o ¾e¦i0ã@s`dZddlmZddlmZe e¡ZGdd„deƒZGdd„deƒZ Gdd „d eƒZ d gZ d S) zKOSMOS-2 model configurationé)ÚPreTrainedConfig)ÚloggingcsbeZdZdZdZdZdgZddddœZ             d‡fdd„ Z‡Z S)ÚKosmos2TextConfiga± 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. ```Úkosmos_2_text_modelÚ text_configÚpast_key_valuesÚattention_headsÚ embed_dimÚlayers)Únum_attention_headsÚ hidden_sizeÚnum_hidden_layersé þééé é Úgeluçš™™™™™¹?ççñh㈵øä>ç{®Gáz”?TéééFc sˆtƒjdi|¤Ž||_||_||_||_||_||_||_||_ ||_ ||_ ||_ ||_ | |_| |_| |_| |_| |_||_||_dS©N©)ÚsuperÚ__init__Ú pad_token_idÚ bos_token_idÚ eos_token_idÚadd_cross_attentionÚ vocab_sizeÚmax_position_embeddingsr r Úffn_dimrÚactivation_functionÚdropoutÚattention_dropoutÚactivation_dropoutÚ layerdropÚlayer_norm_epsÚinit_stdÚscale_embeddingÚ use_cache)Úselfr#r$r r r%rr&r'r(r)r*r+r,r-r.rr r!r"Úkwargs©Ú __class__rúo/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/kosmos2/configuration_kosmos2.pyrUs( zKosmos2TextConfig.__init__)rrrrrrrrrrrrrTTrrrF) Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚbase_config_keyÚkeys_to_ignore_at_inferenceÚ attribute_maprÚ __classcell__rrr1r3rs:4ýìrcsBeZdZdZdZdZ       d‡fdd„ Z‡ZS)ÚKosmos2VisionConfiga¡ 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). ```Úkosmos_2_vision_modelÚ vision_configééréréàéÚ quick_gelurrrçð?c  s^tƒjdi| ¤Ž||_||_||_||_||_||_||_| |_ | |_ | |_ | |_ ||_ dSr)rrr Úintermediate_sizer r Ú num_channelsÚ patch_sizeÚ image_sizeÚinitializer_rangeÚinitializer_factorr(r+Ú hidden_act)r/r rGr r rHrJrIrMr+r(rKrLr0r1rr3r­s zKosmos2VisionConfig.__init__) r@rArrBrrCrDrErrrrF)r4r5r6r7r8r9rr<rrr1r3r=ƒs"&ór=cs8eZdZdZdZeedœZ    d ‡fdd„ Z‡Z S) Ú Kosmos2ConfigaÁ 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. tie_word_embeddings (`bool`, *optional*, defaults to `True`): Whether the model's input and output word embeddings should be tied. 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)rr?Né@Tc s’|dur tƒ}t d¡n t|tƒrtdi|¤Ž}|dur&tƒ}t d¡n t|tƒr2tdi|¤Ž}||_||_||_||_ t ƒj di|¤ŽdS)NzR`text_config` is `None`. initializing the `Kosmos2TextConfig` with default values.zV`vision_config` is `None`. initializing the `Kosmos2VisionConfig` with default values.r) rÚloggerÚinfoÚ isinstanceÚdictr=rr?Úlatent_query_numÚtie_word_embeddingsrr)r/rr?rTrUr0r1rr3rðs    zKosmos2Config.__init__)NNrOT) r4r5r6r7r8rr=Ú sub_configsrr<rrr1r3rNÍs ûrNN) r7Úconfiguration_utilsrÚutilsrÚ get_loggerr4rPrr=rNÚ__all__rrrr3Ús   lJ >