U 9%e@sBdZddlmZddlmZeeZddiZGdddeZ dS) z Pop2Piano model configuration)PretrainedConfig)loggingzsweetcocoa/pop2pianozAhttps://huggingface.co/sweetcocoa/pop2piano/blob/main/config.jsoncs,eZdZdZdZdgZdfdd ZZS)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`. Z pop2pianoZpast_key_values` @N 皙?ư>? gated-geluTreluc s||_||_||_||_||_||_|dk r0|n|j|_||_| |_| |_ | |_ | |_ | |_ ||_ ||_||_|j dddk|_|j|_||_||_tjf|||d|dS)N-rZgated) 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_fnsplitZ is_gated_actZ hidden_sizeZnum_attention_headsZnum_hidden_layerssuper__init__)selfrrrrrrrr r!r"r#r$r%r&rr'rrr(kwargs __class__t/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/transformers/models/pop2piano/configuration_pop2piano.pyr+Ps6zPop2PianoConfig.__init__)rrrrr r Nr r r rrrrTTrrr)__name__ __module__ __qualname____doc__Z model_typeZkeys_to_ignore_at_inferencer+ __classcell__r0r0r.r1rs./rN) r5Zconfiguration_utilsrutilsrZ get_loggerr2loggerZ'POP2PIANO_PRETRAINED_CONFIG_ARCHIVE_MAPrr0r0r0r1s