
    <h'                     @   S r SSKJrJr  SSKJr  SSKJrJrJ	r	J
r
  SSKJr  \R                  " \5      r " S S\5      r " S	 S
\5      r\" SS9 " S S\5      5       r\" SS9 " S S\	5      5       r\" SS9 " S S\5      5       r\" SS9 " S S\
5      5       r/ SQrg)zPyTorch Arcee model.    )auto_docstringlogging   )LlamaConfig)LlamaForCausalLMLlamaForQuestionAnsweringLlamaForSequenceClassificationLlamaForTokenClassification)NemotronMLPc                   p   ^  \ rS rSrSrSrSSSSSS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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_projc                    > [         TU ]  " S0 SU_SU_SU_SU_SU_SU_SU_SU_S	U	_S
U
_SU_SU_SU_SU_SU_SU_SU_SU_SU_SU_SU_UD6  U ?g )N
vocab_sizehidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsnum_key_value_heads
hidden_actmax_position_embeddingsinitializer_rangerms_norm_eps	use_cachepad_token_idbos_token_ideos_token_idtie_word_embeddings
rope_thetarope_scalingattention_biasattention_dropoutmlp_biashead_dim )super__init__pretraining_tp)selfr   r   r   r   r   r   r   r   r   r   r   r   r   r    r!   r"   r#   r$   r%   r&   r'   kwargs	__class__s                          _/var/www/html/shao/venv/lib/python3.13/site-packages/transformers/models/arcee/modular_arcee.pyr*   ArceeConfig.__init__   s    2 	 	
!	
#	
 0	
 0		

 !4	
 !4	
 "	
 %<	
 0	
 &	
  	
 &	
 &	
 &	
 !4	
  "!	
" &#	
$ *%	
& 0'	
( )	
* -	
2     r(   )i }  i 
  i H  r   r   Nrelu2i   g{Gz?gh㈵>TNi  i Fg     @NFg        FN)
__name__
__module____qualname____firstlineno____doc__
model_typebase_model_tp_planr*   __static_attributes____classcell__)r.   s   @r/   r   r       sv    _B J%.%.%.%. )"+   $!-2  2 r1   r   c                       \ rS rSrSrg)ArceeMLP   r(   Nr3   r4   r5   r6   r:   r(   r1   r/   r=   r=      s    r1   r=   zarcee-ai/AFM-4.5B)
checkpointc                       \ rS rSrSrg)ArceeForCausalLM   r(   Nr?   r(   r1   r/   rB   rB          r1   rB   c                       \ rS rSrSrg)ArceeForSequenceClassification   r(   Nr?   r(   r1   r/   rF   rF      rD   r1   rF   c                       \ rS rSrSrg)ArceeForQuestionAnswering   r(   Nr?   r(   r1   r/   rI   rI      rD   r1   rI   c                       \ rS rSrSrg)ArceeForTokenClassification   r(   Nr?   r(   r1   r/   rL   rL      rD   r1   rL   )r   rB   rI   rF   rL   
ArceeModelArceePreTrainedModelN)r7   transformers.utilsr   r   llama.configuration_llamar   llama.modeling_llamar   r   r	   r
   nemotron.modeling_nemotronr   
get_loggerr3   loggerr   r=   rB   rF   rI   rL   __all__r(   r1   r/   <module>rW      s     6 3  5 
		H	%^ + ^ B	{ 	 ./	' 	 0	 ./	%C 	 0	 ./	 9 	 0	 ./	"= 	 0	r1   