g3dZddlZddlmZddlmZddlmZeje Z GddeZ Gd d eZ Gd d eZ dS) zKOSMOS-2 model configurationN)Union)PretrainedConfig)loggingceZdZdZdZdgZddddZ dfd Zede e e j fddfdZ xZS)Kosmos2TextConfigav This is the configuration class to store the configuration of a [`Kosmos2TextModel`]. It is used to instantiate a KOSMOS-2 text decoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the text decoder of the KOSMOS-2 [microsoft/kosmos-2-patch14-224](https://huggingface.co/microsoft/kosmos-2-patch14-224) 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 65037): Vocabulary size of the Kosmos2 model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`Kosmos2Model`]. max_position_embeddings (`int`, *optional*, defaults to 2048): 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). embed_dim (`int`, *optional*, defaults to 2048): Dimensionality of the layers and the pooler layer. layers (`int`, *optional*, defaults to 24): Number of hidden layers in the Transformer encoder. ffn_dim (`int`, *optional*, defaults to 8192): Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder. attention_heads (`int`, *optional*, defaults to 32): Number of attention heads for each attention layer in the Transformer encoder. activation_function (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. dropout (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_dropout (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention probabilities. activation_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for activations inside the fully connected layer. layerdrop (`float`, *optional*, defaults to 0.0): The LayerDrop probability for the decoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556) for more details. layer_norm_eps (`float`, *optional*, defaults to 1e-5): The epsilon used by the layer normalization layers. init_std (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. scale_embedding (`bool`, *optional*, defaults to `True`): Scale embeddings by diving by sqrt(embed_dim). use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). ```kosmos_2_text_modelpast_key_valuesattention_heads embed_dimlayers)num_attention_heads hidden_sizenum_hidden_layers  gelu皙?h㈵>{Gz?Trc tjd|||d|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_dS)N) pad_token_id bos_token_id eos_token_id)super__init__ vocab_sizemax_position_embeddingsr r ffn_dimr activation_functiondropoutattention_dropoutactivation_dropout layerdroplayer_norm_epsinit_stdscale_embedding use_cache)selfr$r%r r r&r r'r(r)r*r+r,r-r.r/rrr kwargs __class__s m/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/kosmos2/configuration_kosmos2.pyr#zKosmos2TextConfig.__init__Rs,  %%%      %'>$"  .#6  !2"4",  ."pretrained_model_name_or_pathreturnrc N|||j|fi|\}}|ddkr|d}d|vrMt|dr=|d|jkr,t d|dd|jd|j|fi|S)N model_typekosmos-2 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_dictgethasattrr8loggerwarning from_dictclsr5r1 config_dicts r3from_pretrainedz!Kosmos2TextConfig.from_pretraineds   (((1c12OZZSYZZ V ??< ( (J 6 6%m4K ; & &73 +E+E &+VbJcgjguJuJu NNr\1Jrr>rrr    s}[33F333r4)rrrrrrrrrrrrrTTrrr)__name__ __module__ __qualname____doc__r8keys_to_ignore_at_inference attribute_mapr# classmethodrstrosPathLikerI __classcell__r2s@r3rrs, , \'J#4"50"%M $"'+#+#+#+#+#+#Z4E#r{BR