# FSMT

## Overview

FSMT (FairSeq MachineTranslation) models were introduced in [Facebook FAIR's WMT19 News Translation Task Submission](https://huggingface.co/papers/1907.06616) by Nathan Ng, Kyra Yee, Alexei Baevski, Myle Ott, Michael Auli, Sergey Edunov.

The abstract of the paper is the following:

*This paper describes Facebook FAIR's submission to the WMT19 shared news translation task. We participate in two
language pairs and four language directions, English <-> German and English <-> Russian. Following our submission from
last year, our baseline systems are large BPE-based transformer models trained with the Fairseq sequence modeling
toolkit which rely on sampled back-translations. This year we experiment with different bitext data filtering schemes,
as well as with adding filtered back-translated data. We also ensemble and fine-tune our models on domain-specific
data, then decode using noisy channel model reranking. Our submissions are ranked first in all four directions of the
human evaluation campaign. On En->De, our system significantly outperforms other systems as well as human translations.
This system improves upon our WMT'18 submission by 4.5 BLEU points.*

This model was contributed by [stas](https://huggingface.co/stas). The original code can be found
[here](https://github.com/pytorch/fairseq/tree/master/examples/wmt19).

## Implementation Notes

- FSMT uses source and target vocabulary pairs that aren't combined into one. It doesn't share embeddings tokens
  either. Its tokenizer is very similar to [XLMTokenizer](/docs/transformers/v5.8.0/en/model_doc/xlm#transformers.XLMTokenizer) and the main model is derived from
  [BartModel](/docs/transformers/v5.8.0/en/model_doc/bart#transformers.BartModel).

## FSMTConfig[[transformers.FSMTConfig]]

#### transformers.FSMTConfig[[transformers.FSMTConfig]]

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

This is the configuration class to store the configuration of a FSMTModel. It is used to instantiate a Fsmt
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 [facebook/wmt19-en-ru](https://huggingface.co/facebook/wmt19-en-ru)

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.

Examples:

```python
>>> from transformers import FSMTConfig, FSMTModel

>>> # Initializing a FSMT facebook/wmt19-en-ru style configuration
>>> config = FSMTConfig()

>>> # Initializing a model (with random weights) from the configuration
>>> model = FSMTModel(config)

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

**Parameters:**

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

langs (`Union[list[str], tuple[str, ...]]`, *optional*, defaults to `('en', 'de')`) : A list with source language and target_language (e.g., ['en', 'ru']).

src_vocab_size (`int`, *optional*, defaults to `42024`) : Vocabulary size of the encoder. Defines the number of different tokens that can be represented by the `inputs_ids` passed to the forward method in the encoder.

tgt_vocab_size (`int`, *optional*, defaults to `42024`) : Vocabulary size of the decoder. Defines the number of different tokens that can be represented by the `inputs_ids` passed to the forward method in the decoder.

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

d_model (`int`, *optional*, defaults to `1024`) : Size of the encoder layers and the pooler layer.

max_length (`int`, *optional*, defaults to 200) : Maximum length to generate.

max_position_embeddings (`int`, *optional*, defaults to `1024`) : The maximum sequence length that this model might ever be used with.

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

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.

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

encoder_layerdrop (`Union[float, int]`, *optional*, defaults to `0.0`) : The LayerDrop probability for the encoder. See the [LayerDrop paper](see https://huggingface.co/papers/1909.11556) for more details.

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

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.

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

decoder_layerdrop (`Union[float, int]`, *optional*, defaults to `0.0`) : The LayerDrop probability for the decoder. See the [LayerDrop paper](see https://huggingface.co/papers/1909.11556) for more details.

attention_dropout (`Union[float, int]`, *optional*, defaults to `0.0`) : The dropout ratio for the attention probabilities.

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

activation_dropout (`Union[float, int]`, *optional*, defaults to `0.0`) : The dropout ratio for activations inside the fully connected layer.

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

decoder_start_token_id (`int`, *optional*, defaults to `2`) : If an encoder-decoder model starts decoding with a different token than `bos`, the id of that token.

scale_embedding (`bool`, *optional*, defaults to `True`) : Whether to scale embeddings by dividing by sqrt(d_model).

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

num_beams (`int`, *optional*, defaults to 5) : Number of beams for beam search that will be used by default in the `generate` method of the model. 1 means no beam search.

length_penalty (`float`, *optional*, defaults to 1) : Exponential penalty to the length that is used with beam-based generation. It is applied as an exponent to the sequence length, which in turn is used to divide the score of the sequence. Since the score is the log likelihood of the sequence (i.e. negative), `length_penalty` > 0.0 promotes longer sequences, while `length_penalty` < 0.0 encourages shorter sequences.

early_stopping (`bool`, *optional*, defaults to `False`) : Flag that will be used by default in the `generate` method of the model. Whether to stop the beam search when at least `num_beams` sentences are finished per batch or not.

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 `1`) : Token id used for padding in the vocabulary.

bos_token_id (`int`, *optional*, defaults to `0`) : 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.

forced_eos_token_id (`Union[int, list[int]]`, *optional*, defaults to `2`) : The id of the token to force as the last generated token when `max_length` is reached. Usually set to `eos_token_id`.

## FSMTTokenizer[[transformers.FSMTTokenizer]]

#### transformers.FSMTTokenizer[[transformers.FSMTTokenizer]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/fsmt/tokenization_fsmt.py#L112)

Construct an FAIRSEQ Transformer tokenizer. Based on Byte-Pair Encoding. The tokenization process is the following:

- Moses preprocessing and tokenization.
- Normalizing all inputs text.
- The arguments `special_tokens` and the function `set_special_tokens`, can be used to add additional symbols (like
  "__classify__") to a vocabulary.
- The argument `langs` defines a pair of languages.

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.FSMTTokenizer.build_inputs_with_special_tokenshttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/fsmt/tokenization_fsmt.py#L377[{"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 FAIRSEQ Transformer sequence has the following format:

- single sequence: ` X `
- pair of sequences: ` A  B `

**Parameters:**

langs (`List[str]`, *optional*) : A list of two languages to translate from and to, for instance `["en", "ru"]`.

src_vocab_file (`str`, *optional*) : File containing the vocabulary for the source language.

tgt_vocab_file (`st`, *optional*) : File containing the vocabulary for the target language.

merges_file (`str`, *optional*) : File containing the merges.

do_lower_case (`bool`, *optional*, defaults to `False`) : Whether or not to lowercase the input when tokenizing.

unk_token (`str`, *optional*, defaults to `"<unk>"`) : The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead.

bos_token (`str`, *optional*, defaults to `"<s>"`) : The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.    When building a sequence using special tokens, this is not the token that is used for the beginning of sequence. The token used is the `cls_token`.   

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

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

**Returns:**

``List[int]``

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

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/fsmt/tokenization_fsmt.py#L403)

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.
#### create_token_type_ids_from_sequences[[transformers.FSMTTokenizer.create_token_type_ids_from_sequences]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/tokenization_python.py#L1294)

Create a mask from the two sequences passed to be used in a sequence-pair classification task.

This method dynamically builds the token type IDs based on the tokenizer's configuration attributes:
- `token_type_ids_pattern`: Pattern to use ("all_zeros" or "bert_style")
- `token_type_ids_include_special_tokens`: Whether to account for special tokens in length calculation

Examples:
```python
# All zeros pattern (default, used by RoBERTa, BART, etc.)
tokenizer.token_type_ids_pattern = "all_zeros"
# Returns: [0, 0, 0, ...] for both sequences

# BERT-style pattern (first sequence gets 0s, second gets 1s)
tokenizer.token_type_ids_pattern = "bert_style"
# Returns: [0, 0, 0, ..., 1, 1, 1, ...] for sequence pairs
```

**Parameters:**

token_ids_0 (`list[int]`) : List of IDs.

token_ids_1 (`list[int]`, *optional*) : Optional second list of IDs for sequence pairs.

**Returns:**

``list[int]``

Token type IDs according to the configured pattern.
#### save_vocabulary[[transformers.FSMTTokenizer.save_vocabulary]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/fsmt/tokenization_fsmt.py#L431)

## FSMTModel[[transformers.FSMTModel]]

#### transformers.FSMTModel[[transformers.FSMTModel]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/fsmt/modeling_fsmt.py#L811)

The bare Fsmt 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.FSMTModel.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/fsmt/modeling_fsmt.py#L823[{"name": "input_ids", "val": ": LongTensor"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "decoder_input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "decoder_attention_mask", "val": ": torch.BoolTensor | None = None"}, {"name": "encoder_outputs", "val": ": tuple[torch.FloatTensor] | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | 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": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "decoder_inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`) --
  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)

  FSMT 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[torch.FloatTensor]`, *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)`.
- **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.
- **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) --
  Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
  is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
  model's internal embedding lookup matrix.
- **decoder_inputs_embeds** (`torch.FloatTensor` 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`.
- **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[Seq2SeqModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.Seq2SeqModelOutput) or `tuple(torch.FloatTensor)`A [Seq2SeqModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.Seq2SeqModelOutput) 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 ([FSMTConfig](/docs/transformers/v5.8.0/en/model_doc/fsmt#transformers.FSMTConfig)) and inputs.
The [FSMTModel](/docs/transformers/v5.8.0/en/model_doc/fsmt#transformers.FSMTModel) 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 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.
- **past_key_values** (`EncoderDecoderCache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [EncoderDecoderCache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.EncoderDecoderCache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).

  Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
  blocks) 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 optional 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.
- **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, 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 optional 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.

**Parameters:**

config ([FSMTConfig](/docs/transformers/v5.8.0/en/model_doc/fsmt#transformers.FSMTConfig)) : 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:**

`[Seq2SeqModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.Seq2SeqModelOutput) or `tuple(torch.FloatTensor)``

A [Seq2SeqModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.Seq2SeqModelOutput) 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 ([FSMTConfig](/docs/transformers/v5.8.0/en/model_doc/fsmt#transformers.FSMTConfig)) and inputs.

## FSMTForConditionalGeneration[[transformers.FSMTForConditionalGeneration]]

#### transformers.FSMTForConditionalGeneration[[transformers.FSMTForConditionalGeneration]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/fsmt/modeling_fsmt.py#L947)

The FSMT Model with a language modeling head. Can be used for summarization.

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.FSMTForConditionalGeneration.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/fsmt/modeling_fsmt.py#L958[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "decoder_input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "decoder_attention_mask", "val": ": torch.BoolTensor | None = None"}, {"name": "encoder_outputs", "val": ": tuple[torch.FloatTensor] | 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.LongTensor | 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.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/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)

  FSMT 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[torch.FloatTensor]`, *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, sequence_length)`, *optional*) --
  Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
  config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
  (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.
- **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[Seq2SeqLMOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.Seq2SeqLMOutput) or `tuple(torch.FloatTensor)`A [Seq2SeqLMOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.Seq2SeqLMOutput) 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 ([FSMTConfig](/docs/transformers/v5.8.0/en/model_doc/fsmt#transformers.FSMTConfig)) and inputs.
The [FSMTForConditionalGeneration](/docs/transformers/v5.8.0/en/model_doc/fsmt#transformers.FSMTForConditionalGeneration) 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, sequence_length, config.vocab_size)`) -- Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
- **past_key_values** (`EncoderDecoderCache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [EncoderDecoderCache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.EncoderDecoderCache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).

  Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
  blocks) 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_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.
- **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, 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 Translation:

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

>>> mname = "facebook/wmt19-ru-en"
>>> model = FSMTForConditionalGeneration.from_pretrained(mname)
>>> tokenizer = AutoTokenizer.from_pretrained(mname)

>>> src_text = "Машинное обучение - это здорово, не так ли?"
>>> input_ids = tokenizer(src_text, return_tensors="pt").input_ids
>>> outputs = model.generate(input_ids, num_beams=5, num_return_sequences=3)
>>> tokenizer.decode(outputs[0], skip_special_tokens=True)
"Machine learning is great, isn't it?"
```

**Parameters:**

config ([FSMTConfig](/docs/transformers/v5.8.0/en/model_doc/fsmt#transformers.FSMTConfig)) : 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:**

`[Seq2SeqLMOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.Seq2SeqLMOutput) or `tuple(torch.FloatTensor)``

A [Seq2SeqLMOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.Seq2SeqLMOutput) 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 ([FSMTConfig](/docs/transformers/v5.8.0/en/model_doc/fsmt#transformers.FSMTConfig)) and inputs.