sgldZddlmZddlmZddlmZddlmZGddeZ Gd d eZ dd gZ y ) zALBERT model configuration) OrderedDict)Mapping)PretrainedConfig) OnnxConfigcPeZdZdZdZ dfd ZxZS) 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/albert-xxlarge-v2](https://huggingface.co/albert/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). pad_token_id (`int`, *optional*, defaults to 0): Padding token id. bos_token_id (`int`, *optional*, defaults to 2): Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 3): End of stream token id. 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 ```albertc t|d|||d|||_||_||_||_||_||_||_| |_ ||_ | |_ | |_ | |_ | |_||_||_||_||_y)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)selfrrrrrrrrrrrrrrr r!r"r r rkwargs __class__s b/var/www/html/venv/lib/python3.12/site-packages/transformers/models/albert/configuration_albert.pyrzAlbertConfig.__init__ls0 sl\hslrs$,&!2!2#6 .$!2#6 ,H)'>$.!2,'>$'>$)i0ui @i@r*gelu_newrrig{Gz?g-q=g?absoluterr-r)__name__ __module__ __qualname____doc__ model_typer __classcell__)r%s@r&r r sYN `J%& # # *+*?*?r'r c6eZdZedeeeeefffdZy)AlbertOnnxConfigreturnc`|jdk(rdddd}nddd}td|fd|fd |fgS) Nzmultiple-choicebatchchoicesequence)rr*r-)rr* input_idsattention_masktoken_type_ids)taskr)r# dynamic_axiss r&inputszAlbertOnnxConfig.inputssO 99) )&8 CL&:6Ll+!<0!<0   r'N)r/r0r1propertyrstrintrArr'r&r6r6s.   WS#X%6 67    r'r6N) r2 collectionsrtypingrconfiguration_utilsronnxrr r6__all__rr'r&rJs? !#3}?#}?B  z  - .r'