
    sg                     f    d Z ddlmZ ddlmZ ddlmZ  ej                  e      Z	 G d de      Z
y)zNemotron model configuration   )PretrainedConfig)rope_config_validation)loggingc                   X     e Zd ZdZdZdgZ	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 d fd	Z xZS )NemotronConfiga  
    This is the configuration class to store the configuration of a [`NemotronModel`]. It is used to instantiate an Nemotron
    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 Nemotron-8B.
    e.g. [nvidia/nemotron-3-8b-base-4k-hf](https://huggingface.co/nvidia/nemotron-3-8b-base-4k-hf).
    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 256000):
            Vocabulary size of the Nemotron model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`NemotronModel`]
        hidden_size (`int`, *optional*, defaults to 6144):
            Dimension of the hidden representations.
        intermediate_size (`int`, *optional*, defaults to 24576):
            Dimension of the MLP representations.
        num_hidden_layers (`int`, *optional*, defaults to 32):
            Number of hidden layers in the Transformer decoder.
        num_attention_heads (`int`, *optional*, defaults to 48):
            Number of attention heads for each attention layer in the Transformer decoder.
        head_dim (`int`, *optional*):
            Projection weights dimension in multi-head attention. Set to hidden_size // num_attention_heads if None
        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`.
        hidden_act (`str` or `function`, *optional*, defaults to `"relu2"`):
            The non-linear activation function (function or string) in the decoder.
        max_position_embeddings (`int`, *optional*, defaults to 4096):
            The maximum sequence length that this model might ever be used with.
        initializer_range (`float`, *optional*, defaults to 0.0134):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        norm_eps (`float`, *optional*, defaults to 1e-05):
            The epsilon used by the normalization layers.
        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`.
        pad_token_id (`int`, *optional*):
            Padding token id.
        bos_token_id (`int`, *optional*, defaults to 2):
            Beginning of stream token id.
        eos_token_id (`int`, *optional*, defaults to 3):
            End of stream token id.
        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
            Whether to tie weight embeddings
        rope_theta (`float`, *optional*, defaults to 10000.0):
            The base period of the RoPE embeddings.
        partial_rotary_factor (`float`, *optional*, defaults to 0.5): Percentage of the query and keys which will have rotary embedding.
        attention_bias (`bool`, *optional*, defaults to `False`):
            Whether to use a bias in the query, key, value and output projection layers during self-attention.
        attention_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the attention probabilities.
        mlp_bias (`bool`, *optional*, defaults to `False`):
            Whether to use a bias in up_proj and down_proj layers in the MLP layers.

    ```python
    >>> from transformers import NemotronModel, NemotronConfig

    >>> # Initializing a Nemotron nemotron-15b style configuration
    >>> configuration = NemotronConfig()

    >>> # Initializing a model from the nemotron-15b style configuration
    >>> model = NemotronModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```nemotronpast_key_valuesc                 @   || _         |	| _        || _        || _        || _        || _        ||n||z  | _        || _        || _        |
| _	        || _
        || _        || _        || _        t        |        || _        || _        || _        t%        | L  d||||d| y )N)pad_token_idbos_token_ideos_token_idtie_word_embeddings )
vocab_sizemax_position_embeddingshidden_sizeintermediate_sizenum_hidden_layersnum_attention_headshead_dimnum_key_value_heads
hidden_actinitializer_rangenorm_eps	use_cache
rope_thetapartial_rotary_factorr   attention_biasattention_dropoutmlp_biassuper__init__)selfr   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r    kwargs	__class__s                          f/var/www/html/venv/lib/python3.12/site-packages/transformers/models/nemotron/configuration_nemotron.pyr"   zNemotronConfig.__init__g   s    2 %'>$&!2!2#6 $,$8kM`>`#6 $!2 "$%:"t$,!2  	
%%% 3		

 	
    )i  i   i `      0   NNrelu2i   gS!uq?gh㈵>TN   r   Fg     @g      ?Fg        F)__name__
__module____qualname____doc__
model_typekeys_to_ignore_at_inferencer"   __classcell__)r%   s   @r&   r   r      se    GR J#4"5   $ !!-2
 2
r'   r   N)r/   configuration_utilsr   modeling_rope_utilsr   utilsr   
get_loggerr,   loggerr   r   r'   r&   <module>r8      s6     # 3 9  
		H	%
% 
r'   