a  d@s>dZddlmZddlmZeeZiZGdddeZ dS)z LLaMA model configuration)PretrainedConfig)loggingcs,eZdZdZdZdgZdfdd ZZS) LlamaConfiga This is the configuration class to store the configuration of a [`LlamaModel`]. It is used to instantiate an LLaMA 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 LLaMA-7B. 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 32000): Vocabulary size of the LLaMA model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`LlamaModel`] hidden_size (`int`, *optional*, defaults to 4096): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 11008): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 32): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 32): Number of attention heads for each attention layer in the Transformer encoder. hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): The non-linear activation function (function or string) in the decoder. 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). initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. rms_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the rms normalization layers. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True`. tie_word_embeddings(`bool`, *optional*, defaults to `False`): Whether to tie weight embeddings Example: ```python >>> from transformers import LlamaModel, LlamaConfig >>> # Initializing a LLaMA llama-7b style configuration >>> configuration = LlamaConfig() >>> # Initializing a model from the llama-7b style configuration >>> model = LlamaModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ZllamaZpast_key_values}+ silu{Gz?ư>TFc s\||_||_||_||_||_||_||_||_| |_| |_ t j f| | | |d|dS)N) pad_token_id bos_token_id eos_token_idtie_word_embeddings) vocab_sizemax_position_embeddings hidden_sizeintermediate_sizenum_hidden_layersnum_attention_heads hidden_actinitializer_range rms_norm_eps use_cachesuper__init__)selfrrrrrrrrrrrrrrkwargs __class__v/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/transformers/models/llama/configuration_llama.pyrTs$zLlamaConfig.__init__)rrrrrr r r r Tr rrF)__name__ __module__ __qualname____doc__Z model_typeZkeys_to_ignore_at_inferencer __classcell__r$r$r"r%rs$1rN) r)Zconfiguration_utilsrutilsrZ get_loggerr&loggerZ#LLAMA_PRETRAINED_CONFIG_ARCHIVE_MAPrr$r$r$r%s