gOdZddlZddlmZddlmZddlmZeje Z GddeZ Gd d eZ Gd d eZ dS) zCLAP model configurationN)Union)PretrainedConfig)loggingceZdZdZdZ dfd Zedeee j fddfdZ xZ S)ClapTextConfiga This is the configuration class to store the configuration of a [`ClapTextModel`]. It is used to instantiate a CLAP 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 CLAP [calp-hsat-fused](https://huggingface.co/laion/clap-hsat-fused) 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 30522): Vocabulary size of the CLAP model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`ClapTextModel`]. 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 `"relu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"relu"`, `"relu"`, `"silu"` and `"relu_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). type_vocab_size (`int`, *optional*, defaults to 2): The vocabulary size of the `token_type_ids` passed when calling [`ClapTextModel`]. 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). is_decoder (`bool`, *optional*, defaults to `False`): Whether the model is used as a decoder or not. If `False`, the model is used as an encoder. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True`. projection_hidden_act (`str`, *optional*, defaults to `"relu"`): The non-linear activation function (function or string) in the projection layer. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. projection_dim (`int`, *optional*, defaults to 512) Dimension of the projection head of the `ClapTextModelWithProjection`. Examples: ```python >>> from transformers import ClapTextConfig, ClapTextModel >>> # Initializing a CLAP text configuration >>> configuration = ClapTextConfig() >>> # Initializing a model (with random weights) from the configuration >>> model = ClapTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```clap_text_modelY gelu皙??-q=rabsoluteTreluc "tjd|||d|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ ||_||_||_| |_dS)N) pad_token_id bos_token_id eos_token_id)super__init__ vocab_size hidden_sizenum_hidden_layersnum_attention_heads hidden_actintermediate_sizehidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_factorlayer_norm_epsposition_embedding_type use_cacheprojection_hidden_actprojection_dim)selfrr r!r"r$r#r%r&r'r(r)r*r.rrrr+r,r-kwargs __class__s g/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/clap/configuration_clap.pyrzClapTextConfig.__init__bs. sl\hsslrsss$&!2#6 $!2#6 ,H)'>$."4,'>$"%:",pretrained_model_name_or_pathreturnrc N|||j|fi|\}}|ddkr|d}d|vrMt|dr=|d|jkr,t d|dd|jd|j|fi|S)N model_typeclap text_configYou are using a model of type to instantiate a model of type N. This is not supported for all configurations of models and can yield errors._set_token_in_kwargsget_config_dictgethasattrr7loggerwarning from_dictclsr4r0 config_dicts r2from_pretrainedzClapTextConfig.from_pretraineds   (((1c12OZZSYZZ V ??< ( (F 2 2%m4K ; & &73 +E+E &+VbJcgjguJuJu NNr\1Jrr>rrr    s}[33F333r3)r r r r r rrrrrrrrrrrrTr __name__ __module__ __qualname____doc__r7r classmethodrstrosPathLikerH __classcell__r1s@r2rrsB B H#J%( # *$)(-(-(-(-(-(-T4E#r{BR