# MPNet ## MPNet ### Overview The MPNet model was proposed in [MPNet: Masked and Permuted Pre-training for Language Understanding](https://arxiv.org/abs/2004.09297) by Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, Tie-Yan Liu. MPNet adopts a novel pre-training method, named masked and permuted language modeling, to inherit the advantages of masked language modeling and permuted language modeling for natural language understanding. The abstract from the paper is the following: *BERT adopts masked language modeling (MLM) for pre-training and is one of the most successful pre-training models. Since BERT neglects dependency among predicted tokens, XLNet introduces permuted language modeling (PLM) for pre-training to address this problem. However, XLNet does not leverage the full position information of a sentence and thus suffers from position discrepancy between pre-training and fine-tuning. In this paper, we propose MPNet, a novel pre-training method that inherits the advantages of BERT and XLNet and avoids their limitations. MPNet leverages the dependency among predicted tokens through permuted language modeling (vs. MLM in BERT), and takes auxiliary position information as input to make the model see a full sentence and thus reducing the position discrepancy (vs. PLM in XLNet). We pre-train MPNet on a large-scale dataset (over 160GB text corpora) and fine-tune on a variety of down-streaming tasks (GLUE, SQuAD, etc). Experimental results show that MPNet outperforms MLM and PLM by a large margin, and achieves better results on these tasks compared with previous state-of-the-art pre-trained methods (e.g., BERT, XLNet, RoBERTa) under the same model setting.* Tips: * MPNet doesn’t have `token_type_ids`, you don’t need to indicate which token belongs to which segment. just separate your segments with the separation token `tokenizer.sep_token` (or `[sep]`). The original code can be found [here](https://github.com/microsoft/MPNet). ### Documentation resources * [Text classification task guide](https://huggingface.co/docs/transformers/tasks/sequence_classification) * [Token classification task guide](https://huggingface.co/docs/transformers/tasks/token_classification) * [Question answering task guide](https://huggingface.co/docs/transformers/tasks/question_answering) * [Masked language modeling task guide](https://huggingface.co/docs/transformers/tasks/masked_language_modeling) * [Multiple choice task guide](https://huggingface.co/docs/transformers/tasks/multiple_choice) ### MPNetConfig #### class transformers.MPNetConfig [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/configuration_mpnet.py#L29) ( vocab\_size = 30527hidden\_size = 768num\_hidden\_layers = 12num\_attention\_heads = 12intermediate\_size = 3072hidden\_act = 'gelu'hidden\_dropout\_prob = 0.1attention\_probs\_dropout\_prob = 0.1max\_position\_embeddings = 512initializer\_range = 0.02layer\_norm\_eps = 1e-12relative\_attention\_num\_buckets = 32pad\_token\_id = 1bos\_token\_id = 0eos\_token\_id = 2\*\*kwargs ) Parameters * **vocab\_size** (`int`, *optional*, defaults to 30527) — Vocabulary size of the MPNet model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [MPNetModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetModel) or [TFMPNetModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.TFMPNetModel). * **hidden\_size** (`int`, *optional*, defaults to 768) — Dimensionality 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) — Dimensionality of the “intermediate” (often named feed-forward) layer in the Transformer encoder. * **hidden\_act** (`str` or `Callable`, *optional*, defaults to `"gelu"`) — The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. * **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 512) — The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048). * **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. * **relative\_attention\_num\_buckets** (`int`, *optional*, defaults to 32) — The number of buckets to use for each attention layer. This is the configuration class to store the configuration of a [MPNetModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetModel) or a [TFMPNetModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.TFMPNetModel). It is used to instantiate a MPNet 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 MPNet [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) architecture. Configuration objects inherit from [PretrainedConfig](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/configuration#transformers.PretrainedConfig) and can be used to control the model outputs. Read the documentation from [PretrainedConfig](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/configuration#transformers.PretrainedConfig) for more information. Examples: Copied ``` >>> from transformers import MPNetModel, MPNetConfig >>> # Initializing a MPNet mpnet-base style configuration >>> configuration = MPNetConfig() >>> # Initializing a model from the mpnet-base style configuration >>> model = MPNetModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` ### MPNetTokenizer #### class transformers.MPNetTokenizer [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/tokenization_mpnet.py#L66) ( vocab\_filedo\_lower\_case = Truedo\_basic\_tokenize = Truenever\_split = Nonebos\_token = '\'eos\_token = '\'sep\_token = '\'cls\_token = '\'unk\_token = '\[UNK]'pad\_token = '\'mask\_token = '\'tokenize\_chinese\_chars = Truestrip\_accents = None\*\*kwargs ) Parameters * **vocab\_file** (`str`) — Path to the vocabulary file. * **do\_lower\_case** (`bool`, *optional*, defaults to `True`) — Whether or not to lowercase the input when tokenizing. * **do\_basic\_tokenize** (`bool`, *optional*, defaults to `True`) — Whether or not to do basic tokenization before WordPiece. * **never\_split** (`Iterable`, *optional*) — Collection of tokens which will never be split during tokenization. Only has an effect when `do_basic_tokenize=True` * **bos\_token** (`str`, *optional*, defaults to `""`) — The beginning of sequence token that was used during pre-training. 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. When building a sequence using special tokens, this is not the token that is used for the end of sequence. The token used is the `sep_token`. * **sep\_token** (`str`, *optional*, defaults to `""`) — 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. * **cls\_token** (`str`, *optional*, defaults to `""`) — 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. * **unk\_token** (`str`, *optional*, defaults to `"[UNK]"`) — The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead. * **pad\_token** (`str`, *optional*, defaults to `""`) — The token used for padding, for example when batching sequences of different lengths. * **mask\_token** (`str`, *optional*, defaults to `""`) — 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. * **tokenize\_chinese\_chars** (`bool`, *optional*, defaults to `True`) — Whether or not to tokenize Chinese characters. This should likely be deactivated for Japanese (see this [issue](https://github.com/huggingface/transformers/issues/328)). * **strip\_accents** (`bool`, *optional*) — Whether or not to strip all accents. If this option is not specified, then it will be determined by the value for `lowercase` (as in the original BERT). This tokenizer inherits from [BertTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bert#transformers.BertTokenizer) which contains most of the methods. Users should refer to the superclass for more information regarding methods. **build\_inputs\_with\_special\_tokens** [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/tokenization_mpnet.py#L233) ( token\_ids\_0: typing.List\[int]token\_ids\_1: typing.Optional\[typing.List\[int]] = None ) → `List[int]` Parameters * **token\_ids\_0** (`List[int]`) — List of IDs to which the special tokens will be added * **token\_ids\_1** (`List[int]`, *optional*) — Optional second list of IDs for sequence pairs. Returns `List[int]` list of [input IDs](https://huggingface.co/docs/transformers/glossary#input-ids) with the appropriate special tokens. Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. A MPNet sequence has the following format: * single sequence: ` X ` * pair of sequences: ` A B ` **get\_special\_tokens\_mask** [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/tokenization_mpnet.py#L258) ( token\_ids\_0: typing.List\[int]token\_ids\_1: typing.Optional\[typing.List\[int]] = Nonealready\_has\_special\_tokens: bool = False ) → `List[int]` Parameters * **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 model Returns `List[int]` A list of integers in the range \[0, 1]: 1 for a special token, 0 for a sequence token. Retrieves sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the tokenizer `prepare_for_model` methods. **create\_token\_type\_ids\_from\_sequences** [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/tokenization_mpnet.py#L285) ( token\_ids\_0: typing.List\[int]token\_ids\_1: typing.Optional\[typing.List\[int]] = None ) → `List[int]` Parameters * **token\_ids\_0** (`List[int]`) — List of ids. * **token\_ids\_1** (`List[int]`, *optional*) — Optional second list of IDs for sequence pairs. Returns `List[int]` List of zeros. Creates a mask from the two sequences passed to be used in a sequence-pair classification task. MPNet does not make use of token type ids, therefore a list of zeros is returned. **save\_vocabulary** [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/tokenization_mpnet.py#L308) ( save\_directory: strfilename\_prefix: typing.Optional\[str] = None ) ### MPNetTokenizerFast #### class transformers.MPNetTokenizerFast [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/tokenization_mpnet_fast.py#L51) ( vocab\_file = Nonetokenizer\_file = Nonedo\_lower\_case = Truebos\_token = '\'eos\_token = '\'sep\_token = '\'cls\_token = '\'unk\_token = '\[UNK]'pad\_token = '\'mask\_token = '\'tokenize\_chinese\_chars = Truestrip\_accents = None\*\*kwargs ) Parameters * **vocab\_file** (`str`) — File containing the vocabulary. * **do\_lower\_case** (`bool`, *optional*, defaults to `True`) — Whether or not to lowercase the input when tokenizing. * **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. When building a sequence using special tokens, this is not the token that is used for the end of sequence. The token used is the `sep_token`. * **sep\_token** (`str`, *optional*, defaults to `""`) — 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. * **cls\_token** (`str`, *optional*, defaults to `""`) — 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. * **unk\_token** (`str`, *optional*, defaults to `"[UNK]"`) — The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead. * **pad\_token** (`str`, *optional*, defaults to `""`) — The token used for padding, for example when batching sequences of different lengths. * **mask\_token** (`str`, *optional*, defaults to `""`) — 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. * **tokenize\_chinese\_chars** (`bool`, *optional*, defaults to `True`) — Whether or not to tokenize Chinese characters. This should likely be deactivated for Japanese (see [this issue](https://github.com/huggingface/transformers/issues/328)). * **strip\_accents** (`bool`, *optional*) — Whether or not to strip all accents. If this option is not specified, then it will be determined by the value for `lowercase` (as in the original BERT). Construct a “fast” MPNet tokenizer (backed by BOINCAI’s *tokenizers* library). Based on WordPiece. This tokenizer inherits from [PreTrainedTokenizerFast](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast) which contains most of the main methods. Users should refer to this superclass for more information regarding those methods. **create\_token\_type\_ids\_from\_sequences** [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/tokenization_mpnet_fast.py#L201) ( token\_ids\_0: typing.List\[int]token\_ids\_1: typing.Optional\[typing.List\[int]] = None ) → `List[int]` Parameters * **token\_ids\_0** (`List[int]`) — List of ids. * **token\_ids\_1** (`List[int]`, *optional*) — Optional second list of IDs for sequence pairs Returns `List[int]` List of zeros. Creates a mask from the two sequences passed to be used in a sequence-pair classification task. MPNet does not make use of token type ids, therefore a list of zeros is returned ### MPNetModel #### class transformers.MPNetModel [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_mpnet.py#L483) ( configadd\_pooling\_layer = True ) Parameters * **config** ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) — 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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. The bare MPNet Model transformer outputting raw hidden-states without any specific head on top. This model inherits from [PreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/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. **forward** [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_mpnet.py#L509) ( input\_ids: typing.Optional\[torch.LongTensor] = Noneattention\_mask: typing.Optional\[torch.FloatTensor] = Noneposition\_ids: typing.Optional\[torch.LongTensor] = Nonehead\_mask: typing.Optional\[torch.FloatTensor] = Noneinputs\_embeds: typing.Optional\[torch.FloatTensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None\*\*kwargs ) → [transformers.modeling\_outputs.BaseModelOutputWithPooling](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)` Parameters * **input\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details. [What are input IDs?](https://huggingface.co/docs/transformers/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?](https://huggingface.co/docs/transformers/glossary#attention-mask) * **position\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`. [What are position IDs?](https://huggingface.co/docs/transformers/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. * **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](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. Returns [transformers.modeling\_outputs.BaseModelOutputWithPooling](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)` A [transformers.modeling\_outputs.BaseModelOutputWithPooling](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) 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 ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) 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. The [MPNetModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetModel) 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: Copied ``` >>> from transformers import AutoTokenizer, MPNetModel >>> import torch >>> tokenizer = AutoTokenizer.from_pretrained("microsoft/mpnet-base") >>> model = MPNetModel.from_pretrained("microsoft/mpnet-base") >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt") >>> outputs = model(**inputs) >>> last_hidden_states = outputs.last_hidden_state ``` ### MPNetForMaskedLM #### class transformers.MPNetForMaskedLM [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_mpnet.py#L573) ( config ) **forward** [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_mpnet.py#L591) ( input\_ids: typing.Optional\[torch.LongTensor] = Noneattention\_mask: typing.Optional\[torch.FloatTensor] = Noneposition\_ids: typing.Optional\[torch.LongTensor] = Nonehead\_mask: typing.Optional\[torch.FloatTensor] = Noneinputs\_embeds: typing.Optional\[torch.FloatTensor] = Nonelabels: typing.Optional\[torch.LongTensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.MaskedLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) or `tuple(torch.FloatTensor)` Parameters * **input\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details. [What are input IDs?](https://huggingface.co/docs/transformers/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?](https://huggingface.co/docs/transformers/glossary#attention-mask) * **position\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`. [What are position IDs?](https://huggingface.co/docs/transformers/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. * **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](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. * **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]` Returns [transformers.modeling\_outputs.MaskedLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) or `tuple(torch.FloatTensor)` A [transformers.modeling\_outputs.MaskedLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/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 ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) 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 [MPNetForMaskedLM](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetForMaskedLM) 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: Copied ``` >>> from transformers import AutoTokenizer, MPNetForMaskedLM >>> import torch >>> tokenizer = AutoTokenizer.from_pretrained("microsoft/mpnet-base") >>> model = MPNetForMaskedLM.from_pretrained("microsoft/mpnet-base") >>> inputs = tokenizer("The capital of France is [MASK].", return_tensors="pt") >>> 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) >>> labels = tokenizer("The capital of France is Paris.", return_tensors="pt")["input_ids"] >>> # mask labels of non-[MASK] tokens >>> labels = torch.where(inputs.input_ids == tokenizer.mask_token_id, labels, -100) >>> outputs = model(**inputs, labels=labels) ``` ### MPNetForSequenceClassification #### class transformers.MPNetForSequenceClassification [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_mpnet.py#L680) ( config ) Parameters * **config** ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) — 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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. MPNet 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](https://huggingface.co/docs/transformers/v4.34.1/en/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. **forward** [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_mpnet.py#L691) ( input\_ids: typing.Optional\[torch.LongTensor] = Noneattention\_mask: typing.Optional\[torch.FloatTensor] = Noneposition\_ids: typing.Optional\[torch.LongTensor] = Nonehead\_mask: typing.Optional\[torch.FloatTensor] = Noneinputs\_embeds: typing.Optional\[torch.FloatTensor] = Nonelabels: typing.Optional\[torch.LongTensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.SequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) or `tuple(torch.FloatTensor)` Parameters * **input\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details. [What are input IDs?](https://huggingface.co/docs/transformers/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?](https://huggingface.co/docs/transformers/glossary#attention-mask) * **position\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`. [What are position IDs?](https://huggingface.co/docs/transformers/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. * **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](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. * **labels** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) — Labels for computing the sequence classification/regression loss. Indices should be in `[0, ..., config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If `config.num_labels > 1` a classification loss is computed (Cross-Entropy). Returns [transformers.modeling\_outputs.SequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) or `tuple(torch.FloatTensor)` A [transformers.modeling\_outputs.SequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/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 ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) 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 [MPNetForSequenceClassification](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetForSequenceClassification) forward method, overrides the `__call__` special method. Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them. Example of single-label classification: Copied ``` >>> import torch >>> from transformers import AutoTokenizer, MPNetForSequenceClassification >>> tokenizer = AutoTokenizer.from_pretrained("microsoft/mpnet-base") >>> model = MPNetForSequenceClassification.from_pretrained("microsoft/mpnet-base") >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt") >>> with torch.no_grad(): ... logits = model(**inputs).logits >>> predicted_class_id = logits.argmax().item() >>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)` >>> num_labels = len(model.config.id2label) >>> model = MPNetForSequenceClassification.from_pretrained("microsoft/mpnet-base", num_labels=num_labels) >>> labels = torch.tensor([1]) >>> loss = model(**inputs, labels=labels).loss ``` Example of multi-label classification: Copied ``` >>> import torch >>> from transformers import AutoTokenizer, MPNetForSequenceClassification >>> tokenizer = AutoTokenizer.from_pretrained("microsoft/mpnet-base") >>> model = MPNetForSequenceClassification.from_pretrained("microsoft/mpnet-base", problem_type="multi_label_classification") >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt") >>> with torch.no_grad(): ... logits = model(**inputs).logits >>> predicted_class_ids = torch.arange(0, logits.shape[-1])[torch.sigmoid(logits).squeeze(dim=0) > 0.5] >>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)` >>> num_labels = len(model.config.id2label) >>> model = MPNetForSequenceClassification.from_pretrained( ... "microsoft/mpnet-base", num_labels=num_labels, problem_type="multi_label_classification" ... ) >>> labels = torch.sum( ... torch.nn.functional.one_hot(predicted_class_ids[None, :].clone(), num_classes=num_labels), dim=1 ... ).to(torch.float) >>> loss = model(**inputs, labels=labels).loss ``` ### MPNetForMultipleChoice #### class transformers.MPNetForMultipleChoice [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_mpnet.py#L772) ( config ) Parameters * **config** ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) — 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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. MPNet 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](https://huggingface.co/docs/transformers/v4.34.1/en/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. **forward** [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_mpnet.py#L783) ( input\_ids: typing.Optional\[torch.LongTensor] = Noneattention\_mask: typing.Optional\[torch.FloatTensor] = Noneposition\_ids: typing.Optional\[torch.LongTensor] = Nonehead\_mask: typing.Optional\[torch.FloatTensor] = Noneinputs\_embeds: typing.Optional\[torch.FloatTensor] = Nonelabels: typing.Optional\[torch.LongTensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.MultipleChoiceModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.MultipleChoiceModelOutput) or `tuple(torch.FloatTensor)` Parameters * **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](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details. [What are input IDs?](https://huggingface.co/docs/transformers/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?](https://huggingface.co/docs/transformers/glossary#attention-mask) * **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?](https://huggingface.co/docs/transformers/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. * **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](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. * **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) Returns [transformers.modeling\_outputs.MultipleChoiceModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.MultipleChoiceModelOutput) or `tuple(torch.FloatTensor)` A [transformers.modeling\_outputs.MultipleChoiceModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/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 ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) 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 [MPNetForMultipleChoice](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetForMultipleChoice) 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: Copied ``` >>> from transformers import AutoTokenizer, MPNetForMultipleChoice >>> import torch >>> tokenizer = AutoTokenizer.from_pretrained("microsoft/mpnet-base") >>> model = MPNetForMultipleChoice.from_pretrained("microsoft/mpnet-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 ``` ### MPNetForTokenClassification #### class transformers.MPNetForTokenClassification [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_mpnet.py#L860) ( config ) Parameters * **config** ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) — 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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. MPNet Model with a token classification head on top (a linear layer on top of the hidden-states output) e.g. for Named-Entity-Recognition (NER) tasks. This model inherits from [PreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/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. **forward** [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_mpnet.py#L872) ( input\_ids: typing.Optional\[torch.LongTensor] = Noneattention\_mask: typing.Optional\[torch.FloatTensor] = Noneposition\_ids: typing.Optional\[torch.LongTensor] = Nonehead\_mask: typing.Optional\[torch.FloatTensor] = Noneinputs\_embeds: typing.Optional\[torch.FloatTensor] = Nonelabels: typing.Optional\[torch.LongTensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.TokenClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or `tuple(torch.FloatTensor)` Parameters * **input\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details. [What are input IDs?](https://huggingface.co/docs/transformers/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?](https://huggingface.co/docs/transformers/glossary#attention-mask) * **position\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`. [What are position IDs?](https://huggingface.co/docs/transformers/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. * **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](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. * **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]`. Returns [transformers.modeling\_outputs.TokenClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or `tuple(torch.FloatTensor)` A [transformers.modeling\_outputs.TokenClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/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 ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) 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 [MPNetForTokenClassification](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetForTokenClassification) 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: Copied ``` >>> from transformers import AutoTokenizer, MPNetForTokenClassification >>> import torch >>> tokenizer = AutoTokenizer.from_pretrained("microsoft/mpnet-base") >>> model = MPNetForTokenClassification.from_pretrained("microsoft/mpnet-base") >>> inputs = tokenizer( ... "BOINCAI is a company based in Paris and New York", add_special_tokens=False, return_tensors="pt" ... ) >>> with torch.no_grad(): ... logits = model(**inputs).logits >>> predicted_token_class_ids = logits.argmax(-1) >>> # Note that tokens are classified rather then input words which means that >>> # there might be more predicted token classes than words. >>> # Multiple token classes might account for the same word >>> predicted_tokens_classes = [model.config.id2label[t.item()] for t in predicted_token_class_ids[0]] >>> labels = predicted_token_class_ids >>> loss = model(**inputs, labels=labels).loss ``` ### MPNetForQuestionAnswering #### class transformers.MPNetForQuestionAnswering [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_mpnet.py#L956) ( config ) Parameters * **config** ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) — 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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. MPNet 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 [PreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/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. **forward** [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_mpnet.py#L967) ( input\_ids: typing.Optional\[torch.LongTensor] = Noneattention\_mask: typing.Optional\[torch.FloatTensor] = Noneposition\_ids: typing.Optional\[torch.LongTensor] = Nonehead\_mask: typing.Optional\[torch.FloatTensor] = Noneinputs\_embeds: typing.Optional\[torch.FloatTensor] = Nonestart\_positions: typing.Optional\[torch.LongTensor] = Noneend\_positions: typing.Optional\[torch.LongTensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.QuestionAnsweringModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.QuestionAnsweringModelOutput) or `tuple(torch.FloatTensor)` Parameters * **input\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details. [What are input IDs?](https://huggingface.co/docs/transformers/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?](https://huggingface.co/docs/transformers/glossary#attention-mask) * **position\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`. [What are position IDs?](https://huggingface.co/docs/transformers/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. * **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](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. * **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. Returns [transformers.modeling\_outputs.QuestionAnsweringModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.QuestionAnsweringModelOutput) or `tuple(torch.FloatTensor)` A [transformers.modeling\_outputs.QuestionAnsweringModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.QuestionAnsweringModelOutput) 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 ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) 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)`) — Span-start scores (before SoftMax). * **end\_logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`) — Span-end 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 [MPNetForQuestionAnswering](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetForQuestionAnswering) 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: Copied ``` >>> from transformers import AutoTokenizer, MPNetForQuestionAnswering >>> import torch >>> tokenizer = AutoTokenizer.from_pretrained("microsoft/mpnet-base") >>> model = MPNetForQuestionAnswering.from_pretrained("microsoft/mpnet-base") >>> question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet" >>> inputs = tokenizer(question, text, return_tensors="pt") >>> with torch.no_grad(): ... outputs = model(**inputs) >>> answer_start_index = outputs.start_logits.argmax() >>> answer_end_index = outputs.end_logits.argmax() >>> predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1] >>> # target is "nice puppet" >>> target_start_index = torch.tensor([14]) >>> target_end_index = torch.tensor([15]) >>> outputs = model(**inputs, start_positions=target_start_index, end_positions=target_end_index) >>> loss = outputs.loss ``` ### TFMPNetModel #### class transformers.TFMPNetModel [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_tf_mpnet.py#L659) ( \*args\*\*kwargs ) Parameters * **config** ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) — 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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. The bare MPNet Model transformer outputting raw hidden-states without any specific head on top. This model inherits from [TFPreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.TFPreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a [tf.keras.Model](https://www.tensorflow.org/api_docs/python/tf/keras/Model) subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior. TensorFlow models and layers in `transformers` accept two formats as input: * having all inputs as keyword arguments (like PyTorch models), or * having all inputs as a list, tuple or dict in the first positional argument. The reason the second format is supported is that Keras methods prefer this format when passing inputs to models and layers. Because of this support, when using methods like `model.fit()` things should “just work” for you - just pass your inputs and labels in any format that `model.fit()` supports! If, however, you want to use the second format outside of Keras methods like `fit()` and `predict()`, such as when creating your own layers or models with the Keras `Functional` API, there are three possibilities you can use to gather all the input Tensors in the first positional argument: * a single Tensor with `input_ids` only and nothing else: `model(input_ids)` * a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: `model([input_ids, attention_mask])` or `model([input_ids, attention_mask, token_type_ids])` * a dictionary with one or several input Tensors associated to the input names given in the docstring: `model({"input_ids": input_ids, "token_type_ids": token_type_ids})` Note that when creating models and layers with [subclassing](https://keras.io/guides/making_new_layers_and_models_via_subclassing/) then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function! **call** [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_tf_mpnet.py#L664) ( input\_ids: TFModelInputType | None = Noneattention\_mask: Optional\[Union\[np.array, tf.Tensor]] = Noneposition\_ids: Optional\[Union\[np.array, tf.Tensor]] = Nonehead\_mask: Optional\[Union\[np.array, tf.Tensor]] = Noneinputs\_embeds: tf.Tensor | None = Noneoutput\_attentions: Optional\[bool] = Noneoutput\_hidden\_states: Optional\[bool] = Nonereturn\_dict: Optional\[bool] = Nonetraining: bool = False ) → [transformers.modeling\_tf\_outputs.TFBaseModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFBaseModelOutput) or `tuple(tf.Tensor)` Parameters * **input\_ids** (`Numpy array` or `tf.Tensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) and [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) for details. [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids) * **attention\_mask** (`Numpy array` or `tf.Tensor` 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?](https://huggingface.co/docs/transformers/glossary#attention-mask) * **position\_ids** (`Numpy array` or `tf.Tensor` 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]`. [What are position IDs?](https://huggingface.co/docs/transformers/glossary#position-ids) * **head\_mask** (`Numpy array` or `tf.Tensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`: * 1 indicates the head is **not masked**, * 0 indicates the head is **masked**. * **inputs\_embeds** (`tf.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) — Optionally, instead of 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. * **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead. * **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead. * **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True. * **training** (`bool`, *optional*, defaults to `False`) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation). Returns [transformers.modeling\_tf\_outputs.TFBaseModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFBaseModelOutput) or `tuple(tf.Tensor)` A [transformers.modeling\_tf\_outputs.TFBaseModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFBaseModelOutput) or a tuple of `tf.Tensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) and inputs. * **last\_hidden\_state** (`tf.Tensor` of shape `(batch_size, sequence_length, hidden_size)`) — Sequence of hidden-states at the output of the last layer of the model. * **hidden\_states** (`tuple(tf.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the initial embedding outputs. * **attentions** (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. The [TFMPNetModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.TFMPNetModel) 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: Copied ``` >>> from transformers import AutoTokenizer, TFMPNetModel >>> import tensorflow as tf >>> tokenizer = AutoTokenizer.from_pretrained("microsoft/mpnet-base") >>> model = TFMPNetModel.from_pretrained("microsoft/mpnet-base") >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="tf") >>> outputs = model(inputs) >>> last_hidden_states = outputs.last_hidden_state ``` ### TFMPNetForMaskedLM #### class transformers.TFMPNetForMaskedLM [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_tf_mpnet.py#L750) ( \*args\*\*kwargs ) Parameters * **config** ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) — 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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. MPNet Model with a `language modeling` head on top. This model inherits from [TFPreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.TFPreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a [tf.keras.Model](https://www.tensorflow.org/api_docs/python/tf/keras/Model) subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior. TensorFlow models and layers in `transformers` accept two formats as input: * having all inputs as keyword arguments (like PyTorch models), or * having all inputs as a list, tuple or dict in the first positional argument. The reason the second format is supported is that Keras methods prefer this format when passing inputs to models and layers. Because of this support, when using methods like `model.fit()` things should “just work” for you - just pass your inputs and labels in any format that `model.fit()` supports! If, however, you want to use the second format outside of Keras methods like `fit()` and `predict()`, such as when creating your own layers or models with the Keras `Functional` API, there are three possibilities you can use to gather all the input Tensors in the first positional argument: * a single Tensor with `input_ids` only and nothing else: `model(input_ids)` * a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: `model([input_ids, attention_mask])` or `model([input_ids, attention_mask, token_type_ids])` * a dictionary with one or several input Tensors associated to the input names given in the docstring: `model({"input_ids": input_ids, "token_type_ids": token_type_ids})` Note that when creating models and layers with [subclassing](https://keras.io/guides/making_new_layers_and_models_via_subclassing/) then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function! **call** [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_tf_mpnet.py#L766) ( input\_ids: TFModelInputType | None = Noneattention\_mask: np.ndarray | tf.Tensor | None = Noneposition\_ids: np.ndarray | tf.Tensor | None = Nonehead\_mask: np.ndarray | tf.Tensor | None = Noneinputs\_embeds: tf.Tensor | None = Noneoutput\_attentions: Optional\[bool] = Noneoutput\_hidden\_states: Optional\[bool] = Nonereturn\_dict: Optional\[bool] = Nonelabels: tf.Tensor | None = Nonetraining: bool = False ) → [transformers.modeling\_tf\_outputs.TFMaskedLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFMaskedLMOutput) or `tuple(tf.Tensor)` Parameters * **input\_ids** (`Numpy array` or `tf.Tensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) and [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) for details. [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids) * **attention\_mask** (`Numpy array` or `tf.Tensor` 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?](https://huggingface.co/docs/transformers/glossary#attention-mask) * **position\_ids** (`Numpy array` or `tf.Tensor` 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]`. [What are position IDs?](https://huggingface.co/docs/transformers/glossary#position-ids) * **head\_mask** (`Numpy array` or `tf.Tensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`: * 1 indicates the head is **not masked**, * 0 indicates the head is **masked**. * **inputs\_embeds** (`tf.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) — Optionally, instead of 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. * **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead. * **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead. * **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True. * **training** (`bool`, *optional*, defaults to `False`) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation). * **labels** (`tf.Tensor` of shape `(batch_size, sequence_length)`, *optional*) — Labels for computing the 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]` Returns [transformers.modeling\_tf\_outputs.TFMaskedLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFMaskedLMOutput) or `tuple(tf.Tensor)` A [transformers.modeling\_tf\_outputs.TFMaskedLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFMaskedLMOutput) or a tuple of `tf.Tensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) and inputs. * **loss** (`tf.Tensor` of shape `(n,)`, *optional*, where n is the number of non-masked labels, returned when `labels` is provided) — Masked language modeling (MLM) loss. * **logits** (`tf.Tensor` of shape `(batch_size, sequence_length, config.vocab_size)`) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). * **hidden\_states** (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the initial embedding outputs. * **attentions** (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. The [TFMPNetForMaskedLM](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.TFMPNetForMaskedLM) 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: Copied ``` >>> from transformers import AutoTokenizer, TFMPNetForMaskedLM >>> import tensorflow as tf >>> tokenizer = AutoTokenizer.from_pretrained("microsoft/mpnet-base") >>> model = TFMPNetForMaskedLM.from_pretrained("microsoft/mpnet-base") >>> inputs = tokenizer("The capital of France is [MASK].", return_tensors="tf") >>> logits = model(**inputs).logits >>> # retrieve index of [MASK] >>> mask_token_index = tf.where((inputs.input_ids == tokenizer.mask_token_id)[0]) >>> selected_logits = tf.gather_nd(logits[0], indices=mask_token_index) >>> predicted_token_id = tf.math.argmax(selected_logits, axis=-1) ``` Copied ``` >>> labels = tokenizer("The capital of France is Paris.", return_tensors="tf")["input_ids"] >>> # mask labels of non-[MASK] tokens >>> labels = tf.where(inputs.input_ids == tokenizer.mask_token_id, labels, -100) >>> outputs = model(**inputs, labels=labels) ``` ### TFMPNetForSequenceClassification #### class transformers.TFMPNetForSequenceClassification [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_tf_mpnet.py#L852) ( \*args\*\*kwargs ) Parameters * **config** ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) — 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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. MPNet 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 [TFPreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.TFPreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a [tf.keras.Model](https://www.tensorflow.org/api_docs/python/tf/keras/Model) subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior. TensorFlow models and layers in `transformers` accept two formats as input: * having all inputs as keyword arguments (like PyTorch models), or * having all inputs as a list, tuple or dict in the first positional argument. The reason the second format is supported is that Keras methods prefer this format when passing inputs to models and layers. Because of this support, when using methods like `model.fit()` things should “just work” for you - just pass your inputs and labels in any format that `model.fit()` supports! If, however, you want to use the second format outside of Keras methods like `fit()` and `predict()`, such as when creating your own layers or models with the Keras `Functional` API, there are three possibilities you can use to gather all the input Tensors in the first positional argument: * a single Tensor with `input_ids` only and nothing else: `model(input_ids)` * a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: `model([input_ids, attention_mask])` or `model([input_ids, attention_mask, token_type_ids])` * a dictionary with one or several input Tensors associated to the input names given in the docstring: `model({"input_ids": input_ids, "token_type_ids": token_type_ids})` Note that when creating models and layers with [subclassing](https://keras.io/guides/making_new_layers_and_models_via_subclassing/) then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function! **call** [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_tf_mpnet.py#L862) ( input\_ids: TFModelInputType | None = Noneattention\_mask: Optional\[Union\[np.array, tf.Tensor]] = Noneposition\_ids: Optional\[Union\[np.array, tf.Tensor]] = Nonehead\_mask: Optional\[Union\[np.array, tf.Tensor]] = Noneinputs\_embeds: tf.Tensor | None = Noneoutput\_attentions: Optional\[bool] = Noneoutput\_hidden\_states: Optional\[bool] = Nonereturn\_dict: Optional\[bool] = Nonelabels: tf.Tensor | None = Nonetraining: bool = False ) → [transformers.modeling\_tf\_outputs.TFSequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFSequenceClassifierOutput) or `tuple(tf.Tensor)` Parameters * **input\_ids** (`Numpy array` or `tf.Tensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) and [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) for details. [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids) * **attention\_mask** (`Numpy array` or `tf.Tensor` 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?](https://huggingface.co/docs/transformers/glossary#attention-mask) * **position\_ids** (`Numpy array` or `tf.Tensor` 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]`. [What are position IDs?](https://huggingface.co/docs/transformers/glossary#position-ids) * **head\_mask** (`Numpy array` or `tf.Tensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`: * 1 indicates the head is **not masked**, * 0 indicates the head is **masked**. * **inputs\_embeds** (`tf.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) — Optionally, instead of 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. * **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead. * **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead. * **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True. * **training** (`bool`, *optional*, defaults to `False`) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation). * **labels** (`tf.Tensor` of shape `(batch_size,)`, *optional*) — Labels for computing the sequence classification/regression loss. Indices should be in `[0, ..., config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If `config.num_labels > 1` a classification loss is computed (Cross-Entropy). Returns [transformers.modeling\_tf\_outputs.TFSequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFSequenceClassifierOutput) or `tuple(tf.Tensor)` A [transformers.modeling\_tf\_outputs.TFSequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFSequenceClassifierOutput) or a tuple of `tf.Tensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) and inputs. * **loss** (`tf.Tensor` of shape `(batch_size, )`, *optional*, returned when `labels` is provided) — Classification (or regression if config.num\_labels==1) loss. * **logits** (`tf.Tensor` of shape `(batch_size, config.num_labels)`) — Classification (or regression if config.num\_labels==1) scores (before SoftMax). * **hidden\_states** (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the initial embedding outputs. * **attentions** (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. The [TFMPNetForSequenceClassification](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.TFMPNetForSequenceClassification) 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: Copied ``` >>> from transformers import AutoTokenizer, TFMPNetForSequenceClassification >>> import tensorflow as tf >>> tokenizer = AutoTokenizer.from_pretrained("microsoft/mpnet-base") >>> model = TFMPNetForSequenceClassification.from_pretrained("microsoft/mpnet-base") >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="tf") >>> logits = model(**inputs).logits >>> predicted_class_id = int(tf.math.argmax(logits, axis=-1)[0]) ``` Copied ``` >>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)` >>> num_labels = len(model.config.id2label) >>> model = TFMPNetForSequenceClassification.from_pretrained("microsoft/mpnet-base", num_labels=num_labels) >>> labels = tf.constant(1) >>> loss = model(**inputs, labels=labels).loss ``` ### TFMPNetForMultipleChoice #### class transformers.TFMPNetForMultipleChoice [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_tf_mpnet.py#L924) ( \*args\*\*kwargs ) Parameters * **config** ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) — 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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. MPNet 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 [TFPreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.TFPreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a [tf.keras.Model](https://www.tensorflow.org/api_docs/python/tf/keras/Model) subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior. TensorFlow models and layers in `transformers` accept two formats as input: * having all inputs as keyword arguments (like PyTorch models), or * having all inputs as a list, tuple or dict in the first positional argument. The reason the second format is supported is that Keras methods prefer this format when passing inputs to models and layers. Because of this support, when using methods like `model.fit()` things should “just work” for you - just pass your inputs and labels in any format that `model.fit()` supports! If, however, you want to use the second format outside of Keras methods like `fit()` and `predict()`, such as when creating your own layers or models with the Keras `Functional` API, there are three possibilities you can use to gather all the input Tensors in the first positional argument: * a single Tensor with `input_ids` only and nothing else: `model(input_ids)` * a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: `model([input_ids, attention_mask])` or `model([input_ids, attention_mask, token_type_ids])` * a dictionary with one or several input Tensors associated to the input names given in the docstring: `model({"input_ids": input_ids, "token_type_ids": token_type_ids})` Note that when creating models and layers with [subclassing](https://keras.io/guides/making_new_layers_and_models_via_subclassing/) then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function! **call** [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_tf_mpnet.py#L934) ( input\_ids: TFModelInputType | None = Noneattention\_mask: np.ndarray | tf.Tensor | None = Noneposition\_ids: np.ndarray | tf.Tensor | None = Nonehead\_mask: np.ndarray | tf.Tensor | None = Noneinputs\_embeds: tf.Tensor | None = Noneoutput\_attentions: Optional\[bool] = Noneoutput\_hidden\_states: Optional\[bool] = Nonereturn\_dict: Optional\[bool] = Nonelabels: tf.Tensor | None = Nonetraining: bool = False ) → [transformers.modeling\_tf\_outputs.TFMultipleChoiceModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFMultipleChoiceModelOutput) or `tuple(tf.Tensor)` Parameters * **input\_ids** (`Numpy array` or `tf.Tensor` of shape `(batch_size, num_choices, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) and [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) for details. [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids) * **attention\_mask** (`Numpy array` or `tf.Tensor` 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?](https://huggingface.co/docs/transformers/glossary#attention-mask) * **position\_ids** (`Numpy array` or `tf.Tensor` 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?](https://huggingface.co/docs/transformers/glossary#position-ids) * **head\_mask** (`Numpy array` or `tf.Tensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`: * 1 indicates the head is **not masked**, * 0 indicates the head is **masked**. * **inputs\_embeds** (`tf.Tensor` of shape `(batch_size, 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. * **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead. * **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead. * **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True. * **training** (`bool`, *optional*, defaults to `False`) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation). * **labels** (`tf.Tensor` of shape `(batch_size,)`, *optional*) — Labels for computing the multiple choice classification loss. Indices should be in `[0, ..., num_choices]` where `num_choices` is the size of the second dimension of the input tensors. (See `input_ids` above) Returns [transformers.modeling\_tf\_outputs.TFMultipleChoiceModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFMultipleChoiceModelOutput) or `tuple(tf.Tensor)` A [transformers.modeling\_tf\_outputs.TFMultipleChoiceModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFMultipleChoiceModelOutput) or a tuple of `tf.Tensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) and inputs. * **loss** (`tf.Tensor` of shape *(batch\_size, )*, *optional*, returned when `labels` is provided) — Classification loss. * **logits** (`tf.Tensor` 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(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the initial embedding outputs. * **attentions** (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. The [TFMPNetForMultipleChoice](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.TFMPNetForMultipleChoice) 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: Copied ``` >>> from transformers import AutoTokenizer, TFMPNetForMultipleChoice >>> import tensorflow as tf >>> tokenizer = AutoTokenizer.from_pretrained("microsoft/mpnet-base") >>> model = TFMPNetForMultipleChoice.from_pretrained("microsoft/mpnet-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="tf", padding=True) >>> inputs = {k: tf.expand_dims(v, 0) for k, v in encoding.items()} >>> outputs = model(inputs) # batch size is 1 >>> # the linear classifier still needs to be trained >>> logits = outputs.logits ``` ### TFMPNetForTokenClassification #### class transformers.TFMPNetForTokenClassification [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_tf_mpnet.py#L1010) ( \*args\*\*kwargs ) Parameters * **config** ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) — 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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. MPNet 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 [TFPreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.TFPreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a [tf.keras.Model](https://www.tensorflow.org/api_docs/python/tf/keras/Model) subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior. TensorFlow models and layers in `transformers` accept two formats as input: * having all inputs as keyword arguments (like PyTorch models), or * having all inputs as a list, tuple or dict in the first positional argument. The reason the second format is supported is that Keras methods prefer this format when passing inputs to models and layers. Because of this support, when using methods like `model.fit()` things should “just work” for you - just pass your inputs and labels in any format that `model.fit()` supports! If, however, you want to use the second format outside of Keras methods like `fit()` and `predict()`, such as when creating your own layers or models with the Keras `Functional` API, there are three possibilities you can use to gather all the input Tensors in the first positional argument: * a single Tensor with `input_ids` only and nothing else: `model(input_ids)` * a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: `model([input_ids, attention_mask])` or `model([input_ids, attention_mask, token_type_ids])` * a dictionary with one or several input Tensors associated to the input names given in the docstring: `model({"input_ids": input_ids, "token_type_ids": token_type_ids})` Note that when creating models and layers with [subclassing](https://keras.io/guides/making_new_layers_and_models_via_subclassing/) then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function! **call** [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_tf_mpnet.py#L1023) ( input\_ids: TFModelInputType | None = Noneattention\_mask: np.ndarray | tf.Tensor | None = Noneposition\_ids: np.ndarray | tf.Tensor | None = Nonehead\_mask: np.ndarray | tf.Tensor | None = Noneinputs\_embeds: tf.Tensor | None = Noneoutput\_attentions: Optional\[bool] = Noneoutput\_hidden\_states: Optional\[bool] = Nonereturn\_dict: Optional\[bool] = Nonelabels: tf.Tensor | None = Nonetraining: bool = False ) → [transformers.modeling\_tf\_outputs.TFTokenClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFTokenClassifierOutput) or `tuple(tf.Tensor)` Parameters * **input\_ids** (`Numpy array` or `tf.Tensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) and [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) for details. [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids) * **attention\_mask** (`Numpy array` or `tf.Tensor` 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?](https://huggingface.co/docs/transformers/glossary#attention-mask) * **position\_ids** (`Numpy array` or `tf.Tensor` 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]`. [What are position IDs?](https://huggingface.co/docs/transformers/glossary#position-ids) * **head\_mask** (`Numpy array` or `tf.Tensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`: * 1 indicates the head is **not masked**, * 0 indicates the head is **masked**. * **inputs\_embeds** (`tf.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) — Optionally, instead of 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. * **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead. * **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead. * **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True. * **training** (`bool`, *optional*, defaults to `False`) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation). * **labels** (`tf.Tensor` of shape `(batch_size, sequence_length)`, *optional*) — Labels for computing the token classification loss. Indices should be in `[0, ..., config.num_labels - 1]`. Returns [transformers.modeling\_tf\_outputs.TFTokenClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFTokenClassifierOutput) or `tuple(tf.Tensor)` A [transformers.modeling\_tf\_outputs.TFTokenClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFTokenClassifierOutput) or a tuple of `tf.Tensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) and inputs. * **loss** (`tf.Tensor` of shape `(n,)`, *optional*, where n is the number of unmasked labels, returned when `labels` is provided) — Classification loss. * **logits** (`tf.Tensor` of shape `(batch_size, sequence_length, config.num_labels)`) — Classification scores (before SoftMax). * **hidden\_states** (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the initial embedding outputs. * **attentions** (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. The [TFMPNetForTokenClassification](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.TFMPNetForTokenClassification) 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: Copied ``` >>> from transformers import AutoTokenizer, TFMPNetForTokenClassification >>> import tensorflow as tf >>> tokenizer = AutoTokenizer.from_pretrained("microsoft/mpnet-base") >>> model = TFMPNetForTokenClassification.from_pretrained("microsoft/mpnet-base") >>> inputs = tokenizer( ... "BOINCAI is a company based in Paris and New York", add_special_tokens=False, return_tensors="tf" ... ) >>> logits = model(**inputs).logits >>> predicted_token_class_ids = tf.math.argmax(logits, axis=-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] for t in predicted_token_class_ids[0].numpy().tolist()] ``` Copied ``` >>> labels = predicted_token_class_ids >>> loss = tf.math.reduce_mean(model(**inputs, labels=labels).loss) ``` ### TFMPNetForQuestionAnswering #### class transformers.TFMPNetForQuestionAnswering [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_tf_mpnet.py#L1084) ( \*args\*\*kwargs ) Parameters * **config** ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) — 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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. MPNet 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 [TFPreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.TFPreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a [tf.keras.Model](https://www.tensorflow.org/api_docs/python/tf/keras/Model) subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior. TensorFlow models and layers in `transformers` accept two formats as input: * having all inputs as keyword arguments (like PyTorch models), or * having all inputs as a list, tuple or dict in the first positional argument. The reason the second format is supported is that Keras methods prefer this format when passing inputs to models and layers. Because of this support, when using methods like `model.fit()` things should “just work” for you - just pass your inputs and labels in any format that `model.fit()` supports! If, however, you want to use the second format outside of Keras methods like `fit()` and `predict()`, such as when creating your own layers or models with the Keras `Functional` API, there are three possibilities you can use to gather all the input Tensors in the first positional argument: * a single Tensor with `input_ids` only and nothing else: `model(input_ids)` * a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: `model([input_ids, attention_mask])` or `model([input_ids, attention_mask, token_type_ids])` * a dictionary with one or several input Tensors associated to the input names given in the docstring: `model({"input_ids": input_ids, "token_type_ids": token_type_ids})` Note that when creating models and layers with [subclassing](https://keras.io/guides/making_new_layers_and_models_via_subclassing/) then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function! **call** [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/mpnet/modeling_tf_mpnet.py#L1096) ( input\_ids: TFModelInputType | None = Noneattention\_mask: Optional\[Union\[np.array, tf.Tensor]] = Noneposition\_ids: Optional\[Union\[np.array, tf.Tensor]] = Nonehead\_mask: Optional\[Union\[np.array, tf.Tensor]] = Noneinputs\_embeds: tf.Tensor | None = Noneoutput\_attentions: Optional\[bool] = Noneoutput\_hidden\_states: Optional\[bool] = Nonereturn\_dict: Optional\[bool] = Nonestart\_positions: tf.Tensor | None = Noneend\_positions: tf.Tensor | None = Nonetraining: bool = False\*\*kwargs ) → [transformers.modeling\_tf\_outputs.TFQuestionAnsweringModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFQuestionAnsweringModelOutput) or `tuple(tf.Tensor)` Parameters * **input\_ids** (`Numpy array` or `tf.Tensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) and [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) for details. [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids) * **attention\_mask** (`Numpy array` or `tf.Tensor` 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?](https://huggingface.co/docs/transformers/glossary#attention-mask) * **position\_ids** (`Numpy array` or `tf.Tensor` 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]`. [What are position IDs?](https://huggingface.co/docs/transformers/glossary#position-ids) * **head\_mask** (`Numpy array` or `tf.Tensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`: * 1 indicates the head is **not masked**, * 0 indicates the head is **masked**. * **inputs\_embeds** (`tf.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) — Optionally, instead of 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. * **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead. * **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead. * **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True. * **training** (`bool`, *optional*, defaults to `False`) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation). * **start\_positions** (`tf.Tensor` 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** (`tf.Tensor` 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. Returns [transformers.modeling\_tf\_outputs.TFQuestionAnsweringModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFQuestionAnsweringModelOutput) or `tuple(tf.Tensor)` A [transformers.modeling\_tf\_outputs.TFQuestionAnsweringModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFQuestionAnsweringModelOutput) or a tuple of `tf.Tensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([MPNetConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.MPNetConfig)) and inputs. * **loss** (`tf.Tensor` of shape `(batch_size, )`, *optional*, returned when `start_positions` and `end_positions` are provided) — Total span extraction loss is the sum of a Cross-Entropy for the start and end positions. * **start\_logits** (`tf.Tensor` of shape `(batch_size, sequence_length)`) — Span-start scores (before SoftMax). * **end\_logits** (`tf.Tensor` of shape `(batch_size, sequence_length)`) — Span-end scores (before SoftMax). * **hidden\_states** (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the initial embedding outputs. * **attentions** (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. The [TFMPNetForQuestionAnswering](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mpnet#transformers.TFMPNetForQuestionAnswering) 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: Copied ``` >>> from transformers import AutoTokenizer, TFMPNetForQuestionAnswering >>> import tensorflow as tf >>> tokenizer = AutoTokenizer.from_pretrained("microsoft/mpnet-base") >>> model = TFMPNetForQuestionAnswering.from_pretrained("microsoft/mpnet-base") >>> question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet" >>> inputs = tokenizer(question, text, return_tensors="tf") >>> outputs = model(**inputs) >>> answer_start_index = int(tf.math.argmax(outputs.start_logits, axis=-1)[0]) >>> answer_end_index = int(tf.math.argmax(outputs.end_logits, axis=-1)[0]) >>> predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1] ``` Copied ``` >>> # target is "nice puppet" >>> target_start_index = tf.constant([14]) >>> target_end_index = tf.constant([15]) >>> outputs = model(**inputs, start_positions=target_start_index, end_positions=target_end_index) >>> loss = tf.math.reduce_mean(outputs.loss) ``` --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://boinc-ai.gitbook.io/transformers/api/models/text-models/mpnet.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.