fTh>SrSSKJr SSKJr SSKJr \R"\5r "SS\5r "SS \5r S S/r g ) zMoshi model configuration)PretrainedConfig)logging) AutoConfigc^^\rSrSrSrSrS/rSU4SjjrSrU=r $)MoshiDepthConfiga6 This is the configuration class to store the configuration of a [`MoshiDepthDecoder`]. It is used to instantiate a Moshi depth decoder model according to the specified arguments, defining the Moshi depth decoder config. 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 32000): Vocabulary size of the MoshiDepthDecoder model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`MoshiDepthDecoder`]. hidden_size (`int`, *optional*, defaults to 1024): Dimensionality of the layers and the pooler layer of the depth decoder. input_size (`int`, *optional*, defaults to 4096): Dimensionality of the input hidden states. Used to connect the main decoder to the depth decoder. num_hidden_layers (`int`, *optional*, defaults to 6): Number of depth decoder layers. num_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the depth decoder block. num_key_value_heads (`int`, *optional*): This is the number of key_value heads that should be used to implement Grouped Query Attention. If `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed by meanpooling all the original heads within that group. For more details checkout [this paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `num_attention_heads`. audio_vocab_size (`int`, *optional*, defaults to 2048): Vocabulary size of the audio part of model. Defines the number of different tokens that can be represented by the `audio_codes` passed when calling the Moshi models. max_position_embeddings (`int`, *optional*, defaults to 9): 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). hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): The non-linear activation function (function or string) in the depth decoder. head_dim (`int`, *optional*, defaults to `hidden_size // num_attention_heads`): The attention head dimension. 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). Only relevant if `config.is_decoder=True`. sliding_window (`int`, *optional*, defaults to 8): Sliding window attention window size. If not specified, will default to `8`. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. ffn_dim (`int`, *optional*, defaults to 5632): Dimensionality of the "intermediate" (often named feed-forward) layer in the depth decoder block. Must be even. rms_norm_eps (`float`, *optional*, defaults to 1e-08): The epsilon used by the rms normalization layers. num_codebooks (`int`, *optional*, defaults to 8): The number of audio codebooks for each audio channels. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether to tie weight embeddings kwargs (*optional*): Dictionary of keyword arguments. Notably: - **audio_encoder_config** ([`PretrainedConfig`], *optional*) -- An instance of a configuration object that defines the audio encoder config. Example: ```python >>> from transformers import ( ... MoshiDepthConfig, ... MoshiDepthDecoder, ... ) >>> configuration = MoshiDepthConfig() >>> # Initializing a MoshiDepthDecoder (with random weights) from the kmhf/hf-moshiko style configuration >>> model = MoshiDepthDecoder(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` moshi_depthpast_key_valuesc N>XlX lX0lX@lXPlUbUOUUlXlXlU =(d X%-UlXl Xl Xl Xl US-S:Xa[SUS35eXlUUlUUlXpl[$TU]L"SSU0UD6 g)Nr `ffn_dim=` must be even.tie_word_embeddings) vocab_size hidden_size input_sizenum_hidden_layersnum_attention_headsnum_key_value_headsmax_position_embeddings hidden_acthead_diminitializer_range use_cachesliding_windowattention_dropout ValueErrorffn_dim rms_norm_eps num_codebooksaudio_vocab_sizesuper__init__)selfrrrrrrr#rrrrrrrr r!r"rkwargs __class__s e/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/moshi/configuration_moshi.pyr%MoshiDepthConfig.__init__hs,%&$!2#6 :M:Y#6_r '>$$ FK$F !2",!2 Q;! y AB B (* 0 K-@KFK)rr#r rrrrrrrr"rrr!rrr)}iNi siluN{Gz?Ti:0yE>r3F) __name__ __module__ __qualname____firstlineno____doc__ model_typekeys_to_ignore_at_inferencer%__static_attributes__ __classcell__r(s@r)rrs^I VJ#4"5  !!'*L*Lr+rc^\rSrSrSrSrS/r\\S.r S U4Sjjr \ S5r \ S\4S j5rS rU=r$) MoshiConfiga This is the configuration class to store the configuration of a [`MoshiModel`]. It is used to instantiate a Moshi model according to the specified arguments, defining the audio encoder, Moshi depth decoder and Moshi decoder configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the Moshiko model, e.g. [kmhf/hf-moshiko](https://huggingface.co/kmhf/hf-moshiko) 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 32000): Vocabulary size of the MoshiDecoder model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`MoshiDecoder`]. hidden_size (`int`, *optional*, defaults to 4096): Dimensionality of the layers and the pooler layer of the main decoder. num_hidden_layers (`int`, *optional*, defaults to 32): Number of decoder layers. num_attention_heads (`int`, *optional*, defaults to 32): Number of attention heads for each attention layer in the main decoder block. num_key_value_heads (`int`, *optional*): This is the number of key_value heads that should be used to implement Grouped Query Attention. If `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed by meanpooling all the original heads within that group. For more details checkout [this paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `num_attention_heads`. audio_vocab_size (`int`, *optional*): Vocabulary size of the audio part of model. Defines the number of different tokens that can be represented by the `audio_codes` passed when calling the Moshi models. max_position_embeddings (`int`, *optional*, defaults to 3000): 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). rope_theta (`float`, *optional*, defaults to 10000.0): The base period of the RoPE embeddings. hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): The non-linear activation function (function or string) in the decoder. head_dim (`int`, *optional*, defaults to `hidden_size // num_attention_heads`): The attention head dimension. 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). Only relevant if `config.is_decoder=True`. sliding_window (`int`, *optional*, defaults to 3000): Sliding window attention window size. If not specified, will default to `3000`. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. ffn_dim (`int`, *optional*, defaults to 22528): Dimensionality of the "intermediate" (often named feed-forward) layer in the main decoder block. Must be even. rms_norm_eps (`float`, *optional*, defaults to 1e-08): The epsilon used by the rms normalization layers. num_codebooks (`int`, *optional*, defaults to 8): The number of audio codebooks for each audio channels. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether to tie weight embeddings kwargs (*optional*): Dictionary of keyword arguments. Notably: - **audio_encoder_config** ([`PretrainedConfig`], *optional*) -- An instance of a configuration object that defines the audio encoder config. - **depth__config** ([`PretrainedConfig`], *optional*) -- An instance of a configuration object that defines the depth decoder config. Example: ```python >>> from transformers import ( ... MoshiConfig, ... MoshiForConditionalGeneration, ... ) >>> configuration = MoshiConfig() >>> # Initializing a MoshiForConditionalGeneration (with random weights) from the kmhf/hf-moshiko style configuration >>> model = MoshiForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # Saving the model, including its configuration >>> model.save_pretrained("kmhf/hf-moshiko") >>> # loading model and config from pretrained folder >>> moshi_config = MoshiConfig.from_pretrained("kmhf/hf-moshiko") >>> model = MoshiForConditionalGeneration.from_pretrained("kmhf/hf-moshiko", config=moshi_config) ```moshir )audio_encoder_configdepth_decoder_configc >XlX lX0lX@lUbUOUUlXplXlXlU =(d X$-UlXl Xl Xl Xl US-S:Xa[SUS35eXlUUlUUlUR#S05nUR#SS5n[$R&"U40UD6UlUR UR(R :a&[SUS UR(R S 35eUcUR(R*OUUlUR#S 05nUR/UR,UUUS .5 [1S0UD6Ul[4TU]l"SS U0UD6 g)Nrr rrrDr;mimiz`num_codebooks=zX` is greater than the maximum number of codebooks that the audio encoder can deal with (z). Please lower it.rE)r#rrr"rr)rrrrrr rope_thetarrrrrrrr r!r"popr for_modelrD codebook_sizer#updaterrEr$r%)r&rrrrrr#rrHrrrrrrr r!r"rr'rDaudio_encoder_model_typerEr(s r)r%MoshiConfig.__init__s,%&!2#6 :M:Y#6_r '>$$$ FK$F !2",!2 Q;! y AB B (*%zz*@"E#7#;#;L&#Q $.$8$89Q$jUi$j!    9 9 G G G!-1IJNJcJcJqJqIrrEF  8H7OD % % 3 3Ue  &zz*@"E##$($9$9)(!.   %5$L7K$L! K-@KFKr+c.URR$)N)rD sampling_rate)r&s r)rPMoshiConfig.sampling_rate6s((666r+rDc 2U"SSUR50UD6$)z Instantiate a [`MoshiConfig`] (or a derived class) from an audio encoder configuration. Returns: [`MoshiConfig`]: An instance of a configuration object rDr)to_dict)clsrDr's r)from_audio_encoder_config%MoshiConfig.from_audio_encoder_config:s* !5!=!=!?   r+)rrDr#rEr rrrrrrr"rrr!rHrrr)r,r- rWNN g@r1Nr2TrXr4iXr5r3F)r6r7r8r9r:r;r<rr sub_configsr%propertyrP classmethodrrUr=r>r?s@r)rArAsU nJ#4"5+5O_`K  $!'CLJ77 .  r+rAN) r:configuration_utilsrutilsrauto.configuration_autor get_loggerr6loggerrrA__all__rr+r)rbsT 30   H %yL'yLxu "u p , -r+