
    Z j(                     l    S SK Jr  SSKJr  SSKJr  SSKJr  \" SS9\ " S S	\5      5       5       rS	/r	g
)    )strict   )PreTrainedConfig)RopeParameters)auto_docstringztencent/Youtu-LLM-2B)
checkpointc                      ^  \ rS rSr% SrSrS/rSSSS.rS/S	/4S
S/S
/4S
/S
/4S.r0 r	Sr
\\S'   Sr\\S'   Sr\\S'   Sr\\S'   Sr\\S'   Sr\\S'   Sr\\S'   Sr\S-  \S'   Sr\\S'   Sr\S-  \S '   Sr\\S!'   S"r\\S#'   S$r\\S%'   Sr\S-  \S&'   S'r\\S('   S)r\\S*'   Sr\S-  \S+'   S,r \S-  \S-'   S.r!\\"\   -  S-  \S/'   S)r#\\S0'   Sr$\%\&-  S-  \S1'   S)r'\S-  \S2'   S3r(\\S4'   S5r)\\-  S-  \S6'   Sr*\S-  \S7'   U 4S8 jr+S9r,U =r-$ ):YoutuConfig"   a  
rope_interleave (`bool`, *optional*, defaults to `True`):
    Whether to interleave the rotary position embeddings.
embedding_initializer_range (`float`, *optional*):
    The standard deviation of the truncated_normal_initializer for initializing all embedding matrices.

```python
>>> from transformers import YoutuModel, YoutuConfig
>>> # Initializing a Youtu-LLM-2B style configuration
>>> configuration = YoutuConfig()
>>> # Accessing the model configuration
>>> configuration = model.config
```youtupast_key_valuescolwiserowwise)zlayers.*.mlp.gate_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   intermediate_size    num_hidden_layers   num_attention_headsnum_key_value_headsi   kv_lora_ranki   Nq_lora_rank@   qk_rope_head_dim   
v_head_dimqk_nope_head_dimsilu
hidden_acti   max_position_embeddingsinitializer_rangegư>rms_norm_epsT	use_cachepad_token_idi  bos_token_idi eos_token_idtie_word_embeddingsrope_parametersrope_interleaveFattention_biasg        attention_dropoutembedding_initializer_rangec                   > U R                   c2  U R                  S:w  a  SSU R                  -  S-  -  U l         OSU l         U R                  =(       d    SU R                   -  U l        U R                  c  U R                  U l        U R
                  U R                  -   U l        U R                  U l        [        TU ](  " S0 UD6  g )Nr   g       @g      @g      ?g{Gz? )r)   r   r4   r   r   r%   r"   qk_head_dimhead_dimsuper__post_init__)selfkwargs	__class__s     ~/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/youtu/configuration_youtu.pyr:   YoutuConfig.__post_init__[   s    !!)1$),d6F6F0F3/N)N&)-&+/+K+K+ksUYUkUkOk(##+'+'?'?D$0043H3HH--''    )r4   r8   r)   r   r7   ).__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planattribute_mapr   int__annotations__r   r   r   r   r   r   r    r"   r$   r%   r'   strr(   r)   floatr*   r+   boolr,   r-   r.   listr/   r0   r   dictr1   r2   r3   r4   r:   __static_attributes____classcell__)r=   s   @r>   r
   r
   "   s    J#4"5"+ )"+ &(9:#%568IJ!"_$56
 MJK!s!s!!!!L#"Kt"c Jd
 cJ#)S)&*ut|*L%It#L#*#%L#*%+1L#S	/D(1 $$48O^d*T18#'OTD[' ND ,/us{T)/044( (r@   r
   N)
huggingface_hub.dataclassesr   configuration_utilsr   modeling_rope_utilsr   utilsr   r
   __all__r6   r@   r>   <module>rY      sJ   6 / 3 1 # 12D(" D(  3D(N /r@   