o ¾e¦i*ã@s6ddlmZddlmZmZGdd„deƒZdgZdS)é)ÚPreTrainedConfigé)ÚCONFIG_MAPPINGÚ AutoConfigcsHeZdZdZdZeedœZdgZ      d‡fd d„ Z‡Z S)Ú Glm46VConfigaÖ This is the configuration class to store the configuration of a [`Glm4vModel`]. It is used to instantiate a GLM-4.6V model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of GLM-4.1V-9B-Thinking [zai-org/GLM-4.1V-9B-Thinking](https://huggingface.co/zai-org/GLM-4.1V-9B-Thinking). Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: text_config (`Union[PreTrainedConfig, dict]`, *optional*, defaults to `Glm4vTextConfig`): The config object or dictionary of the text backbone. vision_config (`Union[PreTrainedConfig, dict]`, *optional*, defaults to `Glm4vVisionConfig`): The config object or dictionary of the vision backbone. image_token_id (`int`, *optional*, defaults to 151343): The image token index to encode the image prompt. video_token_id (`int`, *optional*, defaults to 151344): The video token index to encode the image prompt. image_start_token_id (`int`, *optional*, defaults to 151339): The image start token index to encode the start of image. image_end_token_id (`int`, *optional*, defaults to 151340): The image end token index to encode the end of image. video_start_token_id (`int`, *optional*, defaults to 151361): The video start token index to encode the start of video. video_end_token_id (`int`, *optional*, defaults to 151362): The video end token index to encode the end of video. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether to tie weight embeddings ```python >>> from transformers import Glm46VForConditionalGeneration, Glm46VConfig >>> # Initializing a GLM-4.6V style configuration >>> configuration = Glm46VConfig() >>> # Initializing a model from the GLM-4.6V style configuration >>> model = Glm4vForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Úglm46v)Ú text_configÚ vision_configÚpast_key_valuesNé/Oé0Oé+Oé,OéAOéBOFc  sÐt|tƒr| dd¡|d<t|ddi|¤Ž|_n |dur$tdƒ|_t|tƒr>| dd¡|d<t|ddi|¤Ž|_n |durHtdƒ|_||_||_||_||_ ||_ ||_ | |_ t ƒjdi| ¤ŽdS)NÚ model_typeÚ glm4v_visionÚ glm4v_text©)Ú isinstanceÚdictÚgetrr rÚimage_token_idÚvideo_token_idÚvideo_start_token_idÚvideo_end_token_idÚimage_start_token_idÚimage_end_token_idÚtie_word_embeddingsÚsuperÚ__init__) Úselfrr rrrrrrrÚkwargs©Ú __class__rúm/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/glm46v/configuration_glm46v.pyr Is$    zGlm46VConfig.__init__) NNr r r rrrF) Ú__name__Ú __module__Ú __qualname__Ú__doc__rrÚ sub_configsÚkeys_to_ignore_at_inferencer Ú __classcell__rrr#r%rs* örN)Úconfiguration_utilsrÚautorrrÚ__all__rrrr%Ús  S