o hWC@sdZddlZddlmZddlmZddlmZddlm Z dd l m Z e e Zd d iZGd d d eZGdddeZGdddeZdS)z! InstructBLIP model configurationN)Union)PretrainedConfig)!MODEL_FOR_CAUSAL_LM_MAPPING_NAMES)logging)CONFIG_MAPPINGz Salesforce/instruct-blip-flan-t5zPhttps://huggingface.co/Salesforce/instruct-blip-flan-t5/resolve/main/config.jsoncs\eZdZdZdZ       dfdd Zedeee j fddfddZ Z S)InstructBlipVisionConfigaX This is the configuration class to store the configuration of a [`InstructBlipVisionModel`]. It is used to instantiate a InstructBLIP vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration defaults will yield a similar configuration to that of the InstructBLIP [Salesforce/instruct-blip-flan-t5](https://huggingface.co/Salesforce/instruct-blip-flan-t5) 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 1408): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 6144): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. num_hidden_layers (`int`, *optional*, defaults to 39): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 16): 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 14): The size (resolution) of each patch. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` ``"gelu"` are supported. to 1e-5): The epsilon used by the layer normalization layers. layer_norm_eps (`float`, *optional*, defaults to 1e-06): 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 1e-10): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. qkv_bias (`bool`, *optional*, defaults to `True`): Whether to add a bias to the queries and values in the self-attention layers. Example: ```python >>> from transformers import InstructBlipVisionConfig, InstructBlipVisionModel >>> # Initializing a InstructBlipVisionConfig with Salesforce/instruct-blip-flan-t5 style configuration >>> configuration = InstructBlipVisionConfig() >>> # Initializing a InstructBlipVisionModel (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration >>> model = InstructBlipVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```instructblip_vision_model'geluư>绽|=Tc  sXtjdi| ||_||_||_||_||_||_| |_| |_ ||_ ||_ | |_ dS)N) super__init__ hidden_sizeintermediate_sizenum_hidden_layersnum_attention_heads patch_size image_sizeinitializer_rangeattention_dropoutlayer_norm_eps hidden_actqkv_bias) selfrrrrrrr!r rrr"kwargs __class__rq/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/instructblip/configuration_instructblip.pyrVs z!InstructBlipVisionConfig.__init__pretrained_model_name_or_pathreturnrcK|||j|fi|\}}|ddkr|d}d|vr:t|dr:|d|jkr:td|dd|jd|j|fi|S)N model_type instructblip vision_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._set_token_in_kwargsget_config_dictgethasattrr+loggerwarning from_dictclsr(r$ config_dictrrr'from_pretraineds   z(InstructBlipVisionConfig.from_pretrained) r r r rrrrrrrT __name__ __module__ __qualname____doc__r+r classmethodrstrosPathLiker< __classcell__rrr%r'r !s"2&r csdeZdZdZdZ          dfdd Zedeee j fddfddZ Z S)InstructBlipQFormerConfigaO This is the configuration class to store the configuration of a [`InstructBlipQFormerModel`]. It is used to instantiate a InstructBLIP Querying Transformer (Q-Former) model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the InstructBLIP [Salesforce/instruct-blip-flan-t5](https://huggingface.co/Salesforce/instruct-blip-flan-t5) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Note that [`InstructBlipQFormerModel`] is very similar to [`BertLMHeadModel`] with interleaved cross-attention. Args: vocab_size (`int`, *optional*, defaults to 30522): Vocabulary size of the Q-Former model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling the model. hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. 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. intermediate_size (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder. hidden_act (`str` or `Callable`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention probabilities. max_position_embeddings (`int`, *optional*, defaults to 512): 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). initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. position_embedding_type (`str`, *optional*, defaults to `"absolute"`): Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155). For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658). cross_attention_frequency (`int`, *optional*, defaults to 2): The frequency of adding cross-attention to the Transformer layers. encoder_hidden_size (`int`, *optional*, defaults to 1408): The hidden size of the hidden states for cross-attention. Examples: ```python >>> from transformers import InstructBlipQFormerConfig, InstructBlipQFormerModel >>> # Initializing a InstructBLIP Salesforce/instruct-blip-flan-t5 style configuration >>> configuration = InstructBlipQFormerConfig() >>> # Initializing a model (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration >>> model = InstructBlipQFormerModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```instructblip_qformer:w r皙?{Gz?-q=rabsoluterr c sntjdd| i|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ ||_||_dS)N pad_token_idr)rr vocab_sizerrrr!rhidden_dropout_probattention_probs_dropout_probmax_position_embeddingsrr position_embedding_typecross_attention_frequencyencoder_hidden_size)r#rTrrrrr!rUrVrWrr rSrXrYrZr$r%rr'rs z"InstructBlipQFormerConfig.__init__r(r)rcKr*)Nr+r,qformer_configr.r/r0r1r9rrr'r<r=z)InstructBlipQFormerConfig.from_pretrained)rJrKrLrLrMrrNrNrOrPrQrrRrr r>rrr%r'rHs*=$&rHcs@eZdZdZdZd fdd Zededed e fd d Z Z S) InstructBlipConfiga [`InstructBlipConfig`] is the configuration class to store the configuration of a [`InstructBlipForConditionalGeneration`]. It is used to instantiate a InstructBLIP model according to the specified arguments, defining the vision model, Q-Former model and language model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the InstructBLIP [Salesforce/instruct-blip-flan-t5](https://huggingface.co/Salesforce/instruct-blip-flan-t5) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`InstructBlipVisionConfig`]. qformer_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`InstructBlipQFormerConfig`]. text_config (`dict`, *optional*): Dictionary of configuration options used to initialize any [`PretrainedConfig`]. num_query_tokens (`int`, *optional*, defaults to 32): The number of query tokens passed through the Transformer. kwargs (*optional*): Dictionary of keyword arguments. Example: ```python >>> from transformers import ( ... InstructBlipVisionConfig, ... InstructBlipQFormerConfig, ... OPTConfig, ... InstructBlipConfig, ... InstructBlipForConditionalGeneration, ... ) >>> # Initializing a InstructBlipConfig with Salesforce/instruct-blip-flan-t5 style configuration >>> configuration = InstructBlipConfig() >>> # Initializing a InstructBlipForConditionalGeneration (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration >>> model = InstructBlipForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a InstructBlipConfig from a InstructBlipVisionConfig, InstructBlipQFormerConfig and any PretrainedConfig >>> # Initializing InstructBLIP vision, InstructBLIP Q-Former and language model configurations >>> vision_config = InstructBlipVisionConfig() >>> qformer_config = InstructBlipQFormerConfig() >>> text_config = OPTConfig() >>> config = InstructBlipConfig.from_text_vision_configs(vision_config, qformer_config, text_config) ```r,N c stjdi||duri}td|duri}td|dur*i}tdtdi||_tdi||_d|vrB|dnd}t|di||_ |j j |_ |j j |_ ||_ |jj |j_|j jtv|_d|_d|_dS) NzUvision_config is None. initializing the InstructBlipVisionConfig with default values.zWqformer_config is None. Initializing the InstructBlipQFormerConfig with default values.zTtext_config is None. Initializing the text config with default values (`OPTConfig`).r+optg?rPr)rrr6infor r-rHr[r text_configtie_word_embeddingsis_encoder_decodernum_query_tokensrrZr+ruse_decoder_only_language_modelinitializer_factorr)r#r-r[r`rcr$text_model_typer%rr'r5s*       zInstructBlipConfig.__init__r-r[r`cKs"|d|||d|S)z Instantiate a [`InstructBlipConfig`] (or a derived class) from a InstructBLIP vision model, Q-Former and language model configurations. Returns: [`InstructBlipConfig`]: An instance of a configuration object )r-r[r`Nr)to_dict)r:r-r[r`r$rrr' from_vision_qformer_text_configsRsz3InstructBlipConfig.from_vision_qformer_text_configs)NNNr]) r?r@rArBr+rrCr rHrrhrGrrr%r'r\s5r\)rBrEtypingrconfiguration_utilsrmodels.auto.modeling_autorutilsrautor get_loggerr?r6*INSTRUCTBLIP_PRETRAINED_CONFIG_ARCHIVE_MAPr rHr\rrrr's      ew