o ei=@sbdZddlmZddlmZeeZGdddeZGdddeZ Gdd d eZ gd Z d S) zPix2Struct model configuration)PreTrainedConfig)loggingcsheZdZdZdZdgZddddddddZ              dfdd ZZS)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 probability 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)rnum_attention_headsnum_hidden_layersdecoder_attention_headsencoder_attention_headsencoder_layersdecoder_layersD@ 皙?ư>?gelu_newFNTc s||_||_||_||_||_||_||_||_| |_| |_ | |_ ||_ ||_ ||_ | |_| |_||_||_ | |_||_||_||_tjdi|dSN) vocab_sizerd_kvd_ffr rrelative_attention_num_bucketsrelative_attention_max_distance dropout_ratelayer_norm_epsiloninitializer_factor use_cache eos_token_id bos_token_iddecoder_start_token_id dense_act_fn pad_token_idtie_word_embeddings is_decoderadd_cross_attentionsuper__init__)selfrrr r!r rr"r#r$r%r&r+r*r'r,r(r)r-r.r/kwargs __class__ru/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/pix2struct/configuration_pix2struct.pyr1`s.zPix2StructTextConfig.__init__)rrrrrrrrrrrrrFrrNFTF) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inference attribute_mapr1 __classcell__rrr4r6rsB< rcsDeZdZdZdZ         dfdd ZZS)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 probability 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|||_||_||_| |_||_||_| |_| |_ | |_ ||_ ||_ | |_ ||_||_||_dSr)r0r1rpatch_embed_hidden_sizer!r$r r initializer_ranger&attention_dropoutlayer_norm_epsr+seq_lenr"r#r )r2rrDr!r r r r+rGr$rFrEr&rHr"r#r3r4rr6r1s  zPix2StructVisionConfig.__init__)rrrrrrrrrArArBrrCrr)r7r8r9r:r;r1r>rrr4r6r?s&:r?cs>eZdZdZdZeedZ       d fd d ZZ S) Pix2StructConfiga2 [`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(text_config=config_text, vision_config=config_vision) ``` pix2struct) text_config vision_configNr{Gz?FTc  s|durt||d}tdnt|tr%||d<||d<tdi|}|dur2t}tdn t|tr>tdi|}||_||_|jj|_|jj |_ |jj |_ ||_ ||_ |j |j_ |j |j_ ||_ ||_tjdd|i|dS)N)is_encoder_decoderr-zU`text_config` is `None`. initializing the `Pix2StructTextConfig` with default values.rNr-zY`vision_config` is `None`. initializing the `Pix2StructVisionConfig` with default values.r)rloggerinfo isinstancedictr?rKrLr*r,r(r&rEis_vqar-r0r1) r2rKrLr&rErSr-rNr3r4rr6r1+s4          zPix2StructConfig.__init__)NNrrMFFT) r7r8r9r:r;rr? sub_configsr1r>rrr4r6rIs/ rI)rIrr?N) r:configuration_utilsrutilsr get_loggerr7rOrr?rI__all__rrrr6s   ~c `