
    <hj%                     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$ )Gemma2Config   a  
This is the configuration class to store the configuration of a [`Gemma2Model`]. It is used to instantiate an Gemma2
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 Gemma2-7B.
e.g. [google/gemma2-7b](https://huggingface.co/google/gemma2-7b)
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 Gemma2 model. Defines the number of different tokens that can be represented by the
        `inputs_ids` passed when calling [`Gemma2Model`]
    hidden_size (`int`, *optional*, defaults to 2304):
        Dimension of the hidden representations.
    intermediate_size (`int`, *optional*, defaults to 9216):
        Dimension of the MLP representations.
    num_hidden_layers (`int`, *optional*, defaults to 26):
        Number of hidden layers in the Transformer decoder.
    num_attention_heads (`int`, *optional*, defaults to 8):
        Number of attention heads for each attention layer in the Transformer decoder.
    num_key_value_heads (`int`, *optional*, defaults to 4):
        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, check out [this
        paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to
        `num_attention_heads`.
    head_dim (`int`, *optional*, defaults to 256):
        The attention head dimension.
    hidden_activation (`str` or `function`, *optional*, defaults to `"gelu_pytorch_tanh"`):
        The non-linear activation function (function or string) in the decoder. Will default to `"gelu_pytorch_tanh"`
        if not specified. `"gelu_pytorch_tanh"` uses an approximation of the `"gelu"` activation function.
    max_position_embeddings (`int`, *optional*, defaults to 8192):
        The maximum sequence length that this model might ever be used with.
    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-06):
        The epsilon used by the rms 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*, defaults to 0):
        Padding token id.
    eos_token_id (`int`, *optional*, defaults to 1):
        End of stream token id.
    bos_token_id (`int`, *optional*, defaults to 2):
        Beginning of stream token id.
    tie_word_embeddings (`bool`, *optional*, defaults to `True`):
        Whether to tie weight embeddings
    rope_theta (`float`, *optional*, defaults to 10000.0):
        The base period of the RoPE embeddings.
    attention_bias (`bool`, defaults to `False`, *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.
    query_pre_attn_scalar (`float`, *optional*, defaults to 256):
        scaling factor used on the attention scores
    sliding_window (`int`, *optional*, defaults to 4096):
        in Gemma2, every other layer uses sliding window attention. This is the size of the sliding window.
    layer_types (`list`, *optional*):
        Attention pattern for each layer.
    final_logit_softcapping (`float`, *optional*, defaults to 30.0):
        scaling factor when applying tanh softcapping on the logits.
    attn_logit_softcapping (`float`, *optional*, defaults to 50.0):
        scaling factor when applying tanh softcapping on the attention scores.

```python
>>> from transformers import Gemma2Model, Gemma2Config
>>> # Initializing a Gemma2 gemma2-7b style configuration
>>> configuration = Gemma2Config()
>>> # Initializing a model from the gemma2-7b style configuration
>>> model = Gemma2Model(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```gemma2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                   > [         TU ]  " SUUUUS.UD6  Xl        Xl        X l        X0l        X@l        XPl        Xpl        X`l	        Xl
        Xl        Xl        UU l        UU l        UU l        Xl        UU l        UU l        UU l        UU l        UU l        U R*                  cB  [-        U R                  5       Vs/ sH  n[/        US-   S-  5      (       a  SOSPM     snU l        [1        U R*                  5        g s  snf )N)pad_token_idbos_token_ideos_token_idtie_word_embeddings      sliding_attentionfull_attention )super__init__
vocab_sizemax_position_embeddingshidden_sizeintermediate_sizenum_hidden_layersnum_attention_headshead_dimnum_key_value_headsinitializer_rangerms_norm_eps	use_cache
rope_thetaattention_biasattention_dropouthidden_activationquery_pre_attn_scalarsliding_windowfinal_logit_softcappingattn_logit_softcappinglayer_typesrangeboolr   )selfr   r!   r"   r#   r$   r&   r%   r-   r    r'   r(   r)   r   r   r   r   r*   r+   r,   r.   r/   r2   r0   r1   kwargsi	__class__s                              g/var/www/html/shao/venv/lib/python3.13/site-packages/transformers/models/gemma2/configuration_gemma2.pyr   Gemma2Config.__init__w   s   8 	 	
%%% 3		

 	
 %'>$&!2!2#6  #6 !2("$,!2!2%:",'>$&<#&#X]^b^t^tXu XuSTtQUaK'8'8#>NNXu D 	d../ s   ;#C<)r+   r,   r1   r0   r%   r-   r!   r'   r"   r2   r    r$   r#   r&   r.   r(   r*   r/   r)   r   )i  i 	  i $              gelu_pytorch_tanhi    g{Gz?gư>T    r   r   Tg     @Fg        r>   i   Ng      >@g      I@)__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planr   __static_attributes____classcell__)r8   s   @r9   r   r      s    JX J#4"5%.%.%.%."+ )"+ &(9:#%568IJ!"_$56 - $ ! $#3<0 <0    r   N)configuration_utilsr   r   r   __all__r   rL   r9   <module>rO      s%   , KZ0# Z0z 
rL   