o Zh)@sHddlmZddlmZmZGdddeZGdddeZddgZdS) )PretrainedConfig)CONFIG_MAPPING AutoConfigcsZeZdZdZdZdZddddddd d d d d d d ddgddgdddddffdd ZZS)InternVLVisionConfiga This is the configuration class to store the configuration of a [`InternVLVisionModel`]. It is used to instantiate an InternVLVisionModel 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 InternVL3-1B. e.g. [OpenGVLab/InternVL3-1B-hf](https://huggingface.co/OpenGVLab/InternVL3-1B-hf) Args: hidden_size (`int`, *optional*, defaults to 1024): Dimensionality of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 24): 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. attention_bias (`bool`, *optional*, defaults to `False`): Whether to add a bias to the queries, keys and values. use_qk_norm (`bool`, *optional*, defaults to `False`): Whether to apply normalization to the queries and keys before the attention operation. intermediate_size (`int`, *optional*, defaults to 4096): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. 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"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_dropout (`float`, *optional*, defaults to 0.0): Dropout probability for attention weights. projection_dropout (`float`, *optional*, defaults to 0.0): Dropout probability for the projection layer. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. norm_type (`str`, *optional*, defaults to `"layer_norm"`): The type of normalization to use in the encoder. Can be `"layer_norm"` or `"rms_norm"`. layer_norm_eps (`float`, *optional*, defaults to 1e-06): The epsilon used by the layer normalization layers. image_size (`int` or `list[int]`, *optional*, defaults to `[448, 448]`): The size (resolution) of each image. patch_size (`int` or `list[int]`, *optional*, defaults to `[14, 14]`): The size (resolution) of each patch. num_channels (`int`, *optional*, defaults to 3): The number of input channels. use_mask_token (`bool`, *optional*, defaults to `False`): Whether to use a mask token for masked image modeling. use_absolute_position_embeddings (`bool`, *optional*, defaults to `True`): Whether to use BERT-style absolute position embeddings. layer_scale_init_value (`float`, *optional*, defaults to 0.1): Scale to use in the self-attention layers. 0.1 for base, 1e-5 for large. Set 0 to disable layer scale. use_mean_pooling (`bool`, *optional*, defaults to `True`): Whether to mean pool the final hidden states of the patches instead of using the final hidden state of the CLS token, before applying the classification head. Example: ```python >>> from transformers import InternVLVisionConfig, InternVLVisionModel >>> # Initializing a InternVLVisionModel OpenGVLab/InternVL3-1B-hf style configuration >>> configuration = InternVLVisionConfig() >>> # Initializing a model (with random weights) from the OpenGVLab/InternVL3-1B-hf configuration >>> model = InternVLVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zinternvl_vision vision_configiFigelugg{Gz?Z layer_normgư>irTg?c stjdi|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_t|ttfr9|n||f}t|ttfrF|n||f}||_||_||_||_||_||_||_dS)N)super__init__ hidden_sizenum_hidden_layersnum_attention_headsattention_bias use_qk_normintermediate_size hidden_acthidden_dropout_probattention_dropoutprojection_dropoutinitializer_range norm_typelayer_norm_eps isinstancelisttuple image_size patch_size num_channelsuse_mask_token use_absolute_position_embeddingslayer_scale_init_valueuse_mean_pooling)selfrrrrrrrrrrrrrrr r!r"r#r$r%kwargs __class__r b/var/www/auris/lib/python3.10/site-packages/transformers/models/internvl/configuration_internvl.pyrZs. zInternVLVisionConfig.__init__)__name__ __module__ __qualname____doc__ model_typeZbase_config_keyr __classcell__r r r(r*rs2Arcs@eZdZdZdZeedZ       d fd d ZZ S)InternVLConfiga This is the configuration class to store the configuration of a [`InternVLForConditionalGeneration`]. It is used to instantiate a InternVL model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of InternVL3-1B. e.g. [OpenGVLab/InternVL3-1B-hf](https://huggingface.co/OpenGVLab/InternVL3-1B-hf) 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 (`Union[AutoConfig, dict]`, *optional*, defaults to `InternVisonConfig`): The config object or dictionary of the vision backbone. text_config (`Union[AutoConfig, dict]`, *optional*, defaults to `Qwen2Config`): The config object or dictionary of the text backbone. image_token_id (`int`, *optional*, defaults to 151667): The image token index to encode the image prompt. image_seq_length (`int`, *optional*, defaults to 256): Number of image tokens to use per image patch. downsample_ratio (`float`, *optional*, defaults to 0.5): Factor by which to downsample the image. projector_hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the projector. vision_feature_layer (`int`, *optional*, defaults to -1): The index of the layer to use as the image features. vision_feature_select_strategy (`str`, *optional*, defaults to `"default"`): The feature selection strategy used to select the vision feature from the vision backbone. Can be one of `"default"` or `"full"`. ```python >>> from transformers import InternVLForConditionalGeneration, InternVLConfig >>> # Initializing a InternVL style configuration >>> configuration = InternVLConfig() >>> # Initializing a model (with random weights) from the OpenGVLab/InternVL3-1B-hf configuration >>> model = InternVLForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zinternvl) text_configrNsP?r defaultc  s||_||_||_||_||_||_t|tr tdi||_ nt|tr)||_ n|dur1t|_ t|trNd|vr>|dnd|d<t |ddi|}n |durWt d}||_ t j di| dS)Nr/Zqwen2r )image_token_idimage_seq_lengthdownsample_ratioprojector_hidden_actvision_feature_layervision_feature_select_strategyrdictrrrr2r r) r&rr2r8r9r:r;r<r=r'r(r r*rs&     zInternVLConfig.__init__)NNr3r4r5r r6r7) r+r,r-r.r/rrZ sub_configsrr0r r r(r*r1s* r1N)Zconfiguration_utilsrautorrrr1__all__r r r r*s y S