
    fThz                     z   S SK JrJrJrJr  S SKrS SKJr  SSKJr  SSK	J
r
Jr  SSKJr  SSKJr  SS	KJr  SS
KJr  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%J&r&  SSK'J(r(  \%" 5       (       a  S SK)J*r*  SSK+J,r,  \&RZ                  " \.5      r/\" S5       " S S\R`                  5      5       r1 " S S\R`                  5      r2S r3S7S jr4S\Rj                  S\6S\Rj                  4S jr7 S8S \R`                  S!\Rj                  S"\Rj                  S#\Rj                  S$\\Rj                     S%\8S&\84S' jjr9 " S( S)\R`                  5      r: " S* S+\5      r; " S, S-\R`                  5      r<\# " S. S/\5      5       r=\# " S0 S1\=5      5       r> " S2 S3\\"5      r?\# " S4 S5\=\5      5       r@/ S6QrAg)9    )CallableOptionalTupleUnionN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)AttentionMaskConverter)FlashAttentionKwargs)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)
LossKwargsauto_docstringcan_return_tupleis_torch_flex_attn_availablelogging   )BitNetConfig)	BlockMask)make_flex_block_causal_maskRMSNormc                   8   ^  \ rS rSrSU 4S jjrS rS rSrU =r$ )BitNetRMSNorm2   c                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)z,
BitNetRMSNorm is equivalent to T5LayerNorm
N)super__init__r   	Parametertorchonesweightvariance_epsilon)selfhidden_sizeeps	__class__s      b/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/bitnet/modeling_bitnet.pyr'   BitNetRMSNorm.__init__4   s/     	ll5::k#:; #    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      -  $ )N   T)keepdim)	dtypetor)   float32powmeanrsqrtr,   r+   )r-   hidden_statesinput_dtypevariances       r1   forwardBitNetRMSNorm.forward<   sw    #))%((7 $$Q',,R,>%H?T?T4T(UU{{]--k:::r3   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)tupler+   shaper,   r-   s    r1   
extra_reprBitNetRMSNorm.extra_reprC   s*    ))*+6$2G2G1HIIr3   )r,   r+   )gư>)	__name__
__module____qualname____firstlineno__r'   rA   rG   __static_attributes____classcell__r0   s   @r1   r#   r#   2   s    $;J Jr3   r#   c                   6   ^  \ rS rSrS\4U 4S jjrS rSrU =r$ )	BitNetMLPG   configc                   > [         TU ]  5         Xl        UR                  U l        UR                  U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l	        [        UR                     U l        [        UR                  UR                  S9U l        g )NFbiasr/   )r&   r'   rS   r.   intermediate_sizer   Linear	gate_projup_proj	down_projr	   
hidden_actact_fnr#   rms_norm_epsffn_sub_normr-   rS   r0   s     r1   r'   BitNetMLP.__init__H   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../)&*B*BH[H[\r3   c           	          U R                  U R                  U R                  U R                  U5      5      U R	                  U5      -  5      5      nU$ N)r\   r`   r^   rZ   r[   )r-   xr\   s      r1   rA   BitNetMLP.forwardS   sF    NN4#4#4T[[PQAR5SVZVbVbcdVe5e#fg	r3   )r^   rS   r\   r`   rZ   r.   rX   r[   )	rI   rJ   rK   rL   r   r'   rA   rM   rN   rO   s   @r1   rQ   rQ   G   s    	]| 	] r3   rQ   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$ )z*Rotates half the hidden dims of the input..Nr6   r5   dim)rE   r)   cat)re   x1x2s      r1   rotate_halfrm   X   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r3   c                     UR                  U5      nUR                  U5      nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nXg4$ )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.
)	unsqueezerm   )qkcossinposition_idsunsqueeze_dimq_embedk_embeds           r1   apply_rotary_pos_embrx   _   sS    ( --
&C
--
&Cw;q>C/0Gw;q>C/0Gr3   r>   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)rE   expandreshape)r>   ry   batchnum_key_value_headsslenhead_dims         r1   	repeat_kvr   z   s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr3   modulequerykeyvalueattention_maskscalingdropoutc                 @   [        X R                  5      n[        X0R                  5      n	[        R                  " XR	                  SS5      5      U-  n
Ub"  US S 2S S 2S S 2S UR
                  S   24   nX-   n
[        R                  R                  U
S[        R                  S9R                  UR                  5      n
[        R                  R                  XU R                  S9n
[        R                  " X5      nUR	                  SS5      R                  5       nX4$ )Nr5   r   r6   )ri   r8   )ptrainingr   )r   num_key_value_groupsr)   matmul	transposerE   r   
functionalsoftmaxr:   r9   r8   r   r   
contiguous)r   r   r   r   r   r   r   kwargs
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r1   eager_attention_forwardr      s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#1==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r3   c                   F  ^  \ rS rSrSrS\S\4U 4S jjr  SS\R                  S\
\R                  \R                  4   S\\R                     S	\\   S
\\R                     S\\   S\
\R                  \\R                     \\
\R                        4   4S jjrSrU =r$ )BitNetAttention   z=Multi-headed attention from 'Attention Is All You Need' paperrS   	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                  -  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        [)        UR
                  UR*                  S9U l        g )Nr   g      TrU   rW   )r&   r'   rS   r   getattrr.   num_attention_headsr   r   r   r   attention_dropout	is_causalr   rY   attention_biasq_projk_projv_projo_projr#   r_   attn_sub_normr-   rS   r   r0   s      r1   r'   BitNetAttention.__init__   sf   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 +6+=+=6CVCVWr3   r>   position_embeddingsr   past_key_valuecache_positionr   rz   c                    UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
U R                  U5      R                  U5      R	                  SS5      nUu  p[        XX5      u  pUb$  XUS.nUR                  XU R                  U5      u  p[        nU R                  R                  S:w  ad  U R                  R                  S:X  a-  UR                  SS5      (       a  [        R                  S	5        O[         U R                  R                     nU" U U	U
UU4U R"                  (       d  S
OU R$                  U R&                  S.UD6u  nnUR(                  " / UQSP76 R+                  5       nU R-                  U5      nU R/                  U5      nUU4$ )Nr6   r   r5   )rs   rr   r   eagersdpaoutput_attentionsFz`torch.nn.functional.scaled_dot_product_attention` does not support `output_attentions=True`. Falling back to eager attention. This warning can be removed using the argument `attn_implementation="eager"` when loading the model.        )r   r   )rE   r   r   viewr   r   r   rx   updater   r   rS   _attn_implementationgetloggerwarning_oncer   r   r   r   r}   r   r   r   )r-   r>   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   rr   rs   cache_kwargsattention_interfacer   r   s                     r1   rA   BitNetAttention.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{{//69fjjI\^c>d>d##L
 '>dkk>^>^&_#$7	%
  $}}C$2H2HLL	%
 	%
!\ "));;;;FFH((5kk+.L((r3   )r   r   rS   r   r   r   r   r   r   r   r   r   )NN)rI   rJ   rK   rL   __doc__r   intr'   r)   Tensorr   r   r
   
LongTensorr   r   rA   rM   rN   rO   s   @r1   r   r      s    GX| X X: +/591)||1) #5<<#=>1) !.	1)
 !1) !!1!121) -.1) 
u||Xell3XeELL>Q5RR	S1) 1)r3   r   c                     ^  \ rS rSrS\S\4U 4S jjr       SS\R                  S\	\R                     S\	\R                     S\	\   S	\	\   S
\	\   S\	\R                     S\	\\R                  \R                  4      S\\   S\\R                   \	\\R                   \R                   4      4   4S jjrSrU =r$ )BitNetDecoderLayer   rS   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)rS   r   rW   )r&   r'   r.   r   	self_attnrQ   mlpr#   r_   input_layernormpost_attention_layernormr   s      r1   r'   BitNetDecoderLayer.__init__   sj    !--(LV$,V-?-?VEXEXY(5f6H6HfNaNa(b%r3   r>   r   rt   r   r   	use_cacher   r   r   rz   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X-   nUn
U R                  U5      nU R                  U5      nX-   nU4nU(       a  X4-  nU$ )N)r>   r   rt   r   r   r   r   r    )r   r   r   r   )r-   r>   r   rt   r   r   r   r   r   r   residualself_attn_weightsoutputss                r1   rA   BitNetDecoderLayer.forward   s     !,,]; ,0>> 
,
')%)/) 3
,
 
,
( !0 !55mD/ 0 "++Gr3   )r.   r   r   r   r   )NNNFFNN)rI   rJ   rK   rL   r   r   r'   r)   r   r   r   r
   boolr   r   r   FloatTensorrA   rM   rN   rO   s   @r1   r   r      s   c| c c 2637*.,1$)59KO'||' !.' u//0	'
 !' $D>' D>' !!1!12' &eELL%,,,F&GH' -.' 
u  (51B1BEDUDU1U+V"WW	X' 'r3   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$ )BitNetRotaryEmbeddingi$  rS   c                   > [         TU ]  5         [        US5      (       aH  UR                  b;  UR                  R	                  SUR                  R	                  S5      5      U l        OSU l        UR                  U l        UR                  U l        Xl	        [        U R
                     U l        U R                  U R                  U5      u  o0l        U R                  SUSS9  U R                  U l        g )Nrope_scaling	rope_typetypedefaultinv_freqF)
persistent)r&   r'   hasattrr   r   r   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrS   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r-   rS   devicer   r0   s       r1   r'   BitNetRotaryEmbedding.__init__%  s    6>**v/B/B/N#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q((ZeD!%r3   c                 b   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        R                  " USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r6   r   mpscpuF)device_typeenabledr5   rh   )r8   )r   floatr|   rE   r9   r   
isinstancer   strr)   autocastr   rj   rr   r   rs   r8   )
r-   re   rt   inv_freq_expandedposition_ids_expandedr   freqsembrr   rs   s
             r1   rA   BitNetRotaryEmbedding.forward6  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   $BF  
F.)r   rS   r   r   r   r   r   rd   )rI   rJ   rK   rL   r   r'   r)   no_gradr   rA   rM   rN   rO   s   @r1   r   r   $  s6    /| / /" ]]_<  <r3   r   c                   N    \ rS rSr\rSrSrS/rS/r	Sr
SrSrSrSrSrSrS rSrg)	BitNetPreTrainedModeliF  modelTr   past_key_valuesc                    U R                   R                  n[        U[        R                  5      (       aW  UR
                  R                  R                  SUS9  UR                  b%  UR                  R                  R                  5         g g [        U[        R                  5      (       ad  UR
                  R                  R                  SUS9  UR                  b2  UR
                  R                  UR                     R                  5         g g [        U[        5      (       a&  UR
                  R                  R                  S5        g g )Nr   )r<   stdg      ?)rS   initializer_ranger   r   rY   r+   datanormal_rV   zero_	Embeddingpadding_idxr#   fill_)r-   r   r   s      r1   _init_weights#BitNetPreTrainedModel._init_weightsU  s    kk++fbii((MM&&CS&9{{&  &&( '--MM&&CS&9!!-""6#5#56<<> ...MM$$S) /r3   r   N)rI   rJ   rK   rL   r   config_classbase_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_2_supports_sdpa_supports_flex_attn_supports_cache_class_supports_quantized_cache_supports_static_cache_supports_attention_backendr  rM   r   r3   r1   r   r   F  sS    L&*#-.#4"5!N  $!"&*r3   r   c                     ^  \ rS rSrS\4U 4S jjrS rS r\\	         SS\
\R                     S\
\R                     S\
\R                     S	\
\   S
\
\R                     S\
\   S\
\   S\
\   S\
\R                     S\\   S\4S jj5       5       r SS\\R                  S4   S\R                  S\R                  S	\S\4
S jjr\S\R                  S\S\S\R2                  S\R                  S\4S j5       rSrU =r$ )BitNetModelic  rS   c           	        > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [        UR                  UR                  S9U l        [#        US9U l        SU l        U R)                  5         g s  snf )NrW   )rS   F)r&   r'   pad_token_idr  
vocab_sizer   r  r.   embed_tokens
ModuleListrangenum_hidden_layersr   layersr#   r_   normr   
rotary_embgradient_checkpointing	post_initr   s      r1   r'   BitNetModel.__init__e  s     !.. ++LL):):F<N<NPTP`P`ammDI&JbJbDcdDcy2Dcd
 "&"4"4&:M:MN	/v>&+# 	 es   C?c                     U R                   $ rd   r  rF   s    r1   get_input_embeddings BitNetModel.get_input_embeddingsu  s       r3   c                     Xl         g rd   r#  r-   r   s     r1   set_input_embeddings BitNetModel.set_input_embeddingsx  s    !r3   	input_idsr   rt   r   inputs_embedsr   r   output_hidden_statesr   flash_attn_kwargsrz   c
                 J   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[        S 5      [        45      (       d  [	        S5      eUc  U R                  U5      nU(       a  Uc
  [        5       nU	cD  Ub  UR                  5       OSn[        R                   " XUR"                  S   -   UR$                  S9n	Uc  U	R'                  S5      nU R)                  X%XU5      nUnU R+                  X5      nU(       a  SOS nU(       a  SOS nU R,                  S U R                   R.                    H7  nU(       a  X4-  nU" U4UUUUUU	US	.U
D6nUS   nU(       d  M.  UUS   4-  nM9     U R1                  U5      nU(       a  X4-  n[3        UU(       a  UOS UUS
9$ )Nz:You must specify exactly one of input_ids or inputs_embedszX`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.FzBThe `past_key_values` should be either a `Cache` object or `None`.r   r   r   r   )r   rt   r   r   r   r   r   )last_hidden_stater   r>   
attentions)rS   r   r,  r   
ValueErrorr  r   r   r   r   r   r
   r  r   get_seq_lengthr)   arangerE   r   ro   _update_causal_maskr  r  r  r  r   )r-   r*  r   rt   r   r+  r   r   r,  r   r-  past_seen_tokensr   r>   r   all_hidden_statesall_self_attnsdecoder_layerlayer_outputss                      r1   rA   BitNetModel.forward{  sI    2C1N-TXT_T_TqTq$8$D $++JjJj 	 "+!6IDKK<Q<Q	-t";<YZZ&&4==Yj I /DJ+>??abb  --i8M0*nO!CRC^==?de"\\ ]5H5H5K"KTaThThN )33A6L..>L]
 & #oomJ #7BD0d![[)H4;;+H+HIM#!%55!)
*)."3#-$7
 $
M *!,M  =#3"55' J* 		-0  !11&+/8Od+%	
 	
r3   r   input_tensorc           	         U R                   R                  S:X  a  Ub  US:H  R                  5       (       a  U$ g U R                   R                  S:X  a,  [        U[        R
                  5      (       a  [        U5      nU$ Ub  UR                  5       OSnUb  UR                  OSnU R                   R                  S:X  a5  U(       d.  U(       d'  [        R                  " UUUU R                  S9(       a  g UR                  nUR                  S   n	U(       a  UR                  5       n
O5[        U[        R
                  5      (       a  UR                  S	   OXi-   S-   n
U R                  UU	U
UUUR                  S   S
9nU R                   R                  S:X  aZ  UbW  UR                   R"                  S;   a=  U(       d6  [        R$                  " U5      R&                  n[        R(                  " X5      nU$ )Nflash_attention_2r   flex_attentionr   Fr   )r+  past_key_values_lengthis_trainingr   r6   )sequence_lengthtarget_lengthr8   r   
batch_size)cudaxpunpu)rS   r   anyr   r)   r   r    r3  is_compileabler   _ignore_causal_mask_sdpar   r8   rE   get_max_cache_shape5_prepare_4d_causal_attention_mask_with_cache_positionr   r   finfomin_unmask_unattended)r-   r   r<  r   r   r   r6  using_compilable_cacher8   rB  rC  r   	min_dtypes                r1   r5  BitNetModel._update_causal_mask  s    ;;++/BB)~/D.I.I.K.K%%;;++/??.%,,77!<^!L!!
 @O?Z?99;`aCRC^!?!?di ;;++v5>T]n%>>*'7 MM	 ""&,,Q/!+??AM nell;; $$R(%7!;  PP+')#))!, Q 
 KK,,6*%%**.DD%
 E*..I0CCK[Kr3   rB  rC  r8   rD  c                    U b  U R                  5       S:X  a  U nU$ [        R                  " U5      R                  n[        R                  " X4XUR
                  S9nUS:w  a  [        R                  " USS9nU[        R                  " X$R
                  S9UR                  SS5      :  -  nUSSSS2SS24   R                  USSS5      nU b  UR                  5       nU R                  S   n	USS2SS2SS2SU	24   U SS2SSSS24   R                  UR
                  5      -   n
U
S:H  n
USS2SS2SS2SU	24   R                  X5      USS2SS2SS2SU	24'   U$ )	a  
Creates a causal 4D mask of shape `(batch_size, 1, query_length, key_value_length)` from a 2D mask of shape
`(batch_size, key_value_length)`, or if the input `attention_mask` is already 4D, do nothing.

Args:
    attention_mask (`torch.Tensor`):
        A 2D attention mask of shape `(batch_size, key_value_length)` or a 4D attention mask of shape
        `(batch_size, 1, query_length, key_value_length)`.
    sequence_length (`int`):
        The sequence length being processed.
    target_length (`int`):
        The target length: when generating with static cache, the mask should be as long as the static cache,
        to account for the 0 padding, the part of the cache that is not filled yet.
    dtype (`torch.dtype`):
        The dtype to use for the 4D attention mask.
    cache_position (`torch.Tensor`):
        Indices depicting the position of the input sequence tokens in the sequence.
    batch_size (`torch.Tensor`):
        Batch size.
N   )
fill_valuer8   r   r   )diagonalr/  r6   r   )ri   r)   rM  rN  fullr   triur4  r}   r|   clonerE   r9   masked_fill)r   rB  rC  r8   r   rD  r   r   rQ  mask_lengthpadding_masks              r1   rL  ABitNetModel._prepare_4d_causal_attention_mask_with_cache_position  s}   < %.*<*<*>!*C(K* ' E*..I** 0Y\j\q\qK !##jjqA5<<>S>STWeWmWmnprsWtttK%dD!Q&67>>z1bRTUK))//1,2226*1aL[L+@ANSTVZ\`bcScDdDgDg&&E    ,q05@Aq,;,AV5W5c5c 6Aq!\k\12 r3   )r  r  r  r  r  r  r  )	NNNNNNNNN)F)rI   rJ   rK   rL   r   r'   r$  r(  r   r   r   r)   r   r   r
   r   r   r   r   r   rA   r   r5  staticmethodr   r8   rL  rM   rN   rO   s   @r1   r  r  c  s   |  !"  151537+/59$(,0/359\
E,,-\
 !.\
 u//0	\

 "%\
   1 12\
 D>\
 $D>\
 'tn\
 !!1!12\
 $$89\
 
!\
  \
H #(BellK78B llB 	B
 B  BH 444 4 {{	4
 4 4 4r3   r  c                       \ rS rSrSrg)KwargsForCausalLMiW  r   N)rI   rJ   rK   rL   rM   r   r3   r1   r`  r`  W  s    3r3   r`  c                     ^  \ rS rSrS/rSrSrU 4S jrS rS r	S r
S rS	 rS
 r\\           SS\\R$                     S\\R&                     S\\R$                     S\\   S\\R*                     S\\R$                     S\\   S\\   S\\   S\\R$                     S\\\R&                  4   S\\   S\4S jj5       5       rSrU =r$ )BitNetForCausalLMiZ  zlm_head.weightNc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g )NFrU   )
r&   r'   r  r   r  r   rY   r.   lm_headr   ra   s     r1   r'   BitNetForCausalLM.__init__`  sU      (
 ++yy!3!3V5F5FUS 	r3   c                 .    U R                   R                  $ rd   r   r  rF   s    r1   r$  &BitNetForCausalLM.get_input_embeddingsi  s    zz&&&r3   c                 $    XR                   l        g rd   rg  r'  s     r1   r(  &BitNetForCausalLM.set_input_embeddingsl  s    "'

r3   c                     U R                   $ rd   rd  rF   s    r1   get_output_embeddings'BitNetForCausalLM.get_output_embeddingso  s    ||r3   c                     Xl         g rd   rl  )r-   new_embeddingss     r1   set_output_embeddings'BitNetForCausalLM.set_output_embeddingsr  s    %r3   c                     Xl         g rd   r   )r-   decoders     r1   set_decoderBitNetForCausalLM.set_decoderu  s    
r3   c                     U R                   $ rd   rt  rF   s    r1   get_decoderBitNetForCausalLM.get_decoderx  s    zzr3   r*  r   rt   r   r+  labelsr   r   r,  r   logits_to_keepr   rz   c                    Ub  UOU R                   R                  nU	b  U	OU R                   R                  n	U R                  " SUUUUUUUU	U
S.	UD6nUR                  n[        U[        5      (       a  [        U* S5      OUnU R                  USS2USS24   5      nSnUb)  U R                  " SUX`R                   R                  S.UD6n[        UUUR                  UR                  UR                  S9$ )a  
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
    Labels for computing the masked language modeling loss. Indices should either be in `[0, transformers.,
    config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
    (masked), the loss is only computed for the tokens with labels in `[0, transformers., config.vocab_size]`.

Example:

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

>>> model = BitNetForCausalLM.from_pretrained("microsoft/bitnet-b1.58-2B-4T")
>>> tokenizer = AutoTokenizer.from_pretrained("microsoft/bitnet-b1.58-2B-4T")

>>> prompt = f'<|begin_of_text|>User: Hey, are you conscious? Can you talk to me?<|eot_id|>Assistant: '
>>> inputs = tokenizer(prompt, return_tensors="pt")

>>> # Generate
>>> generate_ids = model.generate(inputs.input_ids, max_length=100)
>>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
"User: Hey, are you conscious? Can you talk to me?Assistant: No, I'm not conscious. I'm an artificial intelligence designed to assist with information and tasks. How can I help you today?"
```N)	r*  r   rt   r   r+  r   r   r,  r   )logitsr{  r  )lossr~  r   r>   r1  r   )rS   r   r,  r   r0  r   r   slicerd  loss_functionr  r   r   r>   r1  )r-   r*  r   rt   r   r+  r{  r   r   r,  r   r|  r   r   r>   slice_indicesr~  r  s                     r1   rA   BitNetForCausalLM.forward{  s   N 2C1N-TXT_T_TqTq$8$D $++JjJj 	
 ,0:: ,
)%+'/!5),
 ,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVF{{OeOepiopD%#33!//))
 	
r3   )rd  r   r  )NNNNNNNNNNr   )rI   rJ   rK   rL   _tied_weights_keys_tp_plan_pp_planr'   r$  r(  rm  rq  rv  ry  r   r   r   r)   r   r   r
   r   r   r   r   r   r`  r   rA   rM   rN   rO   s   @r1   rb  rb  Z  sk   *+HH'(&  151537+/59-1$(,0/35934G
E,,-G
 !.G
 u//0	G

 "%G
   1 12G
 ))*G
 D>G
 $D>G
 'tnG
 !!1!12G
 c5<</0G
 *+G
 
 G
  G
r3   rb  )rb  r  r   )Nr   )r   )Btypingr   r   r   r   r)   r   activationsr	   cache_utilsr
   r   
generationr   integrationsr   modeling_attn_mask_utilsr   modeling_flash_attention_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   r   configuration_bitnetr   !torch.nn.attention.flex_attentionr   integrations.flex_attentionr    
get_loggerrI   r   Moduler#   rQ   rm   rx   r   r   r   r   r   r   r   r   r   r  r`  rb  __all__r   r3   r1   <module>r     s  * 4 3   ! . ) 7 > B 9 O K F & h h .  !!;J 
		H	% Y'JBII J (J(		 "(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % %4L)bii L)^23 2j<BII <D *O * *8 p' p pf ?,j > i
- i
 i
X Hr3   