
    <hB1                     0    S SK JrJr   " S S\5      rS/rg)   )PretrainedConfiglayer_type_validationc                      ^  \ rS rSrSrSrS/rSSSSSSSS.rS/S	/4S
S/S
/4S
/S
/4S.r                    SU 4S jjr	Sr
U =r$ )Exaone4Config   a  
This is the configuration class to store the configuration of a [`Exaone4Model`]. It is used to
instantiate a EXAONE 4.0 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 EXAONE-4.0-Instruct [LGAI-EXAONE/EXAONE-4.0-Instruct](https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-Instruct)
NOTE: `EXAONE-4.0-Instruct` is a placeholder model ID. The exact model ID will be updated in the future.

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 102400):
        Vocabulary size of the EXAONE 4.0 model. Defines the number of different tokens that can be represented by the
        `inputs_ids` passed when calling [`Exaone4Model`].
    hidden_size (`int`, *optional*, defaults to 4096):
        Dimension of the hidden representations.
    intermediate_size (`int`, *optional*, defaults to `hidden_size * 4`):
        Dimensionality of the MLP representations.
    num_hidden_layers (`int`, *optional*, defaults to 32):
        Number of hidden layers in the Transformer encoder.
    num_attention_heads (`int`, *optional*, defaults to 32):
        Number of attention heads for each attention layer in the Transformer decoder.
    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 `"silu"`):
        The non-linear activation function (function or string) in the decoder.
    max_position_embeddings (`int`, *optional*, defaults to 2048):
        The maximum sequence length that this model might ever be used with. Typically set this to something large
        just in case (e.g., 32768 for EXAONE 3.5).
    initializer_range (`float`, *optional*, defaults to 0.02):
        The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
    rms_norm_eps (`float`, *optional*, defaults to 1e-05):
        The epsilon used by the layer 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``.
    bos_token_id (`int`, *optional*, defaults to 0):
        Beginning of stream token id.
    eos_token_id (`int`, *optional*, defaults to 2):
        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.
    rope_scaling (`Dict`, *optional*):
        Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type
        and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
        accordingly.
        Expected contents:
            `rope_type` (`str`):
                The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
                'llama3'], with 'default' being the original RoPE implementation.
            `factor` (`float`, *optional*):
                Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
                most scaling types, a `factor` of x will enable the model to handle sequences of length x *
                original maximum pre-trained length.
            `original_max_position_embeddings` (`int`, *optional*):
                Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
                pretraining.
            `attention_factor` (`float`, *optional*):
                Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
                computation. If unspecified, it defaults to value recommended by the implementation, using the
                `factor` field to infer the suggested value.
            `beta_fast` (`float`, *optional*):
                Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
                ramp function. If unspecified, it defaults to 32.
            `beta_slow` (`float`, *optional*):
                Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
                ramp function. If unspecified, it defaults to 1.
            `short_factor` (`List[float]`, *optional*):
                Only used with 'longrope'. The scaling factor to be applied to short contexts (<
                `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
                size divided by the number of attention heads divided by 2
            `long_factor` (`List[float]`, *optional*):
                Only used with 'longrope'. The scaling factor to be applied to long contexts (<
                `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
                size divided by the number of attention heads divided by 2
            `low_freq_factor` (`float`, *optional*):
                Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
            `high_freq_factor` (`float`, *optional*):
                Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
    attention_dropout (`float`, *optional*, defaults to 0.0):
        The dropout ratio for the attention probabilities.
    sliding_window (`int`, *optional*):
        The size of the sliding window for the sliding window attention.
    sliding_window_pattern (`str`, *optional*):
        The pattern to use for sliding window attention. Can be one of:
            - `None`: No sliding window attention is used
            - `int`: Every `sliding_window` layers, use global attention, else use local attention.
            - `str`: A sequence of "L" (local attention) and "G" (global attention) characters that defines the
              attention pattern. The pattern starts from layer 0 and repeats every `sliding_window` layers. The
              final layer always uses global attention regardless of the pattern.
        For instance, sliding_window_pattern="LLLG" same as sliding_window=4, which means:
            - Layer 0, 1, 2: local attention,
            - Layer 3: global attention,
            ...(repeated)
    layer_types (`list`, *optional*):
        Attention pattern for each layer. Prioritized over `sliding_window_pattern`.

Example:

```python
>>> from transformers import Exaone4Model, Exaone4Config

>>> # Initializing a EXAONE configuration
>>> configuration = Exaone4Config()

>>> # Initializing a model from configuration
>>> model = Exaone4Model(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```exaone4past_key_valuescolwiserowwise)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_proj	input_idsinputs_embedshidden_statesattention_mask)embed_tokenslayersnormc                 ,  > Xl         X l        X@l        XPl        X`l        X0l        Xpl        Xl        Xl        Xl	        Xl
        UU l        Xl        UU l        UU l        UU l        UU l        U R                  c  SnU R                   cH  [#        U R                  5       Vs/ sH#  nUS-   U-  S:w  a  UU R                  :  a  SOSPM%     snU l        SU R                   ;   a  SU l        ['        U R                   5        [(        TU ]T  " SXUS.UD6  g s  snf )	N       sliding_attentionfull_attentionsliding_windowhybrid)bos_token_ideos_token_idtie_word_embeddings )
vocab_sizehidden_sizenum_hidden_layersnum_attention_headsnum_key_value_headsintermediate_size
hidden_actmax_position_embeddingsinitializer_rangerms_norm_eps	use_cacheattention_dropout
rope_thetarope_scalingr   sliding_window_patternlayer_typesrangecache_implementationr   super__init__)selfr   r   r#   r    r!   r"   r$   r%   r&   r'   r(   r   r   r   r*   r+   r)   r   r,   r-   kwargsi	__class__s                          i/var/www/html/shao/venv/lib/python3.13/site-packages/transformers/models/exaone4/configuration_exaone4.pyr1   Exaone4Config.__init__   s4   0 %&!2#6 #6 !2$'>$!2("!2$(,&<#&&%&"#
 t556	  7A U56!;DDZDZ@Z $%& 7	 D t///(0D%d../ 	
%Vi	
ms	
 s    )D)r)   r/   r$   r   r&   r#   r-   r%   r!   r    r"   r'   r+   r*   r   r,   r(   r   )i     i @      r9   r9   silui   g{Gz?gh㈵>Tr      Fg     @Ng        r8      N)__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planr1   __static_attributes____classcell__)r5   s   @r6   r   r      s    un J#4"5 &/%.%.%."+ )"+ &(9:#%568IJ!"_$56  $! +9
 9
    r   N)configuration_utilsr   r   r   __all__r   rH   r6   <module>rK      s%   , KC
$ C
L 
rH   