qixpdZddlmZddlmZddlmZmZeje Z GddeZ dgZ y) zVipLlava model configuration)PreTrainedConfig)logging)CONFIG_MAPPING AutoConfigcNeZdZdZdZddiZeedZddddd gd d d ffd ZxZ S)VipLlavaConfigaN 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. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether to tie weight embeddings 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 ```vipllavaimage_token_idimage_token_index) text_config vision_configN}gelugh㈵>)iii@Fc ||_||_||_||_||_||_||_t|j tr,|jdd|d<t|dd i||_n|tdddddddd d |_t|tr'|jdd |d<t|dd i|}n| td }||_ t |4d i| y)N model_typeclip_vision_modeliiiPri)intermediate_size hidden_size patch_size image_sizenum_hidden_layersnum_attention_heads vocab_sizeprojection_dimllama)r projector_hidden_actprojector_layernorm_epsvision_feature_layersimage_seq_lengthrtie_word_embeddings isinstancedictgetrr super__init__) selfrr r r$r%r&r'r(kwargs __class__s e/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/vipllava/configuration_vipllava.pyr-zVipLlavaConfig.__init__Os"3$8!'>$%:" 0*#6 d(($ /*7*;*;LJ]*^M, '!/ l0K!L!]}!]D   "!/0C!D"& "$$& " "D  k4 ((3 g(NK %(\)BCRkRK  (13K& "6") __name__ __module__ __qualname____doc__r attribute_mapr sub_configsr- __classcell__)r0s@r1r r sM/ bJ-M#-zJK# $2!+#+#r2r N) r6configuration_utilsrutilsrautorr get_loggerr3loggerr __all__r#r2r1r@sA#3-   H %c#%c#L  r2