U &c2 @sPdZddlZddlmZeeZddddd d d d d dd ZGdddeZdS)z XLM configuration N)PretrainedConfigzOhttps://s3.amazonaws.com/models.huggingface.co/bert/xlm-mlm-en-2048-config.jsonzQhttps://s3.amazonaws.com/models.huggingface.co/bert/xlm-mlm-ende-1024-config.jsonzQhttps://s3.amazonaws.com/models.huggingface.co/bert/xlm-mlm-enfr-1024-config.jsonzQhttps://s3.amazonaws.com/models.huggingface.co/bert/xlm-mlm-enro-1024-config.jsonzWhttps://s3.amazonaws.com/models.huggingface.co/bert/xlm-mlm-tlm-xnli15-1024-config.jsonzShttps://s3.amazonaws.com/models.huggingface.co/bert/xlm-mlm-xnli15-1024-config.jsonzQhttps://s3.amazonaws.com/models.huggingface.co/bert/xlm-clm-enfr-1024-config.jsonzQhttps://s3.amazonaws.com/models.huggingface.co/bert/xlm-clm-ende-1024-config.jsonzOhttps://s3.amazonaws.com/models.huggingface.co/bert/xlm-mlm-17-1280-config.jsonzPhttps://s3.amazonaws.com/models.huggingface.co/bert/xlm-mlm-100-1280-config.json) zxlm-mlm-en-2048zxlm-mlm-ende-1024zxlm-mlm-enfr-1024zxlm-mlm-enro-1024zxlm-mlm-tlm-xnli15-1024zxlm-mlm-xnli15-1024zxlm-clm-enfr-1024zxlm-clm-ende-1024zxlm-mlm-17-1280zxlm-mlm-100-1280c!sheZdZdZeZdZd fdd ZeddZ e j ddZ eddZ eddZ eddZ ZS)! XLMConfigay This is the configuration class to store the configuration of a :class:`~transformers.XLMModel`. It is used to instantiate an XLM 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 `xlm-mlm-en-2048 `__ architecture. Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information. Args: vocab_size (:obj:`int`, optional, defaults to 30145): Vocabulary size of the XLM model. Defines the different tokens that can be represented by the `inputs_ids` passed to the forward method of :class:`~transformers.XLMModel`. emb_dim (:obj:`int`, optional, defaults to 2048): Dimensionality of the encoder layers and the pooler layer. n_layer (:obj:`int`, optional, defaults to 12): Number of hidden layers in the Transformer encoder. n_head (:obj:`int`, optional, defaults to 16): Number of attention heads for each attention layer in the Transformer encoder. dropout (:obj:`float`, optional, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_dropout (:obj:`float`, optional, defaults to 0.1): The dropout probability for the attention mechanism gelu_activation (:obj:`boolean`, optional, defaults to :obj:`True`): The non-linear activation function (function or string) in the encoder and pooler. If set to `True`, "gelu" will be used instead of "relu". sinusoidal_embeddings (:obj:`boolean`, optional, defaults to :obj:`False`): Whether to use sinusoidal positional embeddings instead of absolute positional embeddings. causal (:obj:`boolean`, optional, defaults to :obj:`False`): Set this to `True` for the model to behave in a causal manner. Causal models use a triangular attention mask in order to only attend to the left-side context instead if a bidirectional context. asm (:obj:`boolean`, optional, defaults to :obj:`False`): Whether to use an adaptive log softmax projection layer instead of a linear layer for the prediction layer. n_langs (:obj:`int`, optional, defaults to 1): The number of languages the model handles. Set to 1 for monolingual models. use_lang_emb (:obj:`boolean`, optional, defaults to :obj:`True`) Whether to use language embeddings. Some models use additional language embeddings, see `the multilingual models page `__ for information on how to use them. max_position_embeddings (:obj:`int`, optional, defaults to 512): The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048). embed_init_std (:obj:`float`, optional, defaults to 2048^-0.5): The standard deviation of the truncated_normal_initializer for initializing the embedding matrices. init_std (:obj:`int`, optional, defaults to 50257): The standard deviation of the truncated_normal_initializer for initializing all weight matrices except the embedding matrices. layer_norm_eps (:obj:`float`, optional, defaults to 1e-12): The epsilon used by the layer normalization layers. bos_index (:obj:`int`, optional, defaults to 0): The index of the beginning of sentence token in the vocabulary. eos_index (:obj:`int`, optional, defaults to 1): The index of the end of sentence token in the vocabulary. pad_index (:obj:`int`, optional, defaults to 2): The index of the padding token in the vocabulary. unk_index (:obj:`int`, optional, defaults to 3): The index of the unknown token in the vocabulary. mask_index (:obj:`int`, optional, defaults to 5): The index of the masking token in the vocabulary. is_encoder(:obj:`boolean`, optional, defaults to :obj:`True`): Whether the initialized model should be a transformer encoder or decoder as seen in Vaswani et al. summary_type (:obj:`string`, optional, defaults to "first"): Argument used when doing sequence summary. Used in for the multiple choice head in :class:`~transformers.XLMForSequenceClassification`. Is one of the following options: - 'last' => take the last token hidden state (like XLNet) - 'first' => take the first token hidden state (like Bert) - 'mean' => take the mean of all tokens hidden states - 'cls_index' => supply a Tensor of classification token position (GPT/GPT-2) - 'attn' => Not implemented now, use multi-head attention summary_use_proj (:obj:`boolean`, optional, defaults to :obj:`True`): Argument used when doing sequence summary. Used in for the multiple choice head in :class:`~transformers.XLMForSequenceClassification`. Add a projection after the vector extraction summary_activation (:obj:`string` or :obj:`None`, optional, defaults to :obj:`None`): Argument used when doing sequence summary. Used in for the multiple choice head in :class:`~transformers.XLMForSequenceClassification`. 'tanh' => add a tanh activation to the output, Other => no activation. summary_proj_to_labels (:obj:`boolean`, optional, defaults to :obj:`True`): Argument used when doing sequence summary. Used in for the multiple choice head in :class:`~transformers.XLMForSequenceClassification`. If True, the projection outputs to config.num_labels classes (otherwise to hidden_size). Default: False. summary_first_dropout (:obj:`float`, optional, defaults to 0.1): Argument used when doing sequence summary. Used in for the multiple choice head in :class:`~transformers.XLMForSequenceClassification`. Add a dropout before the projection and activation start_n_top (:obj:`int`, optional, defaults to 5): Used in the SQuAD evaluation script for XLM and XLNet. end_n_top (:obj:`int`, optional, defaults to 5): Used in the SQuAD evaluation script for XLM and XLNet. mask_token_id (:obj:`int`, optional, defaults to 0): Model agnostic parameter to identify masked tokens when generating text in an MLM context. lang_id (:obj:`int`, optional, defaults to 1): The ID of the language used by the model. This parameter is used when generating text in a given language. Example:: from transformers import XLMConfig, XLMModel # Initializing a XLM configuration configuration = XLMConfig() # Initializing a model from the configuration model = XLMModel(configuration) # Accessing the model configuration configuration = model.config Attributes: pretrained_config_archive_map (Dict[str, str]): A dictionary containing all the available pre-trained checkpoints. Zxlmu 皙?TFr;f?-q={Gz?rfirstNc"# stjf| |!d|"||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ ||_||_||_||_||_||_||_| |_||_||_||_||_||_||_||_||_||_||_||_ d|"kr|"d|_!dS)zConstructs XLMConfig. ) pad_token_id bos_token_idn_wordsN)"super__init__ vocab_sizeemb_dimn_layersn_headsdropoutattention_dropoutgelu_activationsinusoidal_embeddingscausalasmn_langs use_lang_emblayer_norm_eps bos_index eos_index pad_index unk_index mask_index is_encodermax_position_embeddingsembed_init_stdinit_std summary_typesummary_use_projsummary_activationsummary_proj_to_labelssummary_first_dropout start_n_top end_n_top mask_token_idlang_idr)#selfrrrrrrrrrr r!r"r*r+r#r,r$r%r&r'r(r)r-r.r/r0r1r2r3r4r5rrkwargs __class__B/tmp/pip-unpacked-wheel-ymerj3tt/transformers/configuration_xlm.pyrsD'zXLMConfig.__init__cCs|jSNrr6r:r:r;rszXLMConfig.n_wordscCs ||_dSr<r=)r6valuer:r:r;rscCs|jSr<)rr>r:r:r; hidden_sizeszXLMConfig.hidden_sizecCs|jSr<)rr>r:r:r;num_attention_headsszXLMConfig.num_attention_headscCs|jSr<)rr>r:r:r;num_hidden_layersszXLMConfig.num_hidden_layers)!rrrrr r TFFFrTr r r r rrrrrTrTNTr rrrrrr)__name__ __module__ __qualname____doc__!XLM_PRETRAINED_CONFIG_ARCHIVE_MAPZpretrained_config_archive_mapZ model_typerpropertyrsetterr@rArB __classcell__r:r:r8r;r's^yK    r) rFloggingZconfiguration_utilsr getLoggerrCloggerrGrr:r:r:r;s