
    fTh                        S SK Jr  S SKJrJrJr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  SS
KJr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!  SSK"J#r#J$r$J%r%J&r&J'r'  SSK(J)r)  \&" 5       (       a  S SK*J+r+  SSK,J-r-  \'R\                  " \/5      r0S r1S8S jr2S\Rf                  S\4S\Rf                  4S jr5 S9S\	Rl                  S\Rf                  S\Rf                  S\Rf                  S\\Rf                     S\7S\74S  jjr8 " S! S"\	Rl                  5      r9 " S# S$\	Rl                  5      r: " S% S&\	Rl                  5      r; " S' S(\	Rl                  5      r<\$ " S) S*\5      5       r=\$ " S+ S,\=5      5       r> " S- S.\\#5      r?\$ " S/ S0\=\5      5       r@\$" S1S29 " S3 S4\=5      5       rA\$ " S5 S6\=5      5       rB/ S7QrCg):    )partial)CallableOptionalTupleUnionN   )ACT2FN)CacheDynamicCache)GenerationMixin)AttentionMaskConverter)FlashAttentionKwargs)BaseModelOutputWithPastCausalLMOutputWithPast SequenceClassifierOutputWithPastTokenClassifierOutput)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)
LossKwargsauto_docstringcan_return_tupleis_torch_flex_attn_availablelogging   )	PhiConfig)	BlockMask)make_flex_block_causal_maskc                     U SSU R                   S   S-  24   nU SU R                   S   S-  S24   n[        R                  " U* U4SS9$ )z*Rotates half the hidden dims of the input..N   dim)shapetorchcat)xx1x2s      \/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/phi/modeling_phi.pyrotate_halfr-   (   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''    c                     UR                  U5      nUR                  U5      nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nXg4$ )a  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.
    position_ids (`torch.Tensor`, *optional*):
        Deprecated and unused.
    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.
)	unsqueezer-   )qkcossinposition_idsunsqueeze_dimq_embedk_embeds           r,   apply_rotary_pos_embr9   /   sS    ( --
&C
--
&Cw;q>C/0Gw;q>C/0Gr.   hidden_statesn_repreturnc                     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)r&   expandreshape)r:   r;   batchnum_key_value_headsslenhead_dims         r,   	repeat_kvrD   J   s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr.   modulequerykeyvalueattention_maskscalingdropoutc                 @   [        X R                  5      n[        X0R                  5      n	[        R                  " XR	                  SS5      5      U-  n
Ub"  US S 2S S 2S S 2S UR
                  S   24   n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$ )Nr#   r   r"   )r%   dtype)ptrainingr   )rD   num_key_value_groupsr'   matmul	transposer&   nn
functionalsoftmaxfloat32torN   rK   rP   
contiguous)rE   rF   rG   rH   rI   rJ   rK   kwargs
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r,   eager_attention_forwardr`   V   s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#1==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r.   c                   <  ^  \ rS rSrSrS\S\4U 4S jjr  SS\R                  S\
\R                  \R                  4   S\\R                     S	\\   S
\\R                     S\
\R                  \\R                     \\
\R                        4   4S jjrSrU =r$ )PhiAttentionp   z=Multi-headed attention from 'Attention Is All You Need' paperconfig	layer_idxc                   > [         TU ]  5         Xl        X l        [	        USUR
                  UR                  -  5      U l        UR                  UR                  -  U l	        U R                  S-  U l
        UR                  U l        SU l        [        R                  " UR
                  UR                  U R                  -  SS9U l        [        R                  " UR
                  UR                  U R                  -  SS9U l        [        R                  " UR
                  UR                  U R                  -  SS9U l        [        R                  " UR                  U R                  -  UR
                  SS9U l        ['        U R                  UR(                  -  5      U l        UR,                  U l        U R,                  (       ay  [        R.                  " UR
                  UR                  -  UR0                  SS9U l        [        R.                  " UR
                  UR                  -  UR0                  SS9U l        g g )NrC   g      Tbias)epselementwise_affine)super__init__rd   re   getattrhidden_sizenum_attention_headsrC   rA   rQ   rJ   attention_dropout	is_causalrT   Linearq_projk_projv_projdenseintpartial_rotary_factorrotary_ndimsqk_layernorm	LayerNormlayer_norm_epsq_layernormk_layernormselfrd   re   	__class__s      r,   rl   PhiAttention.__init__s   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii 2 2F4N4NQUQ^Q^4^eijii 2 2F4N4NQUQ^Q^4^eijii 2 2F4N4NQUQ^Q^4^eijYYv99DMMI6K]K]dhi
0L0L LM"//!||""f&@&@@fF[F[pt D  "||""f&@&@@fF[F[pt D	 r.   r:   position_embeddingsrI   past_key_valuecache_positionr<   c                    UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
U R                  U5      R                  U5      R	                  SS5      nU R                  (       a"  U R                  U	5      n	U R                  U
5      n
Uu  pU	SS U R                  24   U	SU R                  S 24   pU
SS U R                  24   U
SU R                  S 24   nn[        UUX5      u  nn[        R                  " X4SS9n	[        R                  " UU4SS9n
Ub$  XUS.nUR                  XU R                  U5      u  p[         nU R"                  R$                  S:w  ad  U R"                  R$                  S:X  a-  UR'                  S	S
5      (       a  [(        R+                  S5        O[,        U R"                  R$                     nU" U U	U
UU4U R.                  (       d  SOU R0                  U R2                  S.UD6u  nnUR4                  " / UQSP76 R7                  5       nU R9                  U5      nUU4$ )Nr"   r   r#   .r$   )r4   r3   r   eagersdpaoutput_attentionsFz`torch.nn.functional.scaled_dot_product_attention` does not support `output_attentions=True`. Falling back to eager attention. This warning can be removed using the argument `attn_implementation="eager"` when loading the model.        )rK   rJ   )r&   rC   rs   viewrS   rt   ru   rz   r}   r~   ry   r9   r'   r(   updatere   r`   rd   _attn_implementationgetloggerwarning_oncer   rP   rp   rJ   r?   rY   rv   )r   r:   r   rI   r   r   rZ   input_shapehidden_shapequery_statesr[   r\   r3   r4   	query_rot
query_passkey_rotkey_passcache_kwargsattention_interfacer_   r]   s                         r,   forwardPhiAttention.forward   s    $))#2.88b8$--8{{=166|DNNqRST[[/44\BLLQPQR
{{=166|DNNqRST++L9L))*5J& 1 1 1112d//112 
 s/d////0sD--//0 
 2)WcO	7 yy)!8bAYY2;
%#&nUL'5'<'<ZW[WeWegs't$J(?;;++w6{{//69fjjI\^c>d>d##L
 '>dkk>^>^&_#$7	%
  $}}C$2H2HLL	%
 	%
!\ "));;;;FFHjj-L((r.   )rp   rd   rv   rC   rq   r~   rt   re   rQ   r}   rs   rz   ry   rJ   ru   )NN)__name__
__module____qualname____firstlineno____doc__r   rw   rl   r'   Tensorr   r   r
   
LongTensorr   __static_attributes____classcell__r   s   @r,   rb   rb   p   s    Gy S 8 +/59A)||A) #5<<#=>A) !.	A)
 !A) !!1!12A) 
u||Xell3XeELL>Q5RR	SA) A)r.   rb   c                   b   ^  \ rS rSrU 4S jrS\R                  S\R                  4S jrSrU =r	$ )PhiMLP   c                   > [         TU ]  5         Xl        [        UR                     U l        [        R                  " UR                  UR                  5      U l
        [        R                  " UR                  UR                  5      U l        g N)rk   rl   rd   r	   
hidden_actactivation_fnrT   rr   rn   intermediate_sizefc1fc2r   rd   r   s     r,   rl   PhiMLP.__init__   sb    #F$5$5699V//1I1IJ99V55v7I7IJr.   r:   r<   c                 l    U R                  U5      nU R                  U5      nU R                  U5      nU$ r   )r   r   r   )r   r:   s     r,   r   PhiMLP.forward   s4    /**=9/r.   )r   rd   r   r   )
r   r   r   r   rl   r'   r   r   r   r   r   s   @r,   r   r      s)    KU\\ ell  r.   r   c                     ^  \ rS rSrS\S\4U 4S jjr       SS\R                  S\	\R                     S\	\R                     S\	\\R                        S	\	\   S
\	\   S\	\R                     S\	\\R                  \R                  4      S\\R                  \	\\R                  \R                  4      4   4S jjrSrU =r$ )PhiDecoderLayer   rd   re   c                   > [         TU ]  5         [        XS9U l        [	        U5      U l        [        R                  " UR                  UR                  S9U l
        [        R                  " UR                  5      U l        g )N)re   ri   )rk   rl   rb   	self_attnr   mlprT   r{   rn   r|   input_layernormDropoutresid_pdropresid_dropoutr   s      r,   rl   PhiDecoderLayer.__init__   s[    %fB&>!||F,>,>FDYDYZZZ(:(:;r.   r:   rI   r5   r   r   	use_cacher   r   r<   c	                     Un
U R                  U5      nU R                  " SUUUUUUUUS.U	D6u  pU R                  U5      nU R                  U R                  U5      5      nX-   U
-   nU4nU(       a  X4-  nU$ )N)r:   rI   r5   r   r   r   r   r    )r   r   r   r   )r   r:   rI   r5   r   r   r   r   r   rZ   residualattn_outputsself_attn_weightsfeed_forward_hidden_statesoutputss                  r,   r   PhiDecoderLayer.forward   s     !,,]; +/.. 
+
')%)/) 3
+
 
+
' )),7%)%7%78O%P"$AHL "++Gr.   )r   r   r   r   )NNNFFNN)r   r   r   r   r   rw   rl   r'   r   r   r   r   boolFloatTensorr   r   r   r   s   @r,   r   r      s
   <y <S < 26378<,1$)59KO%||% !.% u//0	%
 !u||!45% $D>% D>% !!1!12% &eELL%,,,F&GH% 
u  (51B1BEDUDU1U+V"WW	X% %r.   r   c                   l   ^  \ rS rSrSS\4U 4S jjjr\R                  " 5       \S 5       5       r	Sr
U =r$ )PhiRotaryEmbeddingi  rd   c                   > [         TU ]  5         [        US5      (       aH  UR                  b;  UR                  R	                  SUR                  R	                  S5      5      U l        OSU l        UR                  U l        UR                  U l        Xl	        [        U R
                     U l        U R                  U R                  U5      u  o0l        U R                  SUSS9  U R                  U l        g )Nrope_scaling	rope_typetypedefaultinv_freqF)
persistent)rk   rl   hasattrr   r   r   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrd   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r   rd   devicer   r   s       r,   rl   PhiRotaryEmbedding.__init__  s    6>**v/B/B/N#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q((ZeD!%r.   c                 b   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        R                  " USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r"   r   mpscpuF)device_typeenabledr#   r$   )rN   )r   floatr>   r&   rX   r   
isinstancer   strr'   autocastrS   r(   r3   r   r4   rN   )
r   r)   r5   inv_freq_expandedposition_ids_expandedr   freqsembr3   r4   s
             r,   r   PhiRotaryEmbedding.forward  sR    !MM$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.)r   rd   r   r   r   r   r   r   )r   r   r   r   r   rl   r'   no_gradr   r   r   r   r   s   @r,   r   r     s6    /y / /" ]]_<  <r.   r   c                   N    \ rS rSr\rSr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)	PhiPreTrainedModeli/  modelTr   past_key_valuesc                    U R                   R                  n[        U[        R                  5      (       aW  UR
                  R                  R                  SUS9  UR                  b%  UR                  R                  R                  5         g g [        U[        R                  5      (       ad  UR
                  R                  R                  SUS9  UR                  b2  UR
                  R                  UR                     R                  5         g g [        U[        R                  5      (       aJ  UR
                  R                  R                  S5        UR                  R                  R                  5         g g )Nr   )meanstdg      ?)rd   initializer_ranger   rT   rr   weightdatanormal_rh   zero_	Embeddingpadding_idxr{   fill_)r   rE   r   s      r,   _init_weights PhiPreTrainedModel._init_weights>  s   kk++fbii((MM&&CS&9{{&  &&( '--MM&&CS&9!!-""6#5#56<<> .--MM$$S)KK""$ .r.   r   N)r   r   r   r   r   config_classbase_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_2_supports_sdpa_supports_flex_attn_supports_cache_class_supports_quantized_cache_supports_static_cache_supports_attention_backendr   r   r   r.   r,   r   r   /  sS    L&*#*+#4"5!N  $!"&%r.   r   c                     ^  \ rS rSrS\4U 4S jjrS rS r\\	         SS\
\R                     S\
\R                     S\
\R                     S	\
\   S
\
\R                     S\
\   S\
\   S\
\   S\
\R                     S\\   S\4S jj5       5       r SS\\R                  S4   S\R                  S\R                  S	\S\4
S jjr\S\R                  S\S\S\R2                  S\R                  S\4S j5       rSrU =r$ )PhiModeliM  rd   c           	      h  > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [        US9U l        SU l        [
        R"                  " UR$                  5      U l        [
        R(                  " UR                  UR*                  S9U l        U R/                  5         g s  snf )N)rd   Fr   )rk   rl   pad_token_idr   
vocab_sizerT   r   rn   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   
rotary_embgradient_checkpointingr   
embd_pdropembed_dropoutr{   r|   final_layernorm	post_initr   s      r,   rl   PhiModel.__init__O  s     !.. ++LL):):F<N<NPTP`P`ammAFvG_G_A`aA`I_V/A`a
 -F;&+#ZZ(9(9:!||F,>,>FDYDYZ 	 bs   D/c                     U R                   $ r   r  r   s    r,   get_input_embeddingsPhiModel.get_input_embeddings`  s       r.   c                     Xl         g r   r  r   rH   s     r,   set_input_embeddingsPhiModel.set_input_embeddingsc  s    !r.   	input_idsrI   r5   r   inputs_embedsr   r   output_hidden_statesr   flash_attn_kwargsr<   c
                    Ub  UOU R                   R                  nUb  UOU R                   R                  nUb  UOU R                   R                  nUS L US L-  (       a  [	        S5      eU R
                  (       a/  U R                  (       a  U(       a  [        R                  S5        SnUc  U R                  U5      nU(       a  Uc
  [        5       nU	cD  Ub  UR                  5       OSn[        R                  " XUR                  S   -   UR                  S9n	Uc  U	R!                  S5      nU R#                  X%XU5      nU R%                  U5      nUnU R'                  X5      nU(       a  SOS nU(       a  SOS nU R(                  S U R                   R*                    H  nU(       a  X4-  nU R
                  (       a?  U R                  (       a.  U R-                  [/        UR0                  40 U
D6UUUUUUU	U5	      nOU" U4UUUUUU	US.U
D6nUS   nU(       d  M~  UUS   4-  nM     U R3                  U5      nU(       a  X4-  n[5        UU(       a  UOS UUS	9$ )
Nz:You must specify exactly one of input_ids or inputs_embedszX`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.Fr   r   r   r   )rI   r5   r   r   r   r   r   )last_hidden_stater   r:   
attentions)rd   r   r&  r   
ValueErrorr  rP   r   r   r  r   get_seq_lengthr'   aranger&   r   r0   _update_causal_maskr  r  r  r  _gradient_checkpointing_funcr   __call__r  r   )r   r$  rI   r5   r   r%  r   r   r&  r   r'  past_seen_tokensr^   r:   r   all_hidden_statesall_self_attnsdecoder_layerlayer_outputss                      r,   r   PhiModel.forwardf  s    2C1N-TXT_T_TqTq$8$D $++JjJj 	 "+!6IDKK<Q<Q	-t";<YZZ&&4==Yj I  --i8M0*nO!CRC^==?de"\\ ]5H5H5K"KTaThThN )33A6L..>L]
 **=9% #oomJ #7BD0d![[)H4;;+H+HIM#!%55!**t}} $ A AM22H6GH! #%"'
! !.!
!#.!-#2&7'#1(;
! (
! *!,M  =#3"55A JD ,,];  !11&+/8Od+%	
 	
r.   r   input_tensorc           	         U R                   R                  S:X  a  Ub  US:H  R                  5       (       a  U$ g U R                   R                  S:X  a,  [        U[        R
                  5      (       a  [        U5      nU$ Ub  UR                  5       OSnUb  UR                  OSnU R                   R                  S:X  a5  U(       d.  U(       d'  [        R                  " UUUU R                  S9(       a  g UR                  nUR                  S   n	U(       a  UR                  5       n
O5[        U[        R
                  5      (       a  UR                  S	   OXi-   S-   n
U R                  UU	U
UUUR                  S   S
9nU R                   R                  S:X  aZ  UbW  UR                   R"                  S;   a=  U(       d6  [        R$                  " U5      R&                  n[        R(                  " X5      nU$ )Nflash_attention_2r   flex_attentionr   Fr   )r%  past_key_values_lengthis_trainingr   r"   )sequence_lengthtarget_lengthrN   r   
batch_size)cudaxpunpu)rd   r   anyr   r'   r   r    r-  is_compileabler   _ignore_causal_mask_sdparP   rN   r&   get_max_cache_shape5_prepare_4d_causal_attention_mask_with_cache_positionr   r   finfomin_unmask_unattended)r   rI   r8  r   r   r   r2  using_compilable_cacherN   r>  r?  r^   	min_dtypes                r,   r/  PhiModel._update_causal_mask  s    ;;++/BB)~/D.I.I.K.K%%;;++/??.%,,77!<^!L!!
 @O?Z?99;`aCRC^!?!?di ;;++v5>T]n%>>*'7 MM	 ""&,,Q/!+??AM nell;; $$R(%7!;  PP+')#))!, Q 
 KK,,6*%%**.DD%
 E*..I0CCK[Kr.   r>  r?  rN   r@  c                    U b  U R                  5       S:X  a  U nU$ [        R                  " U5      R                  n[        R                  " X4XUR
                  S9nUS:w  a  [        R                  " USS9nU[        R                  " X$R
                  S9UR                  SS5      :  -  nUSSSS2SS24   R                  USSS5      nU b  UR                  5       nU R                  S   n	USS2SS2SS2SU	24   U SS2SSSS24   R                  UR
                  5      -   n
U
S:H  n
USS2SS2SS2SU	24   R                  X5      USS2SS2SS2SU	24'   U$ )	a  
Creates a causal 4D mask of shape `(batch_size, 1, query_length, key_value_length)` from a 2D mask of shape
`(batch_size, key_value_length)`, or if the input `attention_mask` is already 4D, do nothing.

Args:
    attention_mask (`torch.Tensor`):
        A 2D attention mask of shape `(batch_size, key_value_length)` or a 4D attention mask of shape
        `(batch_size, 1, query_length, key_value_length)`.
    sequence_length (`int`):
        The sequence length being processed.
    target_length (`int`):
        The target length: when generating with static cache, the mask should be as long as the static cache,
        to account for the 0 padding, the part of the cache that is not filled yet.
    dtype (`torch.dtype`):
        The dtype to use for the 4D attention mask.
    cache_position (`torch.Tensor`):
        Indices depicting the position of the input sequence tokens in the sequence.
    batch_size (`torch.Tensor`):
        Batch size.
N   )
fill_valuerN   r   r   )diagonalr)  r"   r   )r%   r'   rI  rJ  fullr   triur.  r?   r>   cloner&   rX   masked_fill)rI   r>  r?  rN   r   r@  rZ   r^   rM  mask_lengthpadding_masks              r,   rH  >PhiModel._prepare_4d_causal_attention_mask_with_cache_position  s}   < %.*<*<*>!*C(K* ' E*..I** 0Y\j\q\qK !##jjqA5<<>S>STWeWmWmnprsWtttK%dD!Q&67>>z1bRTUK))//1,2226*1aL[L+@ANSTVZ\`bcScDdDgDg&&E    ,q05@Aq,;,AV5W5c5c 6Aq!\k\12 r.   )r  r  r  r  r  r   r  r  	NNNNNNNNN)F)r   r   r   r   r   rl   r  r"  r   r   r   r'   r   r   r
   r   r   r   r   r   r   r   r/  staticmethodrw   rN   rH  r   r   r   s   @r,   r  r  M  s   y "!"  151537+/59$(,0/359f
E,,-f
 !.f
 u//0	f

 "%f
   1 12f
 D>f
 $D>f
 'tnf
 !!1!12f
 $$89f
 
!f
  f
\ #(BellK78B llB 	B
 B  BH 444 4 {{	4
 4 4 4r.   r  c                       \ rS rSrSrg)KwargsForCausalLMiL  r   N)r   r   r   r   r   r   r.   r,   r]  r]  L  s    3r.   r]  c                     ^  \ rS rSrS/rSS0rSS/S/40rU 4S jrS rS	 r	S
 r
S rS rS r\\           SS\\R$                     S\\R&                     S\\R$                     S\\   S\\R*                     S\\R$                     S\\   S\\   S\\   S\\R$                     S\\\R&                  4   S\\   S\4S jj5       5       rSrU =r$ )PhiForCausalLMiO  zlm_head.weightlm_headcolwise_repr:   logitsc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g )NTrg   )
rk   rl   r  r   r  rT   rr   rn   r`  r  r   s     r,   rl   PhiForCausalLM.__init__U  sU     f%
 ++yy!3!3V5F5FTR 	r.   c                 .    U R                   R                  $ r   r   r  r  s    r,   r  #PhiForCausalLM.get_input_embeddings^      zz&&&r.   c                 $    XR                   l        g r   rf  r!  s     r,   r"  #PhiForCausalLM.set_input_embeddingsa      "'

r.   c                     U R                   $ r   r`  r  s    r,   get_output_embeddings$PhiForCausalLM.get_output_embeddingsd  s    ||r.   c                     Xl         g r   rm  )r   new_embeddingss     r,   set_output_embeddings$PhiForCausalLM.set_output_embeddingsg  s    %r.   c                     Xl         g r   r   )r   decoders     r,   set_decoderPhiForCausalLM.set_decoderj  s    
r.   c                     U R                   $ r   ru  r  s    r,   get_decoderPhiForCausalLM.get_decoderm  s    zzr.   r$  rI   r5   r   r%  labelsr   r   r&  r   logits_to_keeprZ   r<   c                    Ub  UOU R                   R                  nU	b  U	OU R                   R                  n	U R                  " SUUUUUUUU	U
S.	UD6nUR                  n[        U[        5      (       a  [        U* S5      OUnU R                  USS2USS24   5      nSnUb)  U R                  " SUX`R                   R                  S.UD6n[        UUUR                  UR                  UR                  S9$ )a  
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
    Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
    config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
    (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

Example:

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

>>> model = PhiForCausalLM.from_pretrained("meta-phi/Phi-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-phi/Phi-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."
```N)	r$  rI   r5   r   r%  r   r   r&  r   )rb  r|  r  lossrb  r   r:   r+  r   )rd   r   r&  r   r*  r   rw   slicer`  loss_functionr  r   r   r:   r+  )r   r$  rI   r5   r   r%  r|  r   r   r&  r   r}  rZ   r   r:   slice_indicesrb  r  s                     r,   r   PhiForCausalLM.forwardp  s   N 2C1N-TXT_T_TqTq$8$D $++JjJj 	
 ,0:: ,
)%+'/!5),
 ,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVF{{OeOepiopD%#33!//))
 	
r.   )r`  r   r  )NNNNNNNNNNr   )r   r   r   r   _tied_weights_keys_tp_plan_pp_planrl   r  r"  rn  rr  rw  rz  r   r   r   r'   r   r   r
   r   r   r   rw   r   r]  r   r   r   r   r   s   @r,   r_  r_  O  s   *+=)H_-z:;H'(&  151537+/59-1$(,0/35934G
E,,-G
 !.G
 u//0	G

 "%G
   1 12G
 ))*G
 D>G
 $D>G
 'tnG
 !!1!12G
 c5<</0G
 *+G
 
 G
  G
r.   r_  a  
    The Phi Model transformer with a sequence classification head on top (linear layer).

    [`PhiForSequenceClassification`] uses the last token in order to do the classification, as other causal models
    (e.g. GPT-2) do.

    Since it does classification on the last token, it requires to know the position of the last token. If a
    `pad_token_id` is defined in the configuration, it finds the last token that is not a padding token in each row. If
    no `pad_token_id` is defined, it simply takes the last value in each row of the batch. Since it cannot guess the
    padding tokens when `inputs_embeds` are passed instead of `input_ids`, it does the same (take the last value in
    each row of the batch).
    )custom_introc                   *  ^  \ rS rSrU 4S jrS rS r\\         SS\	\
R                     S\	\
R                     S\	\
R                     S\	\   S	\	\
R                     S
\	\
R                     S\	\   S\	\   S\	\   S\4S jj5       5       rSrU =r$ )PhiForSequenceClassificationi  c                    > [         TU ]  U5        UR                  U l        [        U5      U l        [
        R                  " UR                  U R                  SS9U l        U R                  5         g )NFrg   )
rk   rl   
num_labelsr  r   rT   rr   rn   scorer  r   s     r,   rl   %PhiForSequenceClassification.__init__  sS      ++f%
YYv114??O
 	r.   c                 .    U R                   R                  $ r   rf  r  s    r,   r  1PhiForSequenceClassification.get_input_embeddings  rh  r.   c                 $    XR                   l        g r   rf  r!  s     r,   r"  1PhiForSequenceClassification.set_input_embeddings  rk  r.   r$  rI   r5   r   r%  r|  r   r   r&  r<   c
                    U R                  UUUUUUUU	S9n
U
R                  nU R                  U5      nUb  UR                  S   nOUR                  S   nU R                  R
                  c  US:w  a  [        S5      eU R                  R
                  c  SnOUb  XR                  R
                  :g  R                  UR                  [        R                  5      n[        R                  " UR                  S   UR                  [        R                  S9nUU-  R                  S5      nO.Sn[        R                  U R                  R                    S35        U[        R                  " XR                  S	9U4   nSnUb  U R#                  XUU R                  S
9n[%        UUU
R&                  U
R(                  U
R*                  S9$ )e  
labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
    Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
    config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
    `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
rI   r5   r   r%  r   r   r&  Nr   r   z=Cannot handle batch sizes > 1 if no padding token is defined.r"   )r   rN   z will not detect padding tokens in `inputs_embeds`. Results may be unexpected if using padding tokens in conjunction with `inputs_embeds.`r)  )rb  r|  pooled_logitsrd   r  )r   r*  r  r&   rd   r  r,  rX   r   r'   int32r.  argmaxr   r   r   r   r  r   r   r:   r+  )r   r$  rI   r5   r   r%  r|  r   r   r&  transformer_outputsr:   rb  r@  last_non_pad_tokennon_pad_masktoken_indicesr  r  s                      r,   r   $PhiForSequenceClassification.forward  s   * 8<zz)%+'/!5 8B 	8
 ,==M* "+J&,,Q/J;;##+
a\]];;##+!#"%)A)AAEEfmmUZU`U`aL!LL)<V]]Z_ZeZefM"/,">!F!Fr!J!#>>**+ ,Z Z
 u||J}}MOaab%%VR_hlhshs%tD/ /??-;;*55
 	
r.   )r   r  r  rZ  )r   r   r   r   rl   r  r"  r   r   r   r'   r   r   r
   r   r   r   r   r   r   r   s   @r,   r  r    s    '(  151537+/59-1$(,0/3A
E,,-A
 !.A
 u//0	A

 "%A
   1 12A
 ))*A
 D>A
 $D>A
 'tnA
 
*A
  A
r.   r  c                   *  ^  \ rS rSrU 4S jrS rS r\\         SS\	\
R                     S\	\
R                     S\	\
R                     S\	\   S	\	\
R                     S
\	\
R                     S\	\   S\	\   S\	\   S\4S jj5       5       rSrU =r$ )PhiForTokenClassificationi   c                   > [         TU ]  U5        UR                  U l        [        U5      U l        [        USS 5      b  UR                  nO[        USS 5      b  UR                  nOSn[        R                  " U5      U l
        [        R                  " UR                  UR                  5      U l        U R                  5         g )Nclassifier_dropouthidden_dropoutg?)rk   rl   r  r  r   rm   r  r  rT   r   rK   rr   rn   r  r  )r   rd   r  r   s      r,   rl   "PhiForTokenClassification.__init__"  s      ++f%
6/6B!'!:!:V-t4@!'!6!6!$zz"45YYv1163D3DE
 	r.   c                 .    U R                   R                  $ r   rf  r  s    r,   r  .PhiForTokenClassification.get_input_embeddings2  rh  r.   c                 $    XR                   l        g r   rf  r!  s     r,   r"  .PhiForTokenClassification.set_input_embeddings5  rk  r.   r$  rI   r5   r   r%  r|  r   r   r&  r<   c
                    U R                  UUUUUUUU	S9n
U
R                  nU R                  U5      nU R                  U5      nSnUb  U R	                  XU R
                  5      n[        UUU
R                  U
R                  S9$ )r  r  N)r  rb  r:   r+  )	r   r*  rK   r  r  rd   r   r:   r+  )r   r$  rI   r5   r   r%  r|  r   r   r&  r   sequence_outputrb  r  s                 r,   r   !PhiForTokenClassification.forward8  s    * ,0::)%+'/!5 ,6 	,
 "33,,7O,%%fdkkBD$!//))	
 	
r.   )rK   r   r  r  rZ  )r   r   r   r   rl   r  r"  r   r   r   r'   r   r   r
   r   r   r   r   r   r   r   s   @r,   r  r     s     '(  151537+/59-1$(,0/3*
E,,-*
 !.*
 u//0	*

 "%*
   1 12*
 ))**
 D>*
 $D>*
 'tn*
 
*
  *
r.   r  )r   r  r_  r  r  )Nr   )r   )D	functoolsr   typingr   r   r   r   r'   torch.nnrT   activationsr	   cache_utilsr
   r   
generationr   modeling_attn_mask_utilsr   modeling_flash_attention_utilsr   modeling_outputsr   r   r   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   r   configuration_phir   !torch.nn.attention.flex_attentionr   integrations.flex_attentionr    
get_loggerr   r   r-   r9   r   rw   rD   Moduler   r`   rb   r   r   r   r   r  r]  r_  r  r  __all__r   r.   r,   <module>r     s    3 3   ! . ) > B  L F & h h (  !!;J 
		H	%(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % %4[)299 [)|RYY -bii -`< <D % % %: {! { {| ?,j > i
' i
 i
X S
#5 S
S
l C
 2 C
 C
Lr.   