`ip.dZddlmZddlmZejeZGddeZGddeZ Gdd eZ d gZ d S) zKOSMOS-2 model configuration)PretrainedConfig)loggingcbeZdZdZdZdZdgZddddZ dfd ZxZ S)Kosmos2TextConfiga 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://huggingface.co/papers/1909.11556) for more details. layer_norm_eps (`float`, *optional*, defaults to 1e-05): 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). pad_token_id (`int`, *optional*, defaults to 1): Token id used for padding. bos_token_id (`int`, *optional*, defaults to 0): Token id used for beginning of string. eos_token_id (`int`, *optional*, defaults to 2): Token id used for end of string. ```kosmos_2_text_model text_configpast_key_valuesattention_heads embed_dimlayers)num_attention_heads hidden_sizenum_hidden_layers  gelu皙?h㈵>{Gz?Tc 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$r%r r r&r r'r(r)r*r+r,r-r.r/rrr kwargs __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/kosmos2/configuration_kosmos2.pyr#zKosmos2TextConfig.__init__Vs,  %%%      %'>$"  .#6  !2"4",  .")rrrrrrrrrrrrrTTrrr) __name__ __module__ __qualname____doc__ model_typebase_config_keykeys_to_ignore_at_inference attribute_mapr# __classcell__r2s@r3rrs2 2 h'J#O#4"50"%M $"'+#+#+#+#+#+#+#+#+#+#r4rcDeZdZdZdZdZ dfd ZxZS)Kosmos2VisionConfiga This is the configuration class to store the configuration of a [`Kosmos2VisionModel`]. It is used to instantiate a KOSMOS-2 vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the vision encoder 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: hidden_size (`int`, *optional*, defaults to 1024): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 4096): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. num_hidden_layers (`int`, *optional*, defaults to 24): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer encoder. num_channels (`int`, *optional*, defaults to 3): The number of input channels. image_size (`int`, *optional*, defaults to 224): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 14): The size (resolution) of each patch. hidden_act (`str` or `function`, *optional*, defaults to `"quick_gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported. layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. initializer_range (`float`, *optional*, defaults to 0.02): 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). ```kosmos_2_vision_model vision_configrr quick_gelurrr?c  tjdi| ||_||_||_||_||_||_||_| |_ | |_ | |_ | |_ ||_ dS)Nr!)r"r#rintermediate_sizerr num_channels patch_size image_sizeinitializer_rangeinitializer_factorr)r, hidden_act)r0rrKrr rLrNrMrQr,r)rOrPr1r2s r3r#zKosmos2VisionConfig.__init__s ""6"""&!2!2#6 ($$!2"4!2,$r4) rCrDrrErrFrGrHrrrrI)r5r6r7r8r9r:r#r=r>s@r3r@r@sz$ $ L)J%O%%%%%%%%%%r4r@c8eZdZdZdZeedZ dfd ZxZ S) Kosmos2Configat This is the configuration class to store the configuration of a [`Kosmos2Model`]. It is used to instantiate a KOSMOS-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 KOSMOS-2 [microsoft/kosmos-2-patch14-224](https://huggingface.co/microsoft/kosmos-2-patch14-224) architecture. Args: text_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`Kosmos2TextConfig`]. vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`Kosmos2VisionConfig`]. latent_query_num (`int`, *optional*, defaults to 64): The number of latent query tokens that represent the image features used in the text decoder component. kwargs (*optional*): Dictionary of keyword arguments. Example: ```python >>> from transformers import Kosmos2Config, Kosmos2Model >>> # Initializing a Kosmos-2 kosmos-2-patch14-224 style configuration >>> configuration = Kosmos2Config() >>> # Initializing a model (with random weights) from the kosmos-2-patch14-224 style configuration >>> model = Kosmos2Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```zkosmos-2)rrBN@c tjdi||i}td|i}tdt di||_t di||_||_dS)NzR`text_config` is `None`. Initializing the `Kosmos2TextConfig` with default values.zV`vision_config` is `None`. Initializing the `Kosmos2VisionConfig` with default values.r!) r"r#loggerinforrr@rBlatent_query_num)r0rrBrXr1r2s r3r#zKosmos2Config.__init__s ""6"""  K KKl m m m  M KKp q q q,;;{;;0AA=AA 0r4)NNrT) r5r6r7r8r9rr@ sub_configsr#r=r>s@r3rSrSsg  >J"3FYZZK 1111111111r4rSN) r8configuration_utilsrutilsr get_loggerr5rVrr@rS__all__r!r4r3r^s#"333333  H % %i#i#i#i#i#(i#i#i#XG%G%G%G%G%*G%G%G%T7171717171$717171t  r4