
    Z jXU                     `   S SK Jr  S SK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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(  SSK)J*r*  SSK+J,r,  \" S5       " S S\RZ                  5      5       r. " S S\RZ                  5      r/S r0\" S5      S8S j5       r1S\Rd                  S\3S \Rd                  4S! jr4 S9S"\RZ                  S#\Rd                  S$\Rd                  S%\Rd                  S&\Rd                  S-  S'\5S(\5S)\!\#   4S* jjr6\" \15       " S+ S,\RZ                  5      5       r7 " S- S.\5      r8 " S/ S0\RZ                  5      r9\$ " S1 S2\5      5       r:\$ " S3 S4\:5      5       r;\$ " S5 S6\:\5      5       r</ S7Qr=g):    )Callable)OptionalN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernel_func_from_hubuse_kernelized_func)create_causal_mask)FlashAttentionKwargs)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)capture_outputs   )BitNetConfig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$ )BitNetRMSNorm+   epsreturnNc                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)z,
BitNetRMSNorm is equivalent to T5LayerNorm
N)super__init__r   	Parametertorchonesweightvariance_epsilon)selfhidden_sizer$   	__class__s      {/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/bitnet/modeling_bitnet.pyr(   BitNetRMSNorm.__init__-   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      -  $ )N   T)keepdim)	dtypetor*   float32powmeanrsqrtr-   r,   )r.   r4   input_dtypevariances       r1   forwardBitNetRMSNorm.forward5   sw    #))%((7 $$Q',,R,>%H?T?T4T(UU{{]--k:::r3   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)tupler,   shaper-   )r.   s    r1   
extra_reprBitNetRMSNorm.extra_repr<   s*    ))*+6$2G2G1HIIr3   )r-   r,   )gư>)__name__
__module____qualname____firstlineno__floatr(   r*   TensorrA   rF   __static_attributes____classcell__r0   s   @r1   r"   r"   +   sB    $ $$ $ $;U\\ ;ell ;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$ )	BitNetMLP@   configc                   > [         TU ]  5         Xl        UR                  U l        UR                  U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l	        [        UR                     U l        [        UR                  UR                  S9U l        g )NFbiasr$   )r'   r(   rT   r/   intermediate_sizer   Linear	gate_projup_proj	down_projr   
hidden_actact_fnr"   rms_norm_epsffn_sub_normr.   rT   r0   s     r1   r(   BitNetMLP.__init__A   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$ N)r]   ra   r_   r[   r\   )r.   xr]   s      r1   rA   BitNetMLP.forwardL   sF    NN4#4#4T[[PQAR5SVZVbVbcdVe5e#fg	r3   )r_   rT   r]   ra   r[   r/   rY   r\   )	rH   rI   rJ   rK   r   r(   rA   rN   rO   rP   s   @r1   rR   rR   @   s    	]| 	] r3   rR   c                     U SSU R                   S   S-  24   nU SU R                   S   S-  S24   n[        R                  " U* U4SS9$ )z*Rotates half the hidden dims of the input..Nr7   r6   dim)rE   r*   cat)rf   x1x2s      r1   rotate_halfrn   Q   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r3   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.
)	unsqueezern   )qkcossinunsqueeze_dimq_embedk_embeds          r1   apply_rotary_pos_embry   X   sS    & --
&C
--
&Cw;q>C/0Gw;q>C/0Gr3   r4   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)rE   expandreshape)r4   rz   batchnum_key_value_headsslenhead_dims         r1   	repeat_kvr   r   s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr3   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$ )Nr6   r   r7   )rj   r9   )ptrainingr   )r   num_key_value_groupsr*   matmul	transposer   
functionalsoftmaxr;   r:   r9   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightsattn_outputs               r1   eager_attention_forwardr   ~   s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!#4==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r3   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-  4   4S jjrSrU =r$ )BitNetAttention   z=Multi-headed attention from 'Attention Is All You Need' paperrT   	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      TrV   rX   )r'   r(   rT   r   getattrr/   num_attention_headsr   r   r   r   attention_dropout	is_causalr   rZ   attention_biasq_projk_projv_projo_projr"   r`   attn_sub_normr.   rT   r   r0   s      r1   r(   BitNetAttention.__init__   sf   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 +6+=+=6CVCVWr3   Nr4   position_embeddingsr   past_key_valuesr   r%   c                 *   UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
Uu  p[        XX5      u  pUb  UR                  XU R                  5      u  p[        R                  " U R                  R                  [        5      nU" U UU	U
U4U R                  (       d  SOU R                   U R"                  S.UD6u  pUR$                  " / UQSP76 R'                  5       nU R)                  U5      nU R+                  U5      nX4$ )Nr7   r   r6           )r   r   )rE   r   r   viewr   r   r   ry   updater   r   get_interfacerT   _attn_implementationr   r   r   r   r}   r   r   r   )r.   r4   r   r   r   r   input_shapehidden_shapequery_statesr   r   rt   ru   attention_interfacer   r   s                   r1   rA   BitNetAttention.forward   s    $))#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#[ &'6'='=jX\XfXf'g$J(?(M(MKK,,.E)
 %8	%
  $}}C$2H2HLL	%
 	%
! "));;;;FFH((5kk+.((r3   )r   r   rT   r   r   r   r   r   r   r   r   r   re   )rH   rI   rJ   rK   __doc__r   intr(   r*   rM   rD   r   r   r   rA   rN   rO   rP   s   @r1   r   r      s    GX| X X: )-')||') #5<<#=>') t+	')
 ') -.') 
u||U\\D00	1') ')r3   r   c                     ^  \ rS rSrS\S\4U 4S jjr     SS\R                  S\R                  S-  S\R                  S-  S	\
S-  S
\S-  S\\R                  \R                  4   S-  S\\   S\R                  4S jjrSrU =r$ )BitNetDecoderLayer   rT   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)rT   r   rX   )r'   r(   r/   r   	self_attnrR   mlpr"   r`   input_layernormpost_attention_layernormr   s      r1   r(   BitNetDecoderLayer.__init__   sj    !--(LV$,V-?-?VEXEXY(5f6H6HfNaNa(b%r3   Nr4   r   position_idsr   	use_cacher   r   r%   c           
          UnU R                  U5      nU R                  " SUUUUUUS.UD6u  pX-   nUnU R                  U5      nU R                  U5      nX-   nU$ )N)r4   r   r   r   r   r    )r   r   r   r   )
r.   r4   r   r   r   r   r   r   residual_s
             r1   rA   BitNetDecoderLayer.forward   s     !,,];>> 
')%+ 3
 
 !0 !55mD/ 0r3   )r/   r   r   r   r   )NNNFN)rH   rI   rJ   rK   r   r   r(   r*   rM   
LongTensorr   boolrD   r   r   rA   rN   rO   rP   s   @r1   r   r      s    c| c c /304(,!&HL|| t+ &&-	
  $; #5<<#=>E +, 
 r3   r   c                      ^  \ rS rSr% \R
                  \S'   SS\4U 4S jjjr\	   SS\S-  S\
S   S\S-  S	\S
\4   4S jj5       r\R                  " 5       \S 5       5       rSrU =r$ )BitNetRotaryEmbeddingi  inv_freqNrT   c                   > [         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defaultr   F)
persistentoriginal_inv_freq)r'   r(   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrT   rope_parametersr   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r.   rT   devicerope_init_fnr   r0   s        r1   r(   BitNetRotaryEmbedding.__init__  s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L((ZeD0(..2BuUr3   r   ztorch.deviceseq_lenr%   ztorch.Tensorc           	         U R                   S   n[        U SS5      =(       d    U R                  U R                  -  nSnSU[        R
                  " SUS[        R                  S9R                  U[        R                  S9U-  -  -  nXe4$ )	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_thetar   Ng      ?r   r6   r9   )r   r9   )	r   r   r/   r   r*   arangeint64r:   rL   )rT   r   r   baserj   attention_factorr   s          r1   r   5BitNetRotaryEmbedding.compute_default_rope_parameters  s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 ))r3   c                 L   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r7   r   mpscpuF)device_typeenabledr6   ri   r   )r   rL   r|   rE   r:   r   
isinstancetypestrr   r   r*   rk   rt   r   ru   r9   )
r.   rf   r   inv_freq_expandedposition_ids_expandedr   freqsembrt   ru   s
             r1   rA   BitNetRotaryEmbedding.forward9  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#)r   rT   r   r   r   re   )NNN)rH   rI   rJ   rK   r*   rM   __annotations__r   r(   staticmethodr   r   rD   rL   r   no_gradr   rA   rN   rO   rP   s   @r1   r   r     s    llV| V V  &*+/"*t#*(* t* 
~u$	%	* *: ]]_<  <r3   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	)
BitNetPreTrainedModeliI  rT   modelTr   r   )r4   
attentionsr   N)rH   rI   rJ   rK   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_outputsrN   r   r3   r1   r   r   I  sQ    &*#-.#4"5N!"&+%r3   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$ )BitNetModeli\  rT   c           	        > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [        UR                  UR                  S9U l        [#        US9U l        SU l        U R)                  5         g s  snf )NrX   rT   F)r'   r(   pad_token_idpadding_idx
vocab_sizer   	Embeddingr/   embed_tokens
ModuleListrangenum_hidden_layersr   layersr"   r`   normr   
rotary_embgradient_checkpointing	post_initr   s      r1   r(   BitNetModel.__init__^  s     !.. ++LL):):F<N<NPTP`P`ammDI&JbJbDcdDcy2Dcd
 "&"4"4&:M:MN	/v>&+# 	 es   C?N	input_idsr   r   r   inputs_embedsr   r   r%   c           
      >   US L US L-  (       a  [        S5      eUc  U R                  U5      nU(       a  Uc  [        U R                  S9nUcU  Ub  UR	                  5       OSn[
        R                  " UR                  S   UR                  S9U-   nUR                  S5      n[        U R                  UUUUS9n	Un
U R                  XS9nU R                  S U R                  R                    H  nU" U
4U	UUUUS.UD6n
M     U R                  U
5      n
[        U
US	9$ )
Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r   )r   )rT   r  r   r   r   )r   )r   r   r   r   r   )last_hidden_stater   )
ValueErrorr  r	   rT   get_seq_lengthr*   r   rE   r   rq   r   r  r  r  r  r   )r.   r  r   r   r   r  r   r   past_seen_tokenscausal_maskr4   r   decoder_layers                r1   rA   BitNetModel.forwardn  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&++
 	
r3   )r  r  r  r  r
  r  r  )NNNNNN)rH   rI   rJ   rK   r   r(   r   r   r   r*   r   rM   r   FloatTensorr   r   r   r   rA   rN   rO   rP   s   @r1   r  r  \  s    |     .2.204(,26!%2
##d*2
 t+2
 &&-	2

 2
 ((4/2
 $;2
 +,2
 
!2
    2
r3   r  c                   @  ^  \ rS rSrSS0rSrSrU 4S jr\\	        SS\
R                  S-  S\
R                  S-  S\
R                  S-  S	\S-  S
\
R                  S-  S\
R                  S-  S\S-  S\\
R                  -  S\\   S\4S jj5       5       rSrU =r$ )BitNetForCausalLMi  zlm_head.weightzmodel.embed_tokens.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 )NFrV   )
r'   r(   r  r   r  r   rZ   r/   lm_headr  rb   s     r1   r(   BitNetForCausalLM.__init__  sU      (
 ++yy!3!3V5F5FUS 	r3   r  r   r   r   r  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$ )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?"
```)r  r   r   r   r  r   N)logitsr'  r  )lossr*  r   r4   r   r   )r   r  r   r   slicer%  loss_functionrT   r  r   r   r4   r   )r.   r  r   r   r   r  r'  r   r(  r   outputsr4   slice_indicesr*  r+  s                  r1   rA   BitNetForCausalLM.forward  s    H ,0:: ,
)%+',
 ,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r3   )r%  r   r  )NNNNNNNr   )rH   rI   rJ   rK   _tied_weights_keys_tp_plan_pp_planr(   r   r   r*   r   rM   r   r!  r   r   r   r   r   rA   rN   rO   rP   s   @r1   r#  r#    s   *,GHHH  .2.204(,26*.!%-.;
##d*;
 t+;
 &&-	;

 ;
 ((4/;
   4';
 $;;
 ell*;
 +,;
 
 ;
  ;
r3   r#  )r#  r  r   )r   )r   )>collections.abcr   typingr   r*   r   activationsr   cache_utilsr   r	   
generationr
   integrationsr   r   r   masking_utilsr   modeling_flash_attention_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   utils.output_capturingr   configuration_bitnetr   Moduler"   rR   rn   ry   rM   r   r   rL   r   r   r   r   r   r  r#  __all__r   r3   r1   <module>rG     s  ( %    ! . ) f f / B 9 O K F & I I G 5 . Y'JBII J (J(		 "( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%2 )*B)bii B) +B)J(3 (V><BII ><B O  $ F
' F
 F
R K
- K
 K
\ Hr3   