i!`dZddlmZddlmZej eZGddeZdgZ y)zOpenAI ImageGPT configuration)PreTrainedConfig)loggingcfeZdZdZdZdgZdddddZ d fd ZxZS) ImageGPTConfiga= This is the configuration class to store the configuration of a [`ImageGPTModel`]. It is used to instantiate a GPT-2 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 ImageGPT [openai/imagegpt-small](https://huggingface.co/openai/imagegpt-small) 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 512): Vocabulary size of the GPT-2 model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`ImageGPTModel`]. n_positions (`int`, *optional*, defaults to 32*32): 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 512): Dimensionality of the embeddings and hidden states. n_layer (`int`, *optional*, defaults to 24): Number of hidden layers in the Transformer encoder. n_head (`int`, *optional*, defaults to 8): Number of attention heads for each attention layer in the Transformer encoder. 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 `"quick_gelu"`): Activation function (can be one of the activation functions defined in src/transformers/activations.py). Defaults to "quick_gelu". 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. scale_attn_weights (`bool`, *optional*, defaults to `True`): Scale attention weights by dividing by sqrt(hidden_size).. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). scale_attn_by_inverse_layer_idx (`bool`, *optional*, defaults to `False`): Whether to additionally scale attention weights by `1 / layer_idx + 1`. reorder_and_upcast_attn (`bool`, *optional*, defaults to `False`): Whether to scale keys (K) prior to computing attention (dot-product) and upcast attention dot-product/softmax to float() when training with mixed precision. Example: ```python >>> from transformers import ImageGPTConfig, ImageGPTModel >>> # Initializing a ImageGPT configuration >>> configuration = ImageGPTConfig() >>> # Initializing a model (with random weights) from the configuration >>> model = ImageGPTModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```imagegptpast_key_valuesn_embd n_positionsn_headn_layer) hidden_sizemax_position_embeddingsnum_attention_headsnum_hidden_layersc J||_||_||_||_||_||_||_||_||_| |_ | |_ | |_ | |_ | |_ ||_||_||_||_||_||_||_t+|Xdi|y)N)add_cross_attention vocab_sizer r r r n_inneractivation_function resid_pdrop embd_pdrop attn_pdroplayer_norm_epsiloninitializer_rangescale_attn_weights use_cachescale_attn_by_inverse_layer_idxreorder_and_upcast_attn pad_token_id bos_token_id eos_token_idtie_word_embeddingssuper__init__)selfrr r r r rrrrrrrrrr#rrrr r!r"kwargs __class__s o/mnt/e/genesis-system/.venv/lib/python3.12/site-packages/transformers/models/imagegpt/configuration_imagegpt.pyr%zImageGPTConfig.__init__`s2$7 $&    #6 &$$"4!2"4"/N,'>$(((#6  "6")iiiN quick_gelu皙?r.r.gh㈵>g{Gz?TTFFFFNNN) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inference attribute_mapr% __classcell__)r(s@r)rrsw= ~J#4"5#0'& M(!(- %!-/#/#r*rN) r2configuration_utilsrutilsr get_loggerr/loggerr__all__rr*r)r<s>$3   H %x#%x#v  r*