U ,-ex! @sndZddlmZddlmZddlmZddlmZddd d d d d ddZ GdddeZ GdddeZ dS)z ALBERT model configuration) OrderedDict)Mapping)PretrainedConfig) OnnxConfigz>https://huggingface.co/albert-base-v1/resolve/main/config.jsonz?https://huggingface.co/albert-large-v1/resolve/main/config.jsonz@https://huggingface.co/albert-xlarge-v1/resolve/main/config.jsonzAhttps://huggingface.co/albert-xxlarge-v1/resolve/main/config.jsonz>https://huggingface.co/albert-base-v2/resolve/main/config.jsonz?https://huggingface.co/albert-large-v2/resolve/main/config.jsonz@https://huggingface.co/albert-xlarge-v2/resolve/main/config.jsonzAhttps://huggingface.co/albert-xxlarge-v2/resolve/main/config.json)zalbert-base-v1zalbert-large-v1zalbert-xlarge-v1zalbert-xxlarge-v1zalbert-base-v2zalbert-large-v2zalbert-xlarge-v2zalbert-xxlarge-v2cs&eZdZdZdZdfdd ZZS) AlbertConfiga This is the configuration class to store the configuration of a [`AlbertModel`] or a [`TFAlbertModel`]. It is used to instantiate an ALBERT 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 ALBERT [albert-xxlarge-v2](https://huggingface.co/albert-xxlarge-v2) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 30000): Vocabulary size of the ALBERT model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`AlbertModel`] or [`TFAlbertModel`]. embedding_size (`int`, *optional*, defaults to 128): Dimensionality of vocabulary embeddings. hidden_size (`int`, *optional*, defaults to 4096): Dimensionality of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_hidden_groups (`int`, *optional*, defaults to 1): Number of groups for the hidden layers, parameters in the same group are shared. num_attention_heads (`int`, *optional*, defaults to 64): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (`int`, *optional*, defaults to 16384): The dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder. inner_group_num (`int`, *optional*, defaults to 1): The number of inner repetition of attention and ffn. hidden_act (`str` or `Callable`, *optional*, defaults to `"gelu_new"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`float`, *optional*, defaults to 0): The dropout ratio for the attention probabilities. max_position_embeddings (`int`, *optional*, defaults to 512): The maximum sequence length that this model might ever be used with. Typically set this to something large (e.g., 512 or 1024 or 2048). type_vocab_size (`int`, *optional*, defaults to 2): The vocabulary size of the `token_type_ids` passed when calling [`AlbertModel`] or [`TFAlbertModel`]. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. classifier_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout ratio for attached classifiers. position_embedding_type (`str`, *optional*, defaults to `"absolute"`): Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155). For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658). Examples: ```python >>> from transformers import AlbertConfig, AlbertModel >>> # Initializing an ALBERT-xxlarge style configuration >>> albert_xxlarge_configuration = AlbertConfig() >>> # Initializing an ALBERT-base style configuration >>> albert_base_configuration = AlbertConfig( ... hidden_size=768, ... num_attention_heads=12, ... intermediate_size=3072, ... ) >>> # Initializing a model (with random weights) from the ALBERT-base style configuration >>> model = AlbertModel(albert_xxlarge_configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zalbert0u @@gelu_newr{Gz?-q=皙?absoluterc stjf|||d|||_||_||_||_||_||_||_| |_ ||_ | |_ | |_ | |_ | |_||_||_||_||_dS)N) pad_token_id bos_token_id eos_token_id)super__init__ vocab_sizeembedding_size hidden_sizenum_hidden_layersnum_hidden_groupsnum_attention_headsinner_group_num hidden_actintermediate_sizehidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_rangelayer_norm_epsclassifier_dropout_probposition_embedding_type)selfrrrrrr r#r!r"r$r%r&r'r(r)r*r+rrrkwargs __class__p/var/www/html/Darija-Ai-Train/env/lib/python3.8/site-packages/transformers/models/albert/configuration_albert.pyrqs$zAlbertConfig.__init__)rr r r r r rr rrrrrrrrrrrr)__name__ __module__ __qualname____doc__Z model_typer __classcell__r0r0r.r1r$s.Jrc@s.eZdZeeeeeeffdddZdS)AlbertOnnxConfig)returncCs<|jdkrdddd}n ddd}td|fd|fd |fgS) Nzmultiple-choicebatchchoicesequence)rr r)rr Z input_idsZattention_maskZtoken_type_ids)taskr)r,Z dynamic_axisr0r0r1inputss  zAlbertOnnxConfig.inputsN)r2r3r4propertyrstrintr=r0r0r0r1r7sr7N) r5 collectionsrtypingrZconfiguration_utilsrZonnxrZ$ALBERT_PRETRAINED_CONFIG_ARCHIVE_MAPrr7r0r0r0r1s     {