
    iT                     r    d dl mZ d dlmZ ddlmZ ddlmZ  ed      e G d d	e                    Zd	gZ	y
)    )strict)auto_docstring   )PreTrainedConfig)RopeParameterszarcee-ai/AFM-4.5B)
checkpointc                       e Zd ZU dZdZdgZdddddddZdgdgfd	d
gd	gfd	gd	gfdZdZe	e
d<   dZe	e
d<   dZe	e
d<   dZe	e
d<   dZe	e
d<   dZe	dz  e
d<   dZee
d<   dZe	e
d<   dZee
d<   dZee
d<   dZee
d <   dZe	dz  e
d!<   d"Ze	dz  e
d#<   d$Ze	ee	   z  dz  e
d%<   d&Zee
d'<   dZeez  dz  e
d(<   d&Z ee
d)<   d*Z!ee	z  e
d+<   d&Z"ee
d,<   dZ#e	dz  e
d-<    fd.Z$d/ Z% xZ&S )0ArceeConfiga  
    ```python
    >>> from transformers import ArceeModel, ArceeConfig

    >>> # Initializing an Arcee AFM-4.5B-Base style configuration
    >>> configuration = ArceeConfig()

    >>> # Initializing a model from the AFM-4.5B-Base style configuration
    >>> model = ArceeModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```arcee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.up_projzlayers.*.mlp.down_proj	input_idsinputs_embedshidden_statesattention_mask)embed_tokenslayersnormi }  
vocab_sizei 
  hidden_sizei H  intermediate_size    num_hidden_layersnum_attention_headsNnum_key_value_headsrelu2
hidden_acti   max_position_embeddingsg{Gz?initializer_rangegh㈵>rms_norm_epsT	use_cachepad_token_idi  bos_token_idi eos_token_idFtie_word_embeddingsrope_parametersattention_biasg        attention_dropoutmlp_biashead_dimc                     | j                   | j                  | j                  z  | _         | j                  | j                  | _        t	        |   di | y )N )r+   r   r   r   super__post_init__)selfkwargs	__class__s     ~/var/www/vps2.regionflexible.com/Desarrollo/venv/lib/python3.12/site-packages/transformers/models/arcee/configuration_arcee.pyr/   zArceeConfig.__post_init__S   sO    ==  ,,0H0HHDM##+'+'?'?D$''    c                     | j                   | j                  z  dk7  r&t        d| j                    d| j                   d      y)zOPart of `@strict`-powered validation. Validates the architecture of the config.r   zThe hidden size (z6) is not a multiple of the number of attention heads (z).N)r   r   
ValueError)r0   s    r3   validate_architecturez!ArceeConfig.validate_architecture[   sS    d666!;#D$4$4#5 622327  <r4   )'__name__
__module____qualname____doc__
model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planr   int__annotations__r   r   r   r   r   r   strr   r    floatr!   r"   boolr#   r$   r%   listr&   r'   r   dictr(   r)   r*   r+   r/   r7   __classcell__)r2   s   @r3   r
   r
      so    J#4"5%.%.%.%. )"+ &(9:#%568IJ!"_$56 JK"s"s!!&*t*J#'S'#u#L%It#L#*#%L#*%+1L#S	/D(1 %%48O^d*T18 ND %(us{(HdHcDj(r4   r
   N)
huggingface_hub.dataclassesr   transformers.utilsr   configuration_utilsr   modeling_rope_utilsr   r
   __all__r-   r4   r3   <module>rM      sJ   * / - 3 1 ./B" B  0BJ /r4   