Ë ©sgÖãóZ—dZddlmZddlmZej e«ZGd„de«Zy)zXGLM model configurationé)ÚPretrainedConfig)Úloggingcó^‡—eZdZdZdZdgZddddœZ d ˆfd„ ZˆxZS) Ú XGLMConfiga0 This is the configuration class to store the configuration of a [`XGLMModel`]. It is used to instantiate an XGLM 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 XGLM [facebook/xglm-564M](https://huggingface.co/facebook/xglm-564M) 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 256008): Vocabulary size of the XGLM model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`XGLMModel`] or [`FlaxXGLMModel`]. 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). d_model (`int`, *optional*, defaults to 1024): Dimension of the layers and the pooler layer. ffn_dim (`int`, *optional*, defaults to 4096): Dimension of the "intermediate" (often named feed-forward) layer in decoder. num_layers (`int`, *optional*, defaults to 24): Number of hidden layers Transformer decoder. attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer decoder. activation_function (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. dropout (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, dencoder, and pooler. attention_dropout (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention probabilities. activation_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for activations inside the fully connected layer. layerdrop (`float`, *optional*, defaults to 0.0): The LayerDrop probability for the encoder. 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. scale_embedding (`bool`, *optional*, defaults to `True`): Scale embeddings by diving by sqrt(d_model). use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). Example: ```python >>> from transformers import XGLMModel, XGLMConfig >>> # Initializing a XGLM facebook/xglm-564M style configuration >>> configuration = XGLMConfig() >>> # Initializing a model from the facebook/xglm-564M style configuration >>> model = XGLMModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ÚxglmÚpast_key_valuesÚattention_headsÚd_modelÚ num_layers)Únum_attention_headsÚ hidden_sizeÚnum_hidden_layersc óò•—||_||_||_||_||_||_||_||_| |_| |_ | |_ | |_ | |_ ||_ t‰|<d||||dœ|¤Žy)N)Ú pad_token_idÚ bos_token_idÚ eos_token_idÚdecoder_start_token_id©)Ú vocab_sizeÚmax_position_embeddingsr Úffn_dimr r Úactivation_functionÚdropoutÚattention_dropoutÚactivation_dropoutÚ layerdropÚinit_stdÚscale_embeddingÚ use_cacheÚsuperÚ__init__)Úselfrrr rr r rrrrrrrrrrrrÚkwargsÚ __class__s €ú^/var/www/html/venv/lib/python3.12/site-packages/transformers/models/xglm/configuration_xglm.pyr!zXGLMConfig.__init__]s•ø€ð,%ˆŒØ'>ˆÔ$؈Œ ؈Œ Ø$ˆŒØ.ˆÔØ#6ˆÔ ؈Œ Ø!2ˆÔØ"4ˆÔØ"ˆŒØ ˆŒ Ø.ˆÔØ"ˆŒä ‰Ñð Ø%Ø%Ø%Ø#9ñ  ð ó  ó)ièiiiééÚgeluçš™™™™™¹?r*çr+g{®Gáz”?TTééér,) Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚkeys_to_ignore_at_inferenceÚ attribute_mapr!Ú __classcell__)r$s@r%rrsmø„ñ9 ðv€JØ#4Ð"5Ðð 1Ø Ø)ñ€MðØ $ØØØØØ"ØØØØØØØØ ØØØ÷'+ ñ+ r&rN) r2Úconfiguration_utilsrÚutilsrÚ get_loggerr/Úloggerrrr&r%úr;s3ðñå3Ýð ˆ× Ñ ˜HÓ %€ôp Ð!õp r&