o eiC@sbdZddlmZddlmZeeZGdddeZGdddeZ Gdd d eZ gd Z d S) zCLIP model configuration)PreTrainedConfig)loggingcsHeZdZdZdZdZ          dfdd ZZS)CLIPTextConfiga This is the configuration class to store the configuration of a [`CLIPTextModel`]. It is used to instantiate a CLIP text encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the text encoder of the CLIP [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32) architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 49408): Vocabulary size of the CLIP text model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`CLIPModel`]. hidden_size (`int`, *optional*, defaults to 512): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 2048): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. projection_dim (`int`, *optional*, defaults to 512): Dimensionality of text and vision projection layers. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 8): Number of attention heads for each attention layer in the Transformer encoder. max_position_embeddings (`int`, *optional*, defaults to 77): The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048). hidden_act (`str` or `function`, *optional*, defaults to `"quick_gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported. layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). pad_token_id (`int`, *optional*, defaults to 1): Padding token id. bos_token_id (`int`, *optional*, defaults to 49406): Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 49407): End of stream token id. 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_config M quick_geluh㈵>{Gz??c sptjdi|| |_||_||_||_||_||_||_||_ ||_ ||_ | |_ ||_ | |_| |_| |_dSN)super__init__ pad_token_id bos_token_id eos_token_id vocab_size hidden_sizeintermediate_sizeprojection_dimnum_hidden_layersnum_attention_headsmax_position_embeddingslayer_norm_eps hidden_actinitializer_rangeinitializer_factorattention_dropout)selfrrrrr r!r"r$r#r'r%r&rrrkwargs __class__ri/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/clip/configuration_clip.pyrWs  zCLIPTextConfig.__init__)rrr rr r r r rrrrrrr__name__ __module__ __qualname____doc__ model_typebase_config_keyr __classcell__rrr*r,rs(<rcsDeZdZdZdZdZ        dfdd ZZS)CLIPVisionConfiga This is the configuration class to store the configuration of a [`CLIPVisionModel`]. It is used to instantiate a CLIP vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the vision encoder of the CLIP [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32) architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. projection_dim (`int`, *optional*, defaults to 512): Dimensionality of text and vision projection layers. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. num_channels (`int`, *optional*, defaults to 3): The number of input channels. image_size (`int`, *optional*, defaults to 224): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 32): The size (resolution) of each patch. hidden_act (`str` or `function`, *optional*, defaults to `"quick_gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported. layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). 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_config rr r r rrrrc sdtjdi|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_dSr)rrrrrr r! num_channels patch_size image_sizer%r&r'r#r$)r(rrrr r!r<r>r=r$r#r'r%r&r)r*rr,rs zCLIPVisionConfig.__init__) r8r9rr r rr:r;r rrrrr-rrr*r,r5s$6r5cs2eZdZdZdZeedZ d fdd ZZ S) CLIPConfigaO [`CLIPConfig`] is the configuration class to store the configuration of a [`CLIPModel`]. It is used to instantiate a CLIP model according to the specified arguments, defining the text model and vision model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the CLIP [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32) architecture. 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 (`dict`, *optional*): Dictionary of configuration options used to initialize [`CLIPTextConfig`]. vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`CLIPVisionConfig`]. projection_dim (`int`, *optional*, defaults to 512): Dimensionality of text and vision projection layers. logit_scale_init_value (`float`, *optional*, defaults to 2.6592): The initial value of the *logit_scale* parameter. Default is used as per the original CLIP implementation. kwargs (*optional*): Dictionary of keyword arguments. 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)rr7Nr/L F@c  s|dd}|dd}|durT|duri}tdi|}|D]+\} } | |vrN| || krN| dkrN| |vrCd| d| d} nd| d} t| q#|||dur|dur^i}tdi|} d | vrxd d | d D| d <| D]+\} } | |vr| || kr| dkr| |vrd| d | d} nd | d} t| q||| |durt}tdn t|t rtdi|}|durt}tdn t|t rtdi|}||_ ||_ ||_ ||_ d|_tjdi|dS)Ntext_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.id2labelcSsi|] \}}t||qSr)str).0keyvaluerrr, ;sz'CLIPConfig.__init__..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["zO`text_config` is `None`. initializing the `CLIPTextConfig` with default values.zS`vision_config` is `None`. initializing the `CLIPVisionConfig` with default values.rr)poprto_dictitemsloggerinfoupdater5 isinstancedictrr7rlogit_scale_init_valuer&rr) r(rr7rrTr)rBrC_text_config_dictrIrJmessage_vision_config_dictr*rr,r st            zCLIPConfig.__init__)NNrrA) r.r/r0r1r2rr5 sub_configsrr4rrr*r,r?s - r?)r?rr5N) r1configuration_utilsrutilsr get_loggerr.rOrr5r?__all__rrrr,s   h\