U 9%eL@sLdZddlmZddlmZeeZdddddd d ZGd d d eZ d S)z OPT model configuration)PretrainedConfig)loggingz>https://huggingface.co/facebook/opt-125m/blob/main/config.jsonz>https://huggingface.co/facebook/opt-350m/blob/main/config.jsonz>https://huggingface.co/facebook/opt-1.3b/blob/main/config.jsonz>https://huggingface.co/facebook/opt-2.7b/blob/main/config.jsonz>https://huggingface.co/facebook/opt-6.7b/blob/main/config.jsonz=https://huggingface.co/facebook/opt-13b/blob/main/config.json)zfacebook/opt-125mzfacebook/opt-350mzfacebook/opt-1.3bzfacebook/opt-2.7bzfacebook/opt-6.7bzfacebook/opt-13bcs,eZdZdZdZdgZdfdd ZZS) 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 ```optZpast_key_values` TFN皙?relu{Gz?c stjf|||d|||_||_| |_|dk r8|n||_||_||_||_| |_ | |_ | |_ ||_ | |_ ||_||_||_||_||_dS)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)selfrrrrrr#r&rrrrrr!r r"rrrr$r%kwargs __class__h/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/transformers/models/opt/configuration_opt.pyrcs0zOPTConfig.__init__)rrrr r TFNr r rr r rTrrrTT)__name__ __module__ __qualname____doc__Z model_typeZkeys_to_ignore_at_inferencer __classcell__r+r+r)r,r s0?rN) r0Zconfiguration_utilsrutilsrZ get_loggerr-loggerZ!OPT_PRETRAINED_CONFIG_ARCHIVE_MAPrr+r+r+r,s