tj)JdZddlmZddlmZddlmZmZeje Z edeGdd eZ edeGd d eZ edeGd d eZ gdZdS)zCLIP model configuration)strict)PreTrainedConfig)auto_docstringloggingzopenai/clip-vit-base-patch32) checkpointc6eZdZUdZdZdZdZeed<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"Zd S)#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_idcl|j|jzdkr td|jd|jddSzOPart 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 i/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/clip/configuration_clip.pyvalidate_architecturez$CLIPTextConfig.validate_architectureB[  d6 6! ; ;7D$4772777  < ;)__name__ __module__ __qualname____doc__ model_typebase_config_keyr int__annotations__rrrrrrrstrrfloatrrr!r#r$r%listr-r/r,r r s^  #J#OJK!s!!!!$NC$J$$$s    #%S%%%"J"""#'NEDL''',/sU{T)///#u###'* *** !L#*   $L#*$$$+0L#S /D(000r/r c@eZdZUdZdZdZdZeed<dZ eed<dZ eed <d Z eed <d Z eed <d Z eed<dZeeezeeefzdzed<dZeeezeeefzdzed<dZeed<dZeed<dZeezdzed<dZeed<dZeed<dZdS)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!cl|j|jzdkr td|jd|jddSr'r(r*s r,r-z&CLIPVisionConfig.validate_architectureor.r/)r0r1r2r3r4r5rr6r7rrrrr@rBr:tuplerDrr8rr9rrr!r-r;r/r,r=r=KsN  %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}tdn;t|jtr|j}n|j}|ji}tdn;t|jtr|j}n|j}|dd}|dd}|t di|}| D]I\}}||vr@|||kr4|dkr.||vr d|d|d} nd |d } t| J| ||tdi|} d | vr'd | d  D| d <| D]I\}}||vr@|||kr4|dkr.||vr d|d |d} nd|d } t| J| | t di||_tdi||_tj di|dS)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.id2labelc4i|]\}}t||Sr;)r8).0keyvalues r, z,CLIPConfig.__post_init__..s1333(2UCHHe333r/zv` 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=popitemsupdatesuper __post_init__) r+kwargsr r?rLrM_text_config_dictrSrTmessage_vision_config_dict __class__s r,r^zCLIPConfig.__post_init__sZ   #K KKi j j j j (. 9 9 +*2244KK*K   %M KKm n n n n *,< = = / .6688MM .M "::&8$??#ZZ(> >>'''''''r/)r0r1r2r3r4r r= sub_configsr dictr7r?rr6rJr9r!r^ __classcell__)rcs@r,rHrHxs  @J"0CSTTK04K&-44448M4**T1888!$NC$J$$$17ECK$.777'* ***Q(Q(Q(Q(Q(Q(Q(Q(Q(r/rH)rHr r=N)r3huggingface_hub.dataclassesrconfiguration_utilsrutilsrr get_loggerr0rVr r=rH__all__r;r/r,rlsi......333333,,,,,,,,  H % %9:::-----%--;:-`9:::((((('((;:(V9:::{({({({({(!{({(;:{(| ? > >r/