^j)dZddlmZddlmZddlmZmZeje Z edeGdd eZ edeGd d eZ edeGd d eZ gdZy)zCLIP model configuration)strict)PreTrainedConfig)auto_docstringloggingzopenai/clip-vit-base-patch32) checkpointc.eZdZUdZdZdZdZeed<dZ eed<dZ eed <dZ ed zed <d Z eed <dZ eed<dZeed<dZeed<dZed zed<dZeezd zed<dZeed<dZed zed<dZed zed<dZed zed<d Zeeezd zed!<d"Zy )#CLIPTextConfiga Example: ```python >>> from transformers import CLIPTextConfig, CLIPTextModel >>> # Initializing a CLIPTextConfig with openai/clip-vit-base-patch32 style configuration >>> configuration = CLIPTextConfig() >>> # Initializing a CLIPTextModel (with random weights) from the openai/clip-vit-base-patch32 style configuration >>> model = CLIPTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```clip_text_model text_configi vocab_size hidden_sizeiintermediate_sizeNprojection_dim num_hidden_layersnum_attention_headsMmax_position_embeddings quick_gelu hidden_acth㈵>layer_norm_epsattention_dropout{Gz?initializer_range?initializer_factor pad_token_idi bos_token_idi eos_token_idc|j|jzdk7r&td|jd|jdyzOPart of `@strict`-powered validation. Validates the architecture of the config.rzThe hidden size (z6) is not a multiple of the number of attention heads (z).Nrr ValueErrorselfs v/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/clip/configuration_clip.pyvalidate_architecturez$CLIPTextConfig.validate_architectureBS   d66 6! ;#D$4$4#5622327  <)__name__ __module__ __qualname____doc__ model_typebase_config_keyr int__annotations__rrrrrrrstrrfloatrrr!r#r$r%listr-r/r,r r s #J#OJK!s!!$NC$J$s  #%S%"J"#'NEDL',/sU{T)/#u#'* * !L#* $L#*$+0L#S /D(0r/r c&eZdZUdZdZdZdZeed<dZ eed<dZ eed <d Z eed <d Z eed <d Z eed<dZeeezeeefzdzed<dZeeezeeefzdzed<dZeed<dZeed<dZeezdzed<dZeed<dZeed<dZy)CLIPVisionConfiga Example: ```python >>> from transformers import CLIPVisionConfig, CLIPVisionModel >>> # Initializing a CLIPVisionConfig with openai/clip-vit-base-patch32 style configuration >>> configuration = CLIPVisionConfig() >>> # Initializing a CLIPVisionModel (with random weights) from the openai/clip-vit-base-patch32 style configuration >>> model = CLIPVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```clip_vision_model vision_configiri rrrrrrr num_channelsN image_size patch_sizerrrrrrrrr r!c|j|jzdk7r&td|jd|jdyr'r(r*s r,r-z&CLIPVisionConfig.validate_architectureor.r/)r0r1r2r3r4r5rr6r7rrrrr@rBr:tuplerDrr8rr9rrr!r-r;r/r,r=r=Ks %J%OK!s!NCs!!L#;>Jd3i%S/1D8>;=Jd3i%S/1D8="J" NE ,/sU{T)/#u# ##r/r=ceZdZUdZdZeedZdZe ezdze d<dZ e ezdze d<dZ e dze d<d Zee zdze d <d Zedze d <fd ZxZS) CLIPConfiga text_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`CLIPTextConfig`]. vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`CLIPVisionConfig`]. logit_scale_init_value (`float | int`, *optional*, defaults to 2.6592): The initial value of the *logit_scale* parameter. Default is used as per the original CLIP implementation. Example: ```python >>> from transformers import CLIPConfig, CLIPModel >>> # Initializing a CLIPConfig with openai/clip-vit-base-patch32 style configuration >>> configuration = CLIPConfig() >>> # Initializing a CLIPModel (with random weights) from the openai/clip-vit-base-patch32 style configuration >>> model = CLIPModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a CLIPConfig from a CLIPTextConfig and a CLIPVisionConfig >>> from transformers import CLIPTextConfig, CLIPVisionConfig >>> # Initializing a CLIPText and CLIPVision configuration >>> config_text = CLIPTextConfig() >>> config_vision = CLIPVisionConfig() >>> config = CLIPConfig(text_config=config_text, vision_config=config_vision) ```clip)r r?Nr r?rrg/L F@logit_scale_init_valuer r!c |ji}tjdnAt|jtr|jj }n |j}|j i}tjdnAt|j tr|j j }n |j }|jdd}|jdd}|t di|j }|jD]B\}}||vs |||k7s|dk7s||vr d|d|d} nd |d } tj| D|j||tdi|j } d | vr3| d jDcic]\}}t||c}}| d <| jD]B\}}||vs |||k7s|dk7s||vr d|d |d} nd |d } tj| D|j| t di||_tdi||_t |4di|ycc}}w)NzO`text_config` is `None`. Initializing the `CLIPTextConfig` with default values.zS`vision_config` is `None`. initializing the `CLIPVisionConfig` with default values.text_config_dictvision_config_dicttransformers_version`zp` is found in both `text_config_dict` and `text_config` but with different values. The value `text_config_dict["z"]` will be used instead.zj`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["z"]` will be overridden.id2labelzv` is found in both `vision_config_dict` and `vision_config` but with different values. The value `vision_config_dict["zp`vision_config_dict` is provided which will be used to initialize `CLIPVisionConfig`. The value `vision_config["r;)r loggerinfo isinstancer to_dictr?r=popitemsupdater8super __post_init__) r+kwargsr r?rLrM_text_config_dictkeyvaluemessage_vision_config_dict __class__s r,rYzCLIPConfig.__post_init__s    #K KKi j ((. 9**224K**K    %M KKm n **,< = ..668M ..M "::&8$?#ZZ( > ''93s&I)r0r1r2r3r4r r= sub_configsr dictr7r?rr6rJr9r!rY __classcell__)r`s@r,rHrHxs @J"0CSTK04K&-448M4**T18!$NC$J$17ECK$.7'* *Q(Q(r/rH)rHr r=N)r3huggingface_hub.dataclassesrconfiguration_utilsrutilsrr get_loggerr0rQr r=rH__all__r;r/r,ris.3,   H %9:-%-;-`9:('(;(V9:{(!{(;{(| ?r/