g>dZddlmZddlmZddlmZejeZ GddeZ Gdd eZ d dgZ d S) zMoshi model configuration)PretrainedConfig)logging) AutoConfigcReZdZdZdZdgZ dfd ZxZS)MoshiDepthConfiga> 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_values}N silu{Gz?T:0yE>Fc v||_||_||_||_||_||n||_||_| |_| p||z|_| |_ | |_ | |_ ||_ |dzdkrtd|d||_||_||_||_t%jdd|i|dS)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__)selfrrr r!r"r#r/r$r%r&r'r(r)r*r,r-r.rkwargs __class__s i/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/moshi/configuration_moshi.pyr1zMoshiDepthConfig.__init__hs,%&$!2#6 :M:Y#6#6_r '>$$ FK3F$F !2",!2 Q;!  AAAABB B (* 0KK-@KFKKKKK)r r r rrNrrrNrTrrrrrF)__name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inferencer1 __classcell__r4s@r5rrsI I VJ#4"5  !!'*L*L*L*L*L*L*L*L*L*Lr6rceZdZdZdZdZdgZ dfd ZedZ e de fdZ xZ S) 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) ```moshiTr r r N @rrrXrrFc ||_||_||_||_||n||_||_||_| |_| p||z|_| |_ | |_ | |_ ||_ |dzdkrtd|d||_||_||_|di}|dd}t%j|fi||_|j|jjkr td|d |jjd | |jjn||_|d i}||j|||d t1di||_t5jdd |i|dS)Nrrrraudio_encoder_configr;mimiz`num_codebooks=zX` is greater than the maximum number of codebooks that the audio encoder can deal with (z). Please lower it.depth_decoder_config)r/r rr.rr)rrr!r"r#r$ rope_thetar%r&r'r(r)r*r+r,r-r.popr for_modelrG codebook_sizer/updaterrIr0r1)r2rrr!r"r#r/r$rJr%r&r'r(r)r*r,r-r.rr3rGaudio_encoder_model_typerIr4s r5r1zMoshiConfig.__init__s,%&!2#6 :M:Y#6#6_r '>$$$ FK3F$F !2",!2 Q;!  AAAABB B (*%zz*@"EE#7#;#;L&#Q#Q $.$89Q$j$jUi$j$j!   9 G G GF-FFJNJcJqFFF  8H7OD % 3 3Ue  &zz*@"EE##$($9)(!.      %5$L$L7K$L$L!KK-@KFKKKKKr6c|jjS)N)rG sampling_rate)r2s r5rQzMoshiConfig.sampling_rate6s(66r6rGc :|dd|i|S)z Instantiate a [`MoshiConfig`] (or a derived class) from an audio encoder configuration. Returns: [`MoshiConfig`]: An instance of a configuration object rGr)to_dict)clsrGr3s r5from_audio_encoder_configz%MoshiConfig.from_audio_encoder_config:s9s  !5!=!=!?!?    r6)r r rBrBNNrCrDrNrTrCrrErrF)r7r8r9r:r;is_compositionr<r1propertyrQ classmethodrrUr=r>s@r5r@r@sU U nJN#4"5  $!'CLCLCLCLCLCLJ77X7 .   [     r6r@N) r:configuration_utilsrutilsrauto.configuration_autor get_loggerr7loggerrr@__all__rr6r5r_s 333333000000  H % %yLyLyLyLyL'yLyLyLxu u u u u "u u u p , -r6