
    Z jT\                     h   S SK Jr  S SKJr  S SKrS SKJr  SSKJr  SSKJ	r	J
r
  SSKJr  SS	KJr  SS
KJrJr  SSKJr  SSKJrJrJr  SSKJrJr  SSKJrJr  SSKJrJ r   SSK!J"r"  SSK#J$r$J%r%J&r&  SSK'J(r(J)r)  SSK*J+r+  SSK,J-r-   " S S\R\                  5      r/ " S S\R\                  5      r0S r1S\Rd                  S\3S\Rd                  4S jr4 S;S\R\                  S \Rd                  S!\Rd                  S"\Rd                  S#\Rd                  S-  S$\5S%\5S&\"\$   4S' jjr6S<S( jr7 " S) S*\R\                  5      r8\" S+5       " S, S-\R\                  5      5       r9 " S. S/\5      r:\% " S0 S1\ 5      5       r;\% " S2 S3\;5      5       r<\% " S4 S5\;\5      5       r= " S6 S7\\;5      r> " S8 S9\\;5      r?/ S:Qr@g)=    )Callable)OptionalN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs   )
Phi3Configc                   b   ^  \ rS rSrU 4S jrS\R                  S\R                  4S jrSrU =r	$ )Phi3MLP1   c                    > [         TU ]  5         Xl        [        R                  " UR
                  SUR                  -  SS9U l        [        R                  " UR                  UR
                  SS9U l        [        UR                     U l        g )N   Fbias)super__init__configr   Linearhidden_sizeintermediate_sizegate_up_proj	down_projr   
hidden_actactivation_fnselfr*   	__class__s     w/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/phi3/modeling_phi3.pyr)   Phi3MLP.__init__2   sn    IIf&8&8!f>V>V:V]bc6#;#;V=O=OV[\#F$5$56    hidden_statesreturnc                     U R                  U5      nUR                  SSS9u  p2X R                  U5      -  nU R                  U5      $ )Nr%   dim)r.   chunkr1   r/   )r3   r8   	up_statesgates       r5   forwardPhi3MLP.forward:   sH    %%m4	#//!/4 2 24 88	~~i((r7   )r1   r*   r/   r.   )
__name__
__module____qualname____firstlineno__r)   torchFloatTensorrA   __static_attributes____classcell__r4   s   @r5   r"   r"   1   s,    7)U%6%6 )5;L;L ) )r7   r"   c                      ^  \ rS rSr% \R
                  \S'   SS\4U 4S jjjr\	   SS\S-  S\
S   S\S-  S	\S
\4   4S jj5       r\R                  " 5       \S 5       5       rSrU =r$ )Phi3RotaryEmbeddingC   inv_freqNr*   c                   > [         TU ]  5         UR                  U l        UR                  U l        Xl        U R
                  R                  S   U l        U R                  nU R                  S:w  a  [        U R                     nU" U R
                  U5      u  o@l
        U R                  SUSS9  U R                  SUR                  5       SS9  g )N	rope_typedefaultrO   F)
persistentoriginal_inv_freq)r(   r)   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr*   rope_parametersrQ   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r3   r*   devicerope_init_fnrO   r4   s        r5   r)   Phi3RotaryEmbedding.__init__F   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L((ZeD0(..2BuUr7   r]   ztorch.deviceseq_lenr9   ztorch.Tensorc           	      j   U R                   S   nU R                   R                  SS5      n[        U SS5      =(       d    U R                  U R                  -  n[        XT-  5      nSnSU[        R                  " SUS[        R                  S9R                  U[        R                  S	9U-  -  -  nX4$ )
aH  
Computes the inverse frequencies according to the original RoPE implementation
Args:
    config ([`~transformers.PreTrainedConfig`]):
        The model configuration.
    device (`torch.device`):
        The device to use for initialization of the inverse frequencies.
    seq_len (`int`, *optional*):
        The current sequence length. Unused for this type of RoPE.
Returns:
    Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
    post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).

rope_thetapartial_rotary_factorg      ?head_dimNr   r%   dtype)r]   rf   )rX   getgetattrr,   num_attention_headsintrG   arangeint64tofloat)	r*   r]   r`   baserc   rd   r=   attention_factorrO   s	            r5   rY   3Phi3RotaryEmbedding.compute_default_rope_parametersV   s    & %%l3 & 6 6 : :;RTW X6:t4h8J8JfNhNh8h(23 U\\!S!5;;?BB&X]XcXcBdgjjk
 ))r7   c                 L   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r;   r   mpscpuF)device_typeenabledr%   r<   re   )rO   rn   expandshaperm   r]   
isinstancetypestrr   	transposerG   catcosrZ   sinrf   )
r3   xposition_idsinv_freq_expandedposition_ids_expandedru   freqsembr~   r   s
             r5   rA   Phi3RotaryEmbedding.forwardv   sN    !MM$4-8>>@GGHZHZ[\H]_acdehhijiqiqr ,QaZ 8 > > @'1!((--'E'E!((--[`J`ahhmmfkUC&,,.1F1L1L1NNYYZ[]^_E))UN3C'')d444C'')d444C	 D vvAGGv$cff177f&;;; DCs   BF
F#)rZ   r*   rV   rW   rQ   N)NNN)rC   rD   rE   rF   rG   Tensor__annotations__r    r)   staticmethodr   rj   tuplern   rY   no_gradr   rA   rI   rJ   rK   s   @r5   rM   rM   C   s    llVz V V  $(+/"*T!*(* t* 
~u$	%	* *> ]]_<  <r7   rM   c                     U SSU R                   S   S-  24   nU SU R                   S   S-  S24   n[        R                  " U* U4SS9$ )z*Rotates half the hidden dims of the input..Nr;   r%   r<   )rx   rG   r}   )r   x1x2s      r5   rotate_halfr      sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r7   r8   n_repr9   c                     U R                   u  p#pEUS:X  a  U $ U SS2SS2SSS2SS24   R                  X#XU5      n U R                  X#U-  XE5      $ )z
This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
r   N)rx   rw   reshape)r8   r   batchnum_key_value_headsslenrd   s         r5   	repeat_kvr      s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr7   modulequerykeyvalueattention_maskscalingdropoutkwargsc                    [        X R                  5      n[        X0R                  5      n	[        R                  " XR	                  SS5      5      U-  n
Ub  X-   n
[
        R                  R                  U
S[        R                  S9R                  UR                  5      n
[
        R                  R                  XU R                  S9n
[        R                  " X5      nUR	                  SS5      R                  5       nX4$ )Nr%   r   r;   )r=   rf   )ptrainingr   )r   num_key_value_groupsrG   matmulr|   r   
functionalsoftmaxfloat32rm   rf   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightsattn_outputs               r5   eager_attention_forwardr      s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!#4==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r7   c                 N   UR                  U5      nUR                  U5      nUR                  S   nU SSU24   U SUS24   pvUSSU24   USUS24   p[        R                  " Xb-  [	        U5      U-  -   U/SS9n
[        R                  " X-  [	        U5      U-  -   U	/SS9nX4$ )aI  Applies Rotary Position Embedding to the query and key tensors.

Args:
    q (`torch.Tensor`): The query tensor.
    k (`torch.Tensor`): The key tensor.
    cos (`torch.Tensor`): The cosine part of the rotary embedding.
    sin (`torch.Tensor`): The sine part of the rotary embedding.
    unsqueeze_dim (`int`, *optional*, defaults to 1):
        The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
        sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
        that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and
        k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes
        cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have
        the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2.
Returns:
    `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
r;   .Nr<   )	unsqueezerx   rG   r}   r   )qkr~   r   unsqueeze_dim
rotary_dimq_rotq_passk_rotk_passq_embedk_embeds               r5   apply_rotary_pos_embr      s    $ --
&C
--
&C2Jc;J;&'3
+;)<6c;J;&'3
+;)<6ii%++e*<s*BCVLRTUGii%++e*<s*BCVLRTUGr7   c                   0  ^  \ rS rSrSrSS\S\S-  4U 4S jjjr SS\R                  S\
\R                  \R                  4   S	\R                  S-  S
\S-  S\\   S\
\R                  \R                  S-  \
\R                     S-  4   4S jjrSrU =r$ )Phi3Attention   z=Multi-headed attention from 'Attention Is All You Need' paperNr*   	layer_idxc                 p  > [         TU ]  5         Xl        X l        [	        USUR
                  UR                  -  5      U l        UR                  UR                  -  U l	        UR                  U l        U R                  S-  U l
        UR                  U l        SU l        UR                  U R                  -  SUR                  U R                  -  -  -   n[        R                  " UR                  U R                  -  UR
                  SS9U l        [        R                  " UR
                  USS9U l        g )Nrd   g      Tr%   Fr&   )r(   r)   r*   r   rh   r,   ri   rd   r   r   r   attention_dropout	is_causalr   r+   o_projqkv_proj)r3   r*   r   op_sizer4   s       r5   r)   Phi3Attention.__init__   s    "
F4F4F&JdJd4de$*$>$>&B\B\$\!#)#=#= }}d*!'!9!9,,t}}<qFD^D^aeananDn?ooii : :T]] JFL^L^ejk		&"4"4gEJr7   r8   position_embeddingsr   past_key_valuesr   r9   c           
         UR                   S S n/ UQSPU R                  P7nU R                  U5      nU R                  R                  U R                  -  n	USS U	24   n
USXU R
                  U R                  -  -   24   nUSXR
                  U R                  -  -   S 24   nU
R                  U5      R                  SS5      n
UR                  U5      R                  SS5      nUR                  U5      R                  SS5      nUu  p[        XX5      u  pUb  UR                  XU R                  5      u  p[        R                  " U R                  R                  [        5      nU" U U
UUU4U R                  (       d  SOU R                   U R"                  [%        U R                  SS 5      S.UD6u  nnUR&                  " / UQSP76 R)                  5       nU R+                  U5      nUU4$ )Nr;   .r   r%           sliding_window)r   r   r   )rx   rd   r   r*   ri   r   viewr|   r   updater   r   get_interface_attn_implementationr   r   r   r   rh   r   r   r   )r3   r8   r   r   r   r   input_shapehidden_shapeqkv	query_posquery_statesr   r   r~   r   attention_interfacer   r   s                     r5   rA   Phi3Attention.forward   s    $))#2.88b8$--8mmM*KK33dmmC	3

?+id6N6NQUQ^Q^6^*^^^_
3	,D,Dt}},T T VVW#((6@@AF__\2<<QB
#((6@@AF&#7RU#[ &'6'='=jX\XfXf'g$J(?(M(MKK,,.E)
 %8
%
  $}}C$2H2HLL"4;;0@$G
%
 
%
!\ "));;;;FFHkk+.L((r7   )
r   r*   rd   r   r   r   r   r   r   r   r   )rC   rD   rE   rF   __doc__r    rj   r)   rG   r   r   r   r   r   rA   rI   rJ   rK   s   @r5   r   r      s    GKz KcDj K K( )--)||-) #5<<#=>-) t+	-)
 -) -.-) 
u||U\\D0%2E2LL	M-) -)r7   r   RMSNormc                   x   ^  \ rS rSrS
S\SS4U 4S jjjrS\R                  S\R                  4S jrS r	S	r
U =r$ )Phi3RMSNormi  epsr9   Nc                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)z*
Phi3RMSNorm is equivalent to T5LayerNorm
N)r(   r)   r   	ParameterrG   onesweightvariance_epsilon)r3   r,   r   r4   s      r5   r)   Phi3RMSNorm.__init__  s/     	ll5::k#:; #r7   r8   c                    UR                   nUR                  [        R                  5      nUR	                  S5      R                  SSS9nU[        R                  " X0R                  -   5      -  nU R                  UR                  U5      -  $ )Nr%   r;   T)keepdim)	rf   rm   rG   r   powmeanrsqrtr   r   )r3   r8   input_dtypevariances       r5   rA   Phi3RMSNorm.forward  sw    #))%((7 $$Q',,R,>%H?T?T4T(UU{{]--k:::r7   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)r   r   rx   r   )r3   s    r5   
extra_reprPhi3RMSNorm.extra_repr#  s*    ))*+6$2G2G1HIIr7   )r   r   )gư>)rC   rD   rE   rF   rn   r)   rG   r   rA   r   rI   rJ   rK   s   @r5   r   r     sB    $ $$ $ $;U\\ ;ell ;J Jr7   r   c                   T  ^  \ rS rSrS\S\4U 4S jjr     SS\R                  S\R                  S-  S\R                  S-  S	\
S-  S
\S-  S\\R                  \R                  4   S-  S\\   S\\R                  \\R                  \R                  4   S-  4   4S jjrSrU =r$ )Phi3DecoderLayeri'  r*   r   c                   > [         TU ]  5         UR                  U l        [        XS9U l        [        U5      U l        [        UR                  UR                  S9U l	        [        UR                  UR                  S9U l
        Xl        [        R                  " UR                  5      U l        [        R                  " UR                  5      U l        g )N)r*   r   r   )r(   r)   r,   r   	self_attnr"   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr*   r   Dropoutresid_pdropresid_attn_dropoutresid_mlp_dropoutr3   r*   r   r4   s      r5   r)   Phi3DecoderLayer.__init__(  s    !--&fJ6?*6+=+=6CVCVW(3F4F4FFL_L_(`%"$**V-?-?"@!#F,>,>!?r7   Nr8   r   r   r   	use_cacher   r   r9   c           
          UnU R                  U5      nU R                  " SUUUUUUS.UD6u  pXR                  U5      -   nUnU R                  U5      nU R	                  U5      nXR                  U5      -   nU$ )N)r8   r   r   r   r   r    )r   r   r   r   r   r   )
r3   r8   r   r   r   r   r   r   residualself_attn_weightss
             r5   rA   Phi3DecoderLayer.forward3  s     !,,];+/>> ,
')%+ 3,
 ,
( !#:#:=#II 55mD/ #9#9-#HHr7   )r*   r,   r   r   r   r   r   r   )NNNFN)rC   rD   rE   rF   r    rj   r)   rG   r   
LongTensorr   boolr   r   r   rH   rA   rI   rJ   rK   s   @r5   r   r   '  s    	@z 	@c 	@ /304(,!&HL|| t+ &&-	
  $; #5<<#=>E -. 
u  %(9(95;L;L(L"MPT"TT	U r7   r   c                   V    \ rS rSr% \\S'   SrSrS/rS/r	Sr
SrSrSrSr\\S.rSrS	rg
)Phi3PreTrainedModeliR  r*   modelTr   r   )r8   
attentionsz0.0.5r   N)rC   rD   rE   rF   r    r   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputs_versionrI   r   r7   r5   r  r  R  sX    &*#+,#4"5N!"&)# Hr7   r  c                     ^  \ rS rSrS\4U 4S jjr\\\      SS\	R                  S-  S\	R                  S-  S\	R                  S-  S\S-  S	\	R                  S-  S
\S-  S\\   S\4S jj5       5       5       rSrU =r$ )	Phi3Modelif  r*   c           	        > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [        UR                  UR                  S9U l        [#        US9U l        SU l        U R)                  5         g s  snf )Nr   r*   F)r(   r)   pad_token_idpadding_idx
vocab_sizer   	Embeddingr,   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normrM   
rotary_embgradient_checkpointing	post_initr   s      r5   r)   Phi3Model.__init__h  s     !.. ++LL):):F<N<NPTP`P`ammBGH`H`BabBaYf0Bab
   2 28K8KL	-V<&+# 	 cs   C?N	input_idsr   r   r   inputs_embedsr   r   r9   c           
         US L US L-  (       a  [        S5      eUc  U R                  U5      nU(       a  Uc  [        U R                  S9nUcU  Ub  UR	                  5       OSn[
        R                  " UR                  S   UR                  S9U-   nUR                  S5      nU R                  R                  c  [        O[        n	U	" U R                  UUUUS9n
UnU R                  XS9nU R                  S U R                  R                    H  nU" U4U
UUUUS.UD6nM     U R!                  U5      n[#        UU(       a  US	9$ S S	9$ )
Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r   )r]   )r*   r%  r   r   r   )r   )r   r   r   r   r   )last_hidden_stater   )
ValueErrorr  r	   r*   get_seq_lengthrG   rk   rx   r]   r   r   r   r   r   r  r  r  r   )r3   r$  r   r   r   r%  r   r   past_seen_tokensmask_functioncausal_maskr8   r   decoder_layers                 r5   rA   Phi3Model.forwardx  sm    -t";<YZZ  --i8M0*$++>OCRC^==?de <<(;(;A(>}G[G[\_ooL'11!4L.2kk.H.H.P*Vw#;;')+%
 &"oomoW![[)H4;;+H+HIM)*) /#$7 M J 		-0&+/8O
 	
>B
 	
r7   )r  r!  r  r  r  r   r  )NNNNNN)rC   rD   rE   rF   r    r)   r   r   r   rG   r  r   r   rH   r  r   r   r   rA   rI   rJ   rK   s   @r5   r  r  f  s    z     .2.204(,26!%2
##d*2
 t+2
 &&-	2

 2
 ((4/2
 $;2
 +,2
 
!2
    2
r7   r  c                   l  ^  \ rS rSrSS0rSS0rSS/S/40rU 4S jr\\	        SS
\
R                  S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\\
R                  -  S\\   S\4S jj5       5       r      SU 4S jjrSrU =r$ )Phi3ForCausalLMi  zlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr8   logitsc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g )NFr&   )
r(   r)   r  r  r  r   r+   r,   r1  r"  r2   s     r5   r)   Phi3ForCausalLM.__init__  sU     v&
 ++yy!3!3V5F5FUS 	r7   Nr$  r   r   r   r%  labelsr   logits_to_keepr   r9   c	           
      |   U R                   " SUUUUUUS.U	D6n
U
R                  n[        U[        5      (       a  [	        U* S5      OUnU R                  USS2USS24   5      nSnUb)  U R                  " SXU R                  R                  S.U	D6n[        UUU
R                  U
R                  U
R                  S9$ )ai  
Example:

```python
>>> from transformers import AutoTokenizer, Phi3ForCausalLM

>>> model = Phi3ForCausalLM.from_pretrained("meta-phi3/Phi3-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-phi3/Phi3-2-7b-hf")

>>> prompt = "Hey, are you conscious? Can you talk to me?"
>>> inputs = tokenizer(prompt, return_tensors="pt")

>>> # Generate
>>> generate_ids = model.generate(inputs.input_ids, max_length=30)
>>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
"Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
```)r$  r   r   r   r%  r   N)r3  r6  r  )lossr3  r   r8   r  r   )r  r'  ry   rj   slicer1  loss_functionr*   r  r   r   r8   r  )r3   r$  r   r   r   r%  r6  r   r7  r   outputsr8   slice_indicesr3  r9  s                  r5   rA   Phi3ForCausalLM.forward  s    > ,0:: ,
)%+',
 ,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r7   c                 &  > U(       ap  [        U R                  S5      (       aU  UR                  S   U R                  R                  S-   :  a+  UR	                  5       n	XR                  R                  ::  a  S n[
        TU ]  " SUUUUUUUS.UD6n
U
$ )N original_max_position_embeddingsr   )r$  r   r   r%  r   r   r7  r   )hasattrr*   rx   r@  r)  r(   prepare_inputs_for_generation)r3   r$  r   r   r%  r   r   r7  r   past_lengthmodel_inputsr4   s              r5   rB  -Phi3ForCausalLM.prepare_inputs_for_generation  s    " %GHH"dkk&R&RUV&VV)88:KkkJJJ"&w< 	
+)'%)	
 	
 r7   )r1  r  r  )NNNNNNNr   )NNNNTN)rC   rD   rE   rF   _tied_weights_keys_tp_plan_pp_planr)   r   r   rG   r  r   r   rH   r  rj   r   r   r   rA   rB  rI   rJ   rK   s   @r5   r0  r0    s6   *,GH23H_-z:;H  .2.204(,26*.!%-.6
##d*6
 t+6
 &&-	6

 6
 ((4/6
   4'6
 $;6
 ell*6
 +,6
 
 6
  6
v # #r7   r0  c                       \ rS rSrSrg)Phi3ForSequenceClassificationi  r   NrC   rD   rE   rF   rI   r   r7   r5   rJ  rJ        r7   rJ  c                       \ rS rSrSrg)Phi3ForTokenClassificationi#  r   NrK  r   r7   r5   rN  rN  #  rL  r7   rN  )r  r  r0  rJ  rN  )r   )r   )Acollections.abcr   typingr   rG   r   activationsr   cache_utilsr   r	   
generationr
   integrationsr   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   utils.output_capturingr   configuration_phi3r    Moduler"   rM   r   r   rj   r   rn   r   r   r   r   r   r  r  r0  rJ  rN  __all__r   r7   r5   <module>rb     s  , %    ! . ) 7 R B 
 P K F & I I G 5 *)bii )$@<")) @<F(	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%2<?)BII ?)D Y'J")) J (J((1 (V /  & F
# F
 F
R k)? k k\	$DFY 		!>@S 	r7   