
    Z j;e                        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
Jr  SSKJr  SSKJrJrJr  SS	KJr  SS
KJr  SSKJrJr  SSKJrJr  SSKJrJr  SSKJ r   SSK!J"r"J#r#J$r$  SSK%J&r&J'r'  SSK(J)r)J*r*  SSK+J,r,  SSK-J.r.  \)" 5       (       a	  S SK/J0r0J1r1  OSu  r0r1\" S5       " S S\Rd                  5      5       r3 " S S\Rd                  5      r4 " S S\Rd                  5      r5S r6\" S5      S<S  j5       r7S!\Rp                  S"\9S#\Rp                  4S$ jr: S=S%\Rd                  S&\Rp                  S'\Rp                  S(\Rp                  S)\Rp                  S-  S*\;S+\;S,\ \"   4S- jjr<\" \75       " S. S/\Rd                  5      5       r=S0 r>\0\14r?\@" \?5      rA " S1 S2\Rd                  5      rB " S3 S4\5      rC\# " S5 S6\5      5       rD\# " S7 S8\D5      5       rE\# " S9 S:\D\5      5       rF/ S;QrGg)>    )Callable)OptionalN)nn   )CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernel_func_from_hubuse_kernelized_func)create_causal_mask)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)is_causal_conv1d_availableis_torchdynamo_compiling)capture_outputs   )
Lfm2Config)causal_conv1d_fncausal_conv1d_updateNN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$ )Lfm2RMSNorm1   epsreturnNc                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)z*
Lfm2RMSNorm is equivalent to T5LayerNorm
N)super__init__r   	Parametertorchonesweightvariance_epsilon)selfhidden_sizer'   	__class__s      w/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/lfm2/modeling_lfm2.pyr+   Lfm2RMSNorm.__init__3   s/     	ll5::k#:; #    hidden_statesc                    UR                   nUR                  [        R                  5      nUR	                  S5      R                  SSS9nU[        R                  " X0R                  -   5      -  nU R                  UR                  U5      -  $ )N   T)keepdim)	dtypetor-   float32powmeanrsqrtr0   r/   )r1   r7   input_dtypevariances       r4   forwardLfm2RMSNorm.forward;   sw    #))%((7 $$Q',,R,>%H?T?T4T(UU{{]--k:::r6   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)tupler/   shaper0   )r1   s    r4   
extra_reprLfm2RMSNorm.extra_reprB   s*    ))*+6$2G2G1HIIr6   )r0   r/   )gư>)__name__
__module____qualname____firstlineno__floatr+   r-   TensorrD   rI   __static_attributes____classcell__r3   s   @r4   r%   r%   1   sB    $ $$ $ $;U\\ ;ell ;J Jr6   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$ )Lfm2RotaryEmbeddingF   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defaultrW   F)
persistentoriginal_inv_freq)r*   r+   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrX   rope_parametersrZ   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r1   rX   devicerope_init_fnrW   r3   s        r4   r+   Lfm2RotaryEmbedding.__init__I   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L((ZeD0(..2BuUr6   rf   ztorch.deviceseq_lenr(   ztorch.Tensorc           	         U R                   S   n[        U SS5      =(       d    U R                  U R                  -  nSnSU[        R
                  " SUS[        R                  S9R                  U[        R                  S9U-  -  -  nXe4$ )	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_dimNg      ?r   r9   r<   )rf   r<   )	ra   getattrr2   num_attention_headsr-   arangeint64r=   rO   )rX   rf   ri   basedimattention_factorrW   s          r4   rb   3Lfm2RotaryEmbedding.compute_default_rope_parametersY   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 ))r6   c                 L   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r:   r   mpscpuF)device_typeenabledr9   rs   rm   )rW   rO   expandrH   r=   rf   
isinstancetypestrr   	transposer-   catcosrc   sinr<   )
r1   xposition_idsinv_freq_expandedposition_ids_expandedry   freqsembr   r   s
             r4   rD   Lfm2RotaryEmbedding.forwardw   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#)rc   rX   r_   r`   rZ   N)NNN)rK   rL   rM   rN   r-   rP   __annotations__r   r+   staticmethodr   intrG   rO   rb   no_gradr   rD   rQ   rR   rS   s   @r4   rU   rU   F   s    llVz V V  $(+/"*T!*(* t* 
~u$	%	* *: ]]_<  <r6   rU   c                   6   ^  \ rS rSrS\4U 4S jjrS rSrU =r$ )Lfm2MLP   rX   c                   > [         TU ]  5         UR                  nUR                  (       aa  [	        SU-  S-  5      nUR
                  bC  [	        UR
                  U-  5      nUR                  X!R                  -   S-
  UR                  -  -  n[        R                  " UR                  USS9U l
        [        R                  " UR                  USS9U l        [        R                  " X!R                  SS9U l        g )Nr9   r   r   Fbias)r*   r+   intermediate_sizeblock_auto_adjust_ff_dimr   block_ffn_dim_multiplierblock_multiple_ofr   Linearr2   w1w3w2)r1   rX   r   r3   s      r4   r+   Lfm2MLP.__init__   s    "44** #A(9$9A$= >..:$'(G(GJ[([$\!$*$<$<&)A)AAAE&JbJbb%! ))F..0AN))F..0AN))-/A/ANr6   c                     U R                  [        R                  " U R                  U5      5      U R	                  U5      -  5      $ r   )r   Fsilur   r   )r1   r   s     r4   rD   Lfm2MLP.forward   s/    wwqvvdggaj)DGGAJ677r6   )r   r   r   )	rK   rL   rM   rN   r   r+   rD   rQ   rR   rS   s   @r4   r   r      s    Oz O8 8r6   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$ )z*Rotates half the hidden dims of the input..Nr:   r9   r{   )rH   r-   r   )r   x1x2s      r4   rotate_halfr      sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r6   rotary_pos_embc                     UR                  U5      nUR                  U5      nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nXV4$ )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          r4   apply_rotary_pos_embr      sS    & --
&C
--
&Cw;q>C/0Gw;q>C/0Gr6   r7   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)rH   r|   reshape)r7   r   batchnum_key_value_headsslenrl   s         r4   	repeat_kvr      s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr6   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$ )Nr9   r   r:   )rs   r<   )ptrainingr   )r   num_key_value_groupsr-   matmulr   r   
functionalsoftmaxr>   r=   r<   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightsattn_outputs               r4   eager_attention_forwardr      s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!#4==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r6   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\
\R                  \R                  S-  4   4
S jjrSrU =r$ )Lfm2Attention   z=Multi-headed attention from 'Attention Is All You Need' paperrX   	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                  S-  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&                  S9U l        [%        U R                  UR&                  S9U l        g )Nrl   g      TFr   r'   )r*   r+   rX   r   rn   r2   ro   rl   r   r   r   	is_causalr   r   q_projk_projv_projout_projr%   norm_epsq_layernormk_layernormr1   rX   r   r3   s      r4   r+   Lfm2Attention.__init__   sH   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*ii 2 2F4N4NQUQ^Q^4^ejkii 2 2F4N4NQUQ^Q^4^ejkii 2 2F4N4NQUQ^Q^4^ejk		&"<"<t}}"LfN`N`glm&t}}&//J&t}}&//Jr6   Nr7   position_embeddingsr   past_key_valuesr(   c                     UR                   S S n/ UQSPU R                  P7nU R                  U R                  U5      R                  " U6 5      R                  SS5      nU R                  U R                  U5      R                  " U6 5      R                  SS5      n	U R                  U5      R                  " U6 R                  SS5      n
Uu  p[        XX5      u  pUb  UR                  XU R                  5      u  p[        R                  " U R                  R                  [         5      nU" U UU	U
U4SU R"                  S.UD6u  pUR$                  " / UQSP76 R'                  5       nU R)                  U5      nUU4$ )Nr:   r   r9           )r   r   )rH   rl   r   r   viewr   r   r   r   r   updater   r   get_interfacerX   _attn_implementationr   r   r   r   r   )r1   r7   r   r   r   r   input_shapehidden_shapequery_statesr   r   r   r   attention_interfacer   r   outputs                    r4   rD   Lfm2Attention.forward   s    $))#2.88b8$--8''M(B(G(G(VWaabcefg%%dkk-&@&E&E|&TU__`acde
{{=166EOOPQSTU&#7RU#[ &'6'='=jX\XfXf'g$J(?(M(MKK,,.E)
 %8	%
 LL	%
 	%
! "));;;;FFH{+|##r6   )rX   rl   r   r   r   r   r   r   r   r   r   r   r   )rK   rL   rM   rN   __doc__r   r   r+   r-   rP   rG   r   rD   rQ   rR   rS   s   @r4   r   r      s    GKz Kc K( )-%$||%$ #5<<#=>%$ t+	%$
 %$ 
u||U\\D00	1%$ %$r6   r   c                     UbO  UR                   S   S:  a<  UR                   S   S:  a)  U R                  nXSS2SS2S4   -  R                  U5      n U $ )ze
Tunes out the hidden states for padding tokens, see https://github.com/state-spaces/mamba/issues/66
Nr   r   )rH   r<   r=   )r7   r   r<   s      r4   apply_mask_to_padding_statesr     s_    
 !n&:&:1&=&AnFZFZ[\F]`aFa##&1d
)CCGGNr6   c                   *  ^  \ rS rSrS\S\4U 4S jjr  SS\R                  S\	S-  S\R                  S-  4S	 jjr
  SS\R                  S\	S-  S\R                  S-  4S
 jjr  SS\R                  S\	S-  S\R                  S-  4S jjrSrU =r$ )Lfm2ShortConvi,  rX   r   c           	      "  > [         TU ]  5         Xl        X l        UR                  U l        UR                  U l        [        R                  " UR                  UR                  U R
                  UR                  U R                  U R
                  S-
  S9U l        [        R                  " UR                  SUR                  -  U R                  S9U l        [        R                  " UR                  UR                  U R                  S9U l        g )Nr   )in_channelsout_channelskernel_sizegroupsr   paddingr   r   )r*   r+   rX   r   conv_L_cacheL_cache	conv_biasr   r   Conv1dr2   convr   in_projr   r   s      r4   r+   Lfm2ShortConv.__init__-  s    
 	"**$$	II**++%%LL1$
	 yy!3!3Q9K9K5KRVR[R[\		&"4"4f6H6HtyyYr6   Nr   r   r   c                    [        X5      nU R                  U5      R                  SS5      nUR                  SSS9u  pVnXQ-  nU R                  R
                  R                  U R                  R
                  R                  S5      U R                  R
                  R                  S5      5      nUb  UR                  U R                  5      (       ae  [        UR                  S5      UR                  U R                     R                  UU R                  R                  S 5      n	U	R                  S5      n	OxUbV  [         R"                  R%                  XpR&                  UR(                  S   -
  S45      n
UR+                  XR                  5      n
[-        XxU R                  R                  S S9n	Xi-  nU R/                  UR                  SS5      R1                  5       5      nU$ )Nr:   r   r{   r   r9   )
activation)r   r   r   chunkr   r/   r   sizehas_previous_stater   r!   squeezelayersconv_statesr   r   r   r   padr   rH   update_conv_stater    r   r   )r1   r   r   r   BCxBCBxconv_weightsconv_out
conv_stateys               r4   cuda_kernels_forward"Lfm2ShortConv.cuda_kernels_forwardC  s    );ll1o''B/))A2)&aUyy'',,TYY-=-=-B-B1-EtyyGWGWG\G\]^G_`&?+M+Mdnn+]+]+

2&&t~~6BB		H  ))"-H*]]..rLL288B<4OQR3ST
,>>z>>Z
'$))..UYZHLMM!++b"-88:;r6   c                    UR                   S   n[        X5      nU R                  U5      R                  SS5      nUR	                  SSS9u  pgnXa-  nUb  UR                  U R                  5      (       a  UR                  XR                  5      n	[        R                  " U	R                  UR                  5      U R                  R                  S S 2SS S 24   -  SS9n
U R                  (       a  XR                  R                  -  n
U
R                  S5      n
OqUbV  [         R"                  R%                  XR&                  UR                   S   -
  S45      n	UR                  XR                  5      n	U R                  U5      SS U24   n
Xz-  nUR                  SS5      R)                  5       nU R+                  U5      nU$ )Nr   r:   r   r   r{   r   .)rH   r   r   r   r   r  r   r  r-   sumr=   rf   r   r/   r   r   r   r   r  r   r   r   )r1   r   r   r   seqlenr  r  r	  r
  r  r  r  s               r4   slow_forwardLfm2ShortConv.slow_forwardd  ss    (;ll1o''B/))A2)&aU&?+M+Mdnn+]+](::2~~NJyyryy!9DII<L<LQPQSTW<U!U[]^HyyIINN*))"-H*]]..rLL288B<4OQR3ST
,>>z>>Z
yy}S'6'\2HLKKB**,MM!r6   r7   c                     [         (       a;  SUR                  R                  ;   a!  [        5       (       d  U R	                  XU5      $ U R                  XU5      $ )Ncuda)is_fast_path_availablerf   r~   r   r  r  )r1   r7   r   r   s       r4   rD   Lfm2ShortConv.forward  sL     "!f0D0D0I0I&IRjRlRl,,]^\\  PPr6   )r   r   rX   r   r   r   r   r"   )rK   rL   rM   rN   r   r   r+   r-   rP   r   r  r  rD   rQ   rR   rS   s   @r4   r   r   ,  s    ZZ Z2 )-.2	<<  t+	H )-.2	<<  t+	H )-.2	Q||Q Q t+	Q Qr6   r   c                      ^  \ rS rSrS\S\4U 4S jjr    SS\R                  S\	\R                  \R                  4   S-  S\R                  S-  S	\R                  S-  S
\S-  S\R                  4S jjrSrU =r$ )Lfm2DecoderLayeri  rX   r   c                 `  > [         TU ]  5         UR                  U   S:H  U l        U R                  (       a  [	        X5      U l        O[        X5      U l        [        U5      U l	        [        UR                  UR                  S9U l        [        UR                  UR                  S9U l        g )Nfull_attentionr   )r*   r+   layer_typesis_attention_layerr   	self_attnr   r   r   feed_forwardr%   r2   r   operator_normffn_normr   s      r4   r+   Lfm2DecoderLayer.__init__  s    "("4"4Y"?CS"S""*6=DN%f8DI#FO(););Q#F$6$6FOOLr6   Nr7   r   r   r   r   r(   c           	         UnU R                   (       a*  U R                  " SU R                  U5      UUUUS.UD6u  pO U R                  U R                  U5      UUS9nX-   nXR	                  U R                  U5      5      -   nU$ )N)r7   r   r   r   r   )r7   r   r    )r  r   r"  r   r!  r#  )	r1   r7   r   r   r   r   r   residual_s	            r4   rD   Lfm2DecoderLayer.forward  s     !""#~~  "00?$7-) /   M1 !II"00? /- & M
 &0%(9(9$--:V(WWr6   )r   r!  r#  r  r"  r   )NNNN)rK   rL   rM   rN   r   r   r+   r-   rP   rG   
LongTensorr   rD   rQ   rR   rS   s   @r4   r  r    s    
Mz 
Mc 
M IM.204(,|| #5<<#=>E t+	
 &&-  
 r6   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
)Lfm2PreTrainedModeli  rX   modelTr  r   F)r7   
attentionsr&  N)rK   rL   rM   rN   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_outputsrQ   r&  r6   r4   r,  r,    sQ    &*#+,#4"5N""&)#r6   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$ )	Lfm2Modeli  rX   c           	        > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [        US9U l        SU l        [#        UR                  UR$                  S9U l        U R)                  5         g s  snf )NrX   Fr   )r*   r+   pad_token_idpadding_idx
vocab_sizer   	Embeddingr2   embed_tokens
ModuleListrangenum_hidden_layersr  r  rU   
rotary_embgradient_checkpointingr%   r   embedding_norm	post_initr   s      r4   r+   Lfm2Model.__init__  s     !.. ++LL):):F<N<NPTP`P`ammBGH`H`BabBaYf0Bab
 .V<&+#)&*<*<&//R 	 cs   C?N	input_idsr   r   r   inputs_embeds	use_cacher   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R                  S   S:w  a  UOS n
UnU R                  XS9n[        U R                  S U R                  R                   5       H4  u  pU R                  R                  U   S:X  a  U	OU
nU" U4UUUUS	.UD6nM6     U R!                  U5      n[#        UUS
9$ )Nz:You must specify exactly one of input_ids or inputs_embedsr<  r   r   )rf   )rX   rK  r   r   r   )r   r  )r   r   r   r   )last_hidden_stater   )
ValueErrorrA  r   rX   get_seq_lengthr-   rp   rH   rf   r   r   rE  	enumerater  rD  r  rG  r   )r1   rJ  r   r   r   rK  rL  r   past_seen_tokenscausal_masklinear_attentionr7   r   idecoder_layer
layer_masks                   r4   rD   Lfm2Model.forward  s    -t";<YZZ  --i8M0*$++>OCRC^==?de <<(;(;A(>}G[G[\_ooL'11!4L(;;')+%
 .;-@-@-Cq-H>d%"oomoW !*$++6U8U8U*V WA(,(?(?(BFV(V\lJ))$7) / M !X ++M:&++
 	
r6   )rA  rG  rF  r  r>  rE  r?  )NNNNNN)rK   rL   rM   rN   r   r+   r   r   r   r-   r*  rP   r   FloatTensorboolr   r   r   rD   rQ   rR   rS   s   @r4   r:  r:    s    z     .2.204(,26!%6
##d*6
 t+6
 &&-	6

 6
 ((4/6
 $;6
 +,6
 
!6
    6
r6   r:  c                   P  ^  \ rS rSrSS0rSS0rSS/S/40rU 4S jr\\	        SS
\
R                  S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\\
R                  -  S\\   S\4S jj5       5       rSrU =r$ )Lfm2ForCausalLMi  zlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr7   logitsc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g )NFr   )
r*   r+   r:  r-  r?  r   r   r2   r]  rH  )r1   rX   r3   s     r4   r+   Lfm2ForCausalLM.__init__"  sU     v&
 ++yy!3!3V5F5FUS 	r6   NrJ  r   r   r   rK  labelsrL  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$ )ai  
Example:

```python
>>> from transformers import AutoTokenizer, Lfm2ForCausalLM

>>> model = Lfm2ForCausalLM.from_pretrained("meta-lfm2/Lfm2-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-lfm2/Lfm2-2-7b-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  rL  N)r_  rb  r?  )lossr_  r   r7   r.  r&  )r-  rN  r}   r   slicer]  loss_functionrX   r?  r   r   r7   r.  )r1   rJ  r   r   r   rK  rb  rL  rc  r   outputsr7   slice_indicesr_  re  s                  r4   rD   Lfm2ForCausalLM.forward+  s    > ,0:: ,
)%+',
 ,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r6   )r]  r-  r?  )NNNNNNNr   )rK   rL   rM   rN   _tied_weights_keys_tp_plan_pp_planr+   r   r   r-   r*  rP   r   rY  rZ  r   r   r   r   rD   rQ   rR   rS   s   @r4   r\  r\    s   *,GH23H_-z:;H  .2.204(,26*.!%-.6
##d*6
 t+6
 &&-	6

 6
 ((4/6
   4'6
 $;6
 ell*6
 +,6
 
 6
  6
r6   r\  )r\  r:  r,  )r   )r   )Hcollections.abcr   typingr   r-   torch.nn.functionalr   r   r   cache_utilsr   r   
generationr	   integrationsr
   r   r   masking_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   utils.import_utilsr   r   utils.output_capturingr   configuration_lfm2r   causal_conv1dr    r!   Moduler%   rU   r   r   r   rP   r   r   rO   r   r   r   kernel_modulesallr  r   r  r,  r:  r\  __all__r&  r6   r4   <module>r     s3  ( %      . ) f f / 9 O K F & I I G V 5 * DD-7** Y'J")) J (J(><")) ><B8bii 8(( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%2 )*7$BII 7$ +7$t	 #$89^, aQBII aQH)1 )X /  " J
# J
 J
Z F
)? F
 F
R Br6   