IgLdZddlZddlmZmZmZmZddlmZddl m Z ddl m Z e jeZGdd eZGd d eZGd d eZy)zMllama model configurationN)DictListOptionalUnion)PretrainedConfig)rope_config_validation)loggingc eZdZdZdZ ddedededededed ed ed ed ed ededee edee e edeffd Z e defdZ e deeej fddfdZxZS)MllamaVisionConfiga* This is the configuration class to store the configuration of a [`MllamaVisionModel`]. It is used to instantiate an Mllama vision 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 Mllama-11B. e.g. [meta-llama/Llama-3.2-11B-Vision](https://huggingface.co/meta-llama/Llama-3.2-11B-Vision) 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 1280): Dimensionality of the encoder layers and the pooler layer. hidden_act (`str` or `function`, *optional*, defaults to `"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. num_hidden_layers (`int`, *optional*, defaults to 32): Number of hidden layers in the Transformer encoder. num_global_layers (`int`, *optional*, defaults to 8): Number of global layers in the Transformer encoder. Vision model has a second transformer encoder, called global. 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): Number of channels in the input image. intermediate_size (`int`, *optional*, defaults to 5120): Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder. vision_output_dim (`int`, *optional*, defaults to 7680): Dimensionality of the vision model output. Includes output of transformer encoder with intermediate layers and global transformer encoder. image_size (`int`, *optional*, defaults to 448): The size (resolution) of each image *tile*. patch_size (`int`, *optional*, defaults to 14): The size (resolution) of each patch. norm_eps (`float`, *optional*, defaults to 1e-5): The epsilon used by the layer normalization layers. max_num_tiles (`int`, *optional*, defaults to 4): Maximum number of tiles for image splitting. intermediate_layers_indices (`List[int]`, *optional*, defaults to [3, 7, 15, 23, 30]): Indices of intermediate layers of transformer encoder from which to extract and output features. These output features are concatenated with final hidden state of transformer encoder. supported_aspect_ratios (`List[List[int]]`, *optional*): List of supported aspect ratios for image splitting. If not specified, the default supported aspect ratios are [[1, 1], [1, 2], [1, 3], [1, 4], [2, 1], [2, 2], [3, 1], [4, 1]] for `max_num_tiles=4`. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. Example: ```python >>> from transformers import MllamaVisionConfig, MllamaVisionModel >>> # Initializing a Llama config >>> config = MllamaVisionConfig() >>> # Initializing a vision model from the mllama-11b style configuration >>> model = MllamaVisionModel(config) >>> # Accessing the model configuration >>> configuration = model.config ```mllama_vision_model hidden_size hidden_actnum_hidden_layersnum_global_layersnum_attention_heads num_channelsintermediate_sizevision_output_dim image_size patch_sizenorm_eps max_num_tilesintermediate_layers_indicessupported_aspect_ratiosinitializer_rangec Z|*| dk7r tdddgddgddgddgddgddgddgddgg}| gd} ||_||_||_||_||_| |_||_| |_| |_ ||_ | |_ | |_ ||_ ||_||_t!|Ddi|y)Nz;max_num_tiles must be 4 for default supported aspect ratiosr)r) ValueErrorrrrrrrrrrrrrattention_headsrrsuper__init__)selfrrrrrrrrrrrrrrrkwargs __class__s l/var/www/html/answerous/venv/lib/python3.12/site-packages/transformers/models/mllama/configuration_mllama.pyr)zMllamaVisionConfig.__init__\s& # *! !^__()1v1v1v1v1vPQSTvXY[\W]`acd_e&f # & .*< '&$!2(!2$!2$+F(!2*  2'>$!2 "6"returnc,t|jS)N)lenr)r*s r-max_aspect_ratio_idz&MllamaVisionConfig.max_aspect_ratio_ids4//00r.pretrained_model_name_or_pathrc >|j||j|fi|\}}|jddk(r|d}d|vrGt|dr;|d|jk7r)t j d|dd|jd|j|fi|S)N model_typemllama vision_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_dictgethasattrr5loggerwarning from_dictclsr3r+ config_dicts r-from_pretrainedz"MllamaVisionConfig.from_pretraineds   (1c112OZSYZ V ??< (H 4%o6K ; &73 +E+VbJcgjguguJu NN0\1J0KKk>>""pr  s}}[3F33r.)igelu riiih㈵>rNN{Gz?)__name__ __module__ __qualname____doc__r5intstrfloatrrr)propertyr2 classmethodrosPathLikerF __classcell__r,s@r-r r s;< |'J  !#!"#%!%!%;?=A#'!*#*#*# *#  *# ! *#*#*#*#*#*#*#*#&.d3i%8*#"*$tCy/!:*# !!*#X1S114E#r{{BR