
    <h`                     4   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  SS
K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&  \"RN                  " \(5      r)S r*S4S jr+S\RX                  S\-S\RX                  4S jr. S5S\R^                  S\RX                  S\RX                  S\RX                  S\\RX                     S\0S\0S \\   4S! jjr1 " S" S#\R^                  5      r2\" S$5       " S% S&\R^                  5      5       r3 " S' S(\R^                  5      r4 " S) S*\5      r5\  " S+ S,\5      5       r6 " S- S.\R^                  5      r7\  " S/ S0\65      5       r8\  " S1 S2\6\5      5       r9/ S3Qr:g)6    )CallableOptionalUnionN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuplelogging)check_model_inputs   )GraniteConfigc                     U SSU R                   S   S-  24   nU SU R                   S   S-  S24   n[        R                  " U* U4SS9$ )z*Rotates half the hidden dims of the input..N   dim)shapetorchcat)xx1x2s      d/var/www/html/shao/venv/lib/python3.13/site-packages/transformers/models/granite/modeling_granite.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_embr5   4   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)r6   r7   batchnum_key_value_headsslenhead_dims         r(   	repeat_kvr@   O   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$ )Nr   r   r   )r!   dtype)ptrainingr   )r@   num_key_value_groupsr#   matmul	transposer"   r   
functionalsoftmaxfloat32torK   rG   rM   
contiguous)rA   rB   rC   rD   rE   rF   rG   rH   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r(   eager_attention_forwardr[   [   s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!$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\S\\   4U 4S jjjr  SS\	R                  S\\	R                  \	R                  4   S\\	R                     S	\\   S
\\	R                     S\\   S\\	R                  \	R                  4   4S jjrSrU =r$ )GraniteAttentionu   z=Multi-headed attention from 'Attention Is All You Need' paperconfig	layer_idxc                 J  > [         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                  U l        SU l        [        R                  " UR
                  UR                  U R                  -  UR                   S9U l        [        R                  " UR
                  UR                  U R                  -  UR                   S9U l        [        R                  " UR
                  UR                  U R                  -  UR                   S9U l        [        R                  " UR                  U R                  -  UR
                  UR                   S9U l        g )Nr?   Tbias)super__init__r_   r`   getattrhidden_sizenum_attention_headsr?   r=   rN   attention_multiplierrF   attention_dropout	is_causalr   Linearattention_biasq_projk_projv_projo_projselfr_   r`   	__class__s      r(   re   GraniteAttention.__init__x   sF   "
F4F4F&JdJd4de$*$>$>&B\B\$\!22!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r*   r6   position_embeddingsrE   past_key_valuecache_positionrH   r8   c                 4   UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
U R                  U5      R                  U5      R	                  SS5      nUu  p[        XX5      u  pUb$  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 R%                  5       nU R'                  U5      nUU4$ )Nr   r   r   )r0   r/   rx   eager        )rG   rF   )r"   r?   rn   viewrP   ro   rp   r5   updater`   r[   r_   _attn_implementationr   rM   rj   rF   r;   rU   rq   )rs   r6   rv   rE   rw   rx   rH   input_shapehidden_shapequery_statesrV   rW   r/   r0   cache_kwargsattention_interfacerZ   rX   s                     r(   forwardGraniteAttention.forward   s    $))#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&#7RU#[ %#&nUL'5'<'<ZW[WeWegs't$J(?;;++w6"9$++:Z:Z"[$7	%
  $}}C$2H2HLL	%
 	%
!\ "));;;;FFHkk+.L((r*   )rj   r_   r?   rk   ro   r`   rN   rq   rn   rF   rp   N)NN)__name__
__module____qualname____firstlineno____doc__r   r   intre   r#   Tensortupler	   
LongTensorr   r   r   __static_attributes____classcell__rt   s   @r(   r]   r]   u   s    G
} 
# 
 
8 +/59))||)) #5<<#=>)) !.	))
 !)) !!1!12)) +,)) 
u||U\\)	*)) ))r*   r]   RMSNormc                   8   ^  \ rS rSrSU 4S jjrS rS rSrU =r$ )GraniteRMSNorm   c                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)z-
GraniteRMSNorm is equivalent to T5LayerNorm
N)rd   re   r   	Parameterr#   onesweightvariance_epsilon)rs   rg   epsrt   s      r(   re   GraniteRMSNorm.__init__   s/     	ll5::k#:; #r*   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      -  $ )Nr   r   T)keepdim)	rK   rT   r#   rS   powmeanrsqrtr   r   )rs   r6   input_dtypevariances       r(   r   GraniteRMSNorm.forward   sw    #))%((7 $$Q',,R,>%H?T?T4T(UU{{]--k:::r*   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)r   r   r"   r   rs   s    r(   
extra_reprGraniteRMSNorm.extra_repr   s*    ))*+6$2G2G1HIIr*   )r   r   )gư>)	r   r   r   r   re   r   r   r   r   r   s   @r(   r   r      s    $;J Jr*   r   c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )
GraniteMLP   c                   > [         TU ]  5         Xl        UR                  U l        UR                  U l        [
        R                  " U R                  U R                  UR                  S9U l        [
        R                  " U R                  U R                  UR                  S9U l	        [
        R                  " U R                  U R                  UR                  S9U l
        [        UR                     U l        g )Nrb   )rd   re   r_   rg   intermediate_sizer   rl   mlp_bias	gate_projup_proj	down_projr   
hidden_actact_fnrs   r_   rt   s     r(   re   GraniteMLP.__init__   s    !--!'!9!94#3#3T5K5KRXRaRabyy!1!143I3IPVP_P_`4#9#94;K;KRXRaRabV../r*   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ r   )r   r   r   r   )rs   r%   r   s      r(   r   GraniteMLP.forward   s6    NN4;;t~~a/@#ADLLQRO#ST	r*   )r   r_   r   r   rg   r   r   )r   r   r   r   re   r   r   r   r   s   @r(   r   r      s    0 r*   r   c                   v  ^  \ rS rSrS\S\4U 4S jjr       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rSrU =r$ )GraniteDecoderLayer   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
        UR                  U l        g )N)r_   r`   r   )rd   re   rg   r]   	self_attnr   mlpr   rms_norm_epsinput_layernormpost_attention_layernormresidual_multiplierrr   s      r(   re   GraniteDecoderLayer.__init__   sx    !--)Mf%-f.@.@fFYFYZ(6v7I7IvObOb(c%#)#=#= r*   r6   rE   r1   rw   output_attentions	use_cacherx   rv   r8   c	                    Un
U R                  U5      nU R                  " SUUUUUUUUS.U	D6u  pXU R                  -  -   nUn
U R                  U5      nU R	                  U5      nXU R                  -  -   nU4nU(       a  X4-  nU$ )a  
Args:
    hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
    attention_mask (`torch.FloatTensor`, *optional*):
        attention mask of size `(batch_size, sequence_length)` if flash attention is used or `(batch_size, 1,
        query_sequence_length, key_sequence_length)` if default attention is used.
    output_attentions (`bool`, *optional*):
        Whether or not to return the attentions tensors of all attention layers. See `attentions` under
        returned tensors for more detail.
    use_cache (`bool`, *optional*):
        If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding
        (see `past_key_values`).
    past_key_value (`Tuple(torch.FloatTensor)`, *optional*): cached past key and value projection states
    cache_position (`torch.LongTensor` of shape `(sequence_length)`, *optional*):
        Indices depicting the position of the input sequence tokens in the sequence
    position_embeddings (`tuple[torch.FloatTensor, torch.FloatTensor]`, *optional*):
        Tuple containing the cosine and sine positional embeddings of shape `(batch_size, seq_len, head_dim)`,
        with `head_dim` being the embedding dimension of each attention head.
    kwargs (`dict`, *optional*):
        Arbitrary kwargs to be ignored, used for FSDP and other methods that injects code
        into the model
)r6   rE   r1   rw   r   r   rx   rv    )r   r   r   r   r   )rs   r6   rE   r1   rw   r   r   rx   rv   rH   residualself_attn_weightsoutputss                r(   r   GraniteDecoderLayer.forward   s    D !,,]; ,0>> 
,
')%)/) 3
,
 
,
( !43K3K#KK !55mD/ 43K3K#KK "++Gr*   )rg   r   r   r   r   r   )NNNFFNN)r   r   r   r   r   r   re   r#   r   r   r   r	   boolr   FloatTensorr   r   r   r   s   @r(   r   r      s    >} > > 2637*.,1$)59KO?||? !.? u//0	?
 !? $D>? D>? !!1!12? &eELL%,,,F&GH? 
u  (51B1BEDUDU1U+V"WW	X? ?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	)
GranitePreTrainedModeli-  r_   modelTr   past_key_values)r6   
attentionsr   N)r   r   r   r   r   __annotations__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                   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$ )GraniteRotaryEmbeddingi@  r_   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defaultinv_freqF)
persistent)rd   re   hasattr
isinstancer   dictgetr   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr_   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)rs   r_   devicer   rt   s       r(   re   GraniteRotaryEmbedding.__init__A  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    )rK   )r   floatr:   r"   rT   r   r   r   strr#   autocastrP   r$   r/   r   r0   rK   )
rs   r%   r1   inv_freq_expandedposition_ids_expandedr   freqsembr/   r0   s
             r(   r   GraniteRotaryEmbedding.forwardR  sR    !MM$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   r_   r   r   r   r   r   r   )r   r   r   r   r   re   r#   no_gradr   r   r   r   r   s   @r(   r   r   @  s6    /} / /" ]]_<  <r*   r   c                   0  ^  \ rS rSrS\4U 4S jj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rU =r$ )GraniteModelib  r_   c           	      (  > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ sH  n[        X5      PM     sn5      U l        [        UR                  UR                  S9U l        [#        US9U l        SU l        UR(                  U l        U R+                  5         g s  snf )Nr   )r_   F)rd   re   pad_token_idpadding_idx
vocab_sizer   	Embeddingrg   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normr   
rotary_embgradient_checkpointingembedding_multiplier	post_initrr   s      r(   re   GraniteModel.__init__d  s     !.. ++LL):):F<N<NPTP`P`ammEJ6KcKcEdeEd	 3Ede
 #6#5#56;N;NO	0?&+#$*$?$?! 	 fs   D	input_idsrE   r1   r   inputs_embedsr   r   output_hidden_statesrx   rH   r8   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XPR                  -  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                   UUU	UUS9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_   input_embedsrE   rx   r   r1   r   )rE   r1   rw   r   r   rx   rv   )last_hidden_stater   r6   r   )r_   r   r  r   
ValueErrorr  rM   loggerwarning_oncer
  r  r
   get_seq_lengthr#   aranger"   r   r,   r   r  r  r  r  r   )rs   r  rE   r1   r   r  r   r   r  rx   rH   past_seen_tokensrY   r6   rv   all_hidden_statesall_self_attnsdecoder_layerlayer_outputss                      r(   r   GraniteModel.forwardu  s;    2C1N-TXT_T_TqTq$8$D $++JjJj 	 "+!6IDKK<Q<Q	-t";<YZZ&&4==Yj I  --i8M%(A(AA0*nO!CRC^==?de"\\ ]5H5H5K"KTaThThN )33A6L(;;&))+%
 & #oomJ #7BD0d![[)H4;;+H+HIM#!%55!)
*)."3#-$7
 
M *!,M  =#3"55' J* 		-0  !11&+/8Od+%	
 	
r*   )r
  r  r  r  r  r  r  r  )	NNNNNNNNN)r   r   r   r   r   re   r   r   r   r#   r   r   r	   r   r   r   r   r   r   r   r   r   s   @r(   r  r  b  s   } "  151537+/59$(,0/359_
E,,-_
 !._
 u//0	_

 "%_
   1 12_
 D>_
 $D>_
 'tn_
 !!1!12_
 +,_
 
!_
  _
r*   r  c                     ^  \ rS rSrS/rSS0rSS/S/40rU 4S jrS rS	 r	\
\           SS
\\R                     S\\R                     S\\R                     S\\\\\R&                     4      S\\R&                     S\\R                     S\\   S\\   S\\   S\\R                     S\\\R                  4   S\\   S\4S jj5       5       rSrU =r$ )GraniteForCausalLMi  zlm_head.weightlm_headcolwise_repr6   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 )NFrb   )
rd   re   r  r   r  r   rl   rg   r(  r  r   s     r(   re   GraniteForCausalLM.__init__  sU     !&)
 ++yy!3!3V5F5FUS 	r*   c                     Xl         g r   r   )rs   decoders     r(   set_decoderGraniteForCausalLM.set_decoder  s    
r*   c                     U R                   $ r   r.  r   s    r(   get_decoderGraniteForCausalLM.get_decoder  s    zzr*   r  rE   r1   r   r  labelsr   r   r  rx   logits_to_keeprH   r8   c                     Ub  UOU R                   R                  nU	b  U	OU R                   R                  n	U R                  " SUUUUUUUU	U
S.	UD6nUR                  n[        U[        5      (       a  [        U* S5      OUnU R                  USS2USS24   5      nUU R                   R                  -  nSnUb)  U R                  " SUX`R                   R                  S.UD6n[        UUUR                  UR                  UR                  S9$ )a{  
Example:

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

>>> model = GraniteForCausalLM.from_pretrained("meta-granite/Granite-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-granite/Granite-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  rE   r1   r   r  r   r   r  rx   )r*  r5  r  )lossr*  r   r6   r   r   )r_   r   r  r   r  r   r   slicer(  logits_scalingloss_functionr  r   r   r6   r   )rs   r  rE   r1   r   r  r5  r   r   r  rx   r6  rH   r   r6   slice_indicesr*  r8  s                     r(   r   GraniteForCausalLM.forward  s,   D 2C1N-TXT_T_TqTq$8$D $++JjJj 	
 ,0:: ,
)%+'/!5),
 ,
  118B>SV8W8W~ot4]kmA}a,?@A$++444%%pVF{{OeOepiopD%#33!//))
 	
r*   )r(  r   r  )NNNNNNNNNNr   )r   r   r   r   _tied_weights_keys_tp_plan_pp_planre   r0  r3  r   r   r   r#   r   r   r   r	   listr   r   r   r   r   r   r   r   r   r   s   @r(   r'  r'    s   *+=)H_-z:;H  151537KO59-1$(,0/35934C
E,,-C
 !.C
 u//0	C

 "%tE4E4E/F(F"GHC
   1 12C
 ))*C
 D>C
 $D>C
 'tnC
 !!1!12C
 c5<</0C
 +,C
 
 C
  C
r*   r'  )r'  r  r   )Nr   )r{   );typingr   r   r   r#   r   activationsr   cache_utilsr	   r
   
generationr   integrationsr   masking_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   utils.genericr   configuration_graniter   
get_loggerr   r  r)   r5   r   r   r@   Moduler   r[   r]   r   r   r   r   r   r  r'  __all__r   r*   r(   <module>rS     s  , - ,   ! . ) 7 / 9 O K F & R R / 0 
		H	%(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4C)ryy C)L Y'JRYY J (J(  J4 JZ _  $<RYY <D s
) s
 s
l Y
/ Y
 Y
x Kr*   