U ,-eP@sdZddlZddlmZddlmZmZmZmZm Z erPddl m Z ddl m Z ddlmZdd lmZdd l mZeeZd d iZGd ddeZGdddeZGdddeZGdddeZdS)z CLIP model configurationN OrderedDict) TYPE_CHECKINGAnyMappingOptionalUnion)ProcessorMixin) TensorType)PretrainedConfig) OnnxConfig)loggingzopenai/clip-vit-base-patch32zLhttps://huggingface.co/openai/clip-vit-base-patch32/resolve/main/config.jsoncsDeZdZdZdZdfdd Zeeee j fddddZ Z S)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. 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-5): 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): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). 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 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$r%r&r'r(r)r+r*r.r,r-rrr kwargs __class__l/var/www/html/Darija-Ai-Train/env/lib/python3.8/site-packages/transformers/models/clip/configuration_clip.pyr"]szCLIPTextConfig.__init__r pretrained_model_name_or_pathreturncKs~|||j|f|\}}|ddkr2|d}d|krpt|drp|d|jkrptd|dd|jd|j|f|S)N model_typeclip text_configYou are using a model of type to instantiate a model of type N. This is not supported for all configurations of models and can yield errors.Z_set_token_in_kwargsZget_config_dictgethasattrr8loggerwarning from_dictclsr6r0Z config_dictr3r3r4from_pretraineds  zCLIPTextConfig.from_pretrained)rrrrrrrrrrrrrrr __name__ __module__ __qualname____doc__r8r" classmethodrstrosPathLikerF __classcell__r3r3r1r4r's(3$rc sDeZdZdZdZdfdd Zeeee j fddddZ Z S)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. 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. 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-5): 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): 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 rrr rrrrrc s`tjf|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_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(rVrXrWr+r*r.r,r-r0r1r3r4r"szCLIPVisionConfig.__init__r r5cKs~|||j|f|\}}|ddkr2|d}d|krpt|drp|d|jkrptd|dd|jd|j|f|S)Nr8r9 vision_configr;r<r=r>rDr3r3r4rFs  z CLIPVisionConfig.from_pretrained) rRrSrrrr rTrUrrrrrrGr3r3r1r4rQs$2!rQcs:eZdZdZdZd fdd Zeeedd d Z Z S) CLIPConfigaL [`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): Dimentionality of text and vision projection layers. logit_scale_init_value (`float`, *optional*, defaults to 2.6592): The inital value of the *logit_scale* paramter. 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) ```r9Nr/L F@c  s|dd}|dd}tjf||dk r|dkr:i}tf|}|D]V\} } | |krP| || krP| dkrP| |krd| d| d} n d| d} t| qP|||dk rl|dkri}t f|} d | krd d | d D| d <| D]`\} } | |kr| || kr| dkr| |krHd| d | d} n d | d} t| q|| |dkri}t d|dkri}t dtf||_ t f||_ ||_ ||_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 overriden.Zid2labelcSsi|]\}}t||qSr3)rM).0keyvaluer3r3r4 ^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.r)popr!r"rto_dictitemsrArBupdaterQinfor:rYr&logit_scale_init_valuer-) r/r:rYr&rhr0r\r]Z_text_config_dictr`ramessageZ_vision_config_dictr1r3r4r"-sX       "         zCLIPConfig.__init__r:rYcKs|f||d|S)z Instantiate a [`CLIPConfig`] (or a derived class) from clip text model configuration and clip vision model configuration. Returns: [`CLIPConfig`]: An instance of a configuration object rj)rd)rEr:rYr0r3r3r4from_text_vision_configss z#CLIPConfig.from_text_vision_configs)NNrr[) rHrIrJrKr8r"rLrrQrkrPr3r3r1r4rZs-XrZcseZdZeeeeeeffdddZeeeeeeffdddZee dddZ dd eee d eee fd fd d Z eedddZZS)CLIPOnnxConfig)r7cCs0tddddfdddddd fd dddfgS) NZ input_idsbatchsequence)rrZ pixel_valuesrVheightwidth)rrr Zattention_maskrr/r3r3r4inputss   zCLIPOnnxConfig.inputscCs0tdddifdddifdddifdddifgS)NZlogits_per_imagerrmZlogits_per_textZ text_embedsZ image_embedsrrrr3r3r4outputss    zCLIPOnnxConfig.outputscCsdS)Ng-C6?r3rrr3r3r4atol_for_validationsz"CLIPOnnxConfig.atol_for_validationNr r ) processor batch_size seq_length frameworkr7cs2tj|j|||d}tj|j||d}||S)N)rxryrz)rxrz)r!generate_dummy_inputsZ tokenizerZimage_processor)r/rwrxryrzZtext_input_dictZimage_input_dictr1r3r4r{sz$CLIPOnnxConfig.generate_dummy_inputscCsdS)Nr3rrr3r3r4default_onnx_opsetsz!CLIPOnnxConfig.default_onnx_opset)rvrvN)rHrIrJpropertyrrMintrsrtfloatrurrr{r}rPr3r3r1r4rls$   rl)rKrN collectionsrtypingrrrrrZprocessing_utilsr utilsr Zconfiguration_utilsr Zonnxr rZ get_loggerrHrAZ"CLIP_PRETRAINED_CONFIG_ARCHIVE_MAPrrQrZrlr3r3r3r4s$       mi