+
    ~jk                     x    R t ^ RIHt ^RIHt ^RIHt ^RIHt ]! RR7      ] ! R R]4      4       4       t	R.t
R	# )
zQwen2 model configuration)strict)PreTrainedConfig)RopeParameters)auto_docstringzQwen/Qwen2-7B)
checkpointc                      a a ] tR t^t oRtRtR.tRRRRRRRR	R
RRRRR	/tRR.R.3RRR.R.3RR.R.3/tRt	Rt
Rt^ t^ t^ tRtRtRtRtRtRtRtRtRt^tRtRtRtRtRtV 3R ltV3R  ltR!t Vt!V ;t"# )"Qwen2ConfigaQ  
Example:

```python
>>> from transformers import Qwen2Model, Qwen2Config

>>> # Initializing a Qwen2 style configuration
>>> configuration = Qwen2Config()

>>> # Initializing a model from the Qwen2-7B style configuration
>>> model = Qwen2Model(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```qwen2past_key_valueszlayers.*.self_attn.q_projcolwisezlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projrowwisezlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_projembed_tokens	input_idsinputs_embedslayershidden_statesattention_masknormiQ i   i V  silui   g{Gz?gư>TFNg        c                j  < V P                   '       d   V P                  MR V n        V P                  f   V P                  V n        V P                  fK   \        V P                  4       Uu. uF%  pV P                  e   W P                  8  d   RMRNK'  	  upV n        \        SV `$  ! R/ VB  R # u upi )Nsliding_attentionfull_attention )
use_sliding_windowsliding_windownum_key_value_headsnum_attention_headslayer_typesrangenum_hidden_layersmax_window_layerssuper__post_init__)selfkwargsi	__class__s   &, ڂ/Users/mitch_tango/dev/rabbit-r1-livekit/agent/.venv/lib/python3.14/site-packages/transformers/models/qwen2/configuration_qwen2.pyr"   Qwen2Config.__post_init__S   s    595L5L5Ld11RV##+'+'?'?D$#
 t556	  7A &&2q<R<R7R $%& 7	 D 	'' s   ++B0c                  < V ^8  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ R,          ;R&   S[;R&   S[ ;R	&   S[;R
&   S[;R&   S[;R&   S[;R&   S[S[,          R,          ;R&   S[;R&   S[ R,          ;R&   S[ ;R&   S[S[,          R,          ;R&   S[S[ ,          ;R&   S[ R,          ;R&   S[ R,          ;R&   S[ S[S[ ,          ,          R,          ;R&   # )   
vocab_sizehidden_sizeintermediate_sizer   r   Nr   
hidden_actmax_position_embeddingsinitializer_rangerms_norm_eps	use_cachetie_word_embeddingsrope_parametersr   r   r    r   attention_dropoutpad_token_idbos_token_ideos_token_id)intstrfloatboolr   dictlist)format__classdict__s   "r'   __annotate__Qwen2Config.__annotate__   st    L M N O P "Q R S T !U V t(W X Y Z !([ \ #] ^ _ ` a b %c d $d*T18e f $g h $J%i j k l cT!(m n s{(o p *#q r *#s t S	/D(/u     )r   r   r   )#__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planr+   r,   r-   r   r   r   r.   r/   r0   r1   r2   r3   r4   r   r   r    r   r5   r6   r7   r8   r"   __annotate_func____static_attributes____classdictcell____classcell__)r&   r@   s   @@r'   r   r      s      J#4"5 	$Y#Y#Y#Y )	 ) 	+(9:O%568IJ/"_$56 JK"!&(J#(#LI %48O$!%N$(K%(#L#L+/L(y  rC   r   N)rH   huggingface_hub.dataclassesr   configuration_utilsr   modeling_rope_utilsr   utilsr   r   __all__r   rC   r'   <module>rV      sL      . 3 1 # ?+G(" G(  ,G(T /rC   