a hI@sdZddlmZddlmZddlmZmZmZerLddl m Z ddl m Z ddl mZdd lmZdd l mZeeZGd d d eZGd ddeZGdddeZGdddeZgdZdS)zCLIP model configuration OrderedDict)Mapping) TYPE_CHECKINGAnyOptional)ProcessorMixin) TensorType)PretrainedConfig) OnnxConfig)loggingcs*eZdZdZdZdZdfdd 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 ```Zclip_text_model text_config M quick_geluh㈵>{Gz??c sftjf| ||d|||_||_||_||_||_||_||_| |_ ||_ | |_ | |_ | |_ dS)N) pad_token_id bos_token_id eos_token_id)super__init__ vocab_size hidden_sizeintermediate_sizeprojection_dimnum_hidden_layersnum_attention_headsmax_position_embeddingslayer_norm_eps hidden_actinitializer_rangeinitializer_factorattention_dropout)selfr#r$r%r&r'r(r)r+r*r.r,r-rrr kwargs __class__g/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/models/clip/configuration_clip.pyr"bszCLIPTextConfig.__init__)rrrrrrrrrrrrrrr__name__ __module__ __qualname____doc__ model_typeZbase_config_keyr" __classcell__r3r3r1r4r"s&<rc s*eZdZdZdZdZdfdd 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 ```Zclip_vision_model vision_config rrr rrrrrc sdtjfi|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_dS)N)r!r"r$r%r&r'r( num_channels patch_size image_sizer,r-r.r*r+)r/r$r%r&r'r(rBrDrCr+r*r.r,r-r0r1r3r4r"szCLIPVisionConfig.__init__) r>r?rrrrr@rArrrrrr5r3r3r1r4r<s"6r<cs0eZdZdZdZeedZd fdd ZZ S) CLIPConfigaN [`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.from_text_vision_configs(config_text, config_vision) ```Zclip)rr=Nr/L F@c  s|dd}|dd}tjfi||dur|dur>i}tfi|}|D]V\} } | |vrX| || krX| dvrX| |vrd| d| d} n d| d} t| qX|||durz|duri}t fi|} d | vrd d | d D| d <| D]`\} } | |vr| || kr| dvr| |vrVd| d | d} n d | d} t| q|| |duri}td|duri}tdtfi||_ t fi||_ ||_ ||_ d|_dS)Ntext_config_dictvision_config_dict)Ztransformers_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.Zid2labelcSsi|]\}}t||qSr3)str).0keyvaluer3r3r4 Esz'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.r)popr!r"rto_dictitemsloggerinfoupdater<rr=r&logit_scale_init_valuer-) r/rr=r&rUr0rGrHZ_text_config_dictrLrMmessageZ_vision_config_dictr1r3r4r"sh       "      zCLIPConfig.__init__)NNrrF) r6r7r8r9r:rr<Z sub_configsr"r;r3r3r1r4rEs - rEcseZdZeeeeeeffdddZeeeeeeffdddZee dddZ dd eee d eee fd fd d Z eedddZZS)CLIPOnnxConfig)returncCs0tddddfdddddd fd dddfgS) NZ input_idsbatchsequence)rrZ pixel_valuesrBheightwidth)rrrZattention_maskrr/r3r3r4inputsns   zCLIPOnnxConfig.inputscCs0tdddifdddifdddifdddifgS)NZlogits_per_imagerrYZlogits_per_textZ text_embedsZ image_embedsrr^r3r3r4outputsxs    zCLIPOnnxConfig.outputscCsdS)Ng-C6?r3r^r3r3r4atol_for_validationsz"CLIPOnnxConfig.atol_for_validationNr r ) processor batch_size seq_length frameworkrXcs6tj|j|||d}tj|j||d}i||S)N)rdrerf)rdrf)r!generate_dummy_inputs tokenizerZimage_processor)r/rcrdrerfZtext_input_dictZimage_input_dictr1r3r4rgs z$CLIPOnnxConfig.generate_dummy_inputscCsdS)Nr3r^r3r3r4default_onnx_opsetsz!CLIPOnnxConfig.default_onnx_opset)rbrbN)r6r7r8propertyrrJintr_r`floatrarrrgrjr;r3r3r1r4rWms$   rW)rErWrr<N)r9 collectionsrcollections.abcrtypingrrrZprocessing_utilsr utilsr Zconfiguration_utilsr Zonnxr r Z get_loggerr6rRrr<rErW__all__r3r3r3r4s         e\ .