qit`dZddlmZddlmZej eZGddeZdgZ y)zGPT-J model configuration)PreTrainedConfig)loggingcZeZdZdZdZdddddZ d fd ZxZS) GPTJConfiga= This is the configuration class to store the configuration of a [`GPTJModel`]. It is used to instantiate a GPT-J 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 GPT-J [EleutherAI/gpt-j-6B](https://huggingface.co/EleutherAI/gpt-j-6B) 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 50400): Vocabulary size of the GPT-J model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`GPTJModel`]. n_positions (`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). n_embd (`int`, *optional*, defaults to 4096): Dimensionality of the embeddings and hidden states. n_layer (`int`, *optional*, defaults to 28): Number of hidden layers in the Transformer encoder. n_head (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer encoder. rotary_dim (`int`, *optional*, defaults to 64): Number of dimensions in the embedding that Rotary Position Embedding is applied to. n_inner (`int`, *optional*, defaults to None): Dimensionality of the inner feed-forward layers. `None` will set it to 4 times n_embd activation_function (`str`, *optional*, defaults to `"gelu_new"`): Activation function, to be selected in the list `["relu", "silu", "gelu", "tanh", "gelu_new"]`. resid_pdrop (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. embd_pdrop (`int`, *optional*, defaults to 0.1): The dropout ratio for the embeddings. attn_pdrop (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention. layer_norm_epsilon (`float`, *optional*, defaults to 1e-5): The epsilon to use in the layer normalization layers. initializer_range (`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). Example: ```python >>> from transformers import GPTJModel, GPTJConfig >>> # Initializing a GPT-J 6B configuration >>> configuration = GPTJConfig() >>> # Initializing a model from the configuration >>> model = GPTJModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```gptj n_positionsn_embdn_headn_layer)max_position_embeddings hidden_sizenum_attention_headsnum_hidden_layersc ||_||_||_||_||_||_||_||_| |_| |_ | |_ | |_ | |_ ||_ ||_||_||_||_t%|Ldi|y)N) vocab_sizerr r r n_inner rotary_dimactivation_function resid_pdrop embd_pdrop attn_pdroplayer_norm_epsiloninitializer_range use_cache bos_token_id eos_token_id pad_token_idtie_word_embeddingssuper__init__)selfrrr r r rrrrrrrrrrrrrkwargs __class__s ]/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/gptj/configuration_gptj.pyr!zGPTJConfig.__init__Ws,%&    $#6 &$$"4!2"(((#6  "6")iii@Ngelu_newr+r+gh㈵>g{Gz?TPr,NF)__name__ __module__ __qualname____doc__ model_type attribute_mapr! __classcell__)r$s@r%rrse5 nJ#0'& M&!')#)#r&rN) r0configuration_utilsrutilsr get_loggerr-loggerr__all__rr&r%r9s= 3   H %i#!i#X .r&