sgZdZddlmZddlmZej eZGddeZy)zREALM model configuration.)PretrainedConfig)loggingcXeZdZdZdZ dfd ZxZS) RealmConfiga+ This is the configuration class to store the configuration of 1. [`RealmEmbedder`] 2. [`RealmScorer`] 3. [`RealmKnowledgeAugEncoder`] 4. [`RealmRetriever`] 5. [`RealmReader`] 6. [`RealmForOpenQA`] It is used to instantiate an REALM 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 REALM [google/realm-cc-news-pretrained-embedder](https://huggingface.co/google/realm-cc-news-pretrained-embedder) 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 30522): Vocabulary size of the REALM model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`RealmEmbedder`], [`RealmScorer`], [`RealmKnowledgeAugEncoder`], or [`RealmReader`]. hidden_size (`int`, *optional*, defaults to 768): Dimension of the encoder layers and the pooler layer. retriever_proj_size (`int`, *optional*, defaults to 128): Dimension of the retriever(embedder) projection. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. num_candidates (`int`, *optional*, defaults to 8): Number of candidates inputted to the RealmScorer or RealmKnowledgeAugEncoder. intermediate_size (`int`, *optional*, defaults to 3072): Dimension of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. hidden_act (`str` or `function`, *optional*, defaults to `"gelu_new"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1): 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 just in case (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 [`RealmEmbedder`], [`RealmScorer`], [`RealmKnowledgeAugEncoder`], or [`RealmReader`]. 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. span_hidden_size (`int`, *optional*, defaults to 256): Dimension of the reader's spans. max_span_width (`int`, *optional*, defaults to 10): Max span width of the reader. reader_layer_norm_eps (`float`, *optional*, defaults to 1e-3): The epsilon used by the reader's layer normalization layers. reader_beam_size (`int`, *optional*, defaults to 5): Beam size of the reader. reader_seq_len (`int`, *optional*, defaults to 288+32): Maximum sequence length of the reader. num_block_records (`int`, *optional*, defaults to 13353718): Number of block records. searcher_beam_size (`int`, *optional*, defaults to 5000): Beam size of the searcher. Note that when eval mode is enabled, *searcher_beam_size* will be the same as *reader_beam_size*. Example: ```python >>> from transformers import RealmConfig, RealmEmbedder >>> # Initializing a REALM realm-cc-news-pretrained-* style configuration >>> configuration = RealmConfig() >>> # Initializing a model (with random weights) from the google/realm-cc-news-pretrained-embedder style configuration >>> model = RealmEmbedder(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```realmc Rt|d|||d|||_| |_||_||_||_||_||_||_ ||_ | |_ | |_ | |_ | |_||_||_||_||_||_||_||_||_y)N) pad_token_id bos_token_id eos_token_id)super__init__ vocab_sizemax_position_embeddings hidden_sizeretriever_proj_sizenum_hidden_layersnum_attention_headsnum_candidatesintermediate_size hidden_acthidden_dropout_probattention_probs_dropout_probinitializer_rangetype_vocab_sizelayer_norm_epsspan_hidden_sizemax_span_widthreader_layer_norm_epsreader_beam_sizereader_seq_lennum_block_recordssearcher_beam_size)selfrrrrrrrrrrrrrrrrrr r!r"r#r r r kwargs __class__s k/var/www/html/venv/lib/python3.12/site-packages/transformers/models/deprecated/realm/configuration_realm.pyrzRealmConfig.__init__os8 sl\hslrs%'>$&#6 !2#6 ,!2$#6 ,H)!2.,!1,%:" 0,"3"4)i:wi r*i gelu_new皙?r-ig{Gz?g-q= gMbP?i@iir.)__name__ __module__ __qualname____doc__ model_typer __classcell__)r&s@r'rrseR hJ%( #""37575r(rN) r7configuration_utilsrutilsr get_loggerr4loggerrr r(r'r>s3!4   H %N5"N5r(