o Zh>@s^dZddlmZddlmZddlmZeeZ GdddeZ Gdd d eZ d dgZ d S) zMoshi model configuration)PretrainedConfig)logging) AutoConfigcsPeZdZdZdZdgZ            dfdd ZZS)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 ```Z moshi_depthpast_key_values}N silu{Gz?T:0yE>Fc s||_||_||_||_||_|dur|n||_||_| |_| p#|||_| |_ | |_ | |_ ||_ |ddkr?t d|d||_||_||_||_tjdd|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__)selfrrrrrrr+r r!r"r#r$r%r&r(r)r*rkwargs __class__r\/var/www/auris/lib/python3.10/site-packages/transformers/models/moshi/configuration_moshi.pyr-hs( zMoshiDepthConfig.__init__)rr r r r Nr rrNrTrrrrrF)__name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inferencer- __classcell__rrr0r2rs.KrcsxeZdZdZdZdgZeedZ            dfdd Z e ddZ e de fddZZS) 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) ```Zmoshir)audio_encoder_configdepth_decoder_configrr N @rrTrXrrFc sF||_||_||_||_|dur|n||_||_||_| |_| p#|||_| |_ | |_ | |_ ||_ |ddkr?t d|d||_||_||_|di}|dd}tj|fi||_|j|jjkrrt d|d |jjd |durz|jjn||_|d i}||j|||d tdi||_tjdd |i|dS)Nrrrrr;r7Zmimiz`num_codebooks=zX` is greater than the maximum number of codebooks that the audio encoder can deal with (z). Please lower it.r<)r+rrr*rr)rrrrrr rope_thetar!r"r#r$r%r&r'r(r)r*poprZ for_modelr;Z codebook_sizer+updaterr<r,r-)r.rrrrrr+r rAr!r"r#r$r%r&r(r)r*rr/r;Zaudio_encoder_model_typer<r0rr2r-sJ     zMoshiConfig.__init__cCs|jjS)N)r; sampling_rate)r.rrr2rD6szMoshiConfig.sampling_rater;cKs|dd|i|S)z Instantiate a [`MoshiConfig`] (or a derived class) from an audio encoder configuration. Returns: [`MoshiConfig`]: An instance of a configuration object r;Nr)to_dict)clsr;r/rrr2from_audio_encoder_config:s  z%MoshiConfig.from_audio_encoder_config)rr r=r=NNr>r?rNrTr>rr@rrF)r3r4r5r6r7r8rrZ sub_configsr-propertyrD classmethodrrGr9rrr0r2r:s<W E r:N) r6Zconfiguration_utilsrutilsrZauto.configuration_autorZ get_loggerr3loggerrr:__all__rrrr2s    | 9