o Zh@sPdZddlmZddlmZddlmZmZee Z GdddeZ dgZ dS) zVipLlava model configuration)PretrainedConfig)logging)CONFIG_MAPPING AutoConfigcsJeZdZdZdZddiZeedZddddd gd d ffd d ZZ S)VipLlavaConfiga This is the configuration class to store the configuration of a [`VipLlavaForConditionalGeneration`]. It is used to instantiate an VipLlava 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 VipLlava-9B. e.g. [ybelkada/vip-llava-7b-hf](https://huggingface.co/ybelkada/vip-llava-7b-hf) Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vision_config (`VipLlavaVisionConfig`, *optional*): Custom vision config or dict text_config (`Union[AutoConfig, dict]`, *optional*): The config object of the text backbone. Can be any of `LlamaConfig` or `MistralConfig`. image_token_index (`int`, *optional*, defaults to 32000): The image token index to encode the image prompt. projector_hidden_act (`str`, *optional*, defaults to `"gelu"`): The activation function used by the multimodal projector. projector_layernorm_eps (`float`, *optional*, defaults to 1e-05): The layer norm epsilon of the projector layernorm vision_feature_layers (`Union[int, List[int]]`, *optional*, defaults to `[-2, -5, -8, -11, 6]`): The vision feature layer, or list of layers to select the vision features from. image_seq_length (`int`, *optional*, defaults to 576): Sequence length of one image embedding. Example: ```python >>> from transformers import VipLlavaForConditionalGeneration, VipLlavaConfig, CLIPVisionConfig, LlamaConfig >>> # Initializing a CLIP-vision config >>> vision_config = CLIPVisionConfig() >>> # Initializing a Llama config >>> text_config = LlamaConfig() >>> # Initializing a VipLlava vipllava-7b style configuration >>> configuration = VipLlavaConfig(vision_config, text_config) >>> # Initializing a model from the vipllava-7b style configuration >>> model = VipLlavaForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ZvipllavaZimage_token_idimage_token_index) text_config vision_configN}Zgelugh㈵>)iii@c s||_||_||_||_||_||_t|jtr1d|vr |dnd|d<t|dd i||_n|durDtdddddddd d d |_t|trad|vrQ|dnd |d<t|dd i|}n |durjtd }||_ t j d i|dS)N model_typeZclip_vision_modeliiiPr i)Zintermediate_sizeZ hidden_sizeZ patch_sizeZ image_sizeZnum_hidden_layersZnum_attention_headsZ vocab_sizeZprojection_dimllama) rprojector_hidden_actprojector_layernorm_epsvision_feature_layersimage_seq_lengthr isinstancedictrr super__init__) selfr r rrrrrkwargs __class__rb/var/www/auris/lib/python3.10/site-packages/transformers/models/vipllava/configuration_vipllava.pyrNs8    zVipLlavaConfig.__init__) __name__ __module__ __qualname____doc__rZ attribute_maprZ sub_configsr __classcell__rrrr!rs/ rN) r%Zconfiguration_utilsrutilsrautorrZ get_loggerr"loggerr__all__rrrr!s    d