
    <h                     8    S SK Jr  SSKJr   " S S\5      rS/rg)    )Optional   )PretrainedConfigc            /          ^  \ rS rSrSrSrS/r                      SS\S\S\S\S	\S
\S\S\S\S\	S\S\S\S\	S\S\	S\S\S\S\	S\
\\      S\
\\      4,U 4S jjjrSrU =r$ )
Lfm2Config   ag  
This is the configuration class to store the configuration of a [`Lfm2Model`]. It is used to instantiate a LFM2
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 LFM2-1.2B model.
e.g. [LiquidAI/LFM2-1.2B](https://huggingface.co/LiquidAI/LFM2-1.2B)

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 65536):
        Vocabulary size of the LLaMA model. Defines the number of different tokens that can be represented by the
        `inputs_ids` passed when calling [`Lfm2Model`]
    hidden_size (`int`, *optional*, defaults to 2560):
        Dimension of the hidden representations.
    intermediate_size (`int`, *optional*, defaults to 12288):
        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*, 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
        `num_attention_heads`.
    max_position_embeddings (`int`, *optional*, defaults to 128000):
        The maximum sequence length that this model might ever be used with. Lfm2 1 supports up to 2048 tokens,
        Lfm2 2 up to 4096, CodeLfm2 up to 16384.
    initializer_range (`float`, *optional*, defaults to 0.02):
        The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
    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*, defaults to 0):
        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.
    tie_word_embeddings (`bool`, *optional*, defaults to `True`):
        Whether to tie weight embeddings
    rope_theta (`float`, *optional*, defaults to 1000000.0):
        The base period of the RoPE embeddings.
    conv_bias (`bool`, *optional*, defaults to `False`):
        Whether to use bias in the conv layers.
    conv_L_cache (`int`, *optional*, defaults to 3):
        L_cache dim in the conv layers.
    block_multiple_of (`int`, *optional*, defaults to 256):
        Multiple for the `intermediate_size`.
    block_ffn_dim_multiplier (`float`, *optional*, defaults to 1.0):
        Multiplier for the `intermediate_size`.
    block_auto_adjust_ff_dim (`bool`, *optional*, defaults to `True`):
        Whether to adjust the dim of the `intermediate_size`.
    full_attn_idxs (`Optional`, *optional*):
        Index of the layers which use attention.
    layer_types (`Optional`, *optional*):
        Type of each layers.

```python
>>> from transformers import Lfm2Model, Lfm2Config

>>> # Initializing a LFM2 model
>>> configuration = Lfm2Config()

>>> # Initializing a model from the LFM2-1.2B style configuration
>>> model = Lfm2Model(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```lfm2past_key_values
vocab_sizehidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsnum_key_value_headsmax_position_embeddingsinitializer_rangenorm_eps	use_cachepad_token_idbos_token_ideos_token_idtie_word_embeddings
rope_theta	conv_biasconv_L_cacheblock_multiple_ofblock_ffn_dim_multiplierblock_auto_adjust_ff_dimfull_attn_idxslayer_typesc                   > Xl         X l        X@l        UR                  SU5      U l        Xpl        Xl        Xl        Xl        XPl	        X`l
        UU l        UU l        UR                  SU5      U l        UU l        UU l        UU l        UU l        U R"                  cA  Ub  UO[%        ['        U5      5      n['        U5       Vs/ sH  nUU;   a  SOSPM     snU l        UR                  SU5      n[(        TU ]T  " SUUUUS.UD6  g s  snf )Nthetablock_ff_dimfull_attentionconvtie_embedding)r   r   r   r    )r   r   r   getr   r   r   r   r   r   r   r   r   r   r   r   r   r    listrangesuper__init__)selfr   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r    kwargsi	__class__s                            c/var/www/html/shao/venv/lib/python3.13/site-packages/transformers/models/lfm2/configuration_lfm2.pyr,   Lfm2Config.__init__e   s$   4 %&!2 **Wj9'>$" !2 $7 #6  #( "(N<M!N!2(@%(@%&#/=/I^tTYZkTlOmN]bct]uv]uXYA4G 0V S]uvD$jj:MN 	
%%% 3		

 	
  ws   D)r   r   r   r   r   r   r   r   r    r   r   r   r   r   r   r   r   )i   i 
  i 0      r3      i  g{Gz?gh㈵>Tr         Tg    .AFr      g      ?TNN)__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferenceintfloatboolr   r)   strr,   __static_attributes____classcell__)r0   s   @r1   r   r      sT   L\ J#4"5  !&!##%#$'.#'!$(%!$*-)-.2+//=
=
 =
 	=

 =
 !=
 !=
 "%=
 !=
 =
 =
 =
 =
 =
 "=
  !=
" #=
$ %=
& '=
( #()=
* #'+=
, !c+-=
. d3i(/=
 =
    r   N)typingr   configuration_utilsr   r   __all__r'   rE   r1   <module>rI      s&     3O
! O
d .rE   