_attention_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "past_key_values", "val": ": typing.Optional[transformers.cache_utils.Cache] = None"}, {"name": "use_cache", "val": ": typing.Optional[bool] = None"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}, {"name": "cache_position", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/v4.57.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#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?](../glossary#attention-mask) - **token_type_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`: - 0 corresponds to a *sentence A* token, - 1 corresponds to a *sentence B* token. [What are token type IDs?](../glossary#token-type-ids) - **position_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids) - **head_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) -- Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`: - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. - **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. - **encoder_hidden_states** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder. - **encoder_attention_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. - **past_key_values** (`~cache_utils.Cache`, *optional*) -- Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values` returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`. Only `Cache` instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). If no `past_key_values` are passed, `DynamicCache` will be initialized by default. The model will output the same cache format that is fed as input. If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids` of shape `(batch_size, sequence_length)`. - **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](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. - **cache_position** (`torch.Tensor` of shape `(sequence_length)`, *optional*) -- Indices depicting the position of the input sequence tokens in the sequence. Contrarily to `position_ids`, this tensor is not affected by padding. It is used to update the cache in the correct position and to infer the complete sequence length.0[transformers.modeling_outputs.BaseModelOutputWithPoolingAndCrossAttentions](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPoolingAndCrossAttentions) or `tuple(torch.FloatTensor)`A [transformers.modeling_outputs.BaseModelOutputWithPoolingAndCrossAttentions](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPoolingAndCrossAttentions) 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 ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) 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. - **pooler_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`) -- Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining. - **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. - **past_key_values** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a `Cache` instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). 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. The [BigBirdModel](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdModel) 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.
## BigBirdForPreTraining[[transformers.BigBirdForPreTraining]]
class transformers.BigBirdForPreTrainingtransformers.BigBirdForPreTraininghttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_big_bird.py#L2109[{"name": "config", "val": ""}]
forwardtransformers.BigBirdForPreTraining.forwardhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_big_bird.py#L2128[{"name": "input_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "attention_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "token_type_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "position_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "head_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "inputs_embeds", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "labels", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "next_sentence_label", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/v4.57.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#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?](../glossary#attention-mask) - **token_type_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`: - 0 corresponds to a *sentence A* token, - 1 corresponds to a *sentence B* token. [What are token type IDs?](../glossary#token-type-ids) - **position_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids) - **head_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) -- Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`: - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. - **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. - **labels** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Labels for computing the masked language modeling loss. Indices should be in `[-100, 0, ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]` - **next_sentence_label** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) -- Labels for computing the next sequence prediction (classification) loss. If specified, nsp loss will be added to masked_lm loss. Input should be a sequence pair (see `input_ids` docstring) Indices should be in `[0, 1]`: - 0 indicates sequence B is a continuation of sequence A, - 1 indicates sequence B is a random sequence. - **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](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[transformers.models.big_bird.modeling_big_bird.BigBirdForPreTrainingOutput](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.models.big_bird.modeling_big_bird.BigBirdForPreTrainingOutput) or `tuple(torch.FloatTensor)`A [transformers.models.big_bird.modeling_big_bird.BigBirdForPreTrainingOutput](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.models.big_bird.modeling_big_bird.BigBirdForPreTrainingOutput) 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 ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) and inputs. - **loss** (`*optional*`, returned when `labels` is provided, `torch.FloatTensor` of shape `(1,)`) -- Total loss as the sum of the masked language modeling loss and the next sequence prediction (classification) loss. - **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). - **seq_relationship_logits** (`torch.FloatTensor` of shape `(batch_size, 2)`) -- Prediction scores of the next sequence prediction (classification) head (scores of True/False continuation 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 [BigBirdForPreTraining](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdForPreTraining) 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: ```python >>> from transformers import AutoTokenizer, BigBirdForPreTraining >>> import torch >>> tokenizer = AutoTokenizer.from_pretrained("google/bigbird-roberta-base") >>> model = BigBirdForPreTraining.from_pretrained("google/bigbird-roberta-base") >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt") >>> outputs = model(**inputs) >>> prediction_logits = outputs.prediction_logits >>> seq_relationship_logits = outputs.seq_relationship_logits ```
## BigBirdForCausalLM[[transformers.BigBirdForCausalLM]]
class transformers.BigBirdForCausalLMtransformers.BigBirdForCausalLMhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_big_bird.py#L2355[{"name": "config", "val": ""}]- **config** ([BigBirdForCausalLM](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdForCausalLM)) -- 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()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.0 BigBird Model with a `language modeling` head on top for CLM fine-tuning. This model inherits from [PreTrainedModel](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.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](https://pytorch.org/docs/stable/nn.html#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.
forwardtransformers.BigBirdForCausalLM.forwardhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_big_bird.py#L2377[{"name": "input_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "attention_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "token_type_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "position_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "head_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "inputs_embeds", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "encoder_hidden_states", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "encoder_attention_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "past_key_values", "val": ": typing.Optional[transformers.cache_utils.Cache] = None"}, {"name": "labels", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "use_cache", "val": ": typing.Optional[bool] = None"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}, {"name": "cache_position", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/v4.57.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#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?](../glossary#attention-mask) - **token_type_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`: - 0 corresponds to a *sentence A* token, - 1 corresponds to a *sentence B* token. [What are token type IDs?](../glossary#token-type-ids) - **position_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids) - **head_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) -- Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`: - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. - **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. - **encoder_hidden_states** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder. - **encoder_attention_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. - **past_key_values** (`~cache_utils.Cache`, *optional*) -- Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values` returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`. Only `Cache` instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). If no `past_key_values` are passed, `DynamicCache` will be initialized by default. The model will output the same cache format that is fed as input. If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids` of shape `(batch_size, sequence_length)`. - **labels** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Labels for computing the left-to-right language modeling loss (next word prediction). Indices should be in `[-100, 0, ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked), the loss is only computed for the tokens with labels n `[0, ..., config.vocab_size]`. - **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](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. - **cache_position** (`torch.Tensor` of shape `(sequence_length)`, *optional*) -- Indices depicting the position of the input sequence tokens in the sequence. Contrarily to `position_ids`, this tensor is not affected by padding. It is used to update the cache in the correct position and to infer the complete sequence length.0[transformers.modeling_outputs.CausalLMOutputWithCrossAttentions](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) or `tuple(torch.FloatTensor)`A [transformers.modeling_outputs.CausalLMOutputWithCrossAttentions](/docs/transformers/v4.57.0/ja/main_classes/output#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 ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) 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** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a `Cache` instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). 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 [BigBirdForCausalLM](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdForCausalLM) 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: ```python ```
## BigBirdForMaskedLM[[transformers.BigBirdForMaskedLM]]
class transformers.BigBirdForMaskedLMtransformers.BigBirdForMaskedLMhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_big_bird.py#L2211[{"name": "config", "val": ""}]- **config** ([BigBirdForMaskedLM](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdForMaskedLM)) -- 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()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.0 The Big Bird Model with a `language modeling` head on top." This model inherits from [PreTrainedModel](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.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](https://pytorch.org/docs/stable/nn.html#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.
forwardtransformers.BigBirdForMaskedLM.forwardhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_big_bird.py#L2236[{"name": "input_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "attention_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "token_type_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "position_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "head_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "inputs_embeds", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "encoder_hidden_states", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "encoder_attention_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "labels", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/v4.57.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#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?](../glossary#attention-mask) - **token_type_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`: - 0 corresponds to a *sentence A* token, - 1 corresponds to a *sentence B* token. [What are token type IDs?](../glossary#token-type-ids) - **position_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids) - **head_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) -- Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`: - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. - **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. - **encoder_hidden_states** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder. - **encoder_attention_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. - **labels** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Labels for computing the masked language modeling loss. Indices should be in `[-100, 0, ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`. - **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](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[transformers.modeling_outputs.MaskedLMOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) or `tuple(torch.FloatTensor)`A [transformers.modeling_outputs.MaskedLMOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) 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 ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) and inputs. - **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) -- Masked language modeling (MLM) loss. - **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. The [BigBirdForMaskedLM](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdForMaskedLM) 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: ```python >>> import torch >>> from transformers import AutoTokenizer, BigBirdForMaskedLM >>> from datasets import load_dataset >>> tokenizer = AutoTokenizer.from_pretrained("google/bigbird-roberta-base") >>> model = BigBirdForMaskedLM.from_pretrained("google/bigbird-roberta-base") >>> squad_ds = load_dataset("rajpurkar/squad_v2", split="train") >>> # select random long article >>> LONG_ARTICLE_TARGET = squad_ds[81514]["context"] >>> # select random sentence >>> LONG_ARTICLE_TARGET[332:398] 'the highest values are very close to the theoretical maximum value' >>> # add mask_token >>> LONG_ARTICLE_TO_MASK = LONG_ARTICLE_TARGET.replace("maximum", "[MASK]") >>> inputs = tokenizer(LONG_ARTICLE_TO_MASK, return_tensors="pt") >>> # long article input >>> list(inputs["input_ids"].shape) [1, 919] >>> with torch.no_grad(): ... logits = model(**inputs).logits >>> # retrieve index of [MASK] >>> mask_token_index = (inputs.input_ids == tokenizer.mask_token_id)[0].nonzero(as_tuple=True)[0] >>> predicted_token_id = logits[0, mask_token_index].argmax(axis=-1) >>> tokenizer.decode(predicted_token_id) 'maximum' ``` ```python >>> labels = tokenizer(LONG_ARTICLE_TARGET, return_tensors="pt")["input_ids"] >>> labels = torch.where(inputs.input_ids == tokenizer.mask_token_id, labels, -100) >>> outputs = model(**inputs, labels=labels) >>> round(outputs.loss.item(), 2) 1.99 ```
## BigBirdForSequenceClassification[[transformers.BigBirdForSequenceClassification]]
class transformers.BigBirdForSequenceClassificationtransformers.BigBirdForSequenceClassificationhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_big_bird.py#L2479[{"name": "config", "val": ""}]- **config** ([BigBirdForSequenceClassification](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdForSequenceClassification)) -- 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()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.0 BigBird Model transformer with a sequence classification/regression head on top (a linear layer on top of the pooled output) e.g. for GLUE tasks. This model inherits from [PreTrainedModel](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.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](https://pytorch.org/docs/stable/nn.html#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.
forwardtransformers.BigBirdForSequenceClassification.forwardhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_big_bird.py#L2490[{"name": "input_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "attention_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "token_type_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "position_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "head_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "inputs_embeds", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "labels", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/v4.57.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#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?](../glossary#attention-mask) - **token_type_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`: - 0 corresponds to a *sentence A* token, - 1 corresponds to a *sentence B* token. [What are token type IDs?](../glossary#token-type-ids) - **position_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids) - **head_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) -- Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`: - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. - **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. - **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). - **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](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[transformers.modeling_outputs.SequenceClassifierOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) or `tuple(torch.FloatTensor)`A [transformers.modeling_outputs.SequenceClassifierOutput](/docs/transformers/v4.57.0/ja/main_classes/output#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 ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) 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). - **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 [BigBirdForSequenceClassification](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdForSequenceClassification) 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: ```python >>> import torch >>> from transformers import AutoTokenizer, BigBirdForSequenceClassification >>> from datasets import load_dataset >>> tokenizer = AutoTokenizer.from_pretrained("l-yohai/bigbird-roberta-base-mnli") >>> model = BigBirdForSequenceClassification.from_pretrained("l-yohai/bigbird-roberta-base-mnli") >>> squad_ds = load_dataset("rajpurkar/squad_v2", split="train") >>> LONG_ARTICLE = squad_ds[81514]["context"] >>> inputs = tokenizer(LONG_ARTICLE, return_tensors="pt") >>> # long input article >>> list(inputs["input_ids"].shape) [1, 919] >>> with torch.no_grad(): ... logits = model(**inputs).logits >>> predicted_class_id = logits.argmax().item() >>> model.config.id2label[predicted_class_id] 'LABEL_0' ``` ```python >>> num_labels = len(model.config.id2label) >>> model = BigBirdForSequenceClassification.from_pretrained( ... "l-yohai/bigbird-roberta-base-mnli", num_labels=num_labels ... ) >>> labels = torch.tensor(1) >>> loss = model(**inputs, labels=labels).loss >>> round(loss.item(), 2) 1.13 ```
## BigBirdForMultipleChoice[[transformers.BigBirdForMultipleChoice]]
class transformers.BigBirdForMultipleChoicetransformers.BigBirdForMultipleChoicehttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_big_bird.py#L2598[{"name": "config", "val": ""}]- **config** ([BigBirdForMultipleChoice](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdForMultipleChoice)) -- 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()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.0 The Big Bird Model with a multiple choice classification head on top (a linear layer on top of the pooled output and a softmax) e.g. for RocStories/SWAG tasks. This model inherits from [PreTrainedModel](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.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](https://pytorch.org/docs/stable/nn.html#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.
forwardtransformers.BigBirdForMultipleChoice.forwardhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_big_bird.py#L2609[{"name": "input_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "attention_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "token_type_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "position_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "head_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "inputs_embeds", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "labels", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, num_choices, sequence_length)`) -- Indices of input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](/docs/transformers/v4.57.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#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?](../glossary#attention-mask) - **token_type_ids** (`torch.LongTensor` of shape `(batch_size, num_choices, 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. [What are token type IDs?](../glossary#token-type-ids) - **position_ids** (`torch.LongTensor` of shape `(batch_size, num_choices, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`. [What are position IDs?](../glossary#position-ids) - **head_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) -- Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`: - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. - **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, num_choices, 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. - **labels** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) -- Labels for computing the multiple choice classification loss. Indices should be in `[0, ..., num_choices-1]` where `num_choices` is the size of the second dimension of the input tensors. (See `input_ids` above) - **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](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[transformers.modeling_outputs.MultipleChoiceModelOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_outputs.MultipleChoiceModelOutput) or `tuple(torch.FloatTensor)`A [transformers.modeling_outputs.MultipleChoiceModelOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_outputs.MultipleChoiceModelOutput) 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 ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) and inputs. - **loss** (`torch.FloatTensor` of shape *(1,)*, *optional*, returned when `labels` is provided) -- Classification loss. - **logits** (`torch.FloatTensor` of shape `(batch_size, num_choices)`) -- *num_choices* is the second dimension of the input tensors. (see *input_ids* above). 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 [BigBirdForMultipleChoice](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdForMultipleChoice) 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: ```python >>> from transformers import AutoTokenizer, BigBirdForMultipleChoice >>> import torch >>> tokenizer = AutoTokenizer.from_pretrained("google/bigbird-roberta-base") >>> model = BigBirdForMultipleChoice.from_pretrained("google/bigbird-roberta-base") >>> prompt = "In Italy, pizza served in formal settings, such as at a restaurant, is presented unsliced." >>> choice0 = "It is eaten with a fork and a knife." >>> choice1 = "It is eaten while held in the hand." >>> labels = torch.tensor(0).unsqueeze(0) # choice0 is correct (according to Wikipedia ;)), batch size 1 >>> encoding = tokenizer([prompt, prompt], [choice0, choice1], return_tensors="pt", padding=True) >>> outputs = model(**{k: v.unsqueeze(0) for k, v in encoding.items()}, labels=labels) # batch size is 1 >>> # the linear classifier still needs to be trained >>> loss = outputs.loss >>> logits = outputs.logits ```
## BigBirdForTokenClassification[[transformers.BigBirdForTokenClassification]]
class transformers.BigBirdForTokenClassificationtransformers.BigBirdForTokenClassificationhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_big_bird.py#L2702[{"name": "config", "val": ""}]- **config** ([BigBirdForTokenClassification](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdForTokenClassification)) -- 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()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.0 The Big Bird transformer with a token classification head on top (a linear layer on top of the hidden-states output) e.g. for Named-Entity-Recognition (NER) tasks. This model inherits from [PreTrainedModel](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.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](https://pytorch.org/docs/stable/nn.html#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.
forwardtransformers.BigBirdForTokenClassification.forwardhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_big_bird.py#L2717[{"name": "input_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "attention_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "token_type_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "position_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "head_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "inputs_embeds", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "labels", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/v4.57.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#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?](../glossary#attention-mask) - **token_type_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`: - 0 corresponds to a *sentence A* token, - 1 corresponds to a *sentence B* token. [What are token type IDs?](../glossary#token-type-ids) - **position_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids) - **head_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) -- Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`: - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. - **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. - **labels** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Labels for computing the token classification loss. Indices should be in `[0, ..., config.num_labels - 1]`. - **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](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[transformers.modeling_outputs.TokenClassifierOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or `tuple(torch.FloatTensor)`A [transformers.modeling_outputs.TokenClassifierOutput](/docs/transformers/v4.57.0/ja/main_classes/output#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 ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) 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 [BigBirdForTokenClassification](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdForTokenClassification) 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: ```python >>> from transformers import AutoTokenizer, BigBirdForTokenClassification >>> import torch >>> tokenizer = AutoTokenizer.from_pretrained("google/bigbird-roberta-base") >>> model = BigBirdForTokenClassification.from_pretrained("google/bigbird-roberta-base") >>> inputs = tokenizer( ... "HuggingFace is a company based in Paris and New York", add_special_tokens=False, return_tensors="pt" ... ) >>> with torch.no_grad(): ... logits = model(**inputs).logits >>> predicted_token_class_ids = logits.argmax(-1) >>> # Note that tokens are classified rather then input words which means that >>> # there might be more predicted token classes than words. >>> # Multiple token classes might account for the same word >>> predicted_tokens_classes = [model.config.id2label[t.item()] for t in predicted_token_class_ids[0]] >>> predicted_tokens_classes ... >>> labels = predicted_token_class_ids >>> loss = model(**inputs, labels=labels).loss >>> round(loss.item(), 2) ... ```
## BigBirdForQuestionAnswering[[transformers.BigBirdForQuestionAnswering]]
class transformers.BigBirdForQuestionAnsweringtransformers.BigBirdForQuestionAnsweringhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_big_bird.py#L2790[{"name": "config", "val": ""}, {"name": "add_pooling_layer", "val": " = False"}]- **config** ([BigBirdForQuestionAnswering](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdForQuestionAnswering)) -- 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()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. - **add_pooling_layer** (`bool`, *optional*, defaults to `True`) -- Whether to add a pooling layer0 The Big Bird transformer with a span classification head on top for extractive question-answering tasks like SQuAD (a linear layer on top of the hidden-states output to compute `span start logits` and `span end logits`). This model inherits from [PreTrainedModel](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.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](https://pytorch.org/docs/stable/nn.html#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.
forwardtransformers.BigBirdForQuestionAnswering.forwardhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_big_bird.py#L2808[{"name": "input_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "attention_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "question_lengths", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "token_type_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "position_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "head_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "inputs_embeds", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "start_positions", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "end_positions", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/v4.57.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#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?](../glossary#attention-mask) - **question_lengths** (`torch.LongTensor` of shape `(batch_size, 1)`, *optional*) -- The lengths of the questions in the batch. - **token_type_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`: - 0 corresponds to a *sentence A* token, - 1 corresponds to a *sentence B* token. [What are token type IDs?](../glossary#token-type-ids) - **position_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids) - **head_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) -- Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`: - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. - **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. - **start_positions** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) -- Labels for position (index) of the start of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence are not taken into account for computing the loss. - **end_positions** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) -- Labels for position (index) of the end of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence are not taken into account for computing the loss. - **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](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0`transformers.models.big_bird.modeling_big_bird.BigBirdForQuestionAnsweringModelOutput` or `tuple(torch.FloatTensor)`A `transformers.models.big_bird.modeling_big_bird.BigBirdForQuestionAnsweringModelOutput` 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 ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) and inputs. - **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) -- Total span extraction loss is the sum of a Cross-Entropy for the start and end positions. - **start_logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*, defaults to `None`) -- Span-start scores (before SoftMax). - **end_logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*, defaults to `None`) -- Span-end scores (before SoftMax). - **pooler_output** (`torch.FloatTensor` of shape `(batch_size, 1)`) -- pooler output from BigBigModel - **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 [BigBirdForQuestionAnswering](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdForQuestionAnswering) 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: ```python >>> import torch >>> from transformers import AutoTokenizer, BigBirdForQuestionAnswering >>> from datasets import load_dataset >>> tokenizer = AutoTokenizer.from_pretrained("google/bigbird-roberta-base") >>> model = BigBirdForQuestionAnswering.from_pretrained("google/bigbird-roberta-base") >>> squad_ds = load_dataset("rajpurkar/squad_v2", split="train") >>> # select random article and question >>> LONG_ARTICLE = squad_ds[81514]["context"] >>> QUESTION = squad_ds[81514]["question"] >>> QUESTION 'During daytime how high can the temperatures reach?' >>> inputs = tokenizer(QUESTION, LONG_ARTICLE, return_tensors="pt") >>> # long article and question input >>> list(inputs["input_ids"].shape) [1, 929] >>> with torch.no_grad(): ... outputs = model(**inputs) >>> answer_start_index = outputs.start_logits.argmax() >>> answer_end_index = outputs.end_logits.argmax() >>> predict_answer_token_ids = inputs.input_ids[0, answer_start_index : answer_end_index + 1] >>> predict_answer_token = tokenizer.decode(predict_answer_token_ids) ``` ```python >>> target_start_index, target_end_index = torch.tensor([130]), torch.tensor([132]) >>> outputs = model(**inputs, start_positions=target_start_index, end_positions=target_end_index) >>> loss = outputs.loss ```
## FlaxBigBirdModel[[transformers.FlaxBigBirdModel]]
class transformers.FlaxBigBirdModeltransformers.FlaxBigBirdModelhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_flax_big_bird.py#L1891[{"name": "config", "val": ": BigBirdConfig"}, {"name": "input_shape", "val": ": typing.Optional[tuple] = None"}, {"name": "seed", "val": ": int = 0"}, {"name": "dtype", "val": ": dtype = "}, {"name": "_do_init", "val": ": bool = True"}, {"name": "gradient_checkpointing", "val": ": bool = False"}, {"name": "**kwargs", "val": ""}]- **config** ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) -- 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()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.from_pretrained) method to load the model weights. - **dtype** (`jax.numpy.dtype`, *optional*, defaults to `jax.numpy.float32`) -- The data type of the computation. Can be one of `jax.numpy.float32`, `jax.numpy.float16` (on GPUs) and `jax.numpy.bfloat16` (on TPUs). This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given `dtype`. **Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.** If you wish to change the dtype of the model parameters, see [to_fp16()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.to_fp16) and [to_bf16()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.to_bf16).0 The bare BigBird Model transformer outputting raw hidden-states without any specific head on top. This model inherits from [FlaxPreTrainedModel](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading, saving and converting weights from PyTorch models) This model is also a [flax.linen.Module](https://flax.readthedocs.io/en/latest/api_reference/flax.linen/module.html) subclass. Use it as a regular Flax linen Module and refer to the Flax documentation for all matter related to general usage and behavior. Finally, this model supports inherent JAX features such as: - [Just-In-Time (JIT) compilation](https://jax.readthedocs.io/en/latest/jax.html#just-in-time-compilation-jit) - [Automatic Differentiation](https://jax.readthedocs.io/en/latest/jax.html#automatic-differentiation) - [Vectorization](https://jax.readthedocs.io/en/latest/jax.html#vectorization-vmap) - [Parallelization](https://jax.readthedocs.io/en/latest/jax.html#parallelization-pmap)
__call__transformers.FlaxBigBirdModel.__call__https://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_flax_big_bird.py#L1718[{"name": "input_ids", "val": ""}, {"name": "attention_mask", "val": " = None"}, {"name": "token_type_ids", "val": " = None"}, {"name": "position_ids", "val": " = None"}, {"name": "head_mask", "val": " = None"}, {"name": "encoder_hidden_states", "val": " = None"}, {"name": "encoder_attention_mask", "val": " = None"}, {"name": "params", "val": ": typing.Optional[dict] = None"}, {"name": "dropout_rng", "val": ": typing.Optional[PRNGKey] = None"}, {"name": "indices_rng", "val": ": typing.Optional[PRNGKey] = None"}, {"name": "train", "val": ": bool = False"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}, {"name": "past_key_values", "val": ": typing.Optional[dict] = None"}]- **input_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`) -- Indices of input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](/docs/transformers/v4.57.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **attention_mask** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) - **token_type_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`: - 0 corresponds to a *sentence A* token, - 1 corresponds to a *sentence B* token. [What are token type IDs?](../glossary#token-type-ids) - **position_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`. - **head_mask** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, `optional) -- Mask to nullify selected heads of the attention modules. Mask values selected in `[0, 1]`: - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. - **return_dict** (`bool`, *optional*) -- Whether or not to return a [ModelOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPooling](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`A [transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPooling](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPooling) 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 ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) and inputs. - **last_hidden_state** (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`) -- Sequence of hidden-states at the output of the last layer of the model. - **pooler_output** (`jnp.ndarray` of shape `(batch_size, hidden_size)`) -- Last layer hidden-state of the first token of the sequence (classification token) further processed by a Linear layer and a Tanh activation function. The Linear layer weights are trained from the next sentence prediction (classification) objective during pretraining. - **hidden_states** (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the initial embedding outputs. - **attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. The `FlaxBigBirdPreTrainedModel` 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: ```python >>> from transformers import AutoTokenizer, FlaxBigBirdModel >>> tokenizer = AutoTokenizer.from_pretrained("google/bigbird-roberta-base") >>> model = FlaxBigBirdModel.from_pretrained("google/bigbird-roberta-base") >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="jax") >>> outputs = model(**inputs) >>> last_hidden_states = outputs.last_hidden_state ```
## FlaxBigBirdForPreTraining[[transformers.FlaxBigBirdForPreTraining]]
class transformers.FlaxBigBirdForPreTrainingtransformers.FlaxBigBirdForPreTraininghttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_flax_big_bird.py#L1968[{"name": "config", "val": ": BigBirdConfig"}, {"name": "input_shape", "val": ": typing.Optional[tuple] = None"}, {"name": "seed", "val": ": int = 0"}, {"name": "dtype", "val": ": dtype = "}, {"name": "_do_init", "val": ": bool = True"}, {"name": "gradient_checkpointing", "val": ": bool = False"}, {"name": "**kwargs", "val": ""}]- **config** ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) -- 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()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.from_pretrained) method to load the model weights. - **dtype** (`jax.numpy.dtype`, *optional*, defaults to `jax.numpy.float32`) -- The data type of the computation. Can be one of `jax.numpy.float32`, `jax.numpy.float16` (on GPUs) and `jax.numpy.bfloat16` (on TPUs). This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given `dtype`. **Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.** If you wish to change the dtype of the model parameters, see [to_fp16()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.to_fp16) and [to_bf16()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.to_bf16).0 BigBird Model with two heads on top as done during the pretraining: a `masked language modeling` head and a `next sentence prediction (classification)` head. This model inherits from [FlaxPreTrainedModel](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading, saving and converting weights from PyTorch models) This model is also a [flax.linen.Module](https://flax.readthedocs.io/en/latest/api_reference/flax.linen/module.html) subclass. Use it as a regular Flax linen Module and refer to the Flax documentation for all matter related to general usage and behavior. Finally, this model supports inherent JAX features such as: - [Just-In-Time (JIT) compilation](https://jax.readthedocs.io/en/latest/jax.html#just-in-time-compilation-jit) - [Automatic Differentiation](https://jax.readthedocs.io/en/latest/jax.html#automatic-differentiation) - [Vectorization](https://jax.readthedocs.io/en/latest/jax.html#vectorization-vmap) - [Parallelization](https://jax.readthedocs.io/en/latest/jax.html#parallelization-pmap)
__call__transformers.FlaxBigBirdForPreTraining.__call__https://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_flax_big_bird.py#L1718[{"name": "input_ids", "val": ""}, {"name": "attention_mask", "val": " = None"}, {"name": "token_type_ids", "val": " = None"}, {"name": "position_ids", "val": " = None"}, {"name": "head_mask", "val": " = None"}, {"name": "encoder_hidden_states", "val": " = None"}, {"name": "encoder_attention_mask", "val": " = None"}, {"name": "params", "val": ": typing.Optional[dict] = None"}, {"name": "dropout_rng", "val": ": typing.Optional[PRNGKey] = None"}, {"name": "indices_rng", "val": ": typing.Optional[PRNGKey] = None"}, {"name": "train", "val": ": bool = False"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}, {"name": "past_key_values", "val": ": typing.Optional[dict] = None"}]- **input_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`) -- Indices of input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](/docs/transformers/v4.57.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **attention_mask** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) - **token_type_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`: - 0 corresponds to a *sentence A* token, - 1 corresponds to a *sentence B* token. [What are token type IDs?](../glossary#token-type-ids) - **position_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`. - **head_mask** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, `optional) -- Mask to nullify selected heads of the attention modules. Mask values selected in `[0, 1]`: - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. - **return_dict** (`bool`, *optional*) -- Whether or not to return a [ModelOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0`transformers.models.big_bird.modeling_flax_big_bird.FlaxBigBirdForPreTrainingOutput` or `tuple(torch.FloatTensor)`A `transformers.models.big_bird.modeling_flax_big_bird.FlaxBigBirdForPreTrainingOutput` 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 ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) and inputs. - **prediction_logits** (`jnp.ndarray` of shape `(batch_size, sequence_length, config.vocab_size)`) -- Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). - **seq_relationship_logits** (`jnp.ndarray` of shape `(batch_size, 2)`) -- Prediction scores of the next sequence prediction (classification) head (scores of True/False continuation before SoftMax). - **hidden_states** (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the initial embedding outputs. - **attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. The `FlaxBigBirdPreTrainedModel` 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: ```python >>> from transformers import AutoTokenizer, FlaxBigBirdForPreTraining >>> tokenizer = AutoTokenizer.from_pretrained("google/bigbird-roberta-base") >>> model = FlaxBigBirdForPreTraining.from_pretrained("google/bigbird-roberta-base") >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="np") >>> outputs = model(**inputs) >>> prediction_logits = outputs.prediction_logits >>> seq_relationship_logits = outputs.seq_relationship_logits ```
## FlaxBigBirdForCausalLM[[transformers.FlaxBigBirdForCausalLM]]
class transformers.FlaxBigBirdForCausalLMtransformers.FlaxBigBirdForCausalLMhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_flax_big_bird.py#L2600[{"name": "config", "val": ": BigBirdConfig"}, {"name": "input_shape", "val": ": typing.Optional[tuple] = None"}, {"name": "seed", "val": ": int = 0"}, {"name": "dtype", "val": ": dtype = "}, {"name": "_do_init", "val": ": bool = True"}, {"name": "gradient_checkpointing", "val": ": bool = False"}, {"name": "**kwargs", "val": ""}]- **config** ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) -- 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()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.from_pretrained) method to load the model weights. - **dtype** (`jax.numpy.dtype`, *optional*, defaults to `jax.numpy.float32`) -- The data type of the computation. Can be one of `jax.numpy.float32`, `jax.numpy.float16` (on GPUs) and `jax.numpy.bfloat16` (on TPUs). This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given `dtype`. **Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.** If you wish to change the dtype of the model parameters, see [to_fp16()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.to_fp16) and [to_bf16()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.to_bf16).0 BigBird Model with a language modeling head on top (a linear layer on top of the hidden-states output) e.g for autoregressive tasks. This model inherits from [FlaxPreTrainedModel](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading, saving and converting weights from PyTorch models) This model is also a [flax.linen.Module](https://flax.readthedocs.io/en/latest/api_reference/flax.linen/module.html) subclass. Use it as a regular Flax linen Module and refer to the Flax documentation for all matter related to general usage and behavior. Finally, this model supports inherent JAX features such as: - [Just-In-Time (JIT) compilation](https://jax.readthedocs.io/en/latest/jax.html#just-in-time-compilation-jit) - [Automatic Differentiation](https://jax.readthedocs.io/en/latest/jax.html#automatic-differentiation) - [Vectorization](https://jax.readthedocs.io/en/latest/jax.html#vectorization-vmap) - [Parallelization](https://jax.readthedocs.io/en/latest/jax.html#parallelization-pmap)
__call__transformers.FlaxBigBirdForCausalLM.__call__https://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_flax_big_bird.py#L1718[{"name": "input_ids", "val": ""}, {"name": "attention_mask", "val": " = None"}, {"name": "token_type_ids", "val": " = None"}, {"name": "position_ids", "val": " = None"}, {"name": "head_mask", "val": " = None"}, {"name": "encoder_hidden_states", "val": " = None"}, {"name": "encoder_attention_mask", "val": " = None"}, {"name": "params", "val": ": typing.Optional[dict] = None"}, {"name": "dropout_rng", "val": ": typing.Optional[PRNGKey] = None"}, {"name": "indices_rng", "val": ": typing.Optional[PRNGKey] = None"}, {"name": "train", "val": ": bool = False"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}, {"name": "past_key_values", "val": ": typing.Optional[dict] = None"}]- **input_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`) -- Indices of input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](/docs/transformers/v4.57.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **attention_mask** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) - **token_type_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`: - 0 corresponds to a *sentence A* token, - 1 corresponds to a *sentence B* token. [What are token type IDs?](../glossary#token-type-ids) - **position_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`. - **head_mask** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, `optional) -- Mask to nullify selected heads of the attention modules. Mask values selected in `[0, 1]`: - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. - **return_dict** (`bool`, *optional*) -- Whether or not to return a [ModelOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[transformers.modeling_flax_outputs.FlaxCausalLMOutputWithCrossAttentions](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_flax_outputs.FlaxCausalLMOutputWithCrossAttentions) or `tuple(torch.FloatTensor)`A [transformers.modeling_flax_outputs.FlaxCausalLMOutputWithCrossAttentions](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_flax_outputs.FlaxCausalLMOutputWithCrossAttentions) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) and inputs. - **logits** (`jnp.ndarray` of shape `(batch_size, sequence_length, config.vocab_size)`) -- Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). - **hidden_states** (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the initial embedding outputs. - **attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. - **cross_attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Cross attentions weights after the attention softmax, used to compute the weighted average in the cross-attention heads. - **past_key_values** (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- Tuple of `jnp.ndarray` 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 `FlaxBigBirdPreTrainedModel` 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: ```python >>> from transformers import AutoTokenizer, FlaxBigBirdForCausalLM >>> tokenizer = AutoTokenizer.from_pretrained("google/bigbird-roberta-base") >>> model = FlaxBigBirdForCausalLM.from_pretrained("google/bigbird-roberta-base") >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="np") >>> outputs = model(**inputs) >>> # retrieve logts for next token >>> next_token_logits = outputs.logits[:, -1] ```
## FlaxBigBirdForMaskedLM[[transformers.FlaxBigBirdForMaskedLM]]
class transformers.FlaxBigBirdForMaskedLMtransformers.FlaxBigBirdForMaskedLMhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_flax_big_bird.py#L2061[{"name": "config", "val": ": BigBirdConfig"}, {"name": "input_shape", "val": ": typing.Optional[tuple] = None"}, {"name": "seed", "val": ": int = 0"}, {"name": "dtype", "val": ": dtype = "}, {"name": "_do_init", "val": ": bool = True"}, {"name": "gradient_checkpointing", "val": ": bool = False"}, {"name": "**kwargs", "val": ""}]- **config** ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) -- 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()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.from_pretrained) method to load the model weights. - **dtype** (`jax.numpy.dtype`, *optional*, defaults to `jax.numpy.float32`) -- The data type of the computation. Can be one of `jax.numpy.float32`, `jax.numpy.float16` (on GPUs) and `jax.numpy.bfloat16` (on TPUs). This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given `dtype`. **Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.** If you wish to change the dtype of the model parameters, see [to_fp16()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.to_fp16) and [to_bf16()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.to_bf16).0 BigBird Model with a `language modeling` head on top. This model inherits from [FlaxPreTrainedModel](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading, saving and converting weights from PyTorch models) This model is also a [flax.linen.Module](https://flax.readthedocs.io/en/latest/api_reference/flax.linen/module.html) subclass. Use it as a regular Flax linen Module and refer to the Flax documentation for all matter related to general usage and behavior. Finally, this model supports inherent JAX features such as: - [Just-In-Time (JIT) compilation](https://jax.readthedocs.io/en/latest/jax.html#just-in-time-compilation-jit) - [Automatic Differentiation](https://jax.readthedocs.io/en/latest/jax.html#automatic-differentiation) - [Vectorization](https://jax.readthedocs.io/en/latest/jax.html#vectorization-vmap) - [Parallelization](https://jax.readthedocs.io/en/latest/jax.html#parallelization-pmap)
__call__transformers.FlaxBigBirdForMaskedLM.__call__https://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_flax_big_bird.py#L1718[{"name": "input_ids", "val": ""}, {"name": "attention_mask", "val": " = None"}, {"name": "token_type_ids", "val": " = None"}, {"name": "position_ids", "val": " = None"}, {"name": "head_mask", "val": " = None"}, {"name": "encoder_hidden_states", "val": " = None"}, {"name": "encoder_attention_mask", "val": " = None"}, {"name": "params", "val": ": typing.Optional[dict] = None"}, {"name": "dropout_rng", "val": ": typing.Optional[PRNGKey] = None"}, {"name": "indices_rng", "val": ": typing.Optional[PRNGKey] = None"}, {"name": "train", "val": ": bool = False"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}, {"name": "past_key_values", "val": ": typing.Optional[dict] = None"}]- **input_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`) -- Indices of input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](/docs/transformers/v4.57.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **attention_mask** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) - **token_type_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`: - 0 corresponds to a *sentence A* token, - 1 corresponds to a *sentence B* token. [What are token type IDs?](../glossary#token-type-ids) - **position_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`. - **head_mask** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, `optional) -- Mask to nullify selected heads of the attention modules. Mask values selected in `[0, 1]`: - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. - **return_dict** (`bool`, *optional*) -- Whether or not to return a [ModelOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[transformers.modeling_flax_outputs.FlaxMaskedLMOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_flax_outputs.FlaxMaskedLMOutput) or `tuple(torch.FloatTensor)`A [transformers.modeling_flax_outputs.FlaxMaskedLMOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_flax_outputs.FlaxMaskedLMOutput) 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 ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) and inputs. - **logits** (`jnp.ndarray` of shape `(batch_size, sequence_length, config.vocab_size)`) -- Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). - **hidden_states** (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the initial embedding outputs. - **attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. The `FlaxBigBirdPreTrainedModel` 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: ```python >>> from transformers import AutoTokenizer, FlaxBigBirdForMaskedLM >>> tokenizer = AutoTokenizer.from_pretrained("google/bigbird-roberta-base") >>> model = FlaxBigBirdForMaskedLM.from_pretrained("google/bigbird-roberta-base") >>> inputs = tokenizer("The capital of France is [MASK].", return_tensors="jax") >>> outputs = model(**inputs) >>> logits = outputs.logits ```
## FlaxBigBirdForSequenceClassification[[transformers.FlaxBigBirdForSequenceClassification]]
class transformers.FlaxBigBirdForSequenceClassificationtransformers.FlaxBigBirdForSequenceClassificationhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_flax_big_bird.py#L2151[{"name": "config", "val": ": BigBirdConfig"}, {"name": "input_shape", "val": ": typing.Optional[tuple] = None"}, {"name": "seed", "val": ": int = 0"}, {"name": "dtype", "val": ": dtype = "}, {"name": "_do_init", "val": ": bool = True"}, {"name": "gradient_checkpointing", "val": ": bool = False"}, {"name": "**kwargs", "val": ""}]- **config** ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) -- 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()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.from_pretrained) method to load the model weights. - **dtype** (`jax.numpy.dtype`, *optional*, defaults to `jax.numpy.float32`) -- The data type of the computation. Can be one of `jax.numpy.float32`, `jax.numpy.float16` (on GPUs) and `jax.numpy.bfloat16` (on TPUs). This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given `dtype`. **Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.** If you wish to change the dtype of the model parameters, see [to_fp16()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.to_fp16) and [to_bf16()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.to_bf16).0 BigBird Model transformer with a sequence classification/regression head on top (a linear layer on top of the pooled output) e.g. for GLUE tasks. This model inherits from [FlaxPreTrainedModel](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading, saving and converting weights from PyTorch models) This model is also a [flax.linen.Module](https://flax.readthedocs.io/en/latest/api_reference/flax.linen/module.html) subclass. Use it as a regular Flax linen Module and refer to the Flax documentation for all matter related to general usage and behavior. Finally, this model supports inherent JAX features such as: - [Just-In-Time (JIT) compilation](https://jax.readthedocs.io/en/latest/jax.html#just-in-time-compilation-jit) - [Automatic Differentiation](https://jax.readthedocs.io/en/latest/jax.html#automatic-differentiation) - [Vectorization](https://jax.readthedocs.io/en/latest/jax.html#vectorization-vmap) - [Parallelization](https://jax.readthedocs.io/en/latest/jax.html#parallelization-pmap)
__call__transformers.FlaxBigBirdForSequenceClassification.__call__https://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_flax_big_bird.py#L1718[{"name": "input_ids", "val": ""}, {"name": "attention_mask", "val": " = None"}, {"name": "token_type_ids", "val": " = None"}, {"name": "position_ids", "val": " = None"}, {"name": "head_mask", "val": " = None"}, {"name": "encoder_hidden_states", "val": " = None"}, {"name": "encoder_attention_mask", "val": " = None"}, {"name": "params", "val": ": typing.Optional[dict] = None"}, {"name": "dropout_rng", "val": ": typing.Optional[PRNGKey] = None"}, {"name": "indices_rng", "val": ": typing.Optional[PRNGKey] = None"}, {"name": "train", "val": ": bool = False"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}, {"name": "past_key_values", "val": ": typing.Optional[dict] = None"}]- **input_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`) -- Indices of input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](/docs/transformers/v4.57.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **attention_mask** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) - **token_type_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`: - 0 corresponds to a *sentence A* token, - 1 corresponds to a *sentence B* token. [What are token type IDs?](../glossary#token-type-ids) - **position_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`. - **head_mask** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, `optional) -- Mask to nullify selected heads of the attention modules. Mask values selected in `[0, 1]`: - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. - **return_dict** (`bool`, *optional*) -- Whether or not to return a [ModelOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[transformers.modeling_flax_outputs.FlaxSequenceClassifierOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_flax_outputs.FlaxSequenceClassifierOutput) or `tuple(torch.FloatTensor)`A [transformers.modeling_flax_outputs.FlaxSequenceClassifierOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_flax_outputs.FlaxSequenceClassifierOutput) 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 ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) and inputs. - **logits** (`jnp.ndarray` of shape `(batch_size, config.num_labels)`) -- Classification (or regression if config.num_labels==1) scores (before SoftMax). - **hidden_states** (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the initial embedding outputs. - **attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. The `FlaxBigBirdPreTrainedModel` 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: ```python >>> from transformers import AutoTokenizer, FlaxBigBirdForSequenceClassification >>> tokenizer = AutoTokenizer.from_pretrained("google/bigbird-roberta-base") >>> model = FlaxBigBirdForSequenceClassification.from_pretrained("google/bigbird-roberta-base") >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="jax") >>> outputs = model(**inputs) >>> logits = outputs.logits ```
## FlaxBigBirdForMultipleChoice[[transformers.FlaxBigBirdForMultipleChoice]]
class transformers.FlaxBigBirdForMultipleChoicetransformers.FlaxBigBirdForMultipleChoicehttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_flax_big_bird.py#L2232[{"name": "config", "val": ": BigBirdConfig"}, {"name": "input_shape", "val": ": typing.Optional[tuple] = None"}, {"name": "seed", "val": ": int = 0"}, {"name": "dtype", "val": ": dtype = "}, {"name": "_do_init", "val": ": bool = True"}, {"name": "**kwargs", "val": ""}]- **config** ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) -- 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()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.from_pretrained) method to load the model weights. - **dtype** (`jax.numpy.dtype`, *optional*, defaults to `jax.numpy.float32`) -- The data type of the computation. Can be one of `jax.numpy.float32`, `jax.numpy.float16` (on GPUs) and `jax.numpy.bfloat16` (on TPUs). This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given `dtype`. **Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.** If you wish to change the dtype of the model parameters, see [to_fp16()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.to_fp16) and [to_bf16()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.to_bf16).0 BigBird Model with a multiple choice classification head on top (a linear layer on top of the pooled output and a softmax) e.g. for RocStories/SWAG tasks. This model inherits from [FlaxPreTrainedModel](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading, saving and converting weights from PyTorch models) This model is also a [flax.linen.Module](https://flax.readthedocs.io/en/latest/api_reference/flax.linen/module.html) subclass. Use it as a regular Flax linen Module and refer to the Flax documentation for all matter related to general usage and behavior. Finally, this model supports inherent JAX features such as: - [Just-In-Time (JIT) compilation](https://jax.readthedocs.io/en/latest/jax.html#just-in-time-compilation-jit) - [Automatic Differentiation](https://jax.readthedocs.io/en/latest/jax.html#automatic-differentiation) - [Vectorization](https://jax.readthedocs.io/en/latest/jax.html#vectorization-vmap) - [Parallelization](https://jax.readthedocs.io/en/latest/jax.html#parallelization-pmap)
__call__transformers.FlaxBigBirdForMultipleChoice.__call__https://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_flax_big_bird.py#L1718[{"name": "input_ids", "val": ""}, {"name": "attention_mask", "val": " = None"}, {"name": "token_type_ids", "val": " = None"}, {"name": "position_ids", "val": " = None"}, {"name": "head_mask", "val": " = None"}, {"name": "encoder_hidden_states", "val": " = None"}, {"name": "encoder_attention_mask", "val": " = None"}, {"name": "params", "val": ": typing.Optional[dict] = None"}, {"name": "dropout_rng", "val": ": typing.Optional[PRNGKey] = None"}, {"name": "indices_rng", "val": ": typing.Optional[PRNGKey] = None"}, {"name": "train", "val": ": bool = False"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}, {"name": "past_key_values", "val": ": typing.Optional[dict] = None"}]- **input_ids** (`numpy.ndarray` of shape `(batch_size, num_choices, sequence_length)`) -- Indices of input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](/docs/transformers/v4.57.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **attention_mask** (`numpy.ndarray` of shape `(batch_size, num_choices, 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?](../glossary#attention-mask) - **token_type_ids** (`numpy.ndarray` of shape `(batch_size, num_choices, 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. [What are token type IDs?](../glossary#token-type-ids) - **position_ids** (`numpy.ndarray` of shape `(batch_size, num_choices, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`. - **head_mask** (`numpy.ndarray` of shape `(batch_size, num_choices, sequence_length)`, `optional) -- Mask to nullify selected heads of the attention modules. Mask values selected in `[0, 1]`: - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. - **return_dict** (`bool`, *optional*) -- Whether or not to return a [ModelOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[transformers.modeling_flax_outputs.FlaxMultipleChoiceModelOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_flax_outputs.FlaxMultipleChoiceModelOutput) or `tuple(torch.FloatTensor)`A [transformers.modeling_flax_outputs.FlaxMultipleChoiceModelOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_flax_outputs.FlaxMultipleChoiceModelOutput) 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 ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) and inputs. - **logits** (`jnp.ndarray` of shape `(batch_size, num_choices)`) -- *num_choices* is the second dimension of the input tensors. (see *input_ids* above). Classification scores (before SoftMax). - **hidden_states** (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the initial embedding outputs. - **attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. The `FlaxBigBirdPreTrainedModel` 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: ```python >>> from transformers import AutoTokenizer, FlaxBigBirdForMultipleChoice >>> tokenizer = AutoTokenizer.from_pretrained("google/bigbird-roberta-base") >>> model = FlaxBigBirdForMultipleChoice.from_pretrained("google/bigbird-roberta-base") >>> prompt = "In Italy, pizza served in formal settings, such as at a restaurant, is presented unsliced." >>> choice0 = "It is eaten with a fork and a knife." >>> choice1 = "It is eaten while held in the hand." >>> encoding = tokenizer([prompt, prompt], [choice0, choice1], return_tensors="jax", padding=True) >>> outputs = model(**{k: v[None, :] for k, v in encoding.items()}) >>> logits = outputs.logits ```
## FlaxBigBirdForTokenClassification[[transformers.FlaxBigBirdForTokenClassification]]
class transformers.FlaxBigBirdForTokenClassificationtransformers.FlaxBigBirdForTokenClassificationhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_flax_big_bird.py#L2330[{"name": "config", "val": ": BigBirdConfig"}, {"name": "input_shape", "val": ": typing.Optional[tuple] = None"}, {"name": "seed", "val": ": int = 0"}, {"name": "dtype", "val": ": dtype = "}, {"name": "_do_init", "val": ": bool = True"}, {"name": "gradient_checkpointing", "val": ": bool = False"}, {"name": "**kwargs", "val": ""}]- **config** ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) -- 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()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.from_pretrained) method to load the model weights. - **dtype** (`jax.numpy.dtype`, *optional*, defaults to `jax.numpy.float32`) -- The data type of the computation. Can be one of `jax.numpy.float32`, `jax.numpy.float16` (on GPUs) and `jax.numpy.bfloat16` (on TPUs). This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given `dtype`. **Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.** If you wish to change the dtype of the model parameters, see [to_fp16()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.to_fp16) and [to_bf16()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.to_bf16).0 BigBird Model with a token classification head on top (a linear layer on top of the hidden-states output) e.g. for Named-Entity-Recognition (NER) tasks. This model inherits from [FlaxPreTrainedModel](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading, saving and converting weights from PyTorch models) This model is also a [flax.linen.Module](https://flax.readthedocs.io/en/latest/api_reference/flax.linen/module.html) subclass. Use it as a regular Flax linen Module and refer to the Flax documentation for all matter related to general usage and behavior. Finally, this model supports inherent JAX features such as: - [Just-In-Time (JIT) compilation](https://jax.readthedocs.io/en/latest/jax.html#just-in-time-compilation-jit) - [Automatic Differentiation](https://jax.readthedocs.io/en/latest/jax.html#automatic-differentiation) - [Vectorization](https://jax.readthedocs.io/en/latest/jax.html#vectorization-vmap) - [Parallelization](https://jax.readthedocs.io/en/latest/jax.html#parallelization-pmap)
__call__transformers.FlaxBigBirdForTokenClassification.__call__https://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_flax_big_bird.py#L1718[{"name": "input_ids", "val": ""}, {"name": "attention_mask", "val": " = None"}, {"name": "token_type_ids", "val": " = None"}, {"name": "position_ids", "val": " = None"}, {"name": "head_mask", "val": " = None"}, {"name": "encoder_hidden_states", "val": " = None"}, {"name": "encoder_attention_mask", "val": " = None"}, {"name": "params", "val": ": typing.Optional[dict] = None"}, {"name": "dropout_rng", "val": ": typing.Optional[PRNGKey] = None"}, {"name": "indices_rng", "val": ": typing.Optional[PRNGKey] = None"}, {"name": "train", "val": ": bool = False"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}, {"name": "past_key_values", "val": ": typing.Optional[dict] = None"}]- **input_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`) -- Indices of input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](/docs/transformers/v4.57.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **attention_mask** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) - **token_type_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`: - 0 corresponds to a *sentence A* token, - 1 corresponds to a *sentence B* token. [What are token type IDs?](../glossary#token-type-ids) - **position_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`. - **head_mask** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, `optional) -- Mask to nullify selected heads of the attention modules. Mask values selected in `[0, 1]`: - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. - **return_dict** (`bool`, *optional*) -- Whether or not to return a [ModelOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[transformers.modeling_flax_outputs.FlaxTokenClassifierOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_flax_outputs.FlaxTokenClassifierOutput) or `tuple(torch.FloatTensor)`A [transformers.modeling_flax_outputs.FlaxTokenClassifierOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.modeling_flax_outputs.FlaxTokenClassifierOutput) 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 ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) and inputs. - **logits** (`jnp.ndarray` of shape `(batch_size, sequence_length, config.num_labels)`) -- Classification scores (before SoftMax). - **hidden_states** (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the initial embedding outputs. - **attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. The `FlaxBigBirdPreTrainedModel` 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: ```python >>> from transformers import AutoTokenizer, FlaxBigBirdForTokenClassification >>> tokenizer = AutoTokenizer.from_pretrained("google/bigbird-roberta-base") >>> model = FlaxBigBirdForTokenClassification.from_pretrained("google/bigbird-roberta-base") >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="jax") >>> outputs = model(**inputs) >>> logits = outputs.logits ```
## FlaxBigBirdForQuestionAnswering[[transformers.FlaxBigBirdForQuestionAnswering]]
class transformers.FlaxBigBirdForQuestionAnsweringtransformers.FlaxBigBirdForQuestionAnsweringhttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_flax_big_bird.py#L2433[{"name": "config", "val": ": BigBirdConfig"}, {"name": "input_shape", "val": ": typing.Optional[tuple] = None"}, {"name": "seed", "val": ": int = 0"}, {"name": "dtype", "val": ": dtype = "}, {"name": "_do_init", "val": ": bool = True"}, {"name": "gradient_checkpointing", "val": ": bool = False"}, {"name": "**kwargs", "val": ""}]- **config** ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) -- 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()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.from_pretrained) method to load the model weights. - **dtype** (`jax.numpy.dtype`, *optional*, defaults to `jax.numpy.float32`) -- The data type of the computation. Can be one of `jax.numpy.float32`, `jax.numpy.float16` (on GPUs) and `jax.numpy.bfloat16` (on TPUs). This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given `dtype`. **Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.** If you wish to change the dtype of the model parameters, see [to_fp16()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.to_fp16) and [to_bf16()](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel.to_bf16).0 BigBird Model with a span classification head on top for extractive question-answering tasks like SQuAD (a linear layers on top of the hidden-states output to compute `span start logits` and `span end logits`). This model inherits from [FlaxPreTrainedModel](/docs/transformers/v4.57.0/ja/main_classes/model#transformers.FlaxPreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading, saving and converting weights from PyTorch models) This model is also a [flax.linen.Module](https://flax.readthedocs.io/en/latest/api_reference/flax.linen/module.html) subclass. Use it as a regular Flax linen Module and refer to the Flax documentation for all matter related to general usage and behavior. Finally, this model supports inherent JAX features such as: - [Just-In-Time (JIT) compilation](https://jax.readthedocs.io/en/latest/jax.html#just-in-time-compilation-jit) - [Automatic Differentiation](https://jax.readthedocs.io/en/latest/jax.html#automatic-differentiation) - [Vectorization](https://jax.readthedocs.io/en/latest/jax.html#vectorization-vmap) - [Parallelization](https://jax.readthedocs.io/en/latest/jax.html#parallelization-pmap)
__call__transformers.FlaxBigBirdForQuestionAnswering.__call__https://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/big_bird/modeling_flax_big_bird.py#L2436[{"name": "input_ids", "val": ""}, {"name": "attention_mask", "val": " = None"}, {"name": "token_type_ids", "val": " = None"}, {"name": "position_ids", "val": " = None"}, {"name": "head_mask", "val": " = None"}, {"name": "question_lengths", "val": " = None"}, {"name": "params", "val": ": typing.Optional[dict] = None"}, {"name": "dropout_rng", "val": ": typing.Optional[PRNGKey] = None"}, {"name": "indices_rng", "val": ": typing.Optional[PRNGKey] = None"}, {"name": "train", "val": ": bool = False"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}]- **input_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`) -- Indices of input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](/docs/transformers/v4.57.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v4.57.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **attention_mask** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) - **token_type_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`: - 0 corresponds to a *sentence A* token, - 1 corresponds to a *sentence B* token. [What are token type IDs?](../glossary#token-type-ids) - **position_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`. - **head_mask** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, `optional) -- Mask to nullify selected heads of the attention modules. Mask values selected in `[0, 1]`: - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. - **return_dict** (`bool`, *optional*) -- Whether or not to return a [ModelOutput](/docs/transformers/v4.57.0/ja/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0`transformers.models.big_bird.modeling_flax_big_bird.FlaxBigBirdForQuestionAnsweringModelOutput` or `tuple(torch.FloatTensor)`A `transformers.models.big_bird.modeling_flax_big_bird.FlaxBigBirdForQuestionAnsweringModelOutput` 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 ([BigBirdConfig](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.BigBirdConfig)) and inputs. - **start_logits** (`jnp.ndarray` of shape `(batch_size, sequence_length)`) -- Span-start scores (before SoftMax). - **end_logits** (`jnp.ndarray` of shape `(batch_size, sequence_length)`) -- Span-end scores (before SoftMax). - **pooled_output** (`jnp.ndarray` of shape `(batch_size, hidden_size)`) -- pooled_output returned by FlaxBigBirdModel. - **hidden_states** (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the initial embedding outputs. - **attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. The [FlaxBigBirdForQuestionAnswering](/docs/transformers/v4.57.0/ja/model_doc/big_bird#transformers.FlaxBigBirdForQuestionAnswering) 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: ```python >>> from transformers import AutoTokenizer, FlaxBigBirdForQuestionAnswering >>> tokenizer = AutoTokenizer.from_pretrained("google/bigbird-roberta-base") >>> model = FlaxBigBirdForQuestionAnswering.from_pretrained("google/bigbird-roberta-base") >>> question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet" >>> inputs = tokenizer(question, text, return_tensors="jax") >>> outputs = model(**inputs) >>> start_scores = outputs.start_logits >>> end_scores = outputs.end_logits ```