o hFD@svdZddlZddlmZddlmZddlmZee Z ddiZ Gd d d eZ Gd d d eZ Gd ddeZdS)z Pix2Struct model configurationN)Union)PretrainedConfig)loggingzgoogle/pix2struct-textcaps-basezOhttps://huggingface.co/google/pix2struct-textcaps-base/resolve/main/config.jsoncs|eZdZdZdZdgZddddZ            dfdd Zede e e j fddfddZ ZS)Pix2StructTextConfiga This is the configuration class to store the configuration of a [`Pix2StructTextModel`]. It is used to instantiate a Pix2Struct text 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 Pix2Struct text decoder used by the [google/pix2struct-base](https://huggingface.co/google/pix2struct-base) 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 50244): Vocabulary size of the `Pix2Struct` text model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`Pix2StructTextModel`]. hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. d_kv (`int`, *optional*, defaults to 64): Dimensionality of the key, query, value projections in each attention head. d_ff (`int`, *optional*, defaults to 2048): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. num_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. relative_attention_num_buckets (`int`, *optional*, defaults to 32): The number of buckets to use for each attention layer. relative_attention_max_distance (`int`, *optional*, defaults to 128): The maximum distance of the longer sequences for the bucket separation. dropout_rate (`float`, *optional*, defaults to 0.1): The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler. layer_norm_epsilon (`float`, *optional*, defaults to 1e-6): The epsilon used by the layer normalization layers. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). dense_act_fn (`Union[Callable, str]`, *optional*, defaults to `"gelu_new"`): The non-linear activation function (function or string). decoder_start_token_id (`int`, *optional*, defaults to 0): The id of the `decoder_start_token_id` token. use_cache (`bool`, *optional*, defaults to `False`): Whether or not the model should return the last key/values attentions (not used by all models). pad_token_id (`int`, *optional*, defaults to 0): The id of the `padding` token. eos_token_id (`int`, *optional*, defaults to 1): The id of the `end-of-sequence` token. Example: ```python >>> from transformers import Pix2StructTextConfig, Pix2StructTextModel >>> # Initializing a Pix2StructTextConfig with google/pix2struct-base style configuration >>> configuration = Pix2StructTextConfig() >>> # Initializing a Pix2StructTextModel (with random weights) from the google/pix2struct-base style configuration >>> model = Pix2StructTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```pix2struct_text_modelpast_key_values hidden_size num_heads num_layers)r num_attention_headsnum_hidden_layersD@ 皙?ư>?gelu_newrFTc s|||_||_||_||_||_||_||_||_| |_| |_ | |_ ||_ ||_ | |_ | |_tjd||| ||d|dS)N) pad_token_id eos_token_iddecoder_start_token_idtie_word_embeddings is_decoder) vocab_sizer d_kvd_ffr r relative_attention_num_bucketsrelative_attention_max_distance dropout_ratelayer_norm_epsiloninitializer_factor use_cacherr dense_act_fnsuper__init__)selfr r r!r"r r r#r$r%r&r'r)rr(rrrrkwargs __class__rm/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/pix2struct/configuration_pix2struct.pyr+fs0 zPix2StructTextConfig.__init__!pretrainehidden_size_name_or_pathreturnrcK|||j|fi|\}}|ddkr|d}d|vr:t|dr:|d|jkr:td|dd|jd|j|fi|S)N model_type pix2struct text_configYou are using a model of type to instantiate a model of type N. This is not supported for all configurations of models and can yield errors._set_token_in_kwargsget_config_dictgethasattrr4loggerwarning from_dictclsr1r- config_dictrrr0from_pretrained   z$Pix2StructTextConfig.from_pretrained)rrrrrrrrrrrrrFrrFT)__name__ __module__ __qualname____doc__r4keys_to_ignore_at_inference attribute_mapr+ classmethodrstrosPathLikerE __classcell__rrr.r0r!sB<2 rcsdeZdZdZdZ         dfdd Zedeee j fddfddZ Z S)Pix2StructVisionConfiga This is the configuration class to store the configuration of a [`Pix2StructVisionModel`]. It is used to instantiate a Pix2Struct vision model according to the specified arguments, defining the model architecture. Instantiating a configuration defaults will yield a similar configuration to that of the Pix2Struct-base [google/pix2struct-base](https://huggingface.co/google/pix2struct-base) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. patch_embed_hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the input patch_embedding layer in the Transformer encoder. d_ff (`int`, *optional*, defaults to 2048): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. d_kv (`int`, *optional*, defaults to 64): Dimensionality of the key, query, value projections per attention head. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. dense_act_fn (`str` or `function`, *optional*, defaults to `"gelu_new"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` ``"gelu"` are supported. layer_norm_eps (`float`, *optional*, defaults to 1e-06): The epsilon used by the layer normalization layers. dropout_rate (`float`, *optional*, defaults to 0.0): The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. initializer_range (`float`, *optional*, defaults to 1e-10): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). seq_len (`int`, *optional*, defaults to 4096): Maximum sequence length (here number of patches) supported by the model. relative_attention_num_buckets (`int`, *optional*, defaults to 32): The number of buckets to use for each attention layer. relative_attention_max_distance (`int`, *optional*, defaults to 128): The maximum distance (in tokens) to use for each attention layer. Example: ```python >>> from transformers import Pix2StructVisionConfig, Pix2StructVisionModel >>> # Initializing a Pix2StructVisionConfig with google/pix2struct-base style configuration >>> configuration = Pix2StructVisionConfig() >>> # Initializing a Pix2StructVisionModel (with random weights) from the google/pix2struct-base style configuration >>> model = Pix2StructVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```pix2struct_vision_modelrrrrrr绽|=rrrc sptjdi|||_||_||_| |_||_||_| |_| |_ | |_ ||_ ||_ | |_ ||_||_||_dS)Nr)r*r+r patch_embed_hidden_sizer"r%r r initializer_ranger'attention_dropoutlayer_norm_epsr)seq_lenr#r$r!)r,r rWr"r!r r r)rZr%rYrXr'r[r#r$r-r.rr0r+s  zPix2StructVisionConfig.__init__r1r2rcKr3)Nr4r5 vision_configr7r8r9r:rBrrr0rErFz&Pix2StructVisionConfig.from_pretrained)rrrrrrrrrTrTrUrrVrr) rGrHrIrJr4r+rMrrNrOrPrErQrrr.r0rRs2:% rRcsJeZdZdZdZ       dfdd Zed ed efd d Z Z S)Pix2StructConfiga1 [`Pix2StructConfig`] is the configuration class to store the configuration of a [`Pix2StructForConditionalGeneration`]. It is used to instantiate a Pix2Struct model according to the specified arguments, defining the text model and vision model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the Pix2Struct-base [google/pix2struct-base](https://huggingface.co/google/pix2struct-base) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: text_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`Pix2StructTextConfig`]. vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`Pix2StructVisionConfig`]. initializer_factor (`float`, *optional*, defaults to 1.0): Factor to multiply the initialization range with. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. is_vqa (`bool`, *optional*, defaults to `False`): Whether the model has been fine-tuned for VQA or not. kwargs (*optional*): Dictionary of keyword arguments. Example: ```python >>> from transformers import Pix2StructConfig, Pix2StructForConditionalGeneration >>> # Initializing a Pix2StructConfig with google/pix2struct-base style configuration >>> configuration = Pix2StructConfig() >>> # Initializing a Pix2StructForConditionalGeneration (with random weights) from the google/pix2struct-base style configuration >>> model = Pix2StructForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a Pix2StructConfig from a Pix2StructTextConfig and a Pix2StructVisionConfig >>> # Initializing a Pix2Struct text and Pix2Struct vision configuration >>> config_text = Pix2StructTextConfig() >>> config_vision = Pix2StructVisionConfig() >>> config = Pix2StructConfig.from_text_vision_configs(config_text, config_vision) ```r5Nr{Gz?FTc  stjd||d||duri}td|dur"i}tdtdi||_tdi||_|jj|_|jj |_ |jj |_ ||_ ||_ |j |j_ |j |j_ ||_ dS)N)ris_encoder_decoderzOtext_config is None. Initializing the Pix2StructTextConfig with default values.zSvision_config is None. Initializing the Pix2StructVisionConfig with default values.r)r*r+r?inforr6rRr\rrrr'rXis_vqa) r,r6r\r'rXrarr_r-r.rr0r+Vs"         zPix2StructConfig.__init__r6r\cKs|d||d|S)z Instantiate a [`Pix2StructConfig`] (or a derived class) from pix2struct text model configuration and pix2struct vision model configuration. Returns: [`Pix2StructConfig`]: An instance of a configuration object )r6r\Nr)to_dict)rCr6r\r-rrr0from_text_vision_configszs z)Pix2StructConfig.from_text_vision_configs)NNrr^FFT) rGrHrIrJr4r+rMrrRrcrQrrr.r0r]$s"/$r])rJrOtypingrconfiguration_utilsrutilsr get_loggerrGr?(PIX2STRUCT_PRETRAINED_CONFIG_ARCHIVE_MAPrrRr]rrrr0s     w