
    <h".                     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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$ )MiniMaxConfig   ao  
This is the configuration class to store the configuration of a [`MiniMaxModel`]. It is used to instantiate an
MiniMax 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 MiniMax.

[MiniMaxAI/MiniMax-Text-01-hf](https://huggingface.co/MiniMaxAI/MiniMax-Text-01-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 32000):
        Vocabulary size of the MiniMax model. Defines the number of different tokens that can be represented by the
        `inputs_ids` passed when calling [`MiniMaxModel`]
    hidden_size (`int`, *optional*, defaults to 4096):
        Dimension of the hidden representations.
    intermediate_size (`int`, *optional*, defaults to 14336):
        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 8):
        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 `8`.
    head_dim (`int`, *optional*, defaults to `hidden_size // num_attention_heads`):
        The attention head dimension.
    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 `4096*32`):
        The maximum sequence length that this model might ever be used with. MiniMax's sliding window attention
        allows sequence of up to 4096*32 tokens.
    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 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*):
        The id of the padding token.
    bos_token_id (`int`, *optional*, defaults to 1):
        The id of the "beginning-of-sequence" token.
    eos_token_id (`int`, *optional*, defaults to 2):
        The id of the "end-of-sequence" token.
    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 1000000.0):
        The base period of the RoPE embeddings.
    sliding_window (`int`, *optional*):
        Sliding window attention window size. If not specified, will default to `4096`.
    attention_dropout (`float`, *optional*, defaults to 0.0):
        The dropout ratio for the attention probabilities.
    num_experts_per_tok (`int`, *optional*, defaults to 2):
        The number of experts to route per-token, can be also interpreted as the `top-k` routing
        parameter
    num_local_experts (`int`, *optional*, defaults to 8):
        Number of experts per Sparse MLP layer.
    output_router_logits (`bool`, *optional*, defaults to `False`):
        Whether or not the router logits should be returned by the model. Enabeling this will also
        allow the model to output the auxiliary loss. See [here]() for more details
    router_aux_loss_coef (`float`, *optional*, defaults to 0.001):
        The aux loss factor for the total loss.
    router_jitter_noise (`float`, *optional*, defaults to 0.0):
        Amount of noise to add to the router.
    layer_types (`list`, *optional*):
        Attention pattern for each layer.
    block_size (`int`, *optional*, defaults to 256):
        The length of each attention block, determining how queries, keys, and values
        are grouped and processed for intra- and inter-block attention.
    full_attn_alpha_factor (`float`, *optional*, defaults to 1):
        Weight for residual value in residual connection after normal attention.
    full_attn_beta_factor (`float`, *optional*, defaults to 1):
        Weight for hidden state value in residual connection after normal attention.
    linear_attn_alpha_factor (`float`, *optional*, defaults to 1):
        Weight for residual value in residual connection after lightning attention.
    linear_attn_beta_factor (`float`, *optional*, defaults to 1):
        Weight for hidden state value in residual connection after lightning attention.
    mlp_alpha_factor (`float`, *optional*, defaults to 1):
        Weight for residual value in residual connection after MLP.
    mlp_beta_factor (`float`, *optional*, defaults to 1):
        Weight for hidden state value in residual connection after MLP.

```python
>>> from transformers import MiniMaxModel, MiniMaxConfig

>>> # Initializing a MiniMax style configuration
>>> configuration = MiniMaxConfig()

>>> # Initializing a model from the MiniMax style configuration
>>> model = MiniMaxModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```minimaxpast_key_valuescolwiserowwisecolwise_rep)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.block_sparse_moe.gatez&layers.*.block_sparse_moe.experts.*.w1z&layers.*.block_sparse_moe.experts.*.w2z&layers.*.block_sparse_moe.experts.*.w3	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        UU l        Uc  UnX`l	        Xl
        Xl        Xl        Xl        UU l        UU l        Xpl        UU l        UU l        UU l        UU l        UU l        UU l        UU l        UU l        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        [A        U R,                  5        g s  sn"f )N)pad_token_idbos_token_ideos_token_idtie_word_embeddings      full_attentionlinear_attention )!super__init__
vocab_sizemax_position_embeddingshidden_sizeintermediate_sizenum_hidden_layersnum_attention_headssliding_windownum_key_value_heads
hidden_actinitializer_rangerms_norm_eps	use_cache
rope_thetaattention_dropouthead_dimnum_experts_per_toknum_local_expertsoutput_router_logitsrouter_aux_loss_coefrouter_jitter_noiselayer_types
block_sizefull_attn_alpha_factorfull_attn_beta_factorlinear_attn_alpha_factorlinear_attn_beta_factormlp_alpha_factormlp_beta_factorrangeboolr   )$selfr    r"   r#   r$   r%   r'   r.   r(   r!   r)   r*   r+   r   r   r   r   r,   r&   r-   r/   r0   r1   r2   r3   r4   r5   r6   r7   r8   r9   r:   r;   kwargsi	__class__s$                                      i/var/www/html/shao/venv/lib/python3.13/site-packages/transformers/models/minimax/configuration_minimax.pyr   MiniMaxConfig.__init__   sd   H 	 	
%%% 3		

 	
 %'>$&!2!2#6 , &"5#6 $!2("$!2 #6 !2$8!$8!#6 &$&<#%:"(@%'>$ 0.#W\]a]s]sWt WtRSD!a%1$5$5 ;MMWt D 	d../ s   8#D9)r-   r5   r6   r7   r.   r(   r"   r)   r#   r4   r8   r9   r!   r:   r;   r%   r/   r$   r'   r0   r1   r*   r,   r2   r3   r&   r+   r    ) i }  i   i 8      rD      Nsilui   g{Gz?gh㈵>TNr   r   Fg    .AN        r   rE   FgMbP?rG   N   r   r   r   r   r   r   )__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planr   __static_attributes____classcell__)rA   s   @rB   r   r      s    cJ J#4"5%.%.%.%.*72;2;2;	 &(9:#%568IJ!"_$56  )!"" !" !CR0 R0    r   N)configuration_utilsr   r   r   __all__r   rT   rB   <module>rW      s%   , KJ0$ J0Z 
rT   