gjdZddlmZddlmZddlmZejeZ GddeZ dS) zVipLlava model configuration)PretrainedConfig)logging)CONFIG_MAPPINGc@eZdZdZdZdZddddddgd d ffd ZxZS) 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`. ignore_index (`int`, *optional*, defaults to -100): The ignore index for the loss function. 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 (`List[int]`, *optional*, defaults to `[-2, -5, -8, -11, 6]`): The 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 ```vipllavaFNi}gelugh㈵>)iii@c .||_||_||_||_||_||_||_t|jtr/d|vr|dnd|d<t|dd i||_n$|"tdddddddd d |_t|tr*d|vr|dnd |d<t|dd i|}n|td }||_ tj d i| dS)N model_typeclip_vision_modeliiiPr i)intermediate_size hidden_size patch_size image_sizenum_hidden_layersnum_attention_heads vocab_sizeprojection_dimllama) ignore_indeximage_token_indexprojector_hidden_actprojector_layernorm_epsvision_feature_layersimage_seq_length vision_config isinstancedictr text_configsuper__init__) selfr%r(rr r!r"r#r$kwargs __class__s o/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/vipllava/configuration_vipllava.pyr*zVipLlavaConfig.__init__Msh)!2$8!'>$%:" 0* d($ / / /;}/L/L l++Re , '"0 l0K!L!]!]}!]!]D    "!/0C!D"& "$$& " " " "D  k4 ( ( 4EQU`E`E` L(A(AfmK %(\)BCRRkRRKK  (133K&""6""""")__name__ __module__ __qualname____doc__ris_compositionr* __classcell__)r-s@r.rrst/ / bJN# $222-#-#-#-#-#-#-#-#-#-#r/rN) r3configuration_utilsrutilsrautor get_loggerr0loggerrrr/r.r;s#"333333!!!!!!  H % %b#b#b#b#b#%b#b#b#b#b#r/