# ProphetNet

## Overview

The ProphetNet model was proposed in [ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training,](https://huggingface.co/papers/2001.04063) by Yu Yan, Weizhen Qi, Yeyun Gong, Dayiheng Liu, Nan Duan, Jiusheng Chen, Ruofei
Zhang, Ming Zhou on 13 Jan, 2020.

ProphetNet is an encoder-decoder model and can predict n-future tokens for "ngram" language modeling instead of just
the next token.

The abstract from the paper is the following:

*In this paper, we present a new sequence-to-sequence pretraining model called ProphetNet, which introduces a novel
self-supervised objective named future n-gram prediction and the proposed n-stream self-attention mechanism. Instead of
the optimization of one-step ahead prediction in traditional sequence-to-sequence model, the ProphetNet is optimized by
n-step ahead prediction which predicts the next n tokens simultaneously based on previous context tokens at each time
step. The future n-gram prediction explicitly encourages the model to plan for the future tokens and prevent
overfitting on strong local correlations. We pre-train ProphetNet using a base scale dataset (16GB) and a large scale
dataset (160GB) respectively. Then we conduct experiments on CNN/DailyMail, Gigaword, and SQuAD 1.1 benchmarks for
abstractive summarization and question generation tasks. Experimental results show that ProphetNet achieves new
state-of-the-art results on all these datasets compared to the models using the same scale pretraining corpus.*

The Authors' code can be found [here](https://github.com/microsoft/ProphetNet).

## Usage tips

- ProphetNet is a model with absolute position embeddings so it's usually advised to pad the inputs on the right rather than
  the left.
- The model architecture is based on the original Transformer, but replaces the “standard” self-attention mechanism in the decoder by a main self-attention mechanism and a self and n-stream (predict) self-attention mechanism.

## Resources

- [Causal language modeling task guide](../tasks/language_modeling)
- [Translation task guide](../tasks/translation)
- [Summarization task guide](../tasks/summarization)

## ProphetNetConfig[[transformers.ProphetNetConfig]]

#### transformers.ProphetNetConfig[[transformers.ProphetNetConfig]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/prophetnet/configuration_prophetnet.py#L24)

This is the configuration class to store the configuration of a ProphetNetModel. It is used to instantiate a Prophetnet
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 [microsoft/prophetnet-large-uncased](https://huggingface.co/microsoft/prophetnet-large-uncased)

Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.8.0/en/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the
documentation from [PreTrainedConfig](/docs/transformers/v5.8.0/en/main_classes/configuration#transformers.PreTrainedConfig) for more information.

**Parameters:**

is_encoder_decoder (`bool`, *optional*, defaults to `True`) : Whether the model is used as an encoder/decoder or not.

activation_dropout (`Union[float, int]`, *optional*, defaults to `0.1`) : The dropout ratio for activations inside the fully connected layer.

activation_function (`str`, *optional*, defaults to `gelu`) : The non-linear activation function (function or string) in the decoder. For example, `"gelu"`, `"relu"`, `"silu"`, etc.

vocab_size (`int`, *optional*, defaults to `30522`) : Vocabulary size of the model. Defines the number of different tokens that can be represented by the `input_ids`.

hidden_size (`int`, *optional*, defaults to `1024`) : Dimension of the hidden representations.

encoder_ffn_dim (`int`, *optional*, defaults to `4096`) : Dimensionality of the "intermediate" (often named feed-forward) layer in encoder.

num_encoder_layers (`int`, *optional*, defaults to `12`) : Number of hidden layers in the Transformer encoder. Will use the same value as `num_layers` if not set.

num_encoder_attention_heads (`int`, *optional*, defaults to `16`) : Number of attention heads for each attention layer in the Transformer encoder.

decoder_ffn_dim (`int`, *optional*, defaults to `4096`) : Dimensionality of the "intermediate" (often named feed-forward) layer in decoder.

num_decoder_layers (`int`, *optional*, defaults to `12`) : Number of hidden layers in the Transformer decoder. Will use the same value as `num_layers` if not set.

num_decoder_attention_heads (`int`, *optional*, defaults to `16`) : Number of attention heads for each attention layer in the Transformer decoder.

attention_dropout (`Union[float, int]`, *optional*, defaults to `0.1`) : The dropout ratio for the attention probabilities.

dropout (`Union[float, int]`, *optional*, defaults to `0.1`) : The ratio for all dropout layers.

max_position_embeddings (`int`, *optional*, defaults to `512`) : The maximum sequence length that this model might ever be used with.

init_std (`float`, *optional*, defaults to `0.02`) : The standard deviation of the truncated_normal_initializer for initializing all weight matrices.

add_cross_attention (`bool`, *optional*, defaults to `True`) : Whether cross-attention layers should be added to the model.

decoder_start_token_id (`int`, *optional*, defaults to `0`) : If an encoder-decoder model starts decoding with a different token than `bos`, the id of that token.

ngram (`int`, *optional*, defaults to 2) : Number of future tokens to predict. Set to 1 to be same as traditional Language model to predict next first token.

num_buckets (`int`, *optional*, defaults to 32) : The number of buckets to use for each attention layer. This is for relative position calculation. See the [T5 paper](see https://huggingface.co/papers/1910.10683) for more details.

relative_max_distance (`int`, *optional*, defaults to 128) : Relative distances greater than this number will be put into the last same bucket. This is for relative position calculation. See the [T5 paper](see https://huggingface.co/papers/1910.10683) for more details.

disable_ngram_loss (`bool`, *optional*, defaults to `False`) : Whether be trained predicting only the next first token.

eps (`float`, *optional*, defaults to 0.0) : Controls the `epsilon` parameter value for label smoothing in the loss calculation. If set to 0, no label smoothing is performed.

use_cache (`bool`, *optional*, defaults to `True`) : Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True` or when the model is a decoder-only generative model.

pad_token_id (`int`, *optional*, defaults to `0`) : Token id used for padding in the vocabulary.

bos_token_id (`int`, *optional*, defaults to `1`) : Token id used for beginning-of-stream in the vocabulary.

eos_token_id (`Union[int, list[int]]`, *optional*, defaults to `2`) : Token id used for end-of-stream in the vocabulary.

is_decoder (`bool`, *optional*, defaults to `False`) : Whether the model is used as a decoder or not. If `False`, the model is used as an encoder.

tie_word_embeddings (`bool`, *optional*, defaults to `True`) : Whether to tie weight embeddings according to model's `tied_weights_keys` mapping.

## ProphetNetTokenizer[[transformers.ProphetNetTokenizer]]

#### transformers.ProphetNetTokenizer[[transformers.ProphetNetTokenizer]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/prophetnet/tokenization_prophetnet.py#L267)

Construct a ProphetNetTokenizer. Based on WordPiece.

This tokenizer inherits from [PreTrainedTokenizer](/docs/transformers/v5.8.0/en/main_classes/tokenizer#transformers.PythonBackend) which contains most of the main methods. Users should refer to
this superclass for more information regarding those methods.

build_inputs_with_special_tokenstransformers.ProphetNetTokenizer.build_inputs_with_special_tokenshttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/prophetnet/tokenization_prophetnet.py#L450[{"name": "token_ids_0", "val": ": list"}, {"name": "token_ids_1", "val": ": list[int] | None = None"}]- **token_ids_0** (`List[int]`) --
  List of IDs to which the special tokens will be added.
- **token_ids_1** (`List[int]`, *optional*) --
  Optional second list of IDs for sequence pairs.0`List[int]`List of [input IDs](../glossary#input-ids) with the appropriate special tokens.

Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
adding special tokens. A BERT sequence has the following format:

- single sequence: `[CLS] X [SEP]`
- pair of sequences: `[CLS] A [SEP] B [SEP]`

**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.

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`

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.

sep_token (`str`, *optional*, defaults to `"[SEP]"`) : The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for sequence classification or for a text and a question for question answering. It is also used as the last token of a sequence built with special tokens.

x_sep_token (`str`, *optional*, defaults to `"[X_SEP]"`) : Special second separator token, which can be generated by [ProphetNetForConditionalGeneration](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetForConditionalGeneration). It is used to separate bullet-point like sentences in summarization, *e.g.*.

pad_token (`str`, *optional*, defaults to `"[PAD]"`) : The token used for padding, for example when batching sequences of different lengths.

mask_token (`str`, *optional*, defaults to `"[MASK]"`) : The token used for masking values. This is the token used when training this model with masked language modeling. This is the token which the model will try to predict.

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).

clean_up_tokenization_spaces (`bool`, *optional*, defaults to `True`) : Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like extra spaces.

**Returns:**

``List[int]``

List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
#### convert_tokens_to_string[[transformers.ProphetNetTokenizer.convert_tokens_to_string]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/prophetnet/tokenization_prophetnet.py#L395)

Converts a sequence of tokens (string) in a single string.
#### get_special_tokens_mask[[transformers.ProphetNetTokenizer.get_special_tokens_mask]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/prophetnet/tokenization_prophetnet.py#L400)

Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
special tokens using the tokenizer `prepare_for_model` method.

**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`) : Whether or not 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.

## ProphetNet specific outputs[[transformers.models.prophetnet.modeling_prophetnet.ProphetNetSeq2SeqLMOutput]]

#### transformers.models.prophetnet.modeling_prophetnet.ProphetNetSeq2SeqLMOutput[[transformers.models.prophetnet.modeling_prophetnet.ProphetNetSeq2SeqLMOutput]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/prophetnet/modeling_prophetnet.py#L117)

Base class for sequence-to-sequence language models outputs.

**Parameters:**

loss (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) : Language modeling loss.

logits (`torch.FloatTensor` of shape `(batch_size, decoder_sequence_length, config.vocab_size)`) : Prediction scores of the main stream language modeling head (scores for each vocabulary token before SoftMax).

logits_ngram (`torch.FloatTensor` of shape `(batch_size, ngram * decoder_sequence_length, config.vocab_size)`) : Prediction scores of the predict stream language modeling head (scores for each vocabulary token before SoftMax).

past_key_values (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) : It is a [Cache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.Cache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).  Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be used (see `past_key_values` input) to speed up sequential decoding.

decoder_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 decoder at the output of each layer plus the initial embedding outputs.

decoder_ngram_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 + one for the output of each layer) of shape `(batch_size, ngram * decoder_sequence_length, hidden_size)`.  Hidden-states of the predict stream of the decoder at the output of each layer plus the initial embedding outputs.

decoder_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 of the decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

decoder_ngram_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_attn_heads, decoder_sequence_length, decoder_sequence_length)`.  Attentions weights of the predict stream of the decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

cross_attentions (`tuple[torch.FloatTensor]`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) : Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.  Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.

encoder_last_hidden_state (`torch.FloatTensor` of shape `(batch_size, encoder_sequence_length, hidden_size)`, *optional*) : Sequence of hidden-states at the output of the last layer of the encoder of the model.

encoder_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 encoder at the output of each layer plus the initial embedding outputs.

encoder_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 of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

loss (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) : Language modeling loss.

logits (`torch.FloatTensor` of shape `(batch_size, decoder_sequence_length, config.vocab_size)`) : Prediction scores of the main stream language modeling head (scores for each vocabulary token before SoftMax).

logits_ngram (`torch.FloatTensor` of shape `(batch_size, ngram * decoder_sequence_length, config.vocab_size)`) : Prediction scores of the predict stream language modeling head (scores for each vocabulary token before SoftMax).

past_key_values (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) : It is a [Cache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.Cache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).  Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be used (see `past_key_values` input) to speed up sequential decoding.

decoder_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 decoder at the output of each layer plus the initial embedding outputs.

decoder_ngram_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 + one for the output of each layer) of shape `(batch_size, ngram * decoder_sequence_length, hidden_size)`.  Hidden-states of the predict stream of the decoder at the output of each layer plus the initial embedding outputs.

decoder_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 of the decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

decoder_ngram_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_attn_heads, decoder_sequence_length, decoder_sequence_length)`.  Attentions weights of the predict stream of the decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

cross_attentions (`tuple[torch.FloatTensor]`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) : Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.  Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.

encoder_last_hidden_state (`torch.FloatTensor` of shape `(batch_size, encoder_sequence_length, hidden_size)`, *optional*) : Sequence of hidden-states at the output of the last layer of the encoder of the model.

encoder_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 encoder at the output of each layer plus the initial embedding outputs.

encoder_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 of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

#### transformers.models.prophetnet.modeling_prophetnet.ProphetNetSeq2SeqModelOutput[[transformers.models.prophetnet.modeling_prophetnet.ProphetNetSeq2SeqModelOutput]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/prophetnet/modeling_prophetnet.py#L169)

Base class for model encoder's outputs that also contains : pre-computed hidden states that can speed up sequential
decoding.

**Parameters:**

last_hidden_state (`torch.FloatTensor` of shape `(batch_size, decoder_sequence_length, hidden_size)`) : Sequence of main stream hidden-states at the output of the last layer of the decoder of the model.  If `past_key_values` is used only the last hidden-state of the sequences of shape `(batch_size, 1, hidden_size)` is output.

last_hidden_state_ngram (`torch.FloatTensor` of shape `(batch_size,ngram * decoder_sequence_length, config.vocab_size)`, *optional*) : Sequence of predict stream hidden-states at the output of the last layer of the decoder of the model.

past_key_values (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) : It is a [Cache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.Cache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).  Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be used (see `past_key_values` input) to speed up sequential decoding.

decoder_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 decoder at the output of each layer plus the initial embedding outputs.

decoder_ngram_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 + one for the output of each layer) of shape `(batch_size, ngram * decoder_sequence_length, hidden_size)`.  Hidden-states of the predict stream of the decoder at the output of each layer plus the initial embedding outputs.

decoder_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 of the decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

decoder_ngram_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_attn_heads, decoder_sequence_length, decoder_sequence_length)`.  Attentions weights of the predict stream of the decoder, after the attention softmax, used to compute the weighted average in the

cross_attentions (`tuple[torch.FloatTensor]`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) : Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.  Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.

encoder_last_hidden_state (`torch.FloatTensor` of shape `(batch_size, encoder_sequence_length, hidden_size)`, *optional*) : Sequence of hidden-states at the output of the last layer of the encoder of the model.

encoder_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 encoder at the output of each layer plus the initial embedding outputs.

encoder_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 of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

last_hidden_state (`torch.FloatTensor` of shape `(batch_size, decoder_sequence_length, hidden_size)`) : Sequence of main stream hidden-states at the output of the last layer of the decoder of the model.  If `past_key_values` is used only the last hidden-state of the sequences of shape `(batch_size, 1, hidden_size)` is output.

last_hidden_state_ngram (`torch.FloatTensor` of shape `(batch_size,ngram * decoder_sequence_length, config.vocab_size)`, *optional*) : Sequence of predict stream hidden-states at the output of the last layer of the decoder of the model.

past_key_values (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) : It is a [Cache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.Cache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).  Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be used (see `past_key_values` input) to speed up sequential decoding.

decoder_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 decoder at the output of each layer plus the initial embedding outputs.

decoder_ngram_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 + one for the output of each layer) of shape `(batch_size, ngram * decoder_sequence_length, hidden_size)`.  Hidden-states of the predict stream of the decoder at the output of each layer plus the initial embedding outputs.

decoder_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 of the decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

decoder_ngram_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_attn_heads, decoder_sequence_length, decoder_sequence_length)`.  Attentions weights of the predict stream of the decoder, after the attention softmax, used to compute the weighted average in the

cross_attentions (`tuple[torch.FloatTensor]`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) : Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.  Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.

encoder_last_hidden_state (`torch.FloatTensor` of shape `(batch_size, encoder_sequence_length, hidden_size)`, *optional*) : Sequence of hidden-states at the output of the last layer of the encoder of the model.

encoder_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 encoder at the output of each layer plus the initial embedding outputs.

encoder_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 of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

#### transformers.models.prophetnet.modeling_prophetnet.ProphetNetDecoderModelOutput[[transformers.models.prophetnet.modeling_prophetnet.ProphetNetDecoderModelOutput]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/prophetnet/modeling_prophetnet.py#L218)

Base class for model's outputs that may also contain a past key/values (to speed up sequential decoding).

**Parameters:**

last_hidden_state (`torch.FloatTensor` of shape `(batch_size, decoder_sequence_length, hidden_size)`) : Sequence of main stream hidden-states at the output of the last layer of the decoder of the model.  If `past_key_values` is used only the last hidden-state of the sequences of shape `(batch_size, 1, hidden_size)` is output.

last_hidden_state_ngram (`torch.FloatTensor` of shape `(batch_size, ngram * decoder_sequence_length, config.vocab_size)`) : Sequence of predict stream hidden-states at the output of the last layer of the decoder of the model.

past_key_values (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) : It is a [Cache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.Cache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).  Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be used (see `past_key_values` input) to speed up sequential decoding.

hidden_states (`tuple[torch.FloatTensor]`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) : Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.

hidden_states_ngram (`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 + one for the output of each layer) of shape `(batch_size, ngram * decoder_sequence_length, hidden_size)`.  Hidden-states of the predict stream of the decoder at the output of each layer plus the 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.

ngram_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_attn_heads, decoder_sequence_length, decoder_sequence_length)`.  Attentions weights of the predict stream of the decoder, after the attention softmax, used to compute the weighted average in the

cross_attentions (`tuple[torch.FloatTensor]`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) : Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.  Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.

last_hidden_state (`torch.FloatTensor` of shape `(batch_size, decoder_sequence_length, hidden_size)`) : Sequence of main stream hidden-states at the output of the last layer of the decoder of the model.  If `past_key_values` is used only the last hidden-state of the sequences of shape `(batch_size, 1, hidden_size)` is output.

last_hidden_state_ngram (`torch.FloatTensor` of shape `(batch_size, ngram * decoder_sequence_length, config.vocab_size)`) : Sequence of predict stream hidden-states at the output of the last layer of the decoder of the model.

past_key_values (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) : It is a [Cache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.Cache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).  Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be used (see `past_key_values` input) to speed up sequential decoding.

hidden_states (`tuple[torch.FloatTensor]`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) : Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.

hidden_states_ngram (`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 + one for the output of each layer) of shape `(batch_size, ngram * decoder_sequence_length, hidden_size)`.  Hidden-states of the predict stream of the decoder at the output of each layer plus the 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.

ngram_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_attn_heads, decoder_sequence_length, decoder_sequence_length)`.  Attentions weights of the predict stream of the decoder, after the attention softmax, used to compute the weighted average in the

cross_attentions (`tuple[torch.FloatTensor]`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) : Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.  Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.

#### transformers.models.prophetnet.modeling_prophetnet.ProphetNetDecoderLMOutput[[transformers.models.prophetnet.modeling_prophetnet.ProphetNetDecoderLMOutput]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/prophetnet/modeling_prophetnet.py#L262)

Base class for model's outputs that may also contain a past key/values (to speed up sequential decoding).

**Parameters:**

loss (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) : Language modeling loss.

logits (`torch.FloatTensor` of shape `(batch_size, decoder_sequence_length, config.vocab_size)`) : Prediction scores of the main stream language modeling head (scores for each vocabulary token before SoftMax).

logits_ngram (`torch.FloatTensor` of shape `(batch_size, ngram * decoder_sequence_length, config.vocab_size)`) : Prediction scores of the predict stream language modeling head (scores for each vocabulary token before SoftMax).

past_key_values (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) : It is a [Cache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.Cache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).  Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be used (see `past_key_values` input) to speed up sequential decoding.

hidden_states (`tuple[torch.FloatTensor]`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) : Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.

hidden_states_ngram (`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 + one for the output of each layer) of shape `(batch_size, ngram * decoder_sequence_length, hidden_size)`.  Hidden-states of the predict stream of the decoder at the output of each layer plus the 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.

ngram_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_attn_heads, decoder_sequence_length, decoder_sequence_length)`.  Attentions weights of the predict stream of the decoder, after the attention softmax, used to compute the weighted average in the

cross_attentions (`tuple[torch.FloatTensor]`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) : Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.  Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.

loss (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) : Language modeling loss.

logits (`torch.FloatTensor` of shape `(batch_size, decoder_sequence_length, config.vocab_size)`) : Prediction scores of the main stream language modeling head (scores for each vocabulary token before SoftMax).

logits_ngram (`torch.FloatTensor` of shape `(batch_size, ngram * decoder_sequence_length, config.vocab_size)`) : Prediction scores of the predict stream language modeling head (scores for each vocabulary token before SoftMax).

past_key_values (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) : It is a [Cache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.Cache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).  Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be used (see `past_key_values` input) to speed up sequential decoding.

hidden_states (`tuple[torch.FloatTensor]`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) : Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.

hidden_states_ngram (`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 + one for the output of each layer) of shape `(batch_size, ngram * decoder_sequence_length, hidden_size)`.  Hidden-states of the predict stream of the decoder at the output of each layer plus the 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.

ngram_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_attn_heads, decoder_sequence_length, decoder_sequence_length)`.  Attentions weights of the predict stream of the decoder, after the attention softmax, used to compute the weighted average in the

cross_attentions (`tuple[torch.FloatTensor]`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) : Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.  Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.

## ProphetNetModel[[transformers.ProphetNetModel]]

#### transformers.ProphetNetModel[[transformers.ProphetNetModel]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/prophetnet/modeling_prophetnet.py#L1350)

The bare Prophetnet Model outputting raw hidden-states without any specific head on top.

This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/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.

forwardtransformers.ProphetNetModel.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/prophetnet/modeling_prophetnet.py#L1379[{"name": "input_ids", "val": ": torch.Tensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "decoder_input_ids", "val": ": torch.Tensor | None = None"}, {"name": "decoder_attention_mask", "val": ": torch.BoolTensor | None = None"}, {"name": "encoder_outputs", "val": ": tuple | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.Tensor | None = None"}, {"name": "decoder_inputs_embeds", "val": ": torch.Tensor | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are input IDs?](../glossary#input-ids)
- **attention_mask** (`torch.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?](../glossary#attention-mask)
- **decoder_input_ids** (`torch.LongTensor` of shape `(batch_size, target_sequence_length)`, *optional*) --
  Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are decoder input IDs?](../glossary#decoder-input-ids)

  ProphetNet uses the `eos_token_id` as the starting token for `decoder_input_ids` generation. If
  `past_key_values` is used, optionally only the last `decoder_input_ids` have to be input (see
  `past_key_values`).
- **decoder_attention_mask** (`torch.BoolTensor` of shape `(batch_size, target_sequence_length)`, *optional*) --
  Default behavior: generate a tensor that ignores pad tokens in `decoder_input_ids`. Causal mask will also
  be used by default.
- **encoder_outputs** (`tuple`, *optional*) --
  Tuple consists of (`last_hidden_state`, *optional*: `hidden_states`, *optional*: `attentions`)
  `last_hidden_state` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) is a sequence of
  hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.
- **past_key_values** (`~cache_utils.Cache`, *optional*) --
  Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
  blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values`
  returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`.

  Only [Cache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).
  If no `past_key_values` are passed, [DynamicCache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.DynamicCache) will be initialized by default.

  The model will output the same cache format that is fed as input.

  If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't
  have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids`
  of shape `(batch_size, sequence_length)`.
- **inputs_embeds** (`torch.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.
- **decoder_inputs_embeds** (`torch.Tensor` of shape `(batch_size, target_sequence_length, hidden_size)`, *optional*) --
  Optionally, instead of passing `decoder_input_ids` you can choose to directly pass an embedded
  representation. If `past_key_values` is used, optionally only the last `decoder_inputs_embeds` have to be
  input (see `past_key_values`). This is useful if you want more control over how to convert
  `decoder_input_ids` indices into associated vectors than the model's internal embedding lookup matrix.

  If `decoder_input_ids` and `decoder_inputs_embeds` are both unset, `decoder_inputs_embeds` takes the value
  of `inputs_embeds`.
- **use_cache** (`bool`, *optional*) --
  If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see
  `past_key_values`).
- **output_attentions** (`bool`, *optional*) --
  Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
  tensors for more detail.
- **output_hidden_states** (`bool`, *optional*) --
  Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
  more detail.
- **return_dict** (`bool`, *optional*) --
  Whether or not to return a [ModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[ProphetNetSeq2SeqModelOutput](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.models.prophetnet.modeling_prophetnet.ProphetNetSeq2SeqModelOutput) or `tuple(torch.FloatTensor)`A [ProphetNetSeq2SeqModelOutput](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.models.prophetnet.modeling_prophetnet.ProphetNetSeq2SeqModelOutput) 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 ([ProphetNetConfig](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetConfig)) and inputs.
The [ProphetNetModel](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetModel) 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.

- **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, decoder_sequence_length, hidden_size)`) -- Sequence of main stream hidden-states at the output of the last layer of the decoder of the model.

  If `past_key_values` is used only the last hidden-state of the sequences of shape `(batch_size, 1,
  hidden_size)` is output.
- **last_hidden_state_ngram** (`torch.FloatTensor` of shape `(batch_size,ngram * decoder_sequence_length, config.vocab_size)`, *optional*) -- Sequence of predict stream hidden-states at the output of the last layer of the decoder of the model.
- **past_key_values** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [Cache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.Cache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).

  Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be
  used (see `past_key_values` input) to speed up sequential decoding.
- **decoder_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 decoder at the output of each layer plus the initial embedding outputs.
- **decoder_ngram_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 + one for the output of each layer) of
  shape `(batch_size, ngram * decoder_sequence_length, hidden_size)`.

  Hidden-states of the predict stream of the decoder at the output of each layer plus the initial embedding
  outputs.
- **decoder_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 of the decoder, after the attention softmax, used to compute the weighted average in the
  self-attention heads.
- **decoder_ngram_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_attn_heads,
  decoder_sequence_length, decoder_sequence_length)`.

  Attentions weights of the predict stream of the decoder, after the attention softmax, used to compute the
  weighted average in the
- **cross_attentions** (`tuple[torch.FloatTensor]`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
  sequence_length)`.

  Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the
  weighted average in the cross-attention heads.
- **encoder_last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, encoder_sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the encoder of the model.
- **encoder_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 encoder at the output of each layer plus the initial embedding outputs.
- **encoder_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 of the encoder, after the attention softmax, used to compute the weighted average in the
  self-attention heads.

Example:

```python
>>> from transformers import AutoTokenizer, ProphetNetModel

>>> tokenizer = AutoTokenizer.from_pretrained("microsoft/prophetnet-large-uncased")
>>> model = ProphetNetModel.from_pretrained("microsoft/prophetnet-large-uncased")

>>> input_ids = tokenizer(
...     "Studies have been shown that owning a dog is good for you", return_tensors="pt"
... ).input_ids  # Batch size 1
>>> decoder_input_ids = tokenizer("Studies show that", return_tensors="pt").input_ids  # Batch size 1
>>> outputs = model(input_ids=input_ids, decoder_input_ids=decoder_input_ids)

>>> last_hidden_states = outputs.last_hidden_state  # main stream hidden states
>>> last_hidden_states_ngram = outputs.last_hidden_state_ngram  # predict hidden states
```

**Parameters:**

config ([ProphetNetConfig](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetConfig)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[ProphetNetSeq2SeqModelOutput](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.models.prophetnet.modeling_prophetnet.ProphetNetSeq2SeqModelOutput) or `tuple(torch.FloatTensor)``

A [ProphetNetSeq2SeqModelOutput](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.models.prophetnet.modeling_prophetnet.ProphetNetSeq2SeqModelOutput) 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 ([ProphetNetConfig](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetConfig)) and inputs.

## ProphetNetEncoder[[transformers.ProphetNetEncoder]]

#### transformers.ProphetNetEncoder[[transformers.ProphetNetEncoder]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/prophetnet/modeling_prophetnet.py#L943)

The standalone encoder part of the ProphetNetModel.

This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/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.

forwardtransformers.ProphetNetEncoder.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/prophetnet/modeling_prophetnet.py#L963[{"name": "input_ids", "val": ": torch.Tensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.Tensor | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are input IDs?](../glossary#input-ids)
- **attention_mask** (`torch.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?](../glossary#attention-mask)
- **inputs_embeds** (`torch.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.
- **output_hidden_states** (`bool`, *optional*) --
  Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
  more detail.
- **return_dict** (`bool`, *optional*) --
  Whether or not to return a [ModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[BaseModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutput) or `tuple(torch.FloatTensor)`A [BaseModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutput) or a tuple of
`torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various
elements depending on the configuration ([ProphetNetConfig](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetConfig)) and inputs.
The [ProphetNetEncoder](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetEncoder) 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.

- **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.
- **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.

Example:

```python
>>> from transformers import AutoTokenizer, ProphetNetEncoder
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("microsoft/prophetnet-large-uncased")
>>> model = ProphetNetEncoder.from_pretrained("patrickvonplaten/prophetnet-large-uncased-standalone")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> outputs = model(**inputs)

>>> last_hidden_states = outputs.last_hidden_state
```

**Parameters:**

config ([ProphetNetConfig](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetConfig)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[BaseModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutput) or `tuple(torch.FloatTensor)``

A [BaseModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutput) or a tuple of
`torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various
elements depending on the configuration ([ProphetNetConfig](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetConfig)) and inputs.

## ProphetNetDecoder[[transformers.ProphetNetDecoder]]

#### transformers.ProphetNetDecoder[[transformers.ProphetNetDecoder]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/prophetnet/modeling_prophetnet.py#L1050)

The standalone decoder part of the ProphetNetModel.

This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/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.

forwardtransformers.ProphetNetDecoder.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/prophetnet/modeling_prophetnet.py#L1079[{"name": "input_ids", "val": ": torch.Tensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "encoder_hidden_states", "val": ": torch.Tensor | None = None"}, {"name": "encoder_attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.Tensor | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are input IDs?](../glossary#input-ids)
- **attention_mask** (`torch.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?](../glossary#attention-mask)
- **encoder_hidden_states** (`torch.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) --
  Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention
  if the model is configured as a decoder.
- **encoder_attention_mask** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in
  the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`:

  - 1 for tokens that are **not masked**,
  - 0 for tokens that are **masked**.
- **past_key_values** (`~cache_utils.Cache`, *optional*) --
  Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
  blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values`
  returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`.

  Only [Cache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).
  If no `past_key_values` are passed, [DynamicCache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.DynamicCache) will be initialized by default.

  The model will output the same cache format that is fed as input.

  If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't
  have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids`
  of shape `(batch_size, sequence_length)`.
- **inputs_embeds** (`torch.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.
- **use_cache** (`bool`, *optional*) --
  If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see
  `past_key_values`).
- **output_attentions** (`bool`, *optional*) --
  Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
  tensors for more detail.
- **output_hidden_states** (`bool`, *optional*) --
  Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
  more detail.
- **return_dict** (`bool`, *optional*) --
  Whether or not to return a [ModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[ProphetNetDecoderModelOutput](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.models.prophetnet.modeling_prophetnet.ProphetNetDecoderModelOutput) or `tuple(torch.FloatTensor)`A [ProphetNetDecoderModelOutput](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.models.prophetnet.modeling_prophetnet.ProphetNetDecoderModelOutput) 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 ([ProphetNetConfig](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetConfig)) and inputs.
The [ProphetNetDecoder](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetDecoder) 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.

- **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, decoder_sequence_length, hidden_size)`) -- Sequence of main stream hidden-states at the output of the last layer of the decoder of the model.

  If `past_key_values` is used only the last hidden-state of the sequences of shape `(batch_size, 1,
  hidden_size)` is output.
- **last_hidden_state_ngram** (`torch.FloatTensor` of shape `(batch_size, ngram * decoder_sequence_length, config.vocab_size)`) -- Sequence of predict stream hidden-states at the output of the last layer of the decoder of the model.
- **past_key_values** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [Cache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.Cache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).

  Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be
  used (see `past_key_values` input) to speed up sequential decoding.
- **hidden_states** (`tuple[torch.FloatTensor]`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
  one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
- **hidden_states_ngram** (`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 + one for the output of each layer) of
  shape `(batch_size, ngram * decoder_sequence_length, hidden_size)`.

  Hidden-states of the predict stream of the decoder at the output of each layer plus the 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.
- **ngram_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_attn_heads,
  decoder_sequence_length, decoder_sequence_length)`.

  Attentions weights of the predict stream of the decoder, after the attention softmax, used to compute the
  weighted average in the
- **cross_attentions** (`tuple[torch.FloatTensor]`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
  sequence_length)`.

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

Example:

```python
>>> from transformers import AutoTokenizer, ProphetNetDecoder
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("microsoft/prophetnet-large-uncased")
>>> model = ProphetNetDecoder.from_pretrained("microsoft/prophetnet-large-uncased", add_cross_attention=False)
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> outputs = model(**inputs)

>>> last_hidden_states = outputs.last_hidden_state
```

**Parameters:**

config ([ProphetNetConfig](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetConfig)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[ProphetNetDecoderModelOutput](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.models.prophetnet.modeling_prophetnet.ProphetNetDecoderModelOutput) or `tuple(torch.FloatTensor)``

A [ProphetNetDecoderModelOutput](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.models.prophetnet.modeling_prophetnet.ProphetNetDecoderModelOutput) 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 ([ProphetNetConfig](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetConfig)) and inputs.

## ProphetNetForConditionalGeneration[[transformers.ProphetNetForConditionalGeneration]]

#### transformers.ProphetNetForConditionalGeneration[[transformers.ProphetNetForConditionalGeneration]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/prophetnet/modeling_prophetnet.py#L1482)

The ProphetNet Model with a language modeling head. Can be used for sequence generation tasks.

This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/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.

forwardtransformers.ProphetNetForConditionalGeneration.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/prophetnet/modeling_prophetnet.py#L1501[{"name": "input_ids", "val": ": torch.Tensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "decoder_input_ids", "val": ": torch.Tensor | None = None"}, {"name": "decoder_attention_mask", "val": ": torch.BoolTensor | None = None"}, {"name": "encoder_outputs", "val": ": torch.Tensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.Tensor | None = None"}, {"name": "decoder_inputs_embeds", "val": ": torch.Tensor | None = None"}, {"name": "labels", "val": ": torch.Tensor | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are input IDs?](../glossary#input-ids)
- **attention_mask** (`torch.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?](../glossary#attention-mask)
- **decoder_input_ids** (`torch.LongTensor` of shape `(batch_size, target_sequence_length)`, *optional*) --
  Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are decoder input IDs?](../glossary#decoder-input-ids)

  ProphetNet uses the `eos_token_id` as the starting token for `decoder_input_ids` generation. If
  `past_key_values` is used, optionally only the last `decoder_input_ids` have to be input (see
  `past_key_values`).
- **decoder_attention_mask** (`torch.BoolTensor` of shape `(batch_size, target_sequence_length)`, *optional*) --
  Default behavior: generate a tensor that ignores pad tokens in `decoder_input_ids`. Causal mask will also
  be used by default.
- **encoder_outputs** (`torch.Tensor`, *optional*) --
  Tuple consists of (`last_hidden_state`, *optional*: `hidden_states`, *optional*: `attentions`)
  `last_hidden_state` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) is a sequence of
  hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.
- **past_key_values** (`~cache_utils.Cache`, *optional*) --
  Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
  blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values`
  returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`.

  Only [Cache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).
  If no `past_key_values` are passed, [DynamicCache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.DynamicCache) will be initialized by default.

  The model will output the same cache format that is fed as input.

  If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't
  have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids`
  of shape `(batch_size, sequence_length)`.
- **inputs_embeds** (`torch.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.
- **decoder_inputs_embeds** (`torch.Tensor` of shape `(batch_size, target_sequence_length, hidden_size)`, *optional*) --
  Optionally, instead of passing `decoder_input_ids` you can choose to directly pass an embedded
  representation. If `past_key_values` is used, optionally only the last `decoder_inputs_embeds` have to be
  input (see `past_key_values`). This is useful if you want more control over how to convert
  `decoder_input_ids` indices into associated vectors than the model's internal embedding lookup matrix.

  If `decoder_input_ids` and `decoder_inputs_embeds` are both unset, `decoder_inputs_embeds` takes the value
  of `inputs_embeds`.
- **labels** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) --
  Labels for computing the sequence classification/regression loss. Indices should be in `[-100, 0, ...,
  config.vocab_size - 1]`. All labels set to `-100` are ignored (masked), the loss is only computed for
  labels in `[0, ..., config.vocab_size]`
- **use_cache** (`bool`, *optional*) --
  If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see
  `past_key_values`).
- **output_attentions** (`bool`, *optional*) --
  Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
  tensors for more detail.
- **output_hidden_states** (`bool`, *optional*) --
  Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
  more detail.
- **return_dict** (`bool`, *optional*) --
  Whether or not to return a [ModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[ProphetNetSeq2SeqLMOutput](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.models.prophetnet.modeling_prophetnet.ProphetNetSeq2SeqLMOutput) or `tuple(torch.FloatTensor)`A [ProphetNetSeq2SeqLMOutput](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.models.prophetnet.modeling_prophetnet.ProphetNetSeq2SeqLMOutput) 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 ([ProphetNetConfig](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetConfig)) and inputs.
The [ProphetNetForConditionalGeneration](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetForConditionalGeneration) 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.

- **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) -- Language modeling loss.
- **logits** (`torch.FloatTensor` of shape `(batch_size, decoder_sequence_length, config.vocab_size)`) -- Prediction scores of the main stream language modeling head (scores for each vocabulary token before
  SoftMax).
- **logits_ngram** (`torch.FloatTensor` of shape `(batch_size, ngram * decoder_sequence_length, config.vocab_size)`) -- Prediction scores of the predict stream language modeling head (scores for each vocabulary token before
  SoftMax).
- **past_key_values** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [Cache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.Cache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).

  Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be
  used (see `past_key_values` input) to speed up sequential decoding.
- **decoder_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 decoder at the output of each layer plus the initial embedding outputs.
- **decoder_ngram_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 + one for the output of each layer) of
  shape `(batch_size, ngram * decoder_sequence_length, hidden_size)`.

  Hidden-states of the predict stream of the decoder at the output of each layer plus the initial embedding
  outputs.
- **decoder_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 of the decoder, after the attention softmax, used to compute the weighted average in the
  self-attention heads.
- **decoder_ngram_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_attn_heads,
  decoder_sequence_length, decoder_sequence_length)`.

  Attentions weights of the predict stream of the decoder, after the attention softmax, used to compute the
  weighted average in the self-attention heads.
- **cross_attentions** (`tuple[torch.FloatTensor]`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
  sequence_length)`.

  Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the
  weighted average in the cross-attention heads.
- **encoder_last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, encoder_sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the encoder of the model.
- **encoder_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 encoder at the output of each layer plus the initial embedding outputs.
- **encoder_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 of the encoder, after the attention softmax, used to compute the weighted average in the
  self-attention heads.

Example:

```python
>>> from transformers import AutoTokenizer, ProphetNetForConditionalGeneration

>>> tokenizer = AutoTokenizer.from_pretrained("microsoft/prophetnet-large-uncased")
>>> model = ProphetNetForConditionalGeneration.from_pretrained("microsoft/prophetnet-large-uncased")

>>> input_ids = tokenizer(
...     "Studies have been shown that owning a dog is good for you", return_tensors="pt"
... ).input_ids  # Batch size 1
>>> decoder_input_ids = tokenizer("Studies show that", return_tensors="pt").input_ids  # Batch size 1
>>> outputs = model(input_ids=input_ids, decoder_input_ids=decoder_input_ids)

>>> logits_next_token = outputs.logits  # logits to predict next token as usual
>>> logits_ngram_next_tokens = outputs.logits_ngram  # logits to predict 2nd, 3rd, ... next tokens
```

**Parameters:**

config ([ProphetNetConfig](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetConfig)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[ProphetNetSeq2SeqLMOutput](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.models.prophetnet.modeling_prophetnet.ProphetNetSeq2SeqLMOutput) or `tuple(torch.FloatTensor)``

A [ProphetNetSeq2SeqLMOutput](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.models.prophetnet.modeling_prophetnet.ProphetNetSeq2SeqLMOutput) 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 ([ProphetNetConfig](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetConfig)) and inputs.

## ProphetNetForCausalLM[[transformers.ProphetNetForCausalLM]]

#### transformers.ProphetNetForCausalLM[[transformers.ProphetNetForCausalLM]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/prophetnet/modeling_prophetnet.py#L1656)

The standalone decoder part of the ProphetNetModel with a lm head on top. The model can be used for causal

This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/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.

forwardtransformers.ProphetNetForCausalLM.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/prophetnet/modeling_prophetnet.py#L1684[{"name": "input_ids", "val": ": torch.Tensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "encoder_hidden_states", "val": ": torch.Tensor | None = None"}, {"name": "encoder_attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.Tensor | None = None"}, {"name": "labels", "val": ": torch.Tensor | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are input IDs?](../glossary#input-ids)
- **attention_mask** (`torch.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?](../glossary#attention-mask)
- **encoder_hidden_states** (`torch.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) --
  Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention
  if the model is configured as a decoder.
- **encoder_attention_mask** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in
  the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`:

  - 1 for tokens that are **not masked**,
  - 0 for tokens that are **masked**.
- **past_key_values** (`~cache_utils.Cache`, *optional*) --
  Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
  blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values`
  returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`.

  Only [Cache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).
  If no `past_key_values` are passed, [DynamicCache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.DynamicCache) will be initialized by default.

  The model will output the same cache format that is fed as input.

  If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't
  have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids`
  of shape `(batch_size, sequence_length)`.
- **inputs_embeds** (`torch.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.
- **labels** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Labels for computing the left-to-right language modeling loss (next word prediction). Indices should be in
  `[-100, 0, ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are
  ignored (masked), the loss is only computed for the tokens with labels n `[0, ..., config.vocab_size]`
- **use_cache** (`bool`, *optional*) --
  If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see
  `past_key_values`).
- **output_attentions** (`bool`, *optional*) --
  Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
  tensors for more detail.
- **output_hidden_states** (`bool`, *optional*) --
  Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
  more detail.
- **return_dict** (`bool`, *optional*) --
  Whether or not to return a [ModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[ProphetNetDecoderLMOutput](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.models.prophetnet.modeling_prophetnet.ProphetNetDecoderLMOutput) or `tuple(torch.FloatTensor)`A [ProphetNetDecoderLMOutput](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.models.prophetnet.modeling_prophetnet.ProphetNetDecoderLMOutput) 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 ([ProphetNetConfig](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetConfig)) and inputs.
The [ProphetNetForCausalLM](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetForCausalLM) 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.

- **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) -- Language modeling loss.
- **logits** (`torch.FloatTensor` of shape `(batch_size, decoder_sequence_length, config.vocab_size)`) -- Prediction scores of the main stream language modeling head (scores for each vocabulary token before
  SoftMax).
- **logits_ngram** (`torch.FloatTensor` of shape `(batch_size, ngram * decoder_sequence_length, config.vocab_size)`) -- Prediction scores of the predict stream language modeling head (scores for each vocabulary token before
  SoftMax).
- **past_key_values** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [Cache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.Cache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).

  Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be
  used (see `past_key_values` input) to speed up sequential decoding.
- **hidden_states** (`tuple[torch.FloatTensor]`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
  one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
- **hidden_states_ngram** (`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 + one for the output of each layer) of
  shape `(batch_size, ngram * decoder_sequence_length, hidden_size)`.

  Hidden-states of the predict stream of the decoder at the output of each layer plus the 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.
- **ngram_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_attn_heads,
  decoder_sequence_length, decoder_sequence_length)`.

  Attentions weights of the predict stream of the decoder, after the attention softmax, used to compute the
  weighted average in the
- **cross_attentions** (`tuple[torch.FloatTensor]`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
  sequence_length)`.

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

Example:

```python
>>> from transformers import AutoTokenizer, ProphetNetForCausalLM
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("microsoft/prophetnet-large-uncased")
>>> model = ProphetNetForCausalLM.from_pretrained("microsoft/prophetnet-large-uncased")
>>> assert model.config.is_decoder, f"{model.__class__} has to be configured as a decoder."
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> outputs = model(**inputs)

>>> logits = outputs.logits

>>> # Model can also be used with EncoderDecoder framework
>>> from transformers import BertTokenizer, EncoderDecoderModel, AutoTokenizer
>>> import torch

>>> tokenizer_enc = BertTokenizer.from_pretrained("google-bert/bert-large-uncased")
>>> tokenizer_dec = AutoTokenizer.from_pretrained("microsoft/prophetnet-large-uncased")
>>> model = EncoderDecoderModel.from_encoder_decoder_pretrained(
...     "google-bert/bert-large-uncased", "microsoft/prophetnet-large-uncased"
... )

>>> ARTICLE = (
...     "the us state department said wednesday it had received no "
...     "formal word from bolivia that it was expelling the us ambassador there "
...     "but said the charges made against him are `` baseless ."
... )
>>> input_ids = tokenizer_enc(ARTICLE, return_tensors="pt").input_ids
>>> labels = tokenizer_dec(
...     "us rejects charges against its ambassador in bolivia", return_tensors="pt"
... ).input_ids
>>> outputs = model(input_ids=input_ids, decoder_input_ids=labels[:, :-1], labels=labels[:, 1:])

>>> loss = outputs.loss
```

**Parameters:**

config ([ProphetNetConfig](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetConfig)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[ProphetNetDecoderLMOutput](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.models.prophetnet.modeling_prophetnet.ProphetNetDecoderLMOutput) or `tuple(torch.FloatTensor)``

A [ProphetNetDecoderLMOutput](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.models.prophetnet.modeling_prophetnet.ProphetNetDecoderLMOutput) 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 ([ProphetNetConfig](/docs/transformers/v5.8.0/en/model_doc/prophetnet#transformers.ProphetNetConfig)) and inputs.