o ¾e¦i!ã@s@dZddlmZddlmZe e¡ZGdd„deƒZdgZ dS)zOpenAI ImageGPT configurationé)ÚPreTrainedConfig)ÚloggingcsdeZdZdZdZdgZdddddœZ                d‡fdd„ Z‡ZS)ÚImageGPTConfiga= 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 ```ÚimagegptÚpast_key_valuesÚn_embdÚ n_positionsÚn_headÚn_layer)Ú hidden_sizeÚmax_position_embeddingsÚnum_attention_headsÚnum_hidden_layerséééééNÚ quick_geluçš™™™™™¹?çñh㈵øä>ç{®Gáz”?TFc s”||_||_||_||_||_||_||_||_||_| |_ | |_ | |_ | |_ | |_ ||_||_||_||_||_||_||_tƒjdi|¤ŽdS)N©)Úadd_cross_attentionÚ vocab_sizerrr r Ún_innerÚactivation_functionÚ resid_pdropÚ embd_pdropÚ attn_pdropÚlayer_norm_epsilonÚinitializer_rangeÚscale_attn_weightsÚ use_cacheÚscale_attn_by_inverse_layer_idxÚreorder_and_upcast_attnÚ pad_token_idÚ bos_token_idÚ eos_token_idÚtie_word_embeddingsÚsuperÚ__init__)Úselfrrrr r rrrrrr r!r"r#r)r$r%rr&r'r(Úkwargs©Ú __class__rúq/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/imagegpt/configuration_imagegpt.pyr+`s,zImageGPTConfig.__init__)rrrrrNrrrrrrTTFFFFNNN) Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚkeys_to_ignore_at_inferenceÚ attribute_mapr+Ú __classcell__rrr.r0rs>?ü êrN) r4Úconfiguration_utilsrÚutilsrÚ get_loggerr1ÚloggerrÚ__all__rrrr0Ús     {