qin(dZddlmZddlmZddlmZejeZ GddeZ Gdd eZ d dgZ y ) zMusicGen model configuration)PreTrainedConfig)logging) AutoConfigc`eZdZdZdZdZdgZ dfd ZxZS)MusicgenDecoderConfiga This is the configuration class to store the configuration of an [`MusicgenDecoder`]. It is used to instantiate a MusicGen decoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the MusicGen [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) 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 2048): Vocabulary size of the MusicgenDecoder model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`MusicgenDecoder`]. hidden_size (`int`, *optional*, defaults to 1024): Dimensionality of the layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 24): Number of decoder layers. num_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer block. ffn_dim (`int`, *optional*, defaults to 4096): Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer block. activation_function (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the decoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. dropout (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, text_encoder, and pooler. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. activation_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for activations inside the fully connected layer. max_position_embeddings (`int`, *optional*, defaults to 2048): 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). initializer_factor (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layerdrop (`float`, *optional*, defaults to 0.0): The LayerDrop probability for the decoder. See the [LayerDrop paper](see https://huggingface.co/papers/1909.11556) for more details. scale_embedding (`bool`, *optional*, defaults to `False`): Scale embeddings by diving by sqrt(hidden_size). use_cache (`bool`, *optional*, defaults to `True`): Whether the model should return the last key/values attentions (not used by all models) num_codebooks (`int`, *optional*, defaults to 4): The number of parallel codebooks forwarded to the model. tie_word_embeddings(`bool`, *optional*, defaults to `False`): Whether input and output word embeddings should be tied. audio_channels (`int`, *optional*, defaults to 1 Number of channels in the audio data. Either 1 for mono or 2 for stereo. Stereo models generate a separate audio stream for the left/right output channels. Mono models generate a single audio stream output. musicgen_decoderdecoder_configpast_key_valuesc ||_||_||_||_||_| |_||_||_||_| |_ | |_ | |_ ||_ | |_ ||_||_||_||_|dvrt%d|d||_||_||_||_||_t1|ddi|y)N)rz4Expected 1 (mono) or 2 (stereo) audio channels, got z channels.) is_decoderadd_cross_attentioncross_attention_hidden_size vocab_sizemax_position_embeddings hidden_sizeffn_dimnum_hidden_layersnum_attention_headsdropoutattention_dropoutactivation_dropoutactivation_functioninitializer_factor layerdrop use_cachescale_embedding num_codebooks ValueErroraudio_channelstie_word_embeddings pad_token_id bos_token_id eos_token_idsuper__init__)selfrrrrrrrrrrrrrrr r"r$r%r&r#rrrkwargs __class__s e/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/musicgen/configuration_musicgen.pyr(zMusicgenDecoderConfig.__init__Qs6%#6 +F($'>$& !2#6  !2"4#6 "4"".*  'STbSccmno o,#6 ((( "6")r.iTgeluig?r1r1g{Gz?Fr r.r.NFFFN) __name__ __module__ __qualname____doc__ model_typebase_config_keykeys_to_ignore_at_inferencer( __classcell__r+s@r,rrso2h$J&O#4"5 $"!!$(16#6#r-rcFeZdZdZdZeeedZdZfdZ e dZ xZ S)MusicgenConfiga This is the configuration class to store the configuration of a [`MusicgenModel`]. It is used to instantiate a MusicGen model according to the specified arguments, defining the text encoder, audio encoder and MusicGen decoder configs. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: text_encoder (`Union[dict, `PretrainedConfig`]`): An instance of a configuration object that defines the text encoder config. audio_encoder (`Union[dict, `PretrainedConfig`]`): An instance of a configuration object that defines the audio encoder config. decoder (`Union[dict, `PretrainedConfig`]`): An instance of a configuration object that defines the decoder config. Example: ```python >>> from transformers import ( ... MusicgenConfig, ... MusicgenDecoderConfig, ... T5Config, ... EncodecConfig, ... MusicgenForConditionalGeneration, ... ) >>> # Initializing text encoder, audio encoder, and decoder model configurations >>> text_encoder_config = T5Config() >>> audio_encoder_config = EncodecConfig() >>> decoder_config = MusicgenDecoderConfig() >>> configuration = MusicgenConfig( ... text_encoder=text_encoder_config, ... audio_encoder=audio_encoder_config, ... decoder=decoder_config, ... ) >>> # Initializing a MusicgenForConditionalGeneration (with random weights) from the facebook/musicgen-small style configuration >>> model = MusicgenForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> config_text_encoder = model.config.text_encoder >>> config_audio_encoder = model.config.audio_encoder >>> config_decoder = model.config.decoder >>> # Saving the model, including its configuration >>> model.save_pretrained("musicgen-model") >>> # loading model and config from pretrained folder >>> musicgen_config = MusicgenConfig.from_pretrained("musicgen-model") >>> model = MusicgenForConditionalGeneration.from_pretrained("musicgen-model", config=musicgen_config) ```musicgen) text_encoder audio_encoderdecoderTc t|tr'|jd}tj|fi|}t|tr'|jd}tj|fi|}t|tr t di|}||_||_||_|jj|_ |jdd|_ d|d<t|4di|y)Nr8tie_encoder_decoderFTis_encoder_decoderr) isinstancedictpopr for_modelrr@rArBrgetrDr'r()r)r@rArBr*text_encoder_model_typeaudio_encoder_model_typer+s r,r(zMusicgenConfig.__init__s lD )&2&6&6|&D #%//0GX<XL mT *'4'8'8'F $&001I[][M gt $+6g6G(* "&,,"A"A#)::.CU#K '+#$ "6"r-c.|jjS)N)rA sampling_rate)r)s r,rNzMusicgenConfig.sampling_rates!!///r-) r4r5r6r7r8rr sub_configshas_no_defaults_at_initr(propertyrNr;r<s@r,r>r>sA5 nJ"#(K ##*00r-r>N) r7configuration_utilsrutilsrauto.configuration_autor get_loggerr4loggerrr>__all__rr-r,rXsT#30   H %o#,o#dX0%X0v 4 5r-