sg"OdZddlZddlmZmZer ddlmZddlmZeje Z GddeZ Gd d eZ Gd d eZy) zCLVP model configurationN) TYPE_CHECKINGUnion)PretrainedConfig)loggingceZdZdZdZddgZ d fd Ze d dee e jfde dd fd Z xZ S) ClvpEncoderConfigak This is the configuration class to store the configuration of a [`ClvpEncoder`]. It is used to instantiate a CLVP text or CLVP speech encoder according to the specified arguments. Instantiating a configuration with the defaults will yield a similar configuration to that of the encoder of the CLVP [susnato/clvp_dev](https://huggingface.co/susnato/clvp_dev) 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 256): Vocabulary size of the CLVP Encoder model. hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 1536): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. projection_dim (`int`, *optional*, defaults to 768): Dimensionality of the projection vector. num_hidden_layers (`int`, *optional*, defaults to 20): 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. 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"` `"quick_gelu"` are supported. layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. attention_dropout (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention probabilities. dropout (`float`, *optional*, defaults to 0.1): The dropout ratio for the feed-forward layers in [`ClvpEncoderMLP`]. use_rotary_embedding (`bool`, *optional*, defaults to `True`): Whether to use rotary_embedding or not. use_attention_bias (`bool`, *optional*, defaults to `False`): Whether to use bias in Query, Key and Value layers during self attention. summary_type (`str`, *optional*, defaults to `"mean"`): What strategy to use to get pooler_output from the last_hidden_state. `"last"`, `"first"`, `"mean"` and `"cls_index"` are supported. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1.0, used internally for initialization testing). bos_token_id (`int`, *optional*, defaults to 255): Beginning of sequence token id. eos_token_id (`int`, *optional*, defaults to 0): End of sequence token id. Example: ```python >>> from transformers import ClvpEncoderConfig, ClvpEncoder >>> # Initializing a ClvpEncoderConfig with susnato/clvp_dev style configuration >>> encoder_configuration = ClvpEncoderConfig() >>> # Initializing a ClvpEncoder (with random weights) from the susnato/clvp_dev style configuration >>> model = ClvpEncoder(encoder_configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` clvp_encoder text_config speech_configc ||_||_||_||_||_||_||_||_||_| |_ | |_ | |_ | |_ | |_ ||_||_t!|Dd||d|yN) bos_token_id eos_token_id) vocab_size hidden_sizeintermediate_sizeprojection_dimnum_hidden_layersnum_attention_headslayer_norm_eps hidden_actinitializer_factorattention_dropoutdropoutuse_rotary_embeddinguse_attention_bias summary_typerrsuper__init__)selfrrrrrrrrrrrrrrrrkwargs __class__s ^/var/www/html/venv/lib/python3.12/site-packages/transformers/models/clvp/configuration_clvp.pyr!zClvpEncoderConfig.__init__`s(%&!2,!2#6 ,$"4!2 $8!"4((( XlXQWXpretrained_model_name_or_path config_typereturnrc v|j||j|fi|\}}||jvrtd||j ddk(r||}d|vrGt |dr;|d|j k7r)tjd|dd|j d|j|fi|S)NzSWe can only load either 'text_config' or 'speech_config' but you are trying to load model_typeclvpzYou are using a model of type z to instantiate a model of type zN. This is not supported for all configurations of models and can yield errors.) _set_token_in_kwargsget_config_dictbase_config_key ValueErrorgethasattrr+loggerwarning from_dict)clsr'r(r# config_dicts r%from_pretrainedz!ClvpEncoderConfig.from_pretraineds   (1c112OZSYZ V c11 1ejuivw  ??< (F 2%k2K ; &73 +E+VbJcgjguguJu NN0\1J0KKk>>""pr  s}}[3F33r&)ir: geluh㈵>皙?r?TFmean?r)r )__name__ __module__ __qualname____doc__r+r/r! classmethodrstrosPathLiker8 __classcell__r$s@r%r r s; z J$o6O! #%YNXe4,1#r{{2B,C4RU4 44r&r cdeZdZdZdZdZdddddd d d d d d d ddddd dd ddddddgdffd ZxZS)ClvpDecoderConfigaN This is the configuration class to store the configuration of a [`ClvpDecoder`]. It is used to instantiate a CLVP Decoder 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 Decoder part of the CLVP [susnato/clvp_dev](https://huggingface.co/susnato/clvp_dev) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. The architecture is similar to GPT2. Args: vocab_size (`int`, *optional*, defaults to 8194): Vocabulary size of the model. max_position_embeddings (`int`, *optional*, defaults to 608): The maximum sequence length of mel tokens that this model might ever be used with. Similar to `n_positions` in `GPT2Config`. max_text_tokens (`int`, *optional*, defaults to 404): The maximum sequence length of text tokens that this model might ever be used with. Similar to `n_positions` in `GPT2Config`. hidden_size (`int`, *optional*, defaults to 1024): Dimensionality of the embeddings and hidden states. num_hidden_layers (`int`, *optional*, defaults to 30): 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. n_inner (`int`, *optional*): Dimensionality of the inner feed-forward layers. `None` will set it to 4 times `hidden_size`. num_mel_attn_blocks (`int`, *optional*, defaults to 6): Denotes the number of self attention layers in [`ClvpConditioningEncoder`]. activation_function (`str`, *optional*, defaults to `"gelu_new"`): Activation function, to be selected in the list `["relu", "silu", "gelu", "tanh", "gelu_new"]`. resid_pdrop (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. embd_pdrop (`float`, *optional*, defaults to 0.1): The dropout ratio for the embeddings. attention_dropout (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention. layer_norm_epsilon (`float`, *optional*, defaults to 1e-05): The epsilon to use in the layer normalization layers. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. summary_type (`string`, *optional*, defaults to `"cls_index"`): Argument used when doing sequence summary. Has to be one of the following options: - `"last"`: Take the last token hidden state (like XLNet). - `"first"`: Take the first token hidden state (like BERT). - `"mean"`: Take the mean of all tokens hidden states. - `"cls_index"`: Supply a Tensor of classification token position (like GPT/GPT-2). - `"attn"`: Not implemented now, use multi-head attention. summary_use_proj (`bool`, *optional*, defaults to `True`): Whether or not to add a projection after the vector extraction. summary_activation (`str`, *optional*): Pass `"tanh"` for a tanh activation to the output, any other value will result in no activation. summary_proj_to_labels (`bool`, *optional*, defaults to `True`): Whether the projection outputs should have `config.num_labels` or `config.hidden_size` classes. summary_first_dropout (`float`, *optional*, defaults to 0.1): The dropout ratio to be used after the projection and activation. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). bos_token_id (`int`, *optional*, defaults to 8192): Beginning of sequence token id, used at the start of the generation. eos_token_id (`int`, *optional*, defaults to 8193): End of sequence token id, used in the method [`ClvpModelForConditionalGeneration.fix_speech_decoder_output()`] to correct decoder outputs. feature_size (`int`, *optional*, defaults to 80): The feature dimension of the extracted mel features. This value is used in [`ClvpConditioningEncoder`]. use_attention_bias (`bool`, *optional*, defaults to `True`): Whether to use bias in Query, Key and Value layers during self attention. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1.0, used internally for initialization testing). decoder_fixing_codes (`list`, *optional*, defaults to `[83, 45, 45, 248]`): These values are used in the method `fix_speech_decoder_output` to fix decoder generated outputs. Example: ```python >>> from transformers import ClvpDecoderConfig, ClvpDecoder >>> # Initializing a ClvpDecoderConfig with susnato/clvp_dev style configuration >>> decoder_configuration = ClvpDecoderConfig() >>> # Initializing a ClvpDecoder (with random weights) from the susnato/clvp_dev style configuration >>> model = ClvpDecoder(decoder_configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` clvp_decoderdecoder_configi i`iiNgelu_newr?r>g{Gz? cls_indexTi i PrA)S-rXc ||_||_||_||_||_||_||_||_| |_| |_ | |_ | |_ | |_ ||_ ||_||_||_||_||_||_||_||_||_||_||_||_t5|ld||d|yr)rmax_position_embeddingsmax_text_tokensrrrn_innernum_mel_attn_blocksactivation_function resid_pdrop embd_pdroprlayer_norm_epsiloninitializer_rangersummary_use_projsummary_activationsummary_first_dropoutsummary_proj_to_labels use_cache feature_sizerrdecoder_fixing_codesrrr r!)r"rr[r\rrrr]r^r_r`rarrbrcrrdrergrfrhrrrirrrjr#r$s r%r!zClvpDecoderConfig.__init__s<%'>$.&!2#6  #6 #6 &$!2"4!2( 0"4%:"&<#"("4"4$8!(( XlXQWXr&)rCrDrErFr+r/r!rKrLs@r%rNrNsrZ x J&O #& #!.7:Y:Yr&rNc^eZdZdZdZeeedZ d fd Ze dededefdZ xZ S) ClvpConfigaQ [`ClvpConfig`] is the configuration class to store the configuration of a [`ClvpModelForConditionalGeneration`]. It is used to instantiate a CLVP model according to the specified arguments, defining the text model, speech model and decoder model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the CLVP [susnato/clvp_dev](https://huggingface.co/susnato/clvp_dev) architecture. 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 (`dict`, *optional*): Dictionary of configuration options used to initialize the CLVP text encoder. speech_config (`dict`, *optional*): Dictionary of configuration options used to initialize CLVP speech encoder. decoder_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`ClvpDecoderConfig`]. projection_dim (`int`, *optional*, defaults to 768): Dimensionality of text and speech projection layers. logit_scale_init_value (`float`, *optional*, defaults to 2.6592): The initial value of the *logit_scale* parameter. Default is used as per the original CLVP implementation. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1.0, used internally for initialization testing). kwargs (*optional*): Dictionary of keyword arguments. Example: ```python >>> from transformers import ClvpConfig, ClvpModelForConditionalGeneration >>> # Initializing a ClvpConfig with susnato/clvp_dev style configuration >>> configuration = ClvpConfig() >>> # Initializing a ClvpModelForConditionalGeneration (with random weights) from the susnato/clvp_dev style configuration >>> model = ClvpModelForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a CLVPConfig from a CLVPTextConfig, CLVPSpeechConfig and a CLVPAutoRegressiveConfig >>> from transformers import ClvpEncoderConfig, ClvpDecoderConfig >>> # Initializing a CLVP text, CLVP speech and CLVP decoder configuration >>> config_text = ClvpEncoderConfig() >>> config_speech = ClvpEncoderConfig() >>> decoder_config = ClvpDecoderConfig() >>> config = ClvpConfig.from_sub_model_configs(config_text, config_speech, decoder_config) ```r,r r rPc Dt|di||i}tjd|i}tjd|i}tjdt di||_t di||_tdi||_||_ ||_ ||_ y)NzR`text_config` is `None`. Initializing the `ClvpEncoderConfig` with default values.zT`speech_config` is `None`. initializing the `ClvpEncoderConfig` with default values.zU`decoder_config` is `None`. initializing the `ClvpDecoderConfig` with default values.r) r r!r3infor r r rNrPrlogit_scale_init_valuer) r"r r rPrrprr#r$s r%r!zClvpConfig.__init__{s "6"  K KKl m  M KKn o  !N KKo p,;{;.??/A.A,&<#"4r&r r rPc n|d|j|j|jd|S)a Instantiate a [`ClvpConfig`] (or a derived class) from CLVP text model configuration, CLVP speech model configuration and CLVP decoder model configuration. Args: text_config (`ClvpEncoderConfig`): Text model configuration of type [`ClvpEncoderConfig`]. speech_config (`ClvpEncoderConfig`): Speech model configuration of type [`ClvpEncoderConfig`]. decoder_config (`ClvpDecoderConfig`): Decoder model configuration of type [`ClvpDecoderConfig`]. Returns: [`ClvpConfig`]: An instance of a configuration object rmr)to_dict)r6r r rPr#s r%from_sub_model_configsz!ClvpConfig.from_sub_model_configssD0 #++-'//1)113    r&)NNNr:g/L F@rA) rCrDrErFr+r rN sub_configsr!rGrsrKrLs@r%rlrl@sj1 fJ(*+K%5@ & ) *   r&rl)rFrItypingrrconfiguration_utilsrutilsr get_loggerrCr3r rNrlrr&r%rysc '3   H %A4(A4HZY(ZYzx !x r&