qi>dZddlmZddlmZddlmZejeZ GddeZ GddeZ Gd d eZ gd Z y ) zDia model configuration)PreTrainedConfig)RopeParameters)loggingcxeZdZdZdZ ddededededed ed ed ed ed ededzdeffd Z xZ S)DiaEncoderConfiga This is the configuration class to store the configuration of a [`DiaEncoder`]. It is used to instantiate a Dia encoder according to the specified arguments, defining the encoder architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: max_position_embeddings (`int`, *optional*, defaults to 1024): The maximum sequence length that this model might ever be used with. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. hidden_size (`int`, *optional*, defaults to 1024): Dimensionality of the encoder layers and the pooler layer. num_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer encoder. num_key_value_heads (`int`, *optional*, defaults to 16): Number of key and value heads for each attention layer in the Transformer encoder. head_dim (`int`, *optional*, defaults to 128): Dimensionality of the attention head. intermediate_size (`int`, *optional*, defaults to 4096): Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder. norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the normalization layers. vocab_size (`int`, *optional*, defaults to 256): Vocabulary size of the Dia model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`DiaModel`]. hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"swish"` and `"gelu_new"` are supported. rope_parameters (`RopeParameters`, *optional*): Dictionary containing the configuration parameters for the RoPE embeddings. The dictionary should contain a value for `rope_theta` and optionally parameters used for scaling in case you want to use RoPE with longer `max_position_embeddings`. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. dia_encoderNmax_position_embeddingsnum_hidden_layers hidden_sizenum_attention_headsnum_key_value_headshead_dimintermediate_sizenorm_eps vocab_size hidden_actrope_parametersinitializer_rangec  ||_||_||_||_||_||_||_| |_||_| |_ | |_ | |_ t|4di| y)N)r r r rr rrrr rrrsuper__init__)selfr r r r r rrrrrrrkwargs __class__s [/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/dia/configuration_dia.pyrzDiaEncoderConfig.__init__Asq (?$!2&!2#6     $#6 $!2. "6")  rr ih㈵>siluN{Gz?) __name__ __module__ __qualname____doc__ model_typeintfloatstrrr __classcell__rs@rrrs$LJ(,!##%#%!% 15#'#!$## # ! # ! ######($.#!##rrc-eZdZdZdZ ddededededed ed ed ed ed edededededededzdede de dededef,fd Z xZ S)DiaDecoderConfiga This is the configuration class to store the configuration of a [`DiaDecoder`]. It is used to instantiate a Dia decoder according to the specified arguments, defining the decoder architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: max_position_embeddings (`int`, *optional*, defaults to 3072): The maximum sequence length that this model might ever be used with. num_hidden_layers (`int`, *optional*, defaults to 18): Number of hidden layers in the Transformer decoder. hidden_size (`int`, *optional*, defaults to 2048): Dimensionality of the decoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 8192): Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer decoder. num_key_value_heads (`int`, *optional*, defaults to 4): Number of key and value heads for each attention layer in the Transformer decoder. head_dim (`int`, *optional*, defaults to 128): Dimensionality of the attention head. cross_num_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each cross-attention layer in the Transformer decoder. cross_head_dim (`int`, *optional*, defaults to 128): Dimensionality of the cross-attention head. cross_num_key_value_heads (`int`, *optional*, defaults to 16): Number of key and value heads for each cross-attention layer in the Transformer decoder. cross_hidden_size (`int`, *optional*, defaults to 1024): Dimensionality of the cross-attention layers. norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the normalization layers. vocab_size (`int`, *optional*, defaults to 1028): Vocabulary size of the Dia model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`DiaModel`]. hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): The non-linear activation function (function or string) in the decoder. If string, `"gelu"`, `"relu"`, `"swish"` and `"gelu_new"` are supported. num_channels (`int`, *optional*, defaults to 9): Number of channels for the Dia decoder. rope_parameters (`RopeParameters`, *optional*): Dictionary containing the configuration parameters for the RoPE embeddings. The dictionary should contain a value for `rope_theta` and optionally parameters used for scaling in case you want to use RoPE with longer `max_position_embeddings`. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). is_encoder_decoder (`bool`, *optional*, defaults to `True`): Indicating that this model is part of an encoder-decoder architecture. pad_token_id (`int`, *optional*, defaults to 1025): The token id used for padding sequences to the same length within a batch. eos_token_id (`int`, *optional*, defaults to 1024): The token id representing the end-of-sequence token, indicating that generation should stop. bos_token_id (`int`, *optional*, defaults to 1026): The token id representing the beginning-of-sequence token, used to initialize decoding. dia_decoderNr r r rr r rcross_num_attention_headscross_head_dimcross_num_key_value_headscross_hidden_sizerrr num_channelsrr use_cacheis_encoder_decoder pad_token_id eos_token_id bos_token_idc N||_||_||_||_||_||_||_| |_||_| |_ | |_ | |_ | |_ ||_ ||_||_||_||_||_||_||_t+|Xdd|i|y)Nr9r)r r r rr r rr5r3r4r6rrrr7rr8rr:r;r<rr)rr r r rr r rr3r4r5r6rrrr7rrr8r9r:r;r<rrs rrzDiaDecoderConfig.__init__s4(?$!2&!2#6 #6   )B&)B&,!2  $$(!2".((( I,>I&Ir)i ii r r!r r!r rr"ir$ Nr%TTiri) r&r'r(r)r*r+r,r-rboolrr.r/s@rr1r1asU8tJ(,!#!%#%#$)+!)+!% 15#'#'   /0J!$0J0J 0J  0J ! 0J!0J0J$'0J0J$'0J0J0J0J0J !0J"($.#0J$!%0J&'0J(!)0J*+0J,-0J./0J0Jrr1ceZdZdZdZdgZeedZ ddedzdedzde d e d e dzd e dzd e dzd e e dzde de ffd Z dZxZS) DiaConfigav This is the configuration class to store the configuration of a [`DiaModel`]. It is used to instantiate a Dia 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 [nari-labs/Dia-1.6B](https://huggingface.co/nari-labs/Dia-1.6B) architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: encoder_config (`DiaEncoderConfig`, *optional*): Configuration for the encoder part of the model. If not provided, a default `DiaEncoderConfig` will be used. decoder_config (`DiaDecoderConfig`, *optional*): Configuration for the decoder part of the model. If not provided, a default `DiaDecoderConfig` will be used. norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the normalization layers. is_encoder_decoder (`bool`, *optional*, defaults to `True`): Indicating that this model uses an encoder-decoder architecture. pad_token_id (`int`, *optional*): Deprecated. Please set this on `DiaDecoderConfig` directly. If provided, it will be forwarded to `decoder_config`. eos_token_id (`int`, *optional*): Deprecated. Please set this on `DiaDecoderConfig` directly. If provided, it will be forwarded to `decoder_config`. bos_token_id (`int`, *optional*): Deprecated. Please set this on `DiaDecoderConfig` directly. If provided, it will be forwarded to `decoder_config`. delay_pattern (`list[int]`, *optional*, defaults to `[0, 8, 9, 10, 11, 12, 13, 14, 15]`): The delay pattern for the decoder. The length of this list must match `decoder_config.num_channels`. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). Example: ```python >>> from transformers import DiaConfig, DiaModel >>> # Initializing a DiaConfig with default values >>> configuration = DiaConfig() >>> # Initializing a DiaModel (with random weights) from the configuration >>> model = DiaModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` diapast_key_values)encoder_configdecoder_configNrFrGrr9r:r;r< delay_patternrr8c  zt|tr tdi|}t|tr tdi|}||n t|_||n t|_||_||ngd|_| |_| |_ |&tjd||j _ |&tjd||j _ |&tjd||j _|j jt!|jk(sJdt# |Hdd|i| y)N) r@ r zjPassing `pad_token_id` to `DiaConfig` is deprecated. Please set it directly on `DiaDecoderConfig` instead.zjPassing `eos_token_id` to `DiaConfig` is deprecated. Please set it directly on `DiaDecoderConfig` instead.zjPassing `bos_token_id` to `DiaConfig` is deprecated. Please set it directly on `DiaDecoderConfig` instead.z3Number of channels must match delay pattern length.r9r) isinstancedictrr1rFrGrrHrr8logger warning_oncer:r;r<r7lenrr) rrFrGrr9r:r;r<rHrr8rrs rrzDiaConfig.__init__sF nd +-??N nd +-??N0>0JnP`Pb0>0JnP`Pb  .;.G]Mn!2"  #   H 0I&Irc|jS)z^Defaulting to audio config as it's the decoder in this case which is usually the text backbone)rG)rargsrs rget_text_configzDiaConfig.get_text_config<s"""r) NNr"TNNNNr%T)r&r'r(r)r*keys_to_ignore_at_inferencerr1 sub_configsr,rAr+listrrXr.r/s@rrCrCs0dJ#4"5%5IYZK3726#'#'#'#'*.#'2J(4/2J)4/2J 2J ! 2J Dj 2JDj2JDj2JCy4'2J!2J2Jh#rrC)rCrr1N)r)configuration_utilsrmodeling_rope_utilsrutilsr get_loggerr&rSrr1rC__all__rrrrasa31   H %F#'F#RmJ'mJ`m# m#` @r