
    <hp,                     p    S r SSKJrJr  SSKJr  SSKJr  \R                  " \	5      r
 " S S\5      rS/rg)zQwen2 model configuration   )PretrainedConfiglayer_type_validation)rope_config_validation)loggingc                      ^  \ 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$ )Qwen2Config   a  
This is the configuration class to store the configuration of a [`Qwen2Model`]. It is used to instantiate a
Qwen2 model according to the specified arguments, defining the model architecture. Instantiating a configuration
with the defaults will yield a similar configuration to that of
Qwen2-7B-beta [Qwen/Qwen2-7B-beta](https://huggingface.co/Qwen/Qwen2-7B-beta).

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 151936):
        Vocabulary size of the Qwen2 model. Defines the number of different tokens that can be represented by the
        `inputs_ids` passed when calling [`Qwen2Model`]
    hidden_size (`int`, *optional*, defaults to 4096):
        Dimension of the hidden representations.
    intermediate_size (`int`, *optional*, defaults to 22016):
        Dimension 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 encoder.
    num_key_value_heads (`int`, *optional*, defaults to 32):
        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 `32`.
    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 32768):
        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`.
    tie_word_embeddings (`bool`, *optional*, defaults to `False`):
        Whether the model's input and output word embeddings should be tied.
    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
    use_sliding_window (`bool`, *optional*, defaults to `False`):
        Whether to use sliding window attention.
    sliding_window (`int`, *optional*, defaults to 4096):
        Sliding window attention (SWA) window size. If not specified, will default to `4096`.
    max_window_layers (`int`, *optional*, defaults to 28):
        The number of layers using full attention. The first `max_window_layers` layers will use full attention, while any
        additional layer afterwards will use SWA (Sliding Window Attention).
    layer_types (`list`, *optional*):
        Attention pattern for each layer.
    attention_dropout (`float`, *optional*, defaults to 0.0):
        The dropout ratio for the attention probabilities.

```python
>>> from transformers import Qwen2Model, Qwen2Config

>>> # Initializing a Qwen2 style configuration
>>> configuration = Qwen2Config()

>>> # Initializing a model from the Qwen2-7B style configuration
>>> model = Qwen2Model(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```qwen2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         Xl        X l        X0l        X@l        XPl        Xl        U R                  (       a  UOS U l        UU l        Uc  UnX`l	        Xpl
        Xl        Xl        Xl        Xl        Xl        UU l        U R                  b,  SU R                  ;   a  U R                  S   U R                  S'   [#        U 5        UU l        U R$                  cI  ['        U R                  5       Vs/ sH$  nU R                  b  UU R                  :  a  SOSPM&     snU l        [)        U R$                  5        [*        TU ]X  " SSU0UD6  g s  snf )Ntype	rope_typesliding_attentionfull_attentiontie_word_embeddings )
vocab_sizemax_position_embeddingshidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsuse_sliding_windowsliding_windowmax_window_layersnum_key_value_heads
hidden_actinitializer_rangerms_norm_eps	use_cache
rope_thetarope_scalingattention_dropoutr   layer_typesranger   super__init__)selfr   r   r   r    r!   r%   r&   r   r'   r(   r)   r   r*   r+   r"   r#   r$   r-   r,   kwargsi	__class__s                         e/var/www/html/shao/venv/lib/python3.13/site-packages/transformers/models/qwen2/configuration_qwen2.pyr0   Qwen2Config.__init__   s]   . %'>$&!2!2#6 "4040G0GnT!2 &"5#6 $!2("$(!2 (Vt7H7H-H-1->->v-FDk*t$&#
 t556	  7A &&2qD<R<R7R $%& 7	 D 	d../ 	
 3	
	
 s   2*E)r,   r&   r   r'   r   r-   r   r$   r!   r    r%   r(   r+   r*   r#   r)   r"   r   )iQ    i V      r8   r8   silui   g{Gz?gư>TFg     @NFr7      Ng        )__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planr0   __static_attributes____classcell__)r4   s   @r5   r   r      s    hT J#4"5 &/%.%.%."+ )"+ &(9:#%568IJ!"_$56  %! )@
 @
    r   N)r?   configuration_utilsr   r   modeling_rope_utilsr   utilsr   
get_loggerr;   loggerr   __all__r   rF   r5   <module>rM      s>      J 9  
		H	%~
" ~
B /rF   