sgD*|dZddlmZddlmZddlmZejeZ GddeZ Gdd eZ y ) zMusicGen model configuration)PretrainedConfig)logging) AutoConfigcZeZdZdZdZdZdgZ 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://arxiv.org/abs/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 4||_||_| |_||_||_||_| |_| |_| |_||_ | |_ ||_ ||_ ||_ ||_|dvrtd|d||_t#|Hd||||d|y)N)rz4Expected 1 (mono) or 2 (stereo) audio channels, got z channels.) pad_token_id bos_token_id eos_token_idtie_word_embeddings) vocab_sizemax_position_embeddings hidden_sizeffn_dimnum_hidden_layersnum_attention_headsdropoutattention_dropoutactivation_dropoutactivation_functioninitializer_factor layerdrop use_cachescale_embedding num_codebooks ValueErroraudio_channelssuper__init__)selfrrrrrrrrrrrrrr r!r#rrrrkwargs __class__s f/var/www/html/venv/lib/python3.12/site-packages/transformers/models/musicgen/configuration_musicgen.pyr%zMusicgenDecoderConfig.__init__Rs0%'>$& !2#6  !2"4#6 "4"".*  'STbSccmno o,  %%% 3    )r+iTgeluig?r.r.g{Gz?Fr r+r+NF) __name__ __module__ __qualname____doc__ model_typebase_config_keykeys_to_ignore_at_inferencer% __classcell__r(s@r)rrsf2h$J&O#4"5 $"!+2 2 r*rcdeZdZdZdZeeedZdZfdZ e de de defd Z e d ZxZS) MusicgenConfigaj 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: kwargs (*optional*): Dictionary of keyword arguments. Notably: - **text_encoder** ([`PretrainedConfig`], *optional*) -- An instance of a configuration object that defines the text encoder config. - **audio_encoder** ([`PretrainedConfig`], *optional*) -- An instance of a configuration object that defines the audio encoder config. - **decoder** ([`PretrainedConfig`], *optional*) -- 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.from_sub_models_config( ... text_encoder_config, audio_encoder_config, 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|di|d|vsd|vsd|vr td|jd}|jd}|jd}|jd}|jd}t j |fi||_t j |fi||_tdi||_ d|_ y)Nr>r?r@zPConfig has to be initialized with text_encoder, audio_encoder and decoder configr5Tr) r$r%r"popr for_modelr>r?rr@is_encoder_decoder)r&r'text_encoder_configtext_encoder_model_typeaudio_encoder_configaudio_encoder_model_typer r(s r)r%zMusicgenConfig.__init__s "6"  '?&+HI]cLcop p$jj8"5"9"9,"G%zz/:#7#;#;L#I I.&001H`L_`'112JcNbc,>~> "&r*rErGr c n|d|j|j|jd|S)z Instantiate a [`MusicgenConfig`] (or a derived class) from text encoder, audio encoder and decoder configurations. Returns: [`MusicgenConfig`]: An instance of a configuration object r=r)to_dict)clsrErGr r's r)from_sub_models_configz%MusicgenConfig.from_sub_models_configsD  ,446.668"**,    r*c.|jjS)N)r? sampling_rate)r&s r)rNzMusicgenConfig.sampling_rates!!///r*)r1r2r3r4r5rr sub_configsis_compositionr% classmethodrrLpropertyrNr8r9s@r)r;r;sp6 pJ"#(K N'$ - / .   ,00r*r;N) r4configuration_utilsrutilsrauto.configuration_autor get_loggerr1loggerrr;rr*r)rXsF#30   H %k ,k \m0%m0r*