`i$ddlmZddlmZddlmZmZejeZ GddeZ GddeZ ddgZ d S) )PretrainedConfig)logging)CONFIG_MAPPING AutoConfigcBeZdZdZdZdZ dfd ZxZS)SmolVLMVisionConfiga This is the configuration class to store the configuration of a [`SmolVLMVisionModel`]. It is used to instantiate a SmolVLM 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 SigLIP checkpoint [google/siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) used in SmolVLM [HuggingFaceTB/SmolVLM2-2.2B-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct). 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 1152): 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 16): Number of attention heads for each attention layer in the Transformer encoder. num_channels (`int`, *optional*, defaults to 3): Number of channels in the input images. 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 `"gelu_pytorch_tanh"`): 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-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 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. Example: ```python >>> from transformers.models.smolvlm.modeling_smolvlm import SmolVLMVisionTransformer >>> from transformers.models.smolvlm.configuration_smolvlm import SmolVLMVisionConfig >>> # Initializing a SmolVLMVisionConfig with google/siglip-so400m-patch14-384 style configuration >>> configuration = SmolVLMVisionConfig() >>> # Initializing a SmolVLMVisionTransformer (with random weights) from the google/siglip-so400m-patch14-384 style configuration >>> model = SmolVLMVisionTransformer(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```smolvlm_vision vision_config r gelu_pytorch_tanhư>{Gz?c  tjdi| ||_||_||_||_||_||_||_| |_ | |_ ||_ | |_ dS)N) super__init__ hidden_sizeintermediate_sizenum_hidden_layersnum_attention_heads num_channels patch_size image_sizeattention_dropoutlayer_norm_eps hidden_actinitializer_range)selfrrrrrr rr#r"r!r$kwargs __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/smolvlm/configuration_smolvlm.pyrzSmolVLMVisionConfig.__init__Us} ""6"""&!2!2#6 ($$!2,$!2) r r rrrrrrrrr)__name__ __module__ __qualname____doc__ model_typebase_config_keyr __classcell__r's@r(r r sw1 1 f"J%O&3333333333r)r c@eZdZdZdZeedZ d fd ZxZ S) SmolVLMConfiga This is the configuration class to store the configuration of a [`SmolVLMModel`]. It is used to instantiate a SmolVLM 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 model of the SmolVLM [HuggingFaceTB/SmolVLM2-2.2B-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should cache the key/value pairs of the attention mechanism. Only relevant if `config.is_decoder=True`. image_token_id (`int`, *optional*, defaults to 128257): The id of the "image" token. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether or not to tie the word embeddings with the token embeddings. vision_config (`IdeficsVisionConfig` or `dict`, *optional*, defaults to `IdeficsVisionConfig`): Custom vision config or dict for the vision tower text_config (`PretrainedConfig` or `dict`, *optional*, defaults to `LlamaConfig`): Custom text config or dict for the text model scale_factor (`int`, *optional*, defaults to 2): The scale factor for the image encoder. pad_token_id (`int`, *optional*, defaults to 128002): The id of the padding token. Example: ```python >>> from transformers import SmolVLMModel, SmolVLMConfig >>> # Initializing configuration >>> configuration = SmolVLMConfig() >>> # Initializing a model from the configuration >>> model = SmolVLMModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```smolvlm) text_configr TFNrc f||_||_||_|.t|_t dnCt|trtd i||_nt|tr||_t|tr2| dd|d<t|dd i|}n4|2t dtdd|d}||_ ||_ tjd i|||ddS) Nz2vision_config is None, using default vision configr.llamaz.text_config is None, using default text configgh㈵>F) rms_norm_eps pad_token_idtie_word_embeddings)r;r<r)image_token_id use_cacher<r r loggerinfo isinstancedictgetrr5 scale_factorrr) r%r>r=r<r r5rDr;r&r's r(rzSmolVLMConfig.__init__sS-"#6  !4!6!6D  KKL M M M M  t , , /!4!E!E}!E!ED    ': ; ; /!.D  k4 ( ( (3 g(N(NK %(\)BCRRkRRKK  KKH I I I(1!)$)K '(ff6f Refffffffr))Tr6FNNrr7) r*r+r,r-r.rr sub_configsrr0r1s@r(r3r3ss~# # JJ",?RSSK!%g%g%g%g%g%g%g%g%g%gr)r3N) configuration_utilsrutilsrautorr get_loggerr*r?r r3__all__rr)r(rKs,433333--------  H % %R3R3R3R3R3*R3R3R3jNgNgNgNgNg$NgNgNgb !/ 2r)