
    <h)@                     l    S SK Jr  SSKJr  SSKJr  SSKJrJr   " S S\5      r	 " S	 S
\5      r
S
S/rg)    )Optional   )PretrainedConfig)rope_config_validation   )CONFIG_MAPPING
AutoConfigc            	          ^  \ 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r	                         SS\
S\
S\
S\
4U 4S jjjrSrU =r$ )AriaTextConfig   a  
This class handles the configuration for the text component of the Aria model.
Instantiating a configuration with the defaults will yield a similar configuration to that of the model of the Aria
[rhymes-ai/Aria](https://huggingface.co/rhymes-ai/Aria) architecture.
This class extends the LlamaConfig to include additional parameters specific to the Mixture of Experts (MoE) architecture.

Args:
    vocab_size (`int`, *optional*, defaults to 32000):
        Vocabulary size of the LLaMA model. Defines the number of different tokens that can be represented by the
        `inputs_ids` passed when calling [`LlamaModel`]
    hidden_size (`int`, *optional*, defaults to 4096):
        Dimension of the hidden representations.
    intermediate_size (`int`, *optional*, defaults to 4096):
        The size 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 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, check out [this
        paper](https://huggingface.co/papers/2305.13245). 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. Llama 1 supports up to 2048 tokens,
        Llama 2 up to 4096, CodeLlama up to 16384.
    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 2):
        Padding token id.
    bos_token_id (`int`, *optional*, defaults to 1):
        Beginning of stream token id.
    eos_token_id (`int`, *optional*, defaults to 2):
        End of stream token id.
    pretraining_tp (`int`, *optional*, defaults to 1):
        Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
        document](https://huggingface.co/docs/transformers/main/perf_train_gpu_many#tensor-parallelism) to
        understand more about it. This value is necessary to ensure exact reproducibility of the pretraining
        results. Please refer to [this issue](https://github.com/pytorch/pytorch/issues/76232).
    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_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, down_proj and gate_proj layers in the MLP layers.
    head_dim (`int`, *optional*):
        The attention head dimension. If None, it will default to hidden_size // num_heads
    moe_num_experts (`int`, *optional*, defaults to 8):
        The number of experts in the MoE layer.
    moe_topk (`int`, *optional*, defaults to 2):
        The number of top experts to route to for each token.
    moe_num_shared_experts (`int`, *optional*, defaults to 2):
        The number of shared experts.
	aria_text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normtext_configintermediate_sizemoe_num_expertsmoe_topkmoe_num_shared_expertsc                   > [         TU ]  " SUUUUS.UD6  Xl        Xl        X l        X0l        X@l        XPl        Uc  UnX`l        Xpl	        Xl
        Xl        Xl        Xl        UU l        UU l        UU l        UU l        UU l        Ub  UOU R                  U R                  -  U l        U R                  b,  SU R                  ;   a  U R                  S   U R                  S'   [)        U 5        UU l        UU l        UU l        g )N)pad_token_idbos_token_ideos_token_idtie_word_embeddingstype	rope_type )super__init__
vocab_sizemax_position_embeddingshidden_sizer   num_hidden_layersnum_attention_headsnum_key_value_heads
hidden_actinitializer_rangerms_norm_epspretraining_tp	use_cache
rope_thetarope_scalingattention_biasattention_dropoutmlp_biashead_dimr   r   r   r   )selfr'   r)   r   r*   r+   r,   r-   r(   r.   r/   r1   r   r   r    r0   r!   r2   r3   r4   r5   r6   r7   r   r   r   kwargs	__class__s                              c/var/www/html/shao/venv/lib/python3.13/site-packages/transformers/models/aria/configuration_aria.pyr&   AriaTextConfig.__init__   s   : 	 	
%%% 3		

 	
 %'>$&!2!2#6  &"5#6 $!2(,"$(,!2 $,$8d>N>NRVRjRj>j (Vt7H7H-H-1->->v-FDk*t$. &<#    )r4   r5   r7   r-   r)   r.   r   r(   r6   r   r   r   r+   r*   r,   r0   r/   r3   r2   r1   r'   )i }     r>       r?   Nsilui   {Gz?gư>Tr      r   rB   Fg     @NFg        FN   r   r   )__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planbase_config_keyintr&   __static_attributes____classcell__r:   s   @r;   r   r      s    hT J#4"5 &/%.%.%."+ )"+ &(9:#%568IJ!"_$56
 $O !%  $! &'5B= 	B=0 1B=2 3B=4 !$5B= B=r=   r   c                   p   ^  \ rS rSrSrSrSS0r\\S.r	      SS\
S\S	\\   S\
S
\4
U 4S jjjrSrU =r$ )
AriaConfig   a  
This class handles the configuration for both vision and text components of the Aria model,
as well as additional parameters for image token handling and projector mapping.
Instantiating a configuration with the defaults will yield a similar configuration to that of the model of the Aria
[rhymes-ai/Aria](https://huggingface.co/rhymes-ai/Aria) architecture.

Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
documentation from [`PretrainedConfig`] for more information.

Args:
    vision_config (`AriaVisionConfig` or `dict`, *optional*):
        Configuration for the vision component.
    vision_feature_layer (`int`, *optional*, defaults to -1):
        The index of the layer to select the vision feature.
    text_config (`AriaTextConfig` or `dict`, *optional*):
        Configuration for the text component.
    projector_patch_to_query_dict (`dict`, *optional*):
        Mapping of patch sizes to query dimensions.
    image_token_index (`int`, *optional*, defaults to 9):
        Index used to represent image tokens.
    initializer_range (`float`, *optional*, defaults to 0.02):
        The standard deviation of the truncated normal initializer for initializing all weight matrices.

Attributes:
    model_type (`str`):
        Type of the model, set to `"aria"`.
    image_token_index (`int`):
        Index used to represent image tokens.
    projector_patch_to_query_dict (`dict`):
        Mapping of patch sizes to query dimensions.
    vision_config (`AriaVisionConfig`):
        Configuration for the vision component.
    text_config (`AriaTextConfig`):
        Configuration for the text component.
ariaimage_token_idimage_token_index)r   vision_configvision_feature_layerr   projector_patch_to_query_dictr.   c                 *  > XPl         Uc  SSS.nUR                  5        VV	s0 sH  u  p[        U5      [        U	5      _M     sn	nU l        [	        U R                  R                  5       5      U l        X l        [        U[        5      (       a  SUS'   [        US      " S0 UD6nOUc  [        S   " 5       nXl        X`l        [        U[        5      (       a  SU;   a  [        S0 UD6nOUc
  [        5       nX0l        [        T
U ]@  " S0 UD6  g s  sn	nf )N      )i  i$  idefics3_visionrI   r$   )rW   itemsrN   rZ   maxvalues'max_value_projector_patch_to_query_dictrY   
isinstancedictr   rX   r.   r   r   r%   r&   )r8   rX   rY   r   rZ   rW   r.   r9   kvr:   s             r;   r&   AriaConfig.__init__
  s    "3 )0-) JgIlIlIn-oInc!fc!fnIn-o*7:4;];];d;d;f7g4$8!mT***;M,'*=+FGX-XM"*+<=?M*!2k4((\[-H(7;7K (*K&"6"' .ps    D)rW   r.   rb   rZ   r   rX   rY   )NNN	   rA   )rD   rE   rF   rG   rH   rI   attribute_mapr   r	   sub_configsrN   r   rd   floatr&   rO   rP   rQ   s   @r;   rS   rS      s}    "H J-M #1:NK $&&*8<!"#'&# "&# $	&#
 (0~&# &# !&# &#r=   rS   N)typingr   configuration_utilsr   modeling_rope_utilsr   autor   r	   r   rS   __all__r$   r=   r;   <module>rr      s@   *  3 9 -@=% @=FQ#! Q#h )
*r=   