sg'ZdZddlmZddlmZej eZGddeZy)zPop2Piano model configuration)PretrainedConfig)loggingcTeZdZdZdZdgZ dfd ZxZS)Pop2PianoConfiga This is the configuration class to store the configuration of a [`Pop2PianoForConditionalGeneration`]. It is used to instantiate a Pop2PianoForConditionalGeneration 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 Pop2Piano [sweetcocoa/pop2piano](https://huggingface.co/sweetcocoa/pop2piano) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Arguments: vocab_size (`int`, *optional*, defaults to 2400): Vocabulary size of the `Pop2PianoForConditionalGeneration` model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`Pop2PianoForConditionalGeneration`]. composer_vocab_size (`int`, *optional*, defaults to 21): Denotes the number of composers. d_model (`int`, *optional*, defaults to 512): Size of the encoder layers and the pooler layer. d_kv (`int`, *optional*, defaults to 64): Size of the key, query, value projections per attention head. The `inner_dim` of the projection layer will be defined as `num_heads * d_kv`. d_ff (`int`, *optional*, defaults to 2048): Size of the intermediate feed forward layer in each `Pop2PianoBlock`. num_layers (`int`, *optional*, defaults to 6): Number of hidden layers in the Transformer encoder. num_decoder_layers (`int`, *optional*): Number of hidden layers in the Transformer decoder. Will use the same value as `num_layers` if not set. num_heads (`int`, *optional*, defaults to 8): Number of attention heads for each attention layer in the Transformer encoder. relative_attention_num_buckets (`int`, *optional*, defaults to 32): The number of buckets to use for each attention layer. relative_attention_max_distance (`int`, *optional*, defaults to 128): The maximum distance of the longer sequences for the bucket separation. dropout_rate (`float`, *optional*, defaults to 0.1): The ratio for all dropout layers. layer_norm_epsilon (`float`, *optional*, defaults to 1e-6): The epsilon used by the layer normalization layers. 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). feed_forward_proj (`string`, *optional*, defaults to `"gated-gelu"`): Type of feed forward layer to be used. Should be one of `"relu"` or `"gated-gelu"`. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). dense_act_fn (`string`, *optional*, defaults to `"relu"`): Type of Activation Function to be used in `Pop2PianoDenseActDense` and in `Pop2PianoDenseGatedActDense`. pop2pianopast_key_valuesc ||_||_||_||_||_||_||n |j |_||_| |_| |_ | |_ | |_ | |_ ||_ ||_||_|jj!dddk(|_|j|_||_||_t+|Xd|||d|y)N-gated) pad_token_id eos_token_idis_encoder_decoder) vocab_sizecomposer_vocab_sized_modeld_kvd_ff num_layersnum_decoder_layers num_headsrelative_attention_num_bucketsrelative_attention_max_distance dropout_ratelayer_norm_epsiloninitializer_factorfeed_forward_proj use_cache dense_act_fnsplit is_gated_act hidden_sizenum_attention_headsnum_hidden_layerssuper__init__)selfrrrrrrrrrrrrrrrrr rr kwargs __class__s h/var/www/html/venv/lib/python3.12/site-packages/transformers/models/pop2piano/configuration_pop2piano.pyr'zPop2PianoConfig.__init__Ks.%#6    $8J8V"4\`\k\k".L+/N,("4"4!2"( 2288=a@GK<<#, !+  %%1   )i` i@iN g?gư>g?z gated-geluTTr relu)__name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inferencer' __classcell__)r*s@r+rrs^-^J#4"5  ')(+&)1 1 r,rN) r8configuration_utilsrutilsr get_loggerr5loggerrrr,r+r@s3$3   H %d &d r,