o Zh:@szddlmZddlmZddlmZddlmZmZe e Z GdddeZ Gd d d eZ Gd d d eZgd ZdS))List)PretrainedConfig)logging)CONFIG_MAPPING AutoConfigcsNeZdZdZdZdZ           dfdd ZZS)JanusVisionConfiga This is the configuration class to store the configuration of a [`JanusVisionModel`]. It is used to instantiate a `JanusVisionModel` according to the specified arguments, defining the model 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 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. num_channels (`int`, *optional*, defaults to 3): The number of input channels. patch_size (`int`, *optional*, defaults to 16): The size (resolution) of each patch. image_size (`int`, *optional*, defaults to 384): The size (resolution) of each image. attention_dropout (`float`, *optional*, defaults to 0.0): Dropout probability for attention weights. layer_norm_eps (`float`, *optional*, defaults to 1e-06): The epsilon used by the layer normalization layers. 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. mlp_ratio (`float`, *optional*, defaults to 4.0): Ratio of MLP hidden dimensionality to embedding dimensionality. attention_bias (`bool`, *optional*, defaults to `True`): Whether to add a bias to the queries, keys, and values in the attention layers. hidden_dropout_rate (`float`, *optional*, defaults to 0.0): The dropout probability for fully connected layers in the encoder. projection_dim (`int`, *optional*, defaults to 2048): Dimensionality of the MLP projection head. projection_dropout (`float`, *optional*, defaults to 0.0): Dropout probability for the projection layer. use_qk_norm (`bool`, *optional*, defaults to `False`): Whether to normalize the query and key matrices. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated normal initializer for initializing all weight matrices. depth (`int`, *optional*, defaults to 2): Number of hidden layers in the aligner module. num_image_tokens (`int`, *optional*, defaults to 576): Number of image tokens. Zjanus_vision_model vision_configrư>gelu@TF{Gz?r@c stjdi|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_||_||_||_dSN)super__init__ hidden_sizenum_hidden_layersnum_attention_heads num_channels patch_size image_sizeattention_dropoutlayer_norm_eps hidden_act mlp_ratioattention_biashidden_dropout_rateprojection_dimprojection_dropout use_qk_norminitializer_rangedepthnum_image_tokens)selfrrrrrrr r!r"r#r$r%r&r'r(r)r*r+kwargs __class__r\/var/www/auris/lib/python3.10/site-packages/transformers/models/janus/configuration_janus.pyrRs& zJanusVisionConfig.__init__)r r r rr rrrrrTrrrFrrr)__name__ __module__ __qualname____doc__ model_typebase_config_keyr __classcell__rrr.r0r s..r cseZdZdZdZdZdddddd d d gd d d ddd ddfdededededededededeedede ffdd Z Z S)JanusVQVAEConfiga: This is the configuration class to store the configuration of a [`JanusVQVAEModel`]. It is used to instantiate a `JanusVQVAEModel` according to the specified arguments, defining the model architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Instantiating a configuration with the defaults will yield a similar configuration to the VQModel of the [deepseek-community/Janus-Pro-1B](https://huggingface.co/deepseek-community/Janus-Pro-1B). Args: embed_dim (`int`, *optional*, defaults to 8): Dimensionality of each embedding vector. num_embeddings (`int`, *optional*, defaults to 16384): Number of codebook embeddings. double_latent (`bool`, *optional*, defaults to `False`): Whether to use double z channels. latent_channels (`int`, *optional*, defaults to 256): Number of channels for the latent space. num_patches (`int`, *optional*, defaults to 32): Num of patches the input images can be divided into. in_channels (`int`, *optional*, defaults to 3): Number of input channels. out_channels (`int`, *optional*, defaults to 3): Number of out channels. base_channels (`int`, *optional*, defaults to 128): Base channel count. channel_multiplier (`List[int]`, *optional*, defaults to `[1, 1, 2, 2, 4]`): Channel multipliers for each resolution. num_res_blocks (`int`, *optional*, defaults to 2): Number of residual blocks. dropout (`float`, *optional*, defaults to 0.0): Dropout rate. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. projection_dim (`int`, *optional*, defaults to 2048): Dimensionality of the MLP projection head. num_hidden_layers (`int`, *optional*, defaults to 2): Number of hidden layers in VAVAE MLP Connecter module. 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. image_token_embed_dim (`int`, *optional*, defaults to 2048): Dimension of image embeddings. It should be same as the dimensionality of text embeddings. Z janus_vqgan vq_configi@F r)r>rrrrrrr embed_dimnum_embeddings double_latentlatent_channels num_patches in_channels out_channels base_channelschannel_multipliernum_res_blocksdropoutc svtjdi|||_||_||_||_||_||_| |_| |_ | |_ | |_ ||_ ||_ | |_||_||_||_dSr)rrr@rArBrCrErGrHrIrJr)rDrFr&rr"image_token_embed_dim)r,r@rArBrCrDrErFrGrHrIrJr)r&rr"rKr-r.rr0rs" zJanusVQVAEConfig.__init__) r1r2r3r4r5r6intboolrfloatrr7rrr.r0r8sV,    r8cs:eZdZdZdZeeedZ    dfdd Z Z S) JanusConfiga; This is the configuration class to store the configuration of a [`JanusModel`]. It is used to instantiate an Janus 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 Janus-1B or Janus-7B models. e.g. [deepseek-community/Janus-Pro-1B](https://huggingface.co/deepseek-community/Janus-Pro-1B) or [deepseek-community/Janus-Pro-7B](https://huggingface.co/deepseek-community/Janus-Pro-7B) 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 (`Union[AutoConfig, dict]`, *optional*, defaults to `LlamaConfig`): The config object or dictionary of the text backbone. vision_config (`Union[AutoConfig, dict]`, *optional*, defaults to `JanusVisionConfig`): The config object or dictionary of the vision backbone. vq_config (`Union[AutoConfig, dict]`, *optional*, defaults to `JanusVQVAEConfig`): The config object or dictionary of the VQVAE backbone. image_token_id (`int`, *optional*, defaults to 100581): Token index of a placeholder image token. Example: ```python >>> from transformers import JanusForConditionalGeneration, JanusConfig, JanusVisionConfig, JanusVQVAEConfig, LlamaConfig >>> # Initializing a Janus vision config >>> vision_config = JanusVisionConfig() >>> # Initializing a Llama config >>> text_config = LlamaConfig() >>> # Initializing a VQ config >>> vq_config = JanusVQVAEConfig() >>> # Initializing a Janus Pro 1B style configuration >>> configuration = JanusConfig(vision_config=vision_config, text_config=text_config, vq_config=vq_config) >>> # Initializing a model from the Janus Pro 1B style configuration >>> model = JanusForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zjanus) text_configr r9Nc s`t|tr|dd|d<t|dd i||_n"|dur*tdtd|_nt|tr3||_n tdt ||durJtdt |_ n t|trXt d i||_ nt|t ra||_ n tdt ||durxtdt |_ n t|trt d i||_ nt|t r||_ n tdt ||j j|j j|j _||_tjd i|dS) Nr5llamaz7`text_config` is None. Initializing with default valueszTInvalid type for `text_config`. Must be either `dict` or `LlamaConfig`. Type found: zK`vision_config` is None. Initializing with default JanusVisionConfig valuesz\Invalid type for `vision_config`. Must be either `dict` or `JanusVisionConfig`. Type found: zF`vq_config` is None. Initializing with default JanusVQVAEConfig valueszWInvalid type for `vq_config`. Must be either `dict` or `JanusVQVAEConfig`. Type found: r) isinstancedictgetrrPloggerinfor ValueErrortyper r r8r9rrrDimage_token_idrr)r,rPr r9rZr-r.rr0r sP           zJanusConfig.__init__)NNNrQ) r1r2r3r4r5rr r8Z sub_configsrr7rrr.r0rOs-rO)r8r rON)typingrZconfiguration_utilsrutilsrautorrZ get_loggerr1rVr r8rO__all__rrrr0s    _W m