
    cCiuV                     ,   S SK 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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"J#r#  SSK$J%r%  SSK&J'r'  SSK(J)r)  \#RT                  " \+5      r,S r-S4S jr.S\R^                  S\0S\R^                  4S jr1 S5S\Rd                  S\R^                  S\R^                  S\R^                  S\\R^                     S\3S\3S\\    4S  jjr4 " S! S"\Rd                  5      r5 " S# S$\Rd                  5      r6 " S% S&\5      r7 " S' S(\Rd                  5      r8\! " S) S*\5      5       r9\! " S+ S,\95      5       r:\! " S- S.\9\5      5       r; " S/ S0\\95      r< " S1 S2\\95      r=/ S3Qr>g)6    )CallableOptionalUnionN   )ACT2FN)CacheDynamicCache)GenerationMixin)create_causal_mask) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuplelogging)deprecate_kwarg)check_model_inputs   )	PhiConfigc                     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$ )z*Rotates half the hidden dims of the input..N   dim)shapetorchcat)xx1x2s      ^/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/phi/modeling_phi.pyrotate_halfr*   "   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''    c                     UR                  U5      nUR                  U5      nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nXg4$ )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_embr6   )   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)r7   r8   batchnum_key_value_headsslenhead_dims         r)   	repeat_kvrA   D   s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr+   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"  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$ )Nr    r   r   )r"   dtype)ptrainingr   )rA   num_key_value_groupsr$   matmul	transposer#   nn
functionalsoftmaxfloat32torL   rH   rN   
contiguous)rB   rC   rD   rE   rF   rG   rH   rI   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r)   eager_attention_forwardr]   P   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                   0  ^  \ rS rSrSrS\S\4U 4S jjr\" SSSS	9  SS
\	R                  S\\	R                  \	R                  4   S\\	R                     S\\   S\\	R                     S\\	R                  \\	R                     4   4S jj5       rSrU =r$ )PhiAttentionj   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 )Nr@   g      Tbias)epselementwise_affine)super__init__ra   rb   getattrhidden_sizenum_attention_headsr@   r>   rO   rG   attention_dropout	is_causalrR   Linearq_projk_projv_projdenseintpartial_rotary_factorrotary_ndimsqk_layernorm	LayerNormlayer_norm_epsq_layernormk_layernormselfra   rb   	__class__s      r)   ri   PhiAttention.__init__m   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii 2 2F4N4NQUQ^Q^4^eijii 2 2F4N4NQUQ^Q^4^eijii 2 2F4N4NQUQ^Q^4^eijYYv99DMMI6K]K]dhi
0L0L LM"//!||""f&@&@@fF[F[pt D  "||""f&@&@@fF[F[pt D	 r+   past_key_valuepast_key_values4.58new_nameversionr7   position_embeddingsrF   cache_positionr9   c                    UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
U R                  U5      R                  U5      R	                  SS5      nU R                  (       a"  U R                  U	5      n	U R                  U
5      n
Uu  pU	SS U R                  24   U	SU R                  S 24   pU
SS U R                  24   U
SU R                  S 24   nn[        UUX5      u  nn[        R                  " X4SS9n	[        R                  " UU4SS9n
Ub$  XUS.nUR                  XU R                  U5      u  p[         nU R"                  R$                  S:w  a  [&        U R"                  R$                     nU" U U	U
UU4U R(                  (       d  SOU R*                  U R,                  S	.UD6u  nnUR.                  " / UQSP76 R1                  5       nU R3                  U5      nUU4$ )
Nr   r   r    .r!   )r1   r0   r   eager        )rH   rG   )r#   r@   rp   viewrQ   rq   rr   rw   rz   r{   rv   r6   r$   r%   updaterb   r]   ra   _attn_implementationr   rN   rm   rG   r<   rW   rs   )r}   r7   r   rF   r   r   rI   input_shapehidden_shapequery_statesrX   rY   r0   r1   	query_rot
query_passkey_rotkey_passcache_kwargsattention_interfacer\   rZ   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'6'='=jX\XfXfht'u$J(?;;++w6"9$++:Z:Z"[$7	%
  $}}C$2H2HLL	%
 	%
!\ "));;;;FFHjj-L((r+   )rm   ra   rs   r@   rn   r{   rq   rb   rO   rz   rp   rw   rv   rG   rr   )NN)__name__
__module____qualname____firstlineno____doc__r   rt   ri   r   r$   Tensortupler   r   
LongTensorr   __static_attributes____classcell__r~   s   @r)   r_   r_   j   s    Gy S . %0A6R ,059;)||;) #5<<#=>;) !.	;)
 "%;) !!1!12;) 
u||Xell33	4;) S;)r+   r_   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)rh   ri   ra   r   
hidden_actactivation_fnrR   ro   rk   intermediate_sizefc1fc2r}   ra   r~   s     r)   ri   PhiMLP.__init__   sb    #F$5$5699V//1I1IJ99V55v7I7IJr+   r7   r9   c                 l    U R                  U5      nU R                  U5      nU R                  U5      nU$ r   )r   r   r   )r}   r7   s     r)   r   PhiMLP.forward   s4    /**=9/r+   )r   ra   r   r   )
r   r   r   r   ri   r$   r   r   r   r   r   s   @r)   r   r      s)    KU\\ ell  r+   r   c                     ^  \ rS rSrS\S\4U 4S jjr\" SSSS9       SS	\R                  S
\
\R                     S\
\R                     S\
\   S\
\   S\
\   S\
\R                     S\
\\R                  \R                  4      S\\R                  \
\\R                  \R                  4      4   4S jj5       rSrU =r$ )PhiDecoderLayer   ra   rb   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)rb   rf   )rh   ri   r_   	self_attnr   mlprR   rx   rk   ry   input_layernormDropoutresid_pdropresid_dropoutr|   s      r)   ri   PhiDecoderLayer.__init__   s[    %fB&>!||F,>,>FDYDYZZZ(:(:;r+   r   r   r   r   r7   rF   r2   output_attentions	use_cacher   r   r9   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$ )N)r7   rF   r2   r   r   r   r   r    )r   r   r   r   )r}   r7   rF   r2   r   r   r   r   r   rI   residualattn_outputsself_attn_weightsfeed_forward_hidden_statesoutputss                  r)   r   PhiDecoderLayer.forward   s     !,,]; +/.. 
+
')%+/) 3
+
 
+
' )),7%)%7%78O%P"$AHL "++Gr+   )r   r   r   r   )NNNFFNN)r   r   r   r   r   rt   ri   r   r$   r   r   r   r   boolr   FloatTensorr   r   r   r   s   @r)   r   r      s   <y <S < %0A6R 2637+/,1$)59KO%||% !.% u//0	%
 "%% $D>% D>% !!1!12% &eELL%,,,F&GH% 
u  (51B1BEDUDU1U+V"WW	X% S%r+   r   c                      ^  \ rS rSr% \R
                  \S'   SS\4U 4S jjjr\R                  " 5       \
S 5       5       rSrU =r$ )PhiRotaryEmbeddingi  inv_freqra   c                   > [         TU ]  5         [        US5      (       aZ  [        UR                  [
        5      (       a;  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defaultr   F)
persistent)rh   ri   hasattr
isinstancer   dictgetr   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenra   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r}   ra   devicer   r~   s       r)   ri   PhiRotaryEmbedding.__init__  s    6>**z&:M:Mt/T/T#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!   )rL   )r   floatr;   r#   rV   r   r   r   strr$   autocastrQ   r%   r0   r   r1   rL   )
r}   r&   r2   inv_freq_expandedposition_ids_expandedr   freqsembr0   r1   s
             r)   r   PhiRotaryEmbedding.forward  sR    !MM$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   ra   r   r   r   r   r   r   )r   r   r   r   r$   r   __annotations__r   ri   no_gradr   r   r   r   r   s   @r)   r   r     s@    ll/y / /" ]]_<  <r+   r   c                   R    \ rS rSr% \\S'   SrSrS/rS/r	Sr
SrSrSrSr\\S.rSrg	)
PhiPreTrainedModeli'  ra   modelTr   r   )r7   
attentionsr   N)r   r   r   r   r   r   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r_   _can_record_outputsr   r   r+   r)   r   r   '  sQ    &*#*+#4"5N!"&("r+   r   c                   :  ^  \ rS rSrS\4U 4S jjr\" 5       \         SS\\	R                     S\\	R                     S\\	R                     S\\   S\\	R                     S	\\   S
\\   S\\   S\\	R                     S\\   S\4S jj5       5       rSrU =r$ )PhiModeli:  ra   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$                  5      U l        [
        R(                  " UR                  UR*                  S9U l        U R/                  5         g s  snf )Nra   Fr   )rh   ri   pad_token_idpadding_idx
vocab_sizerR   	Embeddingrk   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   
rotary_embgradient_checkpointingr   
embd_pdropembed_dropoutrx   ry   final_layernorm	post_initr|   s      r)   ri   PhiModel.__init__<  s     !.. ++LL):):F<N<NPTP`P`ammAFvG_G_A`aA`I_V/A`a
 -F;&+#ZZ(9(9:!||F,>,>FDYDYZ 	 bs   D/	input_idsrF   r2   r   inputs_embedsr   r   output_hidden_statesr   rI   r9   c
                 2   Ub  UOU R                   R                  nUb  UOU R                   R                  nUb  UOU R                   R                  nUS L US L-  (       a  [	        S5      eU R
                  (       a/  U R                  (       a  U(       a  [        R                  S5        SnUc  U R                  U5      nU(       a  Uc  [        U R                   S9nU	cD  Ub  UR                  5       OSn[        R                  " XUR                  S   -   UR                  S9n	Uc  U	R!                  S5      n[#        U R                   UUU	UUS9nU R%                  U5      nUnU R'                  X5      nU(       a  S	OS nU(       a  S	OS nU R(                  S U R                   R*                    H7  nU(       a  X4-  nU" U4UUUUUU	US
.U
D6nUS   nU(       d  M.  UUS   4-  nM9     U R-                  U5      nU(       a  X4-  n[/        UU(       a  UOS UUS9$ )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   )ra   input_embedsrF   r   r   r2   r   )rF   r2   r   r   r   r   r   )last_hidden_stater   r7   r   )ra   r   r  r   
ValueErrorr  rN   loggerwarning_oncer  r	   get_seq_lengthr$   aranger#   r   r-   r   r  r
  r	  r  r  r   )r}   r  rF   r2   r   r  r   r   r  r   rI   past_seen_tokensr[   r7   r   all_hidden_statesall_self_attnsdecoder_layerlayer_outputss                      r)   r   PhiModel.forwardM  sF    2C1N-TXT_T_TqTq$8$D $++JjJj 	 "+!6IDKK<Q<Q	-t";<YZZ&&4==Yj I  --i8M0*$++>O!CRC^==?de"\\ ]5H5H5K"KTaThThN )33A6L(;;&))+%
 **=9% #oomJ #7BD0d![[)H4;;+H+HIM#!%55!)
*) /"3#-$7
 
M *!,M  =#3"55' J* ,,];  !11&+/8Od+%	
 	
r+   )r  r  r  r  r	  r  r
  r  )	NNNNNNNNN)r   r   r   r   r   ri   r   r   r   r$   r   r   r   r   r   r   r   r   r   r   r   r   s   @r)   r   r   :  s   y "  151537+/59$(,0/359^
E,,-^
 !.^
 u//0	^

 "%^
   1 12^
 D>^
 $D>^
 'tn^
 !!1!12^
 +,^
 
!^
  ^
r+   r   c                   r  ^  \ rS rSrS/rSS0rSS/S/40rU 4S jr\\	         SS\
\R                     S	\
\R                     S
\
\R                     S\
\   S\
\R                     S\
\R                     S\
\   S\
\R                     S\\\R                  4   S\\   S\4S jj5       5       rSrU =r$ )PhiForCausalLMi  zlm_head.weightlm_headcolwise_repr7   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 )NTrd   )
rh   ri   r   r   r  rR   ro   rk   r$  r  r   s     r)   ri   PhiForCausalLM.__init__  sU     f%
 ++yy!3!3V5F5FTR 	r+   r  rF   r2   r   r  labelsr   r   logits_to_keeprI   r9   c
                 ~   U R                   " SUUUUUUUS.U
D6nUR                  n[        U	[        5      (       a  [	        U	* S5      OU	nU R                  USS2USS24   5      nSnUb)  U R                  " SXU R                  R                  S.U
D6n[        UUUR                  UR                  UR                  S9$ )ac  
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."
```)r  rF   r2   r   r  r   r   N)r&  r)  r  )lossr&  r   r7   r   r   )r   r  r   rt   slicer$  loss_functionra   r  r   r   r7   r   )r}   r  rF   r2   r   r  r)  r   r   r*  rI   r   r7   slice_indicesr&  r,  s                   r)   r   PhiForCausalLM.forward  s    @ ,0:: 	,
)%+')	,
 	,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r+   )r$  r   r  )	NNNNNNNNr   )r   r   r   r   _tied_weights_keys_tp_plan_pp_planri   r   r   r   r$   r   r   r   r   r   r   rt   r   r   r   r   r   r   r   s   @r)   r#  r#    s0   *+=)H_-z:;H  151537+/59-1$(59348
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 ))*8
 D>8
 !!1!128
 c5<</08
 +,8
 
 8
  8
r+   r#  c                       \ rS rSrSrg)PhiForSequenceClassificationi  r   Nr   r   r   r   r   r   r+   r)   r5  r5        r+   r5  c                       \ rS rSrSrg)PhiForTokenClassificationi   r   Nr6  r   r+   r)   r9  r9     r7  r+   r9  )r   r   r#  r5  r9  )Nr   )r   )?typingr   r   r   r$   torch.nnrR   activationsr   cache_utilsr   r	   
generationr
   masking_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   utils.deprecationr   utils.genericr   configuration_phir   
get_loggerr   r  r*   r6   r   rt   rA   Moduler   r]   r_   r   r   r   r   r   r#  r5  r9  __all__r   r+   r)   <module>rL     s   - ,   ! . ) / 
 P K F & R R 0 / ( 
		H	%(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4V)299 V)rRYY .0 .b!< !<H   $ r
! r
 r
j H
' H
 H
V	#CEW 		 =?Q 	r+   