g"dZddlmZddlmZmZmZmZddlm Z ddl m Z ddl m Z erddlmZmZe jeZGd d e ZGd d e Zd S)zOpenAI ImageGPT configuration OrderedDict) TYPE_CHECKINGAnyMappingOptional)PretrainedConfig) OnnxConfig)logging)FeatureExtractionMixin TensorTypec^eZdZdZdZdgZdddddZ dfd ZxZS)ImageGPTConfigam This is the configuration class to store the configuration of a [`ImageGPTModel`] or a [`TFImageGPTModel`]. 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`] or [`TFImageGPTModel`]. 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_layersN quick_gelu皙?h㈵>{Gz?TFc ,||_||_||_||_||_||_||_||_| |_| |_ | |_ | |_ | |_ ||_ ||_||_||_t#jdd|i|dS)Ntie_word_embeddings) vocab_sizerrrrn_inneractivation_function resid_pdrop embd_pdrop attn_pdroplayer_norm_epsiloninitializer_rangescale_attn_weights use_cachescale_attn_by_inverse_layer_idxreorder_and_upcast_attnr%super__init__)selfr'rrrrr(r)r*r+r,r-r.r/r0r%r1r2kwargs __class__s o/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/imagegpt/configuration_imagegpt.pyr4zImageGPTConfig.__init__hs*%&    #6 &$$"4!2"4"/N,'>$#6 KK-@KFKKKKK)rrrrrNr r!r!r!r"r#TTFFF) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inference attribute_mapr4 __classcell__)r7s@r8rrs= = ~J#4"5#0'& M(!(- %%'L'L'L'L'L'L'L'L'L'Lr9rceZdZedeeeeefffdZ dd d d ed ed ede ddedededeee ffdZ dS)ImageGPTOnnxConfigreturnc,tddddfgS)N input_idsbatchsequence)rr)r5s r8inputszImageGPTOnnxConfig.inputss)'j99:    r9rIFNr preprocessorr batch_size seq_lengthis_pair frameworkr num_channels image_width image_heightc j|||||} t|| |} | S)a Generate inputs to provide to the ONNX exporter for the specific framework Args: preprocessor ([`PreTrainedTokenizerBase`] or [`FeatureExtractionMixin`]): The preprocessor associated with this model configuration. batch_size (`int`, *optional*, defaults to -1): The batch size to export the model for (-1 means dynamic axis). num_choices (`int`, *optional*, defaults to -1): The number of candidate answers provided for multiple choice task (-1 means dynamic axis). seq_length (`int`, *optional*, defaults to -1): The sequence length to export the model for (-1 means dynamic axis). is_pair (`bool`, *optional*, defaults to `False`): Indicate if the input is a pair (sentence 1, sentence 2) framework (`TensorType`, *optional*, defaults to `None`): The framework (PyTorch or TensorFlow) that the tokenizer will generate tensors for. num_channels (`int`, *optional*, defaults to 3): The number of channels of the generated images. image_width (`int`, *optional*, defaults to 40): The width of the generated images. image_height (`int`, *optional*, defaults to 40): The height of the generated images. Returns: Mapping[str, Tensor] holding the kwargs to provide to the model's forward function )imagesreturn_tensors)_generate_dummy_imagesdict) r5rMrNrOrPrQrRrSrT input_imagerJs r8generate_dummy_inputsz(ImageGPTOnnxConfig.generate_dummy_inputss@L11*lLZeff ll+iPPPQQ r9)rIrKFNr rLrL) r:r;r<propertyrstrintrJboolrrr[r&r9r8rCrCs  WS#X%6 67   X ,0)).)) )  ) L) )))) c ))))))r9rCN)r= collectionsrtypingrrrrconfiguration_utilsr onnxr utilsr r r get_loggerr:loggerrrCr&r9r8rhs$#######888888888888333333766666666  H % %pLpLpLpLpL%pLpLpLf2222222222r9