
    <h*                     8    S SK Jr  S SKJr   " S S\5      rS/rg)   )PretrainedConfig)rope_config_validationc                      ^  \ rS rSrSrSrS/r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$ )ArceeConfig   aG  
This is the configuration class to store the configuration of a [`ArceeModel`]. It is used to instantiate an Arcee
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 AFM-4.5B-Base.

Pre-trained weights are available at
[arcee-ai/AFM-4.5B](https://huggingface.co/arcee-ai/AFM-4.5B)
and were used to build the examples below.

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 Arcee model. Defines the number of different tokens that can be represented by the
        `inputs_ids` passed when calling [`ArceeModel`]
    hidden_size (`int`, *optional*, defaults to 2560):
        Dimension of the hidden representations.
    intermediate_size (`int`, *optional*, defaults to 18432):
        Dimension 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 checkout [this
        paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
        `num_attention_heads`.
    hidden_act (`str` or `function`, *optional*, defaults to `"relu2"`):
        The non-linear activation function (function or string) in the decoder.
    max_position_embeddings (`int`, *optional*, defaults to 4096):
        The maximum sequence length that this model might ever be used with. AFM-4.5B-Base supports up to 16384 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*):
        Padding token id.
    bos_token_id (`int`, *optional*, defaults to 128000):
        Beginning of stream token id.
    eos_token_id (`int`, *optional*, defaults to 128001):
        End of stream token id.
    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', 'yarn'], 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 'yarn'. The original max position embeddings used during pretraining.
            `attention_factor` (`float`, *optional*):
                Used with 'yarn'. 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.
    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_attention_heads

```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normc                   > [         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        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        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_sizeintermediate_sizenum_hidden_layersnum_attention_headsnum_key_value_heads
hidden_actinitializer_rangerms_norm_eps	use_cache
rope_thetarope_scalingattention_biasattention_dropoutmlp_biashead_dimr   )selfr   r   r    r!   r"   r#   r$   r   r%   r&   r'   r   r   r   r   r(   r)   r*   r+   r,   r-   kwargs	__class__s                          e/var/www/html/shao/venv/lib/python3.13/site-packages/transformers/models/arcee/configuration_arcee.pyr   ArceeConfig.__init__   s    2 	 	
%%% 3		

 	
 %'>$&!2!2#6  &"5#6 $!2("$(,!2 $,$8d>N>NRVRjRj>j (Vt7H7H-H-1->->v-FDk*t$    )r*   r+   r-   r$   r   r%   r    r   r,   r"   r!   r#   r&   r)   r(   r'   r   )i }  i 
  i H      r4   Nrelu2i   g{Gz?gh㈵>TNi  i Fg     @NFg        FN)__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planr   __static_attributes____classcell__)r0   s   @r1   r   r      s    _B J#4"5%.%.%.%. )"+ &(9:#%568IJ!"_$56   $!-:% :%r3   r   N)configuration_utilsr   modeling_rope_utilsr   r   __all__r   r3   r1   <module>rD      s&   , 4 9l%" l%^ /r3   