T^(h`dZddlmZddlmZej eZGddeZdgZ y)zOPT model configuration)PretrainedConfig)loggingcVeZdZdZdZdgZ dfd ZxZS) OPTConfiga This is the configuration class to store the configuration of a [`OPTModel`]. It is used to instantiate a OPT 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 OPT [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) 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 50272): Vocabulary size of the OPT model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`OPTModel`] hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 12): Number of decoder layers. ffn_dim (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (often named feed-forward) layer in decoder. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer decoder. activation_function (`str` or `function`, *optional*, defaults to `"relu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. max_position_embeddings (`int`, *optional*, defaults to 2048): 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). do_layer_norm_before (`bool`, *optional*, defaults to `True`): Whether to perform layer normalization before the attention block. word_embed_proj_dim (`int`, *optional*): `word_embed_proj_dim` can be set to down-project word embeddings, *e.g.* `opt-350m`. Defaults to `hidden_size`. dropout (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. layerdrop (`float`, *optional*, defaults to 0.0): The LayerDrop probability. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556) for more details. init_std (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). enable_bias (`bool`, *optional*, defaults to `True`): Whether or not if the linear layers in the attention blocks should use the bias term. layer_norm_elementwise_affine (`bool`, *optional*, defaults to `True`): Whether or not if the layer norms should have learnable parameters. Example: ```python >>> from transformers import OPTConfig, OPTModel >>> # Initializing a OPT facebook/opt-large style configuration >>> configuration = OPTConfig() >>> # Initializing a model (with random weights) from the facebook/opt-large style configuration >>> model = OPTModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```optpast_key_valuesc "t|d|||d|||_||_| |_||n||_||_||_||_| |_ | |_ | |_ ||_ | |_ ||_||_||_||_||_y)N) pad_token_id bos_token_id eos_token_id)super__init__ vocab_sizemax_position_embeddingsnum_attention_headsword_embed_proj_dimffn_dim hidden_sizenum_hidden_layersdropoutattention_dropoutactivation_functioninit_std layerdrop use_cachedo_layer_norm_before enable_biaslayer_norm_elementwise_affine_remove_final_layer_norm)selfrrrrrrr rrrrrrrrr r r rrkwargs __class__s g/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/opt/configuration_opt.pyrzOPTConfig.__init__\s0  %%%   %'>$#6 :M:Y#6_j  &!2 !2#6   ""$8!&-J* )A%)i`i i iTFNg?r&relur'g{Gz?Tr*TT)__name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inferencer __classcell__)r#s@r$rrsc> @J#4"5 $!!& "&*+3A3Ar%rN) r.configuration_utilsrutilsr get_loggerr+loggerr__all__r r%r$r7s?3   H %wA wAt -r%