
    Z j>g                        S SK r S SKJr  S SKJr  S SKrS SKJs  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  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  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.J/r/  SSK0J1r1  SSK2J3r3  \" S5       " S S\Rh                  5      5       r5 " S S\Rh                  5      r6 " S S\Rh                  5      r7S r8\" S5      S;S  j5       r9S!\Rt                  S"\;S#\Rt                  4S$ jr< S<S%\Rh                  S&\Rt                  S'\Rt                  S(\Rt                  S)\Rt                  S-  S*\=S+\=S,\'\)   4S- jjr>S=S. jr?S>S/ jr@ " S0 S1\Rh                  5      rA " S2 S3\5      rB\* " S4 S5\%5      5       rC\* " S6 S7\C5      5       rD\* " S8 S9\C\5      5       rE/ S:QrFg)?    N)Callable)Optional)nn   )initialization)ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernel_func_from_hub)create_causal_mask)FlashAttentionKwargs)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)is_flash_attention_requestedmaybe_autocastmerge_with_config_defaults)capture_outputs   )YoutuConfig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$ )YoutuRMSNorm5   epsreturnNc                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)z+
YoutuRMSNorm is equivalent to T5LayerNorm
N)super__init__r   	Parametertorchonesweightvariance_epsilon)selfhidden_sizer%   	__class__s      y/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/youtu/modeling_youtu.pyr)   YoutuRMSNorm.__init__7   s/     	ll5::k#:; #    hidden_statesc                    UR                   nUR                  [        R                  5      nUR	                  S5      R                  SSS9nU[        R                  " X0R                  -   5      -  nU R                  UR                  U5      -  $ )N   T)keepdim)	dtypetor+   float32powmeanrsqrtr.   r-   )r/   r5   input_dtypevariances       r2   forwardYoutuRMSNorm.forward?   sw    #))%((7 $$Q',,R,>%H?T?T4T(UU{{]--k:::r4   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)tupler-   shaper.   )r/   s    r2   
extra_reprYoutuRMSNorm.extra_reprF   s*    ))*+6$2G2G1HIIr4   )r.   r-   )gư>)__name__
__module____qualname____firstlineno__floatr)   r+   TensorrB   rG   __static_attributes____classcell__r1   s   @r2   r#   r#   5   sB    $ $$ $ $;U\\ ;ell ;J Jr4   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$ )YoutuRotaryEmbeddingJ   inv_freqNconfigc                   > [         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defaultrU   F)
persistentoriginal_inv_freq)r(   r)   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrV   rope_parametersrX   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r/   rV   devicerope_init_fnrU   r1   s        r2   r)   YoutuRotaryEmbedding.__init__M   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L((ZeD0(..2BuUr4   rd   ztorch.deviceseq_lenr&   ztorch.Tensorc           	         U R                   S   n[        U SS5      =(       d    U R                  U R                  -  nSnSU[        R
                  " SUS[        R                  S9R                  U[        R                  S9U-  -  -  nXe4$ )	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head_dimN      ?r   r7   r:   )rd   r:   )	r_   getattrr0   num_attention_headsr+   arangeint64r;   rM   )rV   rd   rg   basedimattention_factorrU   s          r2   r`   4YoutuRotaryEmbedding.compute_default_rope_parameters]   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 ))r4   c                 L   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r8   r   mpscpuF)device_typeenabledr7   rr   rl   )rU   rM   expandrF   r;   rd   
isinstancetypestrr   	transposer+   catcosra   sinr:   )
r/   xposition_idsinv_freq_expandedposition_ids_expandedrx   freqsembr   r   s
             r2   rB   YoutuRotaryEmbedding.forward{   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#)ra   rV   r]   r^   rX   N)NNN)rI   rJ   rK   rL   r+   rN   __annotations__r    r)   staticmethodr   intrE   rM   r`   no_gradr   rB   rO   rP   rQ   s   @r2   rS   rS   J   s    llV{ V V  %)+/"*d"*(* t* 
~u$	%	* *: ]]_<  <r4   rS   c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )YoutuMLP   c                   > [         TU ]  5         Xl        UR                  U l        UR                  U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l	        [        UR                     U l        g NFbias)r(   r)   rV   r0   intermediate_sizer   Linear	gate_projup_proj	down_projr   
hidden_actact_fnr/   rV   r1   s     r2   r)   YoutuMLP.__init__   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r4   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ r   )r   r   r   r   )r/   r   r   s      r2   rB   YoutuMLP.forward   s6    NN4;;t~~a/@#ADLLQRO#ST	r4   )r   rV   r   r   r0   r   r   )rI   rJ   rK   rL   r)   rB   rO   rP   rQ   s   @r2   r   r      s    0 r4   r   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$ )z*Rotates half the hidden dims of the input..Nr8   r7   rz   )rF   r+   r   )r   x1x2s      r2   rotate_halfr      sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r4   rotary_pos_embc                     UR                  U5      nUR                  U5      nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nXV4$ )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.
)	unsqueezer   )qkr   r   unsqueeze_dimq_embedk_embeds          r2   apply_rotary_pos_embr      sS    & --
&C
--
&Cw;q>C/0Gw;q>C/0Gr4   r5   n_repr&   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)rF   r{   reshape)r5   r   batchnum_key_value_headsslenrj   s         r2   	repeat_kvr      s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr4   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$ )Nr7   r   r8   )rr   r:   )ptrainingr   )r   num_key_value_groupsr+   matmulr   r   
functionalsoftmaxr<   r;   r:   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightsattn_outputs               r2   eager_attention_forwardr      s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!#4==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r4   c                    UR                  U5      nUR                  U5      nU R                  u  pgpU R                  XgXS-  S5      R                  SS5      R	                  XgX5      n UR                  u  pgpUR                  XgXS-  S5      R                  SS5      R	                  XgX5      nX-  [        U 5      U-  -   n
X-  [        U5      U-  -   nX4$ )a  
TODO let's just use the original freqcis computation to not have the view
transpose + reshape! This is not optimized!
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`):
        The position indices of the tokens corresponding to the query and key tensors. For example, this can be
        used to pass offsetted position ids when working with a KV-cache.
    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.
r7      r   )r   rF   viewr   r   r   )r   r   r   r   r   r   bhsdr   r   s               r2   apply_rotary_pos_emb_interleaver      s    0 --
&C
--
&CJA!	qQQ",,Q2::1FAJA!	qQQ",,Q2::1FAw;q>C/0Gw;q>C/0Gr4   c                 N    U S::  a  gSU-  [         R                  " U 5      -  S-   $ )Nr   rk   g?)mathlog)scalemscales     r2   yarn_get_mscaler     s(    z<$((5/)C//r4   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
\S-  S\\   S\
\R                  \R                  S-  \
\R                     S-  4   4S jjrSrU =r$ )YoutuAttentioni  z=Multi-headed attention from 'Attention Is All You Need' paperrV   	layer_idxc                 t  > [         TU ]  5         Xl        X l        UR                  UR
                  -  U l        UR                  U l        UR                  U l        UR                  U l	        UR                  U l
        UR                  U l        UR                  U l        UR                  U l        UR                  U l        SU l        U R                  c=  [         R"                  " UR$                  U R                  U R                  -  SS9U l        O[         R"                  " UR$                  UR                  UR(                  S9U l        [-        UR                  5      U l        [         R"                  " UR                  U R                  U R                  -  SS9U l        [         R"                  " UR$                  U R                  U R                  -   UR(                  S9U l        [-        U R                  5      U l        [         R"                  " U R                  U R                  U R                  U R                  -   -  SS9U l        [         R"                  " U R                  U R                  -  UR$                  UR(                  S9U l        U R                  S-  U l        U R                  R<                  R?                  SS5      S:w  aj  U R                  R<                  R?                  SS5      nU R                  R<                  S	   nU(       a#  [A        XC5      nU R:                  U-  U-  U l        g g g )
NTFr   g      rX   rY   mscale_all_dimr   factor)!r(   r)   rV   r   rn   r   r   attention_dropout	num_headsq_lora_rankqk_rope_head_dimkv_lora_rank
v_head_dimqk_nope_head_dimqk_head_dim	is_causalr   r   r0   q_projattention_biasq_a_projr#   q_a_layernormq_b_projkv_a_proj_with_mqakv_a_layernorm	kv_b_projo_projr   r_   getr   )r/   rV   r   r   scaling_factorr   r1   s         r2   r)   YoutuAttention.__init__  s   "$*$>$>&B\B\$\!!'!9!933!-- & 7 7"// ++ & 7 7!--#))F$6$6IYIY8Y`efDKIIf&8&8&:L:LSYShShiDM!-f.@.@!ADIIf&8&8$..4K[K[:[bghDM"$)) 5 55&&#

 +4+<+<=NNd33dooEF
 iiNNT__,&&
 ''D1;;&&**;	BiO![[88<<=MqQN![[88BN(H#||f4v=  Pr4   Nr5   position_embeddingsr   past_key_valuesr   r&   c                 B   UR                   S S u  pgXgSU R                  4nXgSU R                  U R                  -   4n	U R                  c  U R                  U5      n
O/U R                  U R                  U R                  U5      5      5      n
U
R                  U5      R                  SS5      n
[        R                  " XR                  U R                  /SS9u  pU R                  U5      n[        R                  " XR                  U R                  /SS9u  pU R!                  U R#                  U5      5      R                  U	5      R                  SS5      n[        R                  " XR                  U R                  /SS9u  nnUR                  USXpR                  5      nUu  nnU R$                  R&                  (       a  [)        XUU5      u  pO[+        XUU5      u  pUR,                  " / UR                   S S QSP76 n[        R.                  " X4SS9n[        R.                  " X4SS9nUb   UR1                  UUU R2                  5      u  nn[5        U R$                  5      (       aJ  U R                  U R                  :w  a0  [6        R8                  " USU R                  U R                  -
  /5      n[:        R<                  " U R$                  R>                  [@        5      nU" U UUUU4U RB                  (       d  SOU RD                  U RF                  S.UD6u  nn[5        U R$                  5      (       a5  U R                  U R                  :w  a  US S 2S S 2S S 2S U R                  24   nURI                  XgS5      RK                  5       nU RM                  U5      nUU4$ )Nr8   r   r7   rz   r           )r   r   )'rF   r   r   r   r   r   r   r   r   r   r   r+   splitr   r   r   r   r   rV   rope_interleaver   r   r{   r   updater   r   Fpadr   get_interface_attn_implementationr   r   r   r   r   r   r   )r/   r5   r   r   r   r   
batch_size
seq_lengthquery_shape	key_shapeq_statesq_passq_rotcompressed_kvk_passk_rotr   r   r   query_statesr   attention_interfacer   r   s                           r2   rB   YoutuAttention.forwardA  s)    "/!4!4Sb!9
!r43C3CDR1F1F1XY	#{{=1H}}T%7%7m8T%UVH==-771=H/D/DdF[F[.\bde//>M4E4EtG\G\3]cef 3 3F ;<AA)LVVWXZ[\${{64I4I4??3[acd

:q*6K6KL&S;;&&:5cRLE5/c3GLE4fll3B/44yy&b9YYB7
&'6'='=j,X\XfXf'g$J'449I9IT__9\5543C3Cdoo3U/VWL(?(M(MKK,,.E)
 %8	%
  $}}C$2H2HLL	%
 	%
!\ (449I9IT__9\%aA/@/@&@AK!))*"EPPRkk+.L((r4   )r   rV   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   )rI   rJ   rK   rL   __doc__r    r   r)   r+   rN   rE   r	   r   r   rB   rO   rP   rQ   s   @r2   r   r     s    G/>{ />s />l )-?)||?) #5<<#=>?) t+	?)
 ?) -.?) 
u||U\\D0%2E2LL	M?) ?)r4   r   c                     ^  \ rS rSrS\S\4U 4S jjr     SS\R                  S\R                  S-  S\R                  S-  S	\
S-  S
\S-  S\\R                  \R                  4   S-  S\\   S\R                  4S jjrSrU =r$ )YoutuDecoderLayeri  rV   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
        g )N)rV   r   r%   )r(   r)   r0   r   	self_attnr   mlpr#   rms_norm_epsinput_layernormpost_attention_layernormr/   rV   r   r1   s      r2   r)   YoutuDecoderLayer.__init__  sj    !--'vKF#+F,>,>FDWDWX(4V5G5GVM`M`(a%r4   Nr5   r   r   r   	use_cacher   r   r&   c           
          UnU R                  U5      nU R                  " SUUUUUUS.UD6u  pX-   nUnU R                  U5      nU R                  U5      nX-   nU$ )N)r5   r   r   r   r  r    )r  r  r  r  )
r/   r5   r   r   r   r  r   r   residual_s
             r2   rB   YoutuDecoderLayer.forward  s     !,,];>> 
')%+ 3
 
 !0 !55mD/ 0r4   )r0   r  r  r  r  )NNNFN)rI   rJ   rK   rL   r    r   r)   r+   rN   
LongTensorr	   boolrE   r   r   rB   rO   rP   rQ   s   @r2   r  r    s    b{ bs b /304(,!&HL|| t+ &&-	
  $; #5<<#=>E +, 
 r4   r  c                      ^  \ 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\R&                  " 5       U 4S j5       rS	rU =r$ )
YoutuPreTrainedModeli  rV   modelTr  r   )r5   
attentionsc                   > [         TU ]  U5        [        U R                  SS5      n[        U R                  SSU-  5      n[	        U[
        R                  5      (       af  [        R                  " UR                  SUS9  UR                  b8  [        R                  " UR                  R                  UR                     5        g g g )Ninitializer_rangeg{Gz?embedding_initializer_ranger7   r   )r>   std)r(   _init_weightsrm   rV   r|   r   	Embeddinginitnormal_r-   padding_idxzeros_data)r/   r   r&  	embed_stdr1   s       r2   r'  "YoutuPreTrainedModel._init_weights  s    f%dkk#6=DKK)FCP	fbll++LLSi@!!-FMM..v/A/ABC . ,r4   r  )rI   rJ   rK   rL   r    r   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr  r   _can_record_outputsr+   r   r'  rO   rP   rQ   s   @r2   r   r     sn    &*#,-#4"5N!"&*$
 ]]_D Dr4   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$ )
YoutuModeli  rV   c           	        > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [        UR                  UR                  S9U l        [#        US9U l        SU l        U R)                  5         g s  snf )Nr  rV   F)r(   r)   pad_token_idr+  
vocab_sizer   r(  r0   embed_tokens
ModuleListrangenum_hidden_layersr  layersr#   r  normrS   
rotary_embgradient_checkpointing	post_initr  s      r2   r)   YoutuModel.__init__  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcCbiv1Cbc
 !!3!39L9LM	.f=&+# 	 ds   C?N	input_idsr   r   r   inputs_embedsr  r   r&   c           
      >   US L US L-  (       a  [        S5      eUc  U R                  U5      nU(       a  Uc  [        U R                  S9nUcU  Ub  UR	                  5       OSn[
        R                  " UR                  S   UR                  S9U-   nUR                  S5      n[        U R                  UUUUS9n	Un
U R                  XS9nU R                  S U R                  R                    H  nU" U
4U	UUUUS.UD6n
M     U R                  U
5      n
[        U
US	9$ )
Nz:You must specify exactly one of input_ids or inputs_embedsr=  r   r   )rd   )rV   rK  r   r   r   )r   )r   r   r   r   r  )last_hidden_stater   )
ValueErrorr@  r
   rV   get_seq_lengthr+   ro   rF   rd   r   r   rF  rD  rC  rE  r   )r/   rJ  r   r   r   rK  r  r   past_seen_tokenscausal_maskr5   r   decoder_layers                r2   rB   YoutuModel.forward  sF    -t";<YZZ *.*;*;I*FM0*$++>OCRC^==?de <<(;(;A(>}G[G[\_ooL'11!4L(;;')+%
 &"oomoW![[)H4;;+H+HIM)*$7) /# M J 		-0&++
 	
r4   )r@  rG  rD  rE  r+  rF  r?  )NNNNNN)rI   rJ   rK   rL   r    r)   r   r   r   r+   r  rN   r	   FloatTensorr  r   r   r   rB   rO   rP   rQ   s   @r2   r;  r;    s    {     .2.204(,26!%2
##d*2
 t+2
 &&-	2

 2
 ((4/2
 $;2
 +,2
 
!2
    2
r4   r;  c                   P  ^  \ rS rSrSS0rSS0rSS/S/40rU 4S jr\\	        SS
\
R                  S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\\
R                  -  S\\   S\4S jj5       5       rSrU =r$ )YoutuForCausalLMi  zlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr5   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 r   )
r(   r)   r;  r!  r?  r   r   r0   rW  rH  r   s     r2   r)   YoutuForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r4   NrJ  r   r   r   rK  labelsr  logits_to_keepr   r&   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$ )ao  
Example:

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

>>> model = YoutuForCausalLM.from_pretrained("meta-youtu/Youtu-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-youtu/Youtu-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."
```)rJ  r   r   r   rK  r  N)rY  r\  r?  )lossrY  r   r5   r"  r  )r!  rM  r|   r   slicerW  loss_functionrV   r?  r   r   r5   r"  )r/   rJ  r   r   r   rK  r\  r  r]  r   outputsr5   slice_indicesrY  r_  s                  r2   rB   YoutuForCausalLM.forward$  s    > ,0:: ,
)%+',
 ,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r4   )rW  r!  r?  )NNNNNNNr   )rI   rJ   rK   rL   _tied_weights_keys_tp_plan_pp_planr)   r   r   r+   r  rN   r	   rT  r  r   r   r   r   rB   rO   rP   rQ   s   @r2   rV  rV    s   *,GH23H_-z:;H  .2.204(,26*.!%-.6
##d*6
 t+6
 &&-	6

 6
 ((4/6
   4'6
 $;6
 ell*6
 +,6
 
 6
  6
r4   rV  )r   r;  rV  )r   )r   )Nr   )r   r   )Gr   collections.abcr   typingr   r+   torch.nn.functionalr   r   r    r   r)  activationsr   cache_utilsr	   r
   
generationr   integrationsr   r   masking_utilsr   modeling_flash_attention_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   r   utils.output_capturingr   configuration_youtur    Moduler#   rS   r   r   r   rN   r   r   rM   r   r   r   r   r  r   r;  rV  __all__r  r4   r2   <module>r}     s  6  $      & ! . ) Q / B 9 O K F & I I e e 5 , Y'J299 J (J(><299 ><Bryy  ( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%2#L0s)RYY s)l(2 (V D? D D8 F
% F
 F
R F
+_ F
 F
R Er4   