Transformers
  • 🌍GET STARTED
    • Transformers
    • Quick tour
    • Installation
  • 🌍TUTORIALS
    • Run inference with pipelines
    • Write portable code with AutoClass
    • Preprocess data
    • Fine-tune a pretrained model
    • Train with a script
    • Set up distributed training with BOINC AI Accelerate
    • Load and train adapters with BOINC AI PEFT
    • Share your model
    • Agents
    • Generation with LLMs
  • 🌍TASK GUIDES
    • 🌍NATURAL LANGUAGE PROCESSING
      • Text classification
      • Token classification
      • Question answering
      • Causal language modeling
      • Masked language modeling
      • Translation
      • Summarization
      • Multiple choice
    • 🌍AUDIO
      • Audio classification
      • Automatic speech recognition
    • 🌍COMPUTER VISION
      • Image classification
      • Semantic segmentation
      • Video classification
      • Object detection
      • Zero-shot object detection
      • Zero-shot image classification
      • Depth estimation
    • 🌍MULTIMODAL
      • Image captioning
      • Document Question Answering
      • Visual Question Answering
      • Text to speech
    • 🌍GENERATION
      • Customize the generation strategy
    • 🌍PROMPTING
      • Image tasks with IDEFICS
  • 🌍DEVELOPER GUIDES
    • Use fast tokenizers from BOINC AI Tokenizers
    • Run inference with multilingual models
    • Use model-specific APIs
    • Share a custom model
    • Templates for chat models
    • Run training on Amazon SageMaker
    • Export to ONNX
    • Export to TFLite
    • Export to TorchScript
    • Benchmarks
    • Notebooks with examples
    • Community resources
    • Custom Tools and Prompts
    • Troubleshoot
  • 🌍PERFORMANCE AND SCALABILITY
    • Overview
    • 🌍EFFICIENT TRAINING TECHNIQUES
      • Methods and tools for efficient training on a single GPU
      • Multiple GPUs and parallelism
      • Efficient training on CPU
      • Distributed CPU training
      • Training on TPUs
      • Training on TPU with TensorFlow
      • Training on Specialized Hardware
      • Custom hardware for training
      • Hyperparameter Search using Trainer API
    • 🌍OPTIMIZING INFERENCE
      • Inference on CPU
      • Inference on one GPU
      • Inference on many GPUs
      • Inference on Specialized Hardware
    • Instantiating a big model
    • Troubleshooting
    • XLA Integration for TensorFlow Models
    • Optimize inference using `torch.compile()`
  • 🌍CONTRIBUTE
    • How to contribute to transformers?
    • How to add a model to BOINC AI Transformers?
    • How to convert a BOINC AI Transformers model to TensorFlow?
    • How to add a pipeline to BOINC AI Transformers?
    • Testing
    • Checks on a Pull Request
  • 🌍CONCEPTUAL GUIDES
    • Philosophy
    • Glossary
    • What BOINC AI Transformers can do
    • How BOINC AI Transformers solve tasks
    • The Transformer model family
    • Summary of the tokenizers
    • Attention mechanisms
    • Padding and truncation
    • BERTology
    • Perplexity of fixed-length models
    • Pipelines for webserver inference
    • Model training anatomy
  • 🌍API
    • 🌍MAIN CLASSES
      • Agents and Tools
      • 🌍Auto Classes
        • Extending the Auto Classes
        • AutoConfig
        • AutoTokenizer
        • AutoFeatureExtractor
        • AutoImageProcessor
        • AutoProcessor
        • Generic model classes
          • AutoModel
          • TFAutoModel
          • FlaxAutoModel
        • Generic pretraining classes
          • AutoModelForPreTraining
          • TFAutoModelForPreTraining
          • FlaxAutoModelForPreTraining
        • Natural Language Processing
          • AutoModelForCausalLM
          • TFAutoModelForCausalLM
          • FlaxAutoModelForCausalLM
          • AutoModelForMaskedLM
          • TFAutoModelForMaskedLM
          • FlaxAutoModelForMaskedLM
          • AutoModelForMaskGenerationge
          • TFAutoModelForMaskGeneration
          • AutoModelForSeq2SeqLM
          • TFAutoModelForSeq2SeqLM
          • FlaxAutoModelForSeq2SeqLM
          • AutoModelForSequenceClassification
          • TFAutoModelForSequenceClassification
          • FlaxAutoModelForSequenceClassification
          • AutoModelForMultipleChoice
          • TFAutoModelForMultipleChoice
          • FlaxAutoModelForMultipleChoice
          • AutoModelForNextSentencePrediction
          • TFAutoModelForNextSentencePrediction
          • FlaxAutoModelForNextSentencePrediction
          • AutoModelForTokenClassification
          • TFAutoModelForTokenClassification
          • FlaxAutoModelForTokenClassification
          • AutoModelForQuestionAnswering
          • TFAutoModelForQuestionAnswering
          • FlaxAutoModelForQuestionAnswering
          • AutoModelForTextEncoding
          • TFAutoModelForTextEncoding
        • Computer vision
          • AutoModelForDepthEstimation
          • AutoModelForImageClassification
          • TFAutoModelForImageClassification
          • FlaxAutoModelForImageClassification
          • AutoModelForVideoClassification
          • AutoModelForMaskedImageModeling
          • TFAutoModelForMaskedImageModeling
          • AutoModelForObjectDetection
          • AutoModelForImageSegmentation
          • AutoModelForImageToImage
          • AutoModelForSemanticSegmentation
          • TFAutoModelForSemanticSegmentation
          • AutoModelForInstanceSegmentation
          • AutoModelForUniversalSegmentation
          • AutoModelForZeroShotImageClassification
          • TFAutoModelForZeroShotImageClassification
          • AutoModelForZeroShotObjectDetection
        • Audio
          • AutoModelForAudioClassification
          • AutoModelForAudioFrameClassification
          • TFAutoModelForAudioFrameClassification
          • AutoModelForCTC
          • AutoModelForSpeechSeq2Seq
          • TFAutoModelForSpeechSeq2Seq
          • FlaxAutoModelForSpeechSeq2Seq
          • AutoModelForAudioXVector
          • AutoModelForTextToSpectrogram
          • AutoModelForTextToWaveform
        • Multimodal
          • AutoModelForTableQuestionAnswering
          • TFAutoModelForTableQuestionAnswering
          • AutoModelForDocumentQuestionAnswering
          • TFAutoModelForDocumentQuestionAnswering
          • AutoModelForVisualQuestionAnswering
          • AutoModelForVision2Seq
          • TFAutoModelForVision2Seq
          • FlaxAutoModelForVision2Seq
      • Callbacks
      • Configuration
      • Data Collator
      • Keras callbacks
      • Logging
      • Models
      • Text Generation
      • ONNX
      • Optimization
      • Model outputs
      • Pipelines
      • Processors
      • Quantization
      • Tokenizer
      • Trainer
      • DeepSpeed Integration
      • Feature Extractor
      • Image Processor
    • 🌍MODELS
      • 🌍TEXT MODELS
        • ALBERT
        • BART
        • BARThez
        • BARTpho
        • BERT
        • BertGeneration
        • BertJapanese
        • Bertweet
        • BigBird
        • BigBirdPegasus
        • BioGpt
        • Blenderbot
        • Blenderbot Small
        • BLOOM
        • BORT
        • ByT5
        • CamemBERT
        • CANINE
        • CodeGen
        • CodeLlama
        • ConvBERT
        • CPM
        • CPMANT
        • CTRL
        • DeBERTa
        • DeBERTa-v2
        • DialoGPT
        • DistilBERT
        • DPR
        • ELECTRA
        • Encoder Decoder Models
        • ERNIE
        • ErnieM
        • ESM
        • Falcon
        • FLAN-T5
        • FLAN-UL2
        • FlauBERT
        • FNet
        • FSMT
        • Funnel Transformer
        • GPT
        • GPT Neo
        • GPT NeoX
        • GPT NeoX Japanese
        • GPT-J
        • GPT2
        • GPTBigCode
        • GPTSAN Japanese
        • GPTSw3
        • HerBERT
        • I-BERT
        • Jukebox
        • LED
        • LLaMA
        • LLama2
        • Longformer
        • LongT5
        • LUKE
        • M2M100
        • MarianMT
        • MarkupLM
        • MBart and MBart-50
        • MEGA
        • MegatronBERT
        • MegatronGPT2
        • Mistral
        • mLUKE
        • MobileBERT
        • MPNet
        • MPT
        • MRA
        • MT5
        • MVP
        • NEZHA
        • NLLB
        • NLLB-MoE
        • NystrΓΆmformer
        • Open-Llama
        • OPT
        • Pegasus
        • PEGASUS-X
        • Persimmon
        • PhoBERT
        • PLBart
        • ProphetNet
        • QDQBert
        • RAG
        • REALM
        • Reformer
        • RemBERT
        • RetriBERT
        • RoBERTa
        • RoBERTa-PreLayerNorm
        • RoCBert
        • RoFormer
        • RWKV
        • Splinter
        • SqueezeBERT
        • SwitchTransformers
        • T5
        • T5v1.1
        • TAPEX
        • Transformer XL
        • UL2
        • UMT5
        • X-MOD
        • XGLM
        • XLM
        • XLM-ProphetNet
        • XLM-RoBERTa
        • XLM-RoBERTa-XL
        • XLM-V
        • XLNet
        • YOSO
      • 🌍VISION MODELS
        • BEiT
        • BiT
        • Conditional DETR
        • ConvNeXT
        • ConvNeXTV2
        • CvT
        • Deformable DETR
        • DeiT
        • DETA
        • DETR
        • DiNAT
        • DINO V2
        • DiT
        • DPT
        • EfficientFormer
        • EfficientNet
        • FocalNet
        • GLPN
        • ImageGPT
        • LeViT
        • Mask2Former
        • MaskFormer
        • MobileNetV1
        • MobileNetV2
        • MobileViT
        • MobileViTV2
        • NAT
        • PoolFormer
        • Pyramid Vision Transformer (PVT)
        • RegNet
        • ResNet
        • SegFormer
        • SwiftFormer
        • Swin Transformer
        • Swin Transformer V2
        • Swin2SR
        • Table Transformer
        • TimeSformer
        • UperNet
        • VAN
        • VideoMAE
        • Vision Transformer (ViT)
        • ViT Hybrid
        • ViTDet
        • ViTMAE
        • ViTMatte
        • ViTMSN
        • ViViT
        • YOLOS
      • 🌍AUDIO MODELS
        • Audio Spectrogram Transformer
        • Bark
        • CLAP
        • EnCodec
        • Hubert
        • MCTCT
        • MMS
        • MusicGen
        • Pop2Piano
        • SEW
        • SEW-D
        • Speech2Text
        • Speech2Text2
        • SpeechT5
        • UniSpeech
        • UniSpeech-SAT
        • VITS
        • Wav2Vec2
        • Wav2Vec2-Conformer
        • Wav2Vec2Phoneme
        • WavLM
        • Whisper
        • XLS-R
        • XLSR-Wav2Vec2
      • 🌍MULTIMODAL MODELS
        • ALIGN
        • AltCLIP
        • BLIP
        • BLIP-2
        • BridgeTower
        • BROS
        • Chinese-CLIP
        • CLIP
        • CLIPSeg
        • Data2Vec
        • DePlot
        • Donut
        • FLAVA
        • GIT
        • GroupViT
        • IDEFICS
        • InstructBLIP
        • LayoutLM
        • LayoutLMV2
        • LayoutLMV3
        • LayoutXLM
        • LiLT
        • LXMERT
        • MatCha
        • MGP-STR
        • Nougat
        • OneFormer
        • OWL-ViT
        • Perceiver
        • Pix2Struct
        • Segment Anything
        • Speech Encoder Decoder Models
        • TAPAS
        • TrOCR
        • TVLT
        • ViLT
        • Vision Encoder Decoder Models
        • Vision Text Dual Encoder
        • VisualBERT
        • X-CLIP
      • 🌍REINFORCEMENT LEARNING MODELS
        • Decision Transformer
        • Trajectory Transformer
      • 🌍TIME SERIES MODELS
        • Autoformer
        • Informer
        • Time Series Transformer
      • 🌍GRAPH MODELS
        • Graphormer
  • 🌍INTERNAL HELPERS
    • Custom Layers and Utilities
    • Utilities for pipelines
    • Utilities for Tokenizers
    • Utilities for Trainer
    • Utilities for Generation
    • Utilities for Image Processors
    • Utilities for Audio processing
    • General Utilities
    • Utilities for Time Series
Powered by GitBook
On this page
  • MarianMT
  • Implementation Notes
  • Naming
  • Examples
  • Multilingual Models
  • Old Style Multi-Lingual Models
  • Documentation resources
  • MarianConfig
  • MarianTokenizer
  • MarianModel
  • MarianMTModel
  • MarianForCausalLM
  • TFMarianModel
  • TFMarianMTModel
  • FlaxMarianModel
  • FlaxMarianMTModel
  1. API
  2. MODELS
  3. TEXT MODELS

MarianMT

PreviousM2M100NextMarkupLM

Last updated 1 year ago

MarianMT

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

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

Tips:

  • A framework for translation models, using the same models as BART.

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 .

  • Models were originally trained by using the 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 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.

  • This model was contributed by .

Naming

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

  • 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

  • Since Marian models are smaller than many other translation models available in the library, they can be useful for fine-tuning experiments and integration tests.

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.

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

Copied

>>> 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 franΓ§ais",
 'Isto deve ir para o portuguΓͺs.',
 'Y esto al espaΓ±ol']

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

Copied

from boincai_hub import list_models

model_list = list_models()
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:

Copied

['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

Copied

>>> from transformers import MarianMTModel, MarianTokenizer

>>> src_text = [
...     ">>fr<< this is a sentence in english that we want to translate to french",
...     ">>pt<< This should go to portuguese",
...     ">>es<< And this to Spanish",
... ]

>>> model_name = "Helsinki-NLP/opus-mt-en-ROMANCE"
>>> tokenizer = MarianTokenizer.from_pretrained(model_name)

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

Documentation resources

MarianConfig

class transformers.MarianConfig

( vocab_size = 58101decoder_vocab_size = Nonemax_position_embeddings = 1024encoder_layers = 12encoder_ffn_dim = 4096encoder_attention_heads = 16decoder_layers = 12decoder_ffn_dim = 4096decoder_attention_heads = 16encoder_layerdrop = 0.0decoder_layerdrop = 0.0use_cache = Trueis_encoder_decoder = Trueactivation_function = 'gelu'd_model = 1024dropout = 0.1attention_dropout = 0.0activation_dropout = 0.0init_std = 0.02decoder_start_token_id = 58100scale_embedding = Falsepad_token_id = 58100eos_token_id = 0forced_eos_token_id = 0share_encoder_decoder_embeddings = True**kwargs )

Parameters

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

  • encoder_layers (int, optional, defaults to 12) β€” Number of encoder layers.

  • decoder_layers (int, optional, defaults to 12) β€” Number of decoder layers.

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

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

  • decoder_ffn_dim (int, optional, defaults to 4096) β€” Dimensionality of the β€œintermediate” (often named feed-forward) layer in decoder.

  • encoder_ffn_dim (int, optional, defaults to 4096) β€” Dimensionality of the β€œintermediate” (often named feed-forward) layer in decoder.

  • activation_function (str or function, optional, defaults to "gelu") β€” 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) β€” The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.

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

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

  • max_position_embeddings (int, optional, defaults to 1024) β€” 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) β€” The standard deviation of the truncated_normal_initializer for initializing all weight matrices.

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

  • use_cache (bool, optional, defaults to True) β€” 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) β€” The id of the token to force as the last generated token when max_length is reached. Usually set to eos_token_id.

Examples:

Copied

>>> 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

( source_spmtarget_spmvocabtarget_vocab_file = Nonesource_lang = Nonetarget_lang = Noneunk_token = '<unk>'eos_token = '</s>'pad_token = '<pad>'model_max_length = 512sp_model_kwargs: typing.Union[typing.Dict[str, typing.Any], NoneType] = Noneseparate_vocabs = False**kwargs )

Parameters

  • source_lang (str, optional) β€” A string representing the source language.

  • target_lang (str, optional) β€” A string representing the target language.

  • unk_token (str, optional, defaults to "<unk>") β€” 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>") β€” The end of sequence token.

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

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

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

    • enable_sampling: Enable subword regularization.

    • nbest_size: Sampling parameters for unigram. Invalid for BPE-Dropout.

      • nbest_size = {0,1}: No sampling is performed.

      • nbest_size > 1: samples from the nbest_size results.

      • nbest_size < 0: assuming that nbest_size is infinite and samples from the all hypothesis (lattice) using forward-filtering-and-backward-sampling algorithm.

    • alpha: Smoothing parameter for unigram sampling, and dropout probability of merge operations for BPE-dropout.

Examples:

Copied

>>> from transformers import MarianForCausalLM, MarianTokenizer

>>> model = MarianForCausalLM.from_pretrained("Helsinki-NLP/opus-mt-en-de")
>>> 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, text_target=tgt_texts, return_tensors="pt", padding=True)

>>> outputs = model(**inputs)  # should work

build_inputs_with_special_tokens

( token_ids_0token_ids_1 = None )

Build model inputs from a sequence by appending eos_token_id.

MarianModel

class transformers.MarianModel

( config: MarianConfig )

Parameters

forward

Parameters

  • input_ids (torch.LongTensor of shape (batch_size, sequence_length)) β€” Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

  • attention_mask (torch.Tensor of shape (batch_size, sequence_length), optional) β€” 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.

  • decoder_input_ids (torch.LongTensor of shape (batch_size, target_sequence_length), optional) β€” Indices of decoder input sequence tokens in the vocabulary.

    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) β€” Default behavior: generate a tensor that ignores pad tokens in decoder_input_ids. Causal mask will also be used by default.

  • head_mask (torch.Tensor of shape (encoder_layers, encoder_attention_heads), optional) β€” 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 head is masked.

  • decoder_head_mask (torch.Tensor of shape (decoder_layers, decoder_attention_heads), optional) β€” 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.

  • cross_attn_head_mask (torch.Tensor of shape (decoder_layers, decoder_attention_heads), optional) β€” Mask to nullify selected heads of the cross-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) β€” 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.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) β€” 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.

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

Returns

  • last_hidden_state (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size)) β€” 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) β€” 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) β€” 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) β€” 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) β€” 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) β€” 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) β€” 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) β€” 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.

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

>>> from transformers import AutoTokenizer, MarianModel

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

>>> inputs = tokenizer("Studies have been shown that owning a dog is good for you", return_tensors="pt")
>>> decoder_inputs = tokenizer(
...     "<pad> Studien haben gezeigt dass es hilfreich ist einen Hund zu besitzen",
...     return_tensors="pt",
...     add_special_tokens=False,
... )
>>> outputs = model(input_ids=inputs.input_ids, decoder_input_ids=decoder_inputs.input_ids)

>>> last_hidden_states = outputs.last_hidden_state
>>> list(last_hidden_states.shape)
[1, 26, 512]

MarianMTModel

class transformers.MarianMTModel

( config: MarianConfig )

Parameters

forward

Parameters

  • input_ids (torch.LongTensor of shape (batch_size, sequence_length)) β€” Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

  • attention_mask (torch.Tensor of shape (batch_size, sequence_length), optional) β€” 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.

  • decoder_input_ids (torch.LongTensor of shape (batch_size, target_sequence_length), optional) β€” Indices of decoder input sequence tokens in the vocabulary.

    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) β€” Default behavior: generate a tensor that ignores pad tokens in decoder_input_ids. Causal mask will also be used by default.

  • head_mask (torch.Tensor of shape (encoder_layers, encoder_attention_heads), optional) β€” 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 head is masked.

  • decoder_head_mask (torch.Tensor of shape (decoder_layers, decoder_attention_heads), optional) β€” 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.

  • cross_attn_head_mask (torch.Tensor of shape (decoder_layers, decoder_attention_heads), optional) β€” Mask to nullify selected heads of the cross-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) β€” 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.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) β€” 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.

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

  • labels (torch.LongTensor of shape (batch_size, sequence_length), optional) β€” 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

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) β€” Language modeling loss.

  • logits (torch.FloatTensor of shape (batch_size, sequence_length, config.vocab_size)) β€” 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) β€” 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) β€” 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) β€” 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) β€” 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) β€” 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) β€” 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) β€” 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.

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.

Examples:

Copied

>>> from transformers import AutoTokenizer, MarianMTModel

>>> src = "fr"  # source language
>>> trg = "en"  # target language

>>> model_name = f"Helsinki-NLP/opus-mt-{src}-{trg}"
>>> model = MarianMTModel.from_pretrained(model_name)
>>> tokenizer = AutoTokenizer.from_pretrained(model_name)

>>> sample_text = "oΓΉ est l'arrΓͺt de bus ?"
>>> batch = tokenizer([sample_text], return_tensors="pt")

>>> generated_ids = model.generate(**batch)
>>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
"Where's the bus stop?"

MarianForCausalLM

class transformers.MarianForCausalLM

( config )

forward

Parameters

  • input_ids (torch.LongTensor of shape (batch_size, sequence_length)) β€” Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

  • attention_mask (torch.Tensor of shape (batch_size, sequence_length), optional) β€” 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.

  • encoder_hidden_states (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) β€” 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) β€” 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 (decoder_layers, decoder_attention_heads), optional) β€” Mask to nullify selected heads of the attention modules. Mask values selected in [0, 1]:

    • 1 indicates the head is not masked,

    • 0 indicates the head is masked.

  • cross_attn_head_mask (torch.Tensor of shape (decoder_layers, decoder_attention_heads), optional) β€” Mask to nullify selected heads of the cross-attention modules. Mask values selected in [0, 1]:

    • 1 indicates the head is not masked,

    • 0 indicates the head is masked.

  • past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) β€” 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). The two additional tensors are only required when the model is used as a decoder in a Sequence to Sequence model.

    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.

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

Returns

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

  • logits (torch.FloatTensor of shape (batch_size, sequence_length, config.vocab_size)) β€” 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) β€” Tuple of torch.FloatTensor (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

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

  • attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) β€” 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) β€” 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) β€” 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:

Copied

>>> from transformers import AutoTokenizer, MarianForCausalLM

>>> tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-fr-en")
>>> model = MarianForCausalLM.from_pretrained("Helsinki-NLP/opus-mt-fr-en", 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)

>>> logits = outputs.logits
>>> expected_shape = [1, inputs.input_ids.shape[-1], model.config.vocab_size]
>>> list(logits.shape) == expected_shape
True

TFMarianModel

class transformers.TFMarianModel

( *args**kwargs )

Parameters

TensorFlow models and layers in transformers accept two formats as input:

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

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

The reason the second format is supported is that Keras methods prefer this format when passing inputs to models and layers. Because of this support, when using methods like model.fit() things should β€œjust work” for you - just pass your inputs and labels in any format that model.fit() supports! If, however, you want to use the second format outside of Keras methods like fit() and predict(), such as when creating your own layers or models with the Keras Functional API, there are three possibilities you can use to gather all the input Tensors in the first positional argument:

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

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

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

call

Parameters

  • input_ids (tf.Tensor of shape (batch_size, sequence_length)) β€” Indices of input sequence tokens in the vocabulary.

  • attention_mask (tf.Tensor of shape (batch_size, sequence_length), optional) β€” 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.

  • decoder_input_ids (tf.Tensor of shape (batch_size, target_sequence_length), optional) β€” Indices of decoder input sequence tokens in the vocabulary.

    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) β€” will be made by default and ignore pad tokens. It is not recommended to set this for most use cases.

  • decoder_position_ids (tf.Tensor of shape (batch_size, sequence_length), optional) β€” Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

  • head_mask (tf.Tensor of shape (encoder_layers, encoder_attention_heads), optional) β€” 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 head is masked.

  • decoder_head_mask (tf.Tensor of shape (decoder_layers, decoder_attention_heads), optional) β€” 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.

  • cross_attn_head_mask (tf.Tensor of shape (decoder_layers, decoder_attention_heads), optional) β€” Mask to nullify selected heads of the cross-attention modules. Mask values selected in [0, 1]:

    • 1 indicates the head is not masked,

    • 0 indicates the head is masked.

  • encoder_outputs (tf.FloatTensor, optional) β€” 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) β€” 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) β€” 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) β€” 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) β€” 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.

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

Returns

  • last_hidden_state (tf.Tensor of shape (batch_size, sequence_length, hidden_size)) β€” 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) β€” 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) β€” 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) β€” 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.

  • cross_attentions (tuple(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) β€” Tuple of tf.Tensor (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 (tf.Tensor of shape (batch_size, sequence_length, hidden_size), optional) β€” 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) β€” 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) β€” 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.

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

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

>>> tokenizer = AutoTokenizer.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 )

Parameters

TensorFlow models and layers in transformers accept two formats as input:

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

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

The reason the second format is supported is that Keras methods prefer this format when passing inputs to models and layers. Because of this support, when using methods like model.fit() things should β€œjust work” for you - just pass your inputs and labels in any format that model.fit() supports! If, however, you want to use the second format outside of Keras methods like fit() and predict(), such as when creating your own layers or models with the Keras Functional API, there are three possibilities you can use to gather all the input Tensors in the first positional argument:

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

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

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

call

Parameters

  • input_ids (tf.Tensor of shape ({0})) β€” Indices of input sequence tokens in the vocabulary.

  • attention_mask (tf.Tensor of shape ({0}), optional) β€” 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.

  • decoder_input_ids (tf.Tensor of shape (batch_size, target_sequence_length), optional) β€” Indices of decoder input sequence tokens in the vocabulary.

    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) β€” will be made by default and ignore pad tokens. It is not recommended to set this for most use cases.

  • decoder_position_ids (tf.Tensor of shape (batch_size, sequence_length), optional) β€” Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

  • head_mask (tf.Tensor of shape (encoder_layers, encoder_attention_heads), optional) β€” 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 head is masked.

  • decoder_head_mask (tf.Tensor of shape (decoder_layers, decoder_attention_heads), optional) β€” 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.

  • cross_attn_head_mask (tf.Tensor of shape (decoder_layers, decoder_attention_heads), optional) β€” Mask to nullify selected heads of the cross-attention modules. Mask values selected in [0, 1]:

    • 1 indicates the head is not masked,

    • 0 indicates the head is masked.

  • encoder_outputs (tf.FloatTensor, optional) β€” 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) β€” 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) β€” 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) β€” 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) β€” 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.

  • training (bool, optional, defaults to False) β€” 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) β€” 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

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

  • logits (tf.Tensor of shape (batch_size, sequence_length, config.vocab_size)) β€” 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) β€” 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) β€” 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) β€” 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.

  • cross_attentions (tuple(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) β€” Tuple of tf.Tensor (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 (tf.Tensor of shape (batch_size, sequence_length, hidden_size), optional) β€” 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) β€” 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) β€” 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.

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.

Examples:

Copied

>>> from transformers import AutoTokenizer, TFMarianMTModel
>>> from typing import List

>>> src = "fr"  # source language
>>> trg = "en"  # target language
>>> sample_text = "oΓΉ est l'arrΓͺt de bus ?"
>>> model_name = f"Helsinki-NLP/opus-mt-{src}-{trg}"

>>> model = TFMarianMTModel.from_pretrained(model_name)
>>> tokenizer = AutoTokenizer.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 ?"

FlaxMarianModel

class transformers.FlaxMarianModel

( config: MarianConfiginput_shape: typing.Tuple[int] = (1, 1)seed: int = 0dtype: dtype = <class 'jax.numpy.float32'>_do_init: bool = True**kwargs )

Parameters

  • dtype (jax.numpy.dtype, optional, defaults to jax.numpy.float32) β€” The data type of the computation. Can be one of jax.numpy.float32, jax.numpy.float16 (on GPUs) and jax.numpy.bfloat16 (on TPUs).

    This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given dtype.

    Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.

Finally, this model supports inherent JAX features such as:

__call__

Parameters

  • input_ids (jnp.ndarray of shape (batch_size, sequence_length)) β€” Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

  • attention_mask (jnp.ndarray of shape (batch_size, sequence_length), optional) β€” 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.

  • decoder_input_ids (jnp.ndarray of shape (batch_size, target_sequence_length), optional) β€” Indices of decoder input sequence tokens in the vocabulary.

    For translation and summarization training, decoder_input_ids should be provided. If no decoder_input_ids is provided, the model will create this tensor by shifting the input_ids to the right for denoising pre-training following the paper.

  • decoder_attention_mask (jnp.ndarray of shape (batch_size, target_sequence_length), optional) β€” Default behavior: generate a tensor that ignores pad tokens in decoder_input_ids. Causal mask will also be used by default.

  • position_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) β€” Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

  • decoder_position_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) β€” Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

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

Returns

  • last_hidden_state (jnp.ndarray of shape (batch_size, sequence_length, hidden_size)) β€” 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(jnp.ndarray)), optional, returned when use_cache=True is passed or when config.use_cache=True) β€” Tuple of tuple(jnp.ndarray) 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(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) β€” Tuple of jnp.ndarray (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

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

  • decoder_attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) β€” Tuple of jnp.ndarray (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(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) β€” Tuple of jnp.ndarray (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 (jnp.ndarray of shape (batch_size, sequence_length, hidden_size), optional) β€” Sequence of hidden-states at the output of the last layer of the encoder of the model.

  • encoder_hidden_states (tuple(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) β€” Tuple of jnp.ndarray (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

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

  • encoder_attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) β€” Tuple of jnp.ndarray (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.

The FlaxMarianPreTrainedModel forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

>>> from transformers import AutoTokenizer, FlaxMarianModel

>>> tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-en-de")
>>> model = FlaxMarianModel.from_pretrained("Helsinki-NLP/opus-mt-en-de")

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

>>> last_hidden_states = outputs.last_hidden_state

FlaxMarianMTModel

class transformers.FlaxMarianMTModel

( config: MarianConfiginput_shape: typing.Tuple[int] = (1, 1)seed: int = 0dtype: dtype = <class 'jax.numpy.float32'>_do_init: bool = True**kwargs )

Parameters

  • dtype (jax.numpy.dtype, optional, defaults to jax.numpy.float32) β€” The data type of the computation. Can be one of jax.numpy.float32, jax.numpy.float16 (on GPUs) and jax.numpy.bfloat16 (on TPUs).

    This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given dtype.

    Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.

Finally, this model supports inherent JAX features such as:

__call__

Parameters

  • input_ids (jnp.ndarray of shape (batch_size, sequence_length)) β€” Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

  • attention_mask (jnp.ndarray of shape (batch_size, sequence_length), optional) β€” 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.

  • decoder_input_ids (jnp.ndarray of shape (batch_size, target_sequence_length), optional) β€” Indices of decoder input sequence tokens in the vocabulary.

    For translation and summarization training, decoder_input_ids should be provided. If no decoder_input_ids is provided, the model will create this tensor by shifting the input_ids to the right for denoising pre-training following the paper.

  • decoder_attention_mask (jnp.ndarray of shape (batch_size, target_sequence_length), optional) β€” Default behavior: generate a tensor that ignores pad tokens in decoder_input_ids. Causal mask will also be used by default.

  • position_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) β€” Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

  • decoder_position_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) β€” Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

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

Returns

  • logits (jnp.ndarray of shape (batch_size, sequence_length, config.vocab_size)) β€” Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).

  • past_key_values (tuple(tuple(jnp.ndarray)), optional, returned when use_cache=True is passed or when config.use_cache=True) β€” Tuple of tuple(jnp.ndarray) 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(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) β€” Tuple of jnp.ndarray (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

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

  • decoder_attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) β€” Tuple of jnp.ndarray (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(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) β€” Tuple of jnp.ndarray (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 (jnp.ndarray of shape (batch_size, sequence_length, hidden_size), optional) β€” Sequence of hidden-states at the output of the last layer of the encoder of the model.

  • encoder_hidden_states (tuple(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) β€” Tuple of jnp.ndarray (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

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

  • encoder_attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) β€” Tuple of jnp.ndarray (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.

The FlaxMarianPreTrainedModel forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

>>> from transformers import AutoTokenizer, FlaxMarianMTModel

>>> model = FlaxMarianMTModel.from_pretrained("Helsinki-NLP/opus-mt-en-de")
>>> tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-en-de")

>>> text = "My friends are cool but they eat too many carbs."
>>> input_ids = tokenizer(text, max_length=64, return_tensors="jax").input_ids

>>> sequences = model.generate(input_ids, max_length=64, num_beams=2).sequences

>>> outputs = tokenizer.batch_decode(sequences, skip_special_tokens=True)
>>> # should give *Meine Freunde sind cool, aber sie essen zu viele Kohlenhydrate.*

The language codes used to name models are inconsistent. Two digit codes can usually be found , three digit codes require googling β€œlanguage code {code}β€œ.

You can see a models’s supported language codes in its model card, under target constituents, like in .

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

vocab_size (int, optional, defaults to 58101) β€” Vocabulary size of the Marian model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling or .

encoder_layerdrop (float, optional, defaults to 0.0) β€” The LayerDrop probability for the encoder. See the [LayerDrop paper](see ) for more details.

decoder_layerdrop (float, optional, defaults to 0.0) β€” The LayerDrop probability for the decoder. See the [LayerDrop paper](see ) for more details.

This is the configuration class to store the configuration of a . 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 architecture.

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

source_spm (str) β€” file (generally has a .spm extension) that contains the vocabulary for the source language.

target_spm (str) β€” file (generally has a .spm extension) that contains the vocabulary for the target language.

sp_model_kwargs (dict, optional) β€” Will be passed to the SentencePieceProcessor.__init__() method. The can be used, among other things, to set:

Construct a Marian tokenizer. Based on .

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

config () β€” 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 method to load the model weights.

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

( input_ids: LongTensor = Noneattention_mask: typing.Optional[torch.Tensor] = Nonedecoder_input_ids: typing.Optional[torch.LongTensor] = Nonedecoder_attention_mask: typing.Optional[torch.Tensor] = Nonehead_mask: typing.Optional[torch.Tensor] = Nonedecoder_head_mask: typing.Optional[torch.Tensor] = Nonecross_attn_head_mask: typing.Optional[torch.Tensor] = Noneencoder_outputs: typing.Union[typing.Tuple[torch.Tensor], transformers.modeling_outputs.BaseModelOutput, NoneType] = Nonepast_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = Noneinputs_embeds: typing.Optional[torch.FloatTensor] = Nonedecoder_inputs_embeds: typing.Optional[torch.FloatTensor] = Noneuse_cache: typing.Optional[bool] = Noneoutput_attentions: typing.Optional[bool] = Noneoutput_hidden_states: typing.Optional[bool] = Nonereturn_dict: typing.Optional[bool] = None ) β†’ or tuple(torch.FloatTensor)

Indices can be obtained using . See and for details.

Indices can be obtained using . See and for details.

return_dict (bool, optional) β€” Whether or not to return a instead of a plain tuple.

or tuple(torch.FloatTensor)

A 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 () and inputs.

The forward method, overrides the __call__ special method.

config () β€” 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 method to load the model weights.

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

( input_ids: LongTensor = Noneattention_mask: typing.Optional[torch.Tensor] = Nonedecoder_input_ids: typing.Optional[torch.LongTensor] = Nonedecoder_attention_mask: typing.Optional[torch.Tensor] = Nonehead_mask: typing.Optional[torch.Tensor] = Nonedecoder_head_mask: typing.Optional[torch.Tensor] = Nonecross_attn_head_mask: typing.Optional[torch.Tensor] = Noneencoder_outputs: typing.Union[typing.Tuple[torch.Tensor], transformers.modeling_outputs.BaseModelOutput, NoneType] = Nonepast_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = Noneinputs_embeds: typing.Optional[torch.FloatTensor] = Nonedecoder_inputs_embeds: typing.Optional[torch.FloatTensor] = Nonelabels: typing.Optional[torch.LongTensor] = Noneuse_cache: typing.Optional[bool] = Noneoutput_attentions: typing.Optional[bool] = Noneoutput_hidden_states: typing.Optional[bool] = Nonereturn_dict: typing.Optional[bool] = None ) β†’ or tuple(torch.FloatTensor)

Indices can be obtained using . See and for details.

Indices can be obtained using . See and for details.

return_dict (bool, optional) β€” Whether or not to return a instead of a plain tuple.

or tuple(torch.FloatTensor)

A 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 () and inputs.

The forward method, overrides the __call__ special method.

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

( input_ids: LongTensor = Noneattention_mask: typing.Optional[torch.Tensor] = Noneencoder_hidden_states: typing.Optional[torch.FloatTensor] = Noneencoder_attention_mask: typing.Optional[torch.FloatTensor] = Nonehead_mask: typing.Optional[torch.Tensor] = Nonecross_attn_head_mask: typing.Optional[torch.Tensor] = Nonepast_key_values: typing.Optional[typing.List[torch.FloatTensor]] = Noneinputs_embeds: typing.Optional[torch.FloatTensor] = Nonelabels: typing.Optional[torch.LongTensor] = Noneuse_cache: typing.Optional[bool] = Noneoutput_attentions: typing.Optional[bool] = Noneoutput_hidden_states: typing.Optional[bool] = Nonereturn_dict: typing.Optional[bool] = None ) β†’ or tuple(torch.FloatTensor)

Indices can be obtained using . See and for details.

return_dict (bool, optional) β€” Whether or not to return a instead of a plain tuple.

or tuple(torch.FloatTensor)

A 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 () and inputs.

config () β€” 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 method to load the model weights.

The bare MARIAN Model outputting raw hidden-states without any specific head on top. This model inherits from . 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 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 that when creating models and layers with then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function!

( input_ids: tf.Tensor | None = Noneattention_mask: tf.Tensor | None = Nonedecoder_input_ids: tf.Tensor | None = Nonedecoder_attention_mask: tf.Tensor | None = Nonedecoder_position_ids: tf.Tensor | None = Nonehead_mask: tf.Tensor | None = Nonedecoder_head_mask: tf.Tensor | None = Nonecross_attn_head_mask: tf.Tensor | None = Noneencoder_outputs: tf.Tensor | None = Nonepast_key_values: Tuple[Tuple[tf.Tensor]] | None = Noneinputs_embeds: tf.Tensor | None = Nonedecoder_inputs_embeds: tf.Tensor | None = Noneuse_cache: bool | None = Noneoutput_attentions: bool | None = Noneoutput_hidden_states: bool | None = Nonereturn_dict: bool | None = Nonetraining: bool = False**kwargs ) β†’ or tuple(tf.Tensor)

Indices can be obtained using . See and for details.

Indices can be obtained using . See and for details.

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

or tuple(tf.Tensor)

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

The forward method, overrides the __call__ special method.

config () β€” 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 method to load the model weights.

The MARIAN Model with a language modeling head. Can be used for summarization. This model inherits from . 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 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 that when creating models and layers with then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function!

( input_ids: tf.Tensor | None = Noneattention_mask: tf.Tensor | None = Nonedecoder_input_ids: tf.Tensor | None = Nonedecoder_attention_mask: tf.Tensor | None = Nonedecoder_position_ids: tf.Tensor | None = Nonehead_mask: tf.Tensor | None = Nonedecoder_head_mask: tf.Tensor | None = Nonecross_attn_head_mask: tf.Tensor | None = Noneencoder_outputs: TFBaseModelOutput | None = Nonepast_key_values: Tuple[Tuple[tf.Tensor]] | None = Noneinputs_embeds: tf.Tensor | None = Nonedecoder_inputs_embeds: tf.Tensor | None = Noneuse_cache: bool | None = Noneoutput_attentions: bool | None = Noneoutput_hidden_states: bool | None = Nonereturn_dict: bool | None = Nonelabels: tf.Tensor | None = Nonetraining: bool = False ) β†’ or tuple(tf.Tensor)

Indices can be obtained using . See and for details.

Indices can be obtained using . See and for details.

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

or tuple(tf.Tensor)

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

The forward method, overrides the __call__ special method.

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

config () β€” 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 method to load the model weights.

If you wish to change the dtype of the model parameters, see and .

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

( input_ids: Arrayattention_mask: typing.Optional[jax.Array] = Nonedecoder_input_ids: typing.Optional[jax.Array] = Nonedecoder_attention_mask: typing.Optional[jax.Array] = Noneposition_ids: typing.Optional[jax.Array] = Nonedecoder_position_ids: typing.Optional[jax.Array] = Noneoutput_attentions: typing.Optional[bool] = Noneoutput_hidden_states: typing.Optional[bool] = Nonereturn_dict: typing.Optional[bool] = Nonetrain: bool = Falseparams: dict = Nonedropout_rng: PRNGKey = None ) β†’ or tuple(torch.FloatTensor)

Indices can be obtained using . See and for details.

Indices can be obtained using . See and for details.

If you want to change padding behavior, you should modify to your needs. See diagram 1 in for more information on the default strategy.

return_dict (bool, optional) β€” Whether or not to return a instead of a plain tuple.

or tuple(torch.FloatTensor)

A 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 () and inputs.

config () β€” 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 method to load the model weights.

If you wish to change the dtype of the model parameters, see and .

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

( input_ids: Arrayattention_mask: typing.Optional[jax.Array] = Nonedecoder_input_ids: typing.Optional[jax.Array] = Nonedecoder_attention_mask: typing.Optional[jax.Array] = Noneposition_ids: typing.Optional[jax.Array] = Nonedecoder_position_ids: typing.Optional[jax.Array] = Noneoutput_attentions: typing.Optional[bool] = Noneoutput_hidden_states: typing.Optional[bool] = Nonereturn_dict: typing.Optional[bool] = Nonetrain: bool = Falseparams: dict = Nonedropout_rng: PRNGKey = None ) β†’ or tuple(torch.FloatTensor)

Indices can be obtained using . See and for details.

Indices can be obtained using . See and for details.

If you want to change padding behavior, you should modify to your needs. See diagram 1 in for more information on the default strategy.

return_dict (bool, optional) β€” Whether or not to return a instead of a plain tuple.

or tuple(torch.FloatTensor)

A 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 () and inputs.

🌍
🌍
🌍
here
Fine-tune on GPU
opus-mt-en-roa
Tatoeba-Challenge repo
Translation task guide
Summarization task guide
Causal language modeling task guide
<source>
MarianModel
TFMarianModel
https://arxiv.org/abs/1909.11556
https://arxiv.org/abs/1909.11556
MarianModel
Helsinki-NLP/opus-mt-en-de
PretrainedConfig
PretrainedConfig
<source>
SentencePiece
SentencePiece
Python wrapper for SentencePiece
SentencePiece
PreTrainedTokenizer
<source>
<source>
MarianConfig
from_pretrained()
PreTrainedModel
torch.nn.Module
<source>
transformers.modeling_outputs.Seq2SeqModelOutput
AutoTokenizer
PreTrainedTokenizer.encode()
PreTrainedTokenizer.call()
What are input IDs?
What are attention masks?
AutoTokenizer
PreTrainedTokenizer.encode()
PreTrainedTokenizer.call()
What are decoder input IDs?
ModelOutput
transformers.modeling_outputs.Seq2SeqModelOutput
transformers.modeling_outputs.Seq2SeqModelOutput
MarianConfig
MarianModel
<source>
MarianConfig
from_pretrained()
PreTrainedModel
torch.nn.Module
<source>
transformers.modeling_outputs.Seq2SeqLMOutput
AutoTokenizer
PreTrainedTokenizer.encode()
PreTrainedTokenizer.call()
What are input IDs?
What are attention masks?
AutoTokenizer
PreTrainedTokenizer.encode()
PreTrainedTokenizer.call()
What are decoder input IDs?
ModelOutput
transformers.modeling_outputs.Seq2SeqLMOutput
transformers.modeling_outputs.Seq2SeqLMOutput
MarianConfig
MarianMTModel
here
<source>
<source>
transformers.modeling_outputs.CausalLMOutputWithCrossAttentions
AutoTokenizer
PreTrainedTokenizer.encode()
PreTrainedTokenizer.call()
What are input IDs?
What are attention masks?
ModelOutput
transformers.modeling_outputs.CausalLMOutputWithCrossAttentions
transformers.modeling_outputs.CausalLMOutputWithCrossAttentions
MarianConfig
<source>
MarianConfig
from_pretrained()
TFPreTrainedModel
tf.keras.Model
subclassing
<source>
transformers.modeling_tf_outputs.TFSeq2SeqModelOutput
AutoTokenizer
PreTrainedTokenizer.encode()
PreTrainedTokenizer.call()
What are input IDs?
What are attention masks?
AutoTokenizer
PreTrainedTokenizer.encode()
PreTrainedTokenizer.call()
What are decoder input IDs?
ModelOutput
transformers.modeling_tf_outputs.TFSeq2SeqModelOutput
transformers.modeling_tf_outputs.TFSeq2SeqModelOutput
MarianConfig
TFMarianModel
<source>
MarianConfig
from_pretrained()
TFPreTrainedModel
tf.keras.Model
subclassing
<source>
transformers.modeling_tf_outputs.TFSeq2SeqLMOutput
AutoTokenizer
PreTrainedTokenizer.encode()
PreTrainedTokenizer.call()
What are input IDs?
What are attention masks?
AutoTokenizer
PreTrainedTokenizer.encode()
PreTrainedTokenizer.call()
What are decoder input IDs?
ModelOutput
transformers.modeling_tf_outputs.TFSeq2SeqLMOutput
transformers.modeling_tf_outputs.TFSeq2SeqLMOutput
MarianConfig
TFMarianMTModel
here
<source>
MarianConfig
from_pretrained()
to_fp16()
to_bf16()
FlaxPreTrainedModel
flax.nn.Module
Just-In-Time (JIT) compilation
Automatic Differentiation
Vectorization
Parallelization
<source>
transformers.modeling_flax_outputs.FlaxSeq2SeqModelOutput
AutoTokenizer
PreTrainedTokenizer.encode()
PreTrainedTokenizer.call()
What are input IDs?
What are attention masks?
AutoTokenizer
PreTrainedTokenizer.encode()
PreTrainedTokenizer.call()
What are decoder input IDs?
the paper
ModelOutput
transformers.modeling_flax_outputs.FlaxSeq2SeqModelOutput
transformers.modeling_flax_outputs.FlaxSeq2SeqModelOutput
MarianConfig
<source>
MarianConfig
from_pretrained()
to_fp16()
to_bf16()
FlaxPreTrainedModel
flax.nn.Module
Just-In-Time (JIT) compilation
Automatic Differentiation
Vectorization
Parallelization
<source>
transformers.modeling_flax_outputs.FlaxSeq2SeqLMOutput
AutoTokenizer
PreTrainedTokenizer.encode()
PreTrainedTokenizer.call()
What are input IDs?
What are attention masks?
AutoTokenizer
PreTrainedTokenizer.encode()
PreTrainedTokenizer.call()
What are decoder input IDs?
the paper
ModelOutput
transformers.modeling_flax_outputs.FlaxSeq2SeqLMOutput
transformers.modeling_flax_outputs.FlaxSeq2SeqLMOutput
MarianConfig
Github Issue
here
JΓΆrg Tiedemann
Marian
BartForConditionalGeneration
sshleifer