gLdZddlZddlmZmZmZmZddlmZddl m Z ddl m Z e j eZGdd eZGd d eZGd d eZdS)zMllama model configurationN)DictListOptionalUnion)PretrainedConfig)rope_config_validation)loggingc eZdZdZdZ d&dededededededededededededee edee e edeffd Z e d!efd"Z e d#eeejfd!d$fd%ZxZS)'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_modelgelu rh㈵>N{Gz? 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|/| dkrtdddgddgddgddgddgddgddgddgg}| gd} ||_||_||_||_||_| |_||_| |_| |_ ||_ | |_ | |_ ||_ ||_||_t!jdi|dS)Nrz;max_num_tiles must be 4 for default supported aspect ratiosr)r) ValueErrorrrrrr r"r!r#r&rr%r$attention_headsr'r(super__init__)selfrrrrrrr r!r"r#r$r%r&r'r(kwargs __class__s k/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/mllama/configuration_mllama.pyr4zMllamaVisionConfig.__init__\s & # *!! !^___()1v1v1v1v1vPQSTvXY[\W]`acd_e&f # & .*<*<*< '&$!2(!2$!2$+F(!2*  2'>$!2""6"""""returnc*t|jS)N)lenr')r5s r8max_aspect_ratio_idz&MllamaVisionConfig.max_aspect_ratio_ids4/000r9pretrained_model_name_or_pathrc N|||j|fi|\}}|ddkr|d}d|vrMt|dr=|d|jkr,t d|dd|jd|j|fi|S)N model_typemllama vision_configYou are using a model of type to instantiate a model of type N. This is not supported for all configurations of models and can yield errors._set_token_in_kwargsget_config_dictgethasattrr@loggerwarning from_dictclsr>r6 config_dicts r8from_pretrainedz"MllamaVisionConfig.from_pretraineds   (((1c12OZZSYZZ V ??< ( (H 4 4%o6K ; & &73 +E+E &+VbJcgjguJuJu NNr\1Jrr>rrr    s}[33F333r9)rrrrrrrrrrrrNNr)__name__ __module__ __qualname____doc__r@intstrfloatrrr4propertyr= classmethodrosPathLikerQ __classcell__r7s@r8r r s< < |'J  !#!"#%!%!%;?=A#'!*#*#*#*# *#  *# ! *#*#*#*#*#*#*#*#&.d3i%8*#"*$tCy/!:*# !!*#*#*#*#*#*#X1S111X14E#r{BR