MarianMT¶

Bugs: If you see something strange, file a Github Issue and assign @patrickvonplaten.

Translations should be similar, but not identical to output in the test set linked to in each model card.

Implementation Notes¶

  • Each model is about 298 MB on disk, there are more than 1,000 models.

  • The list of supported language pairs can be found here.

  • Models were originally trained by Jörg Tiedemann using the Marian C++ library, which supports fast training and translation.

  • All models are transformer encoder-decoders with 6 layers in each component. Each model’s performance is documented in a model card.

  • The 80 opus models that require BPE preprocessing are not supported.

  • The modeling code is the same as BartForConditionalGeneration with a few minor modifications:

    • static (sinusoid) positional embeddings (MarianConfig.static_position_embeddings=True)

    • no layernorm_embedding (MarianConfig.normalize_embedding=False)

    • the model starts generating with pad_token_id (which has 0 as a token_embedding) as the prefix (Bart uses <s/>),

  • Code to bulk convert models can be found in convert_marian_to_pytorch.py.

Naming¶

  • All model names use the following format: Helsinki-NLP/opus-mt-{src}-{tgt}

  • The language codes used to name models are inconsistent. Two digit codes can usually be found here, three digit codes require googling “language code {code}”.

  • Codes formatted like es_AR are usually code_{region}. That one is Spanish from Argentina.

  • The models were converted in two stages. The first 1000 models use ISO-639-2 codes to identify languages, the second group use a combination of ISO-639-5 codes and ISO-639-2 codes.

Examples¶

Multilingual Models¶

  • All model names use the following format: Helsinki-NLP/opus-mt-{src}-{tgt}:

  • If a model can output multiple languages, and you should specify a language code by prepending the desired output language to the src_text.

  • You can see a models’s supported language codes in its model card, under target constituents, like in opus-mt-en-roa.

  • Note that if a model is only multilingual on the source side, like Helsinki-NLP/opus-mt-roa-en, no language codes are required.

New multi-lingual models from the Tatoeba-Challenge repo require 3 character language codes:

>>> from transformers import MarianMTModel, MarianTokenizer
>>> src_text = [
...     '>>fra<< this is a sentence in english that we want to translate to french',
...     '>>por<< This should go to portuguese',
...     '>>esp<< And this to Spanish'
>>> ]

>>> model_name = 'Helsinki-NLP/opus-mt-en-roa'
>>> tokenizer = MarianTokenizer.from_pretrained(model_name)
>>> print(tokenizer.supported_language_codes)
['>>zlm_Latn<<', '>>mfe<<', '>>hat<<', '>>pap<<', '>>ast<<', '>>cat<<', '>>ind<<', '>>glg<<', '>>wln<<', '>>spa<<', '>>fra<<', '>>ron<<', '>>por<<', '>>ita<<', '>>oci<<', '>>arg<<', '>>min<<']

>>> model = MarianMTModel.from_pretrained(model_name)
>>> translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
>>> [tokenizer.decode(t, skip_special_tokens=True) for t in translated]
["c'est une phrase en anglais que nous voulons traduire en français",
 'Isto deve ir para o portuguĂŞs.',
 'Y esto al español']

Here is the code to see all available pretrained models on the hub:

from transformers.hf_api import HfApi
model_list = HfApi().model_list()
org = "Helsinki-NLP"
model_ids = [x.modelId for x in model_list if x.modelId.startswith(org)]
suffix = [x.split('/')[1] for x in model_ids]
old_style_multi_models = [f'{org}/{s}' for s in suffix if s != s.lower()]

Old Style Multi-Lingual Models¶

These are the old style multi-lingual models ported from the OPUS-MT-Train repo: and the members of each language group:

['Helsinki-NLP/opus-mt-NORTH_EU-NORTH_EU',
 'Helsinki-NLP/opus-mt-ROMANCE-en',
 'Helsinki-NLP/opus-mt-SCANDINAVIA-SCANDINAVIA',
 'Helsinki-NLP/opus-mt-de-ZH',
 'Helsinki-NLP/opus-mt-en-CELTIC',
 'Helsinki-NLP/opus-mt-en-ROMANCE',
 'Helsinki-NLP/opus-mt-es-NORWAY',
 'Helsinki-NLP/opus-mt-fi-NORWAY',
 'Helsinki-NLP/opus-mt-fi-ZH',
 'Helsinki-NLP/opus-mt-fi_nb_no_nn_ru_sv_en-SAMI',
 'Helsinki-NLP/opus-mt-sv-NORWAY',
 'Helsinki-NLP/opus-mt-sv-ZH']
GROUP_MEMBERS = {
 'ZH': ['cmn', 'cn', 'yue', 'ze_zh', 'zh_cn', 'zh_CN', 'zh_HK', 'zh_tw', 'zh_TW', 'zh_yue', 'zhs', 'zht', 'zh'],
 'ROMANCE': ['fr', 'fr_BE', 'fr_CA', 'fr_FR', 'wa', 'frp', 'oc', 'ca', 'rm', 'lld', 'fur', 'lij', 'lmo', 'es', 'es_AR', 'es_CL', 'es_CO', 'es_CR', 'es_DO', 'es_EC', 'es_ES', 'es_GT', 'es_HN', 'es_MX', 'es_NI', 'es_PA', 'es_PE', 'es_PR', 'es_SV', 'es_UY', 'es_VE', 'pt', 'pt_br', 'pt_BR', 'pt_PT', 'gl', 'lad', 'an', 'mwl', 'it', 'it_IT', 'co', 'nap', 'scn', 'vec', 'sc', 'ro', 'la'],
 'NORTH_EU': ['de', 'nl', 'fy', 'af', 'da', 'fo', 'is', 'no', 'nb', 'nn', 'sv'],
 'SCANDINAVIA': ['da', 'fo', 'is', 'no', 'nb', 'nn', 'sv'],
 'SAMI': ['se', 'sma', 'smj', 'smn', 'sms'],
 'NORWAY': ['nb_NO', 'nb', 'nn_NO', 'nn', 'nog', 'no_nb', 'no'],
 'CELTIC': ['ga', 'cy', 'br', 'gd', 'kw', 'gv']
}

Example of translating english to many romance languages, using old-style 2 character language codes

MarianConfig¶

class transformers.MarianConfig(vocab_size=50265, max_position_embeddings=1024, encoder_layers=12, encoder_ffn_dim=4096, encoder_attention_heads=16, decoder_layers=12, decoder_ffn_dim=4096, decoder_attention_heads=16, encoder_layerdrop=0.0, decoder_layerdrop=0.0, use_cache=True, is_encoder_decoder=True, activation_function='gelu', d_model=1024, dropout=0.1, attention_dropout=0.0, activation_dropout=0.0, init_std=0.02, decoder_start_token_id=58100, classifier_dropout=0.0, scale_embedding=False, gradient_checkpointing=False, pad_token_id=58100, eos_token_id=0, forced_eos_token_id=0, **kwargs)[source]¶

This is the configuration class to store the configuration of a MarianModel. It is used to instantiate an Marian 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 Marian Helsinki-NLP/opus-mt-en-de architecture.

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

Parameters

  • vocab_size (int, optional, defaults to 50265) – Vocabulary size of the Marian model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling MarianModel or TFMarianModel.

  • d_model (int, optional, defaults to 1024) – Dimensionality of the layers and the pooler layer.

  • encoder_layers (int, optional, defaults to 12) – Number of encoder layers.

  • decoder_layers (int, optional, defaults to 12) – Number of decoder layers.

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

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

  • decoder_ffn_dim (int, optional, defaults to 4096) – Dimensionality of the “intermediate” (often named feed-forward) layer in decoder.

  • encoder_ffn_dim (int, optional, defaults to 4096) – Dimensionality of the “intermediate” (often named feed-forward) layer in decoder.

  • activation_function (str or function, optional, defaults to "gelu") – The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu", "relu", "silu" and "gelu_new" are supported.

  • dropout (float, optional, defaults to 0.1) – The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.

  • attention_dropout (float, optional, defaults to 0.0) – The dropout ratio for the attention probabilities.

  • activation_dropout (float, optional, defaults to 0.0) – The dropout ratio for activations inside the fully connected layer.

  • classifier_dropout (float, optional, defaults to 0.0) – The dropout ratio for classifier.

  • max_position_embeddings (int, optional, defaults to 1024) – The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048).

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

  • encoder_layerdrop – (float, optional, defaults to 0.0): The LayerDrop probability for the encoder. See the LayerDrop paper for more details.

  • decoder_layerdrop – (float, optional, defaults to 0.0): The LayerDrop probability for the decoder. See the LayerDrop paper for more details.

  • gradient_checkpointing (bool, optional, defaults to False) – If True, use gradient checkpointing to save memory at the expense of slower backward pass.

  • scale_embedding (bool, optional, defaults to False) – Scale embeddings by diving by sqrt(d_model).

  • use_cache (bool, optional, defaults to True) – Whether or not the model should return the last key/values attentions (not used by all models)

  • forced_eos_token_id (int, optional, defaults to 0) – The id of the token to force as the last generated token when max_length is reached. Usually set to eos_token_id.

Examples:

>>> from transformers import MarianModel, MarianConfig

>>> # Initializing a Marian Helsinki-NLP/opus-mt-en-de style configuration
>>> configuration = MarianConfig()

>>> # Initializing a model from the Helsinki-NLP/opus-mt-en-de style configuration
>>> model = MarianModel(configuration)

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

MarianTokenizer¶

class transformers.MarianTokenizer(vocab, source_spm, target_spm, source_lang=None, target_lang=None, unk_token='<unk>', eos_token='</s>', pad_token='<pad>', model_max_length=512, **kwargs)[source]¶

Construct a Marian tokenizer. Based on SentencePiece.

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

Parameters

  • source_spm (str) – SentencePiece file (generally has a .spm extension) that contains the vocabulary for the source language.

  • target_spm (str) – SentencePiece file (generally has a .spm extension) that contains the vocabulary for the target language.

  • source_lang (str, optional) – A string representing the source language.

  • target_lang (str, optional) – A string representing the target language.

  • 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.

  • eos_token (str, optional, defaults to "</s>") – The end of sequence token.

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

  • model_max_length (int, optional, defaults to 512) – The maximum sentence length the model accepts.

  • additional_special_tokens (List[str], optional, defaults to ["<eop>", "<eod>"]) – Additional special tokens used by the tokenizer.

Examples:

>>> from transformers import MarianTokenizer
>>> tokenizer = MarianTokenizer.from_pretrained('Helsinki-NLP/opus-mt-en-de')
>>> src_texts = [ "I am a small frog.", "Tom asked his teacher for advice."]
>>> tgt_texts = ["Ich bin ein kleiner Frosch.", "Tom bat seinen Lehrer um Rat."]  # optional
>>> inputs = tokenizer(src_texts, return_tensors="pt", padding=True)
>>> with tokenizer.as_target_tokenizer():
...     labels = tokenizer(tgt_texts, return_tensors="pt", padding=True)
>>> inputs["labels"] = labels["input_ids"]
# keys  [input_ids, attention_mask, labels].
>>> outputs = model(**inputs) should work
as_target_tokenizer()[source]¶

Temporarily sets the tokenizer for encoding the targets. Useful for tokenizer associated to sequence-to-sequence models that need a slightly different processing for the labels.

MarianModel¶

class transformers.MarianModel(config: transformers.models.marian.configuration_marian.MarianConfig)[source]¶

The bare Marian Model outputting raw hidden-states without any specific head on top. This model inherits from 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 subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

Parameters

config (MarianConfig) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

forward(input_ids=None, attention_mask=None, decoder_input_ids=None, decoder_attention_mask=None, head_mask=None, decoder_head_mask=None, encoder_outputs=None, past_key_values=None, inputs_embeds=None, decoder_inputs_embeds=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]¶

The MarianModel forward method, overrides the __call__() special method.

Note

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.

Parameters

  • input_ids (torch.LongTensor of shape (batch_size, sequence_length)) –

    Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

    Indices can be obtained using MarianTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

    What are 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?

  • 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 MarianTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

    What are input IDs?

    Marian uses the pad_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.LongTensor 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.

    If you want to change padding behavior, you should read modeling_marian._prepare_decoder_inputs() and modify to your needs. See diagram 1 in the paper for more information on the default strategy.

  • head_mask (torch.Tensor of shape (num_layers, num_heads), optional) –

    Mask to nullify selected heads of the attention modules in the encoder. Mask values selected in [0, 1]:

    • 1 indicates the head is not masked,

    • 0 indicates the heas is masked.

  • decoder_head_mask (torch.Tensor of shape (num_layers, num_heads), optional) –

    Mask to nullify selected heads of the attention modules in the decoder. Mask values selected in [0, 1]:

    • 1 indicates the head is not masked,

    • 0 indicates the head is masked.

  • encoder_outputs (tuple(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 (Tuple[Tuple[torch.Tensor]] of length config.n_layers with each tuple having 2 tuples each of which has 2 tensors of shape (batch_size, num_heads, sequence_length - 1, embed_size_per_head)) –

    Contains precomputed key and value hidden-states of the attention blocks. Can be used to speed up decoding.

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

  • inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) – Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.

  • 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.

  • use_cache (bool, optional) – If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).

  • output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.

  • output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.

  • return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.

Returns

A Seq2SeqModelOutput (if return_dict=True is passed or when config.return_dict=True) or a tuple of torch.FloatTensor comprising various elements depending on the configuration (MarianConfig) and inputs.

  • last_hidden_state (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size)) – Sequence of hidden-states at the output of the last layer of the 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 (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) – Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

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

  • 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 + 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 + 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:

>>> from transformers import MarianTokenizer, MarianModel

>>> tokenizer = MarianTokenizer.from_pretrained('Helsinki-NLP/opus-mt-en-de')
>>> model = MarianModel.from_pretrained('Helsinki-NLP/opus-mt-en-de')

>>> 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("<pad> Studien haben gezeigt dass es hilfreich ist einen Hund zu besitzen",
... return_tensors="pt", add_special_tokens=False).input_ids  # Batch size 1
>>> outputs = model(input_ids=input_ids, decoder_input_ids=decoder_input_ids)

>>> last_hidden_states = outputs.last_hidden_state

Return type

Seq2SeqModelOutput or tuple(torch.FloatTensor)

MarianMTModel¶

class transformers.MarianMTModel(config: transformers.models.marian.configuration_marian.MarianConfig)[source]¶

The Marian Model with a language modeling head. Can be used for summarization. This model inherits from 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 subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

Parameters

config (MarianConfig) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

forward(input_ids=None, attention_mask=None, decoder_input_ids=None, decoder_attention_mask=None, head_mask=None, decoder_head_mask=None, encoder_outputs=None, past_key_values=None, inputs_embeds=None, decoder_inputs_embeds=None, labels=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]¶

The MarianMTModel forward method, overrides the __call__() special method.

Note

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.

Parameters

  • input_ids (torch.LongTensor of shape (batch_size, sequence_length)) –

    Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

    Indices can be obtained using MarianTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

    What are 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?

  • 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 MarianTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

    What are input IDs?

    Marian uses the pad_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.LongTensor 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.

    If you want to change padding behavior, you should read modeling_marian._prepare_decoder_inputs() and modify to your needs. See diagram 1 in the paper for more information on the default strategy.

  • head_mask (torch.Tensor of shape (num_layers, num_heads), optional) –

    Mask to nullify selected heads of the attention modules in the encoder. Mask values selected in [0, 1]:

    • 1 indicates the head is not masked,

    • 0 indicates the heas is masked.

  • decoder_head_mask (torch.Tensor of shape (num_layers, num_heads), optional) –

    Mask to nullify selected heads of the attention modules in the decoder. Mask values selected in [0, 1]:

    • 1 indicates the head is not masked,

    • 0 indicates the head is masked.

  • encoder_outputs (tuple(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 (Tuple[Tuple[torch.Tensor]] of length config.n_layers with each tuple having 2 tuples each of which has 2 tensors of shape (batch_size, num_heads, sequence_length - 1, embed_size_per_head)) –

    Contains precomputed key and value hidden-states of the attention blocks. Can be used to speed up decoding.

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

  • inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) – Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.

  • 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.

  • use_cache (bool, optional) – If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).

  • output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.

  • output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.

  • return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.

  • labels (torch.LongTensor of shape (batch_size, sequence_length), optional) – Labels for 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].

Returns

A Seq2SeqLMOutput (if return_dict=True is passed or when config.return_dict=True) or a tuple of torch.FloatTensor comprising various elements depending on the configuration (MarianConfig) and inputs.

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

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

  • 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 + 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 + 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.

Pytorch version of marian-nmt’s transformer.h (c++). Designed for the OPUS-NMT translation checkpoints. Available models are listed here.

Examples:

>>> from transformers import MarianTokenizer, MarianMTModel
>>> from typing import List
>>> src = 'fr'  # source language
>>> trg = 'en'  # target language
>>> sample_text = "oĂą est l'arrĂŞt de bus ?"
>>> model_name = f'Helsinki-NLP/opus-mt-{src}-{trg}'

>>> model = MarianMTModel.from_pretrained(model_name)
>>> tokenizer = MarianTokenizer.from_pretrained(model_name)
>>> batch = tokenizer([sample_text], return_tensors="pt")
>>> gen = model.generate(**batch)
>>> tokenizer.batch_decode(gen, skip_special_tokens=True)
"Where is the bus stop ?"

Return type

Seq2SeqLMOutput or tuple(torch.FloatTensor)

MarianForCausalLM¶

class transformers.MarianForCausalLM(config)[source]¶
forward(input_ids=None, attention_mask=None, encoder_hidden_states=None, encoder_attention_mask=None, head_mask=None, encoder_head_mask=None, past_key_values=None, inputs_embeds=None, labels=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]¶
Args:
input_ids (torch.LongTensor of shape (batch_size, sequence_length)):

Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

Indices can be obtained using MarianTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

What are 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?

encoder_hidden_states (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional):

Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder.

encoder_attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional):

Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in [0, 1]:

head_mask (torch.Tensor of shape (num_layers, num_heads), optional):

Mask to nullify selected heads of the attention modules. Mask values selected in [0, 1]:

  • 1 indicates the head is not masked,

  • 0 indicates the heas is masked.

encoder_head_mask (torch.Tensor of shape (num_layers, num_heads), optional):

Mask to nullify selected heads of the attention modules in encoder to avoid performing cross-attention on hidden heads. Mask values selected in [0, 1]:

  • 1 indicates the head is not masked,

  • 0 indicates the heas is masked.

past_key_values (tuple(tuple(torch.FloatTensor)) of length config.n_layers with each tuple having 4 tensors of shape (batch_size, num_heads, sequence_length - 1, embed_size_per_head)):

Contains precomputed key and value hidden-states of the attention blocks. Can be used to speed up decoding.

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

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).

  • 1 for tokens that are not masked,

  • 0 for tokens that are masked.

output_attentions (bool, optional):

Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.

output_hidden_states (bool, optional):

Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.

return_dict (bool, optional):

Whether or not to return a ModelOutput instead of a plain tuple.

Returns

A CausalLMOutputWithCrossAttentions (if return_dict=True is passed or when config.return_dict=True) or a tuple of torch.FloatTensor comprising various elements depending on the configuration (MarianConfig) and inputs.

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

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

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

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

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

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

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

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

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

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

Example:

>>> from transformers import MarianTokenizer, MarianForCausalLM

>>> tokenizer = MarianTokenizer.from_pretrained('facebook/bart-large')
>>> model = MarianForCausalLM.from_pretrained('facebook/bart-large', add_cross_attention=False)
>>> 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)

>>> last_hidden_states = outputs.last_hidden_state

Return type

CausalLMOutputWithCrossAttentions or tuple(torch.FloatTensor)

TFMarianModel¶

class transformers.TFMarianModel(*args, **kwargs)[source]¶

The bare MARIAN Model outputting raw hidden-states without any specific head on top. This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

Note

TF 2.0 models accepts two formats as inputs:

  • having all inputs as keyword arguments (like PyTorch models), or

  • having all inputs as a list, tuple or dict in the first positional arguments.

This second option is useful when using tf.keras.Model.fit() method which currently requires having all the tensors in the first argument of the model call function: model(inputs).

If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :

  • a single Tensor with input_ids only and nothing else: model(input_ids)

  • a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: model([input_ids, attention_mask]) or model([input_ids, attention_mask, token_type_ids])

  • a dictionary with one or several input Tensors associated to the input names given in the docstring: model({"input_ids": input_ids, "token_type_ids": token_type_ids})

Parameters

config (MarianConfig) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

call(input_ids=None, attention_mask=None, decoder_input_ids=None, decoder_attention_mask=None, head_mask=None, decoder_head_mask=None, encoder_outputs: Optional[Union[Tuple, transformers.modeling_tf_outputs.TFBaseModelOutput]] = None, past_key_values=None, inputs_embeds=None, decoder_inputs_embeds=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None, training=False, **kwargs)[source]¶

The TFMarianModel forward method, overrides the __call__() special method.

Note

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.

Parameters

  • input_ids (tf.Tensor of shape (batch_size, sequence_length)) –

    Indices of input sequence tokens in the vocabulary.

    Indices can be obtained using MarianTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

    What are input IDs?

  • attention_mask (tf.Tensor of shape (batch_size, sequence_length), optional) –

    Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:

    • 1 for tokens that are not masked,

    • 0 for tokens that are masked.

    What are attention masks?

  • decoder_input_ids (tf.Tensor of shape (batch_size, target_sequence_length), optional) –

    Indices of decoder input sequence tokens in the vocabulary.

    Indices can be obtained using MarianTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

    What are input IDs?

    Marian uses the pad_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 (tf.Tensor of shape (batch_size, target_sequence_length), optional) – will be made by default and ignore pad tokens. It is not recommended to set this for most use cases.

  • head_mask (tf.Tensor of shape (encoder_layers, encoder_attention_heads), optional) –

    Mask to nullify selected heads of the attention modules in the encoder. Mask values selected in [0, 1]:

    • 1 indicates the head is not masked,

    • 0 indicates the heas is masked.

  • decoder_head_mask (tf.Tensor of shape (decoder_layers, decoder_attention_heads), optional) –

    Mask to nullify selected heads of the attention modules in the decoder. Mask values selected in [0, 1]:

    • 1 indicates the head is not masked,

    • 0 indicates the head is masked.

  • encoder_outputs (tf.FloatTensor, optional) – hidden states at the output of the last layer of the encoder. Used in the cross-attention of the decoder. of shape (batch_size, sequence_length, hidden_size) is a sequence of

  • past_key_values (Tuple[Tuple[tf.Tensor]] of length config.n_layers) – contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding. If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all decoder_input_ids of shape (batch_size, sequence_length).

  • use_cache (bool, optional, defaults to True) – If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values). Set to False during training, True during generation

  • output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.

  • output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.

  • return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.

  • training (bool, optional, defaults to False) – Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).

Returns

A TFSeq2SeqModelOutput (if return_dict=True is passed or when config.return_dict=True) or a tuple of tf.Tensor comprising various elements depending on the configuration (MarianConfig) and inputs.

  • last_hidden_state (tf.Tensor of shape (batch_size, sequence_length, hidden_size)) – Sequence of hidden-states at the output of the last layer of the 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 (List[tf.Tensor], optional, returned when use_cache=True is passed or when config.use_cache=True) – List of tf.Tensor of length config.n_layers, with each tensor of shape (2, batch_size, num_heads, sequence_length, embed_size_per_head)).

    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(tf.Tensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of tf.Tensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

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

  • decoder_attentions (tuple(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of tf.Tensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

  • encoder_last_hidden_state (tf.Tensor 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(tf.Tensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of tf.Tensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

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

  • encoder_attentions (tuple(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of tf.Tensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

Return type

TFSeq2SeqModelOutput or tuple(tf.Tensor)

Example:

>>> from transformers import MarianTokenizer, TFMarianModel
>>> import tensorflow as tf

>>> tokenizer = MarianTokenizer.from_pretrained('Helsinki-NLP/opus-mt-en-de')
>>> model = TFMarianModel.from_pretrained('Helsinki-NLP/opus-mt-en-de')

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

>>> last_hidden_states = outputs.last_hidden_state

TFMarianMTModel¶

class transformers.TFMarianMTModel(*args, **kwargs)[source]¶

The MARIAN Model with a language modeling head. Can be used for summarization. This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

Note

TF 2.0 models accepts two formats as inputs:

  • having all inputs as keyword arguments (like PyTorch models), or

  • having all inputs as a list, tuple or dict in the first positional arguments.

This second option is useful when using tf.keras.Model.fit() method which currently requires having all the tensors in the first argument of the model call function: model(inputs).

If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :

  • a single Tensor with input_ids only and nothing else: model(input_ids)

  • a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: model([input_ids, attention_mask]) or model([input_ids, attention_mask, token_type_ids])

  • a dictionary with one or several input Tensors associated to the input names given in the docstring: model({"input_ids": input_ids, "token_type_ids": token_type_ids})

Parameters

config (MarianConfig) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

call(input_ids=None, attention_mask=None, decoder_input_ids=None, decoder_attention_mask=None, head_mask=None, decoder_head_mask=None, encoder_outputs: Optional[transformers.modeling_tf_outputs.TFBaseModelOutput] = None, past_key_values=None, inputs_embeds=None, decoder_inputs_embeds=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None, labels=None, training=False, **kwargs)[source]¶

The TFMarianMTModel forward method, overrides the __call__() special method.

Note

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.

Parameters

  • input_ids (tf.Tensor of shape ({0})) –

    Indices of input sequence tokens in the vocabulary.

    Indices can be obtained using MarianTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

    What are input IDs?

  • attention_mask (tf.Tensor of shape ({0}), optional) –

    Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:

    • 1 for tokens that are not masked,

    • 0 for tokens that are masked.

    What are attention masks?

  • decoder_input_ids (tf.Tensor of shape (batch_size, target_sequence_length), optional) –

    Indices of decoder input sequence tokens in the vocabulary.

    Indices can be obtained using MarianTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

    What are input IDs?

    Marian uses the pad_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 (tf.Tensor of shape (batch_size, target_sequence_length), optional) – will be made by default and ignore pad tokens. It is not recommended to set this for most use cases.

  • head_mask (tf.Tensor of shape (encoder_layers, encoder_attention_heads), optional) –

    Mask to nullify selected heads of the attention modules in the encoder. Mask values selected in [0, 1]:

    • 1 indicates the head is not masked,

    • 0 indicates the heas is masked.

  • decoder_head_mask (tf.Tensor of shape (decoder_layers, decoder_attention_heads), optional) –

    Mask to nullify selected heads of the attention modules in the decoder. Mask values selected in [0, 1]:

    • 1 indicates the head is not masked,

    • 0 indicates the head is masked.

  • encoder_outputs (tf.FloatTensor, optional) – hidden states at the output of the last layer of the encoder. Used in the cross-attention of the decoder. of shape (batch_size, sequence_length, hidden_size) is a sequence of

  • past_key_values (Tuple[Tuple[tf.Tensor]] of length config.n_layers) – contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding. If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all decoder_input_ids of shape (batch_size, sequence_length).

  • use_cache (bool, optional, defaults to True) – If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values). Set to False during training, True during generation

  • output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.

  • output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.

  • return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.

  • training (bool, optional, defaults to False) – Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).

  • labels (tf.tensor of shape (batch_size, sequence_length), optional) – Labels for computing the masked language modeling loss. Indices should 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].

Returns

A TFSeq2SeqLMOutput (if return_dict=True is passed or when config.return_dict=True) or a tuple of tf.Tensor comprising various elements depending on the configuration (MarianConfig) and inputs.

  • loss (tf.Tensor of shape (n,), optional, where n is the number of non-masked labels, returned when labels is provided) – Language modeling loss.

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

  • past_key_values (List[tf.Tensor], optional, returned when use_cache=True is passed or when config.use_cache=True) – List of tf.Tensor of length config.n_layers, with each tensor of shape (2, batch_size, num_heads, sequence_length, embed_size_per_head)).

    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(tf.Tensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of tf.Tensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

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

  • decoder_attentions (tuple(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of tf.Tensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

  • encoder_last_hidden_state (tf.Tensor 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(tf.Tensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of tf.Tensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

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

  • encoder_attentions (tuple(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of tf.Tensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

TF version of marian-nmt’s transformer.h (c++). Designed for the OPUS-NMT translation checkpoints. Available models are listed here.

Examples:

>>> from transformers import MarianTokenizer, TFMarianMTModel
>>> from typing import List
>>> src = 'fr'  # source language
>>> trg = 'en'  # target language
>>> sample_text = "oĂą est l'arrĂŞt de bus ?"
>>> model_name = f'Helsinki-NLP/opus-mt-{src}-{trg}'

>>> model = TFMarianMTModel.from_pretrained(model_name)
>>> tokenizer = MarianTokenizer.from_pretrained(model_name)
>>> batch = tokenizer([sample_text], return_tensors="tf")
>>> gen = model.generate(**batch)
>>> tokenizer.batch_decode(gen, skip_special_tokens=True)
"Where is the bus stop ?"

Return type

TFSeq2SeqLMOutput or tuple(tf.Tensor)