
    bCiS                     $   S SK JrJrJr  S SKrS SKJr  SSKJr  SSKJ	r	J
r
  SSKJr  SSKJr  SS	KJr  SS
KJr  SSKJr  SSKJrJr  SSKJrJr  SSKJrJr  SSKJr  SSK J!r!J"r"J#r#  SSK$J%r%  SSK&J'r'  SSK(J)r)  \" S5       " S S\RT                  5      5       r+ " S S\RT                  5      r,S r-S6S jr.S\R^                  S\0S\R^                  4S jr1 S7S \RT                  S!\R^                  S"\R^                  S#\R^                  S$\\R^                     S%\2S&\2S'\\!   4S( jjr3 " S) S*\RT                  5      r4 " S+ S,\5      r5 " S- S.\RT                  5      r6\" " S/ S0\5      5       r7\" " S1 S2\75      5       r8\" " S3 S4\7\5      5       r9/ S5Qr:g)8    )CallableOptionalUnionN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask)FlashAttentionKwargs)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)deprecate_kwarg)check_model_inputs   )BitNetConfigRMSNormc                   8   ^  \ rS rSrSU 4S jjrS rS rSrU =r$ )BitNetRMSNorm+   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      d/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/bitnet/modeling_bitnet.pyr$   BitNetRMSNorm.__init__-   s/     	ll5::k#:; #    c                    UR                   nUR                  [        R                  5      nUR	                  S5      R                  SSS9nU[        R                  " X0R                  -   5      -  nU R                  UR                  U5      -  $ )N   T)keepdim)	dtypetor&   float32powmeanrsqrtr)   r(   )r*   hidden_statesinput_dtypevariances       r.   forwardBitNetRMSNorm.forward5   sw    #))%((7 $$Q',,R,>%H?T?T4T(UU{{]--k:::r0   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)tupler(   shaper)   )r*   s    r.   
extra_reprBitNetRMSNorm.extra_repr<   s*    ))*+6$2G2G1HIIr0   )r)   r(   )gư>)	__name__
__module____qualname____firstlineno__r$   r>   rC   __static_attributes____classcell__r-   s   @r.   r    r    +   s    $;J Jr0   r    c                   6   ^  \ rS rSrS\4U 4S jjrS rSrU =r$ )	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$   rO   r+   intermediate_sizer   Linear	gate_projup_proj	down_projr   
hidden_actact_fnr    rms_norm_epsffn_sub_normr*   rO   r-   s     r.   r$   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[\r0   c           	          U R                  U R                  U R                  U R                  U5      5      U R	                  U5      -  5      5      nU$ N)rX   r\   rZ   rV   rW   )r*   xrX   s      r.   r>   BitNetMLP.forwardL   sF    NN4#4#4T[[PQAR5SVZVbVbcdVe5e#fg	r0   )rZ   rO   rX   r\   rV   r+   rT   rW   )	rE   rF   rG   rH   r   r$   r>   rI   rJ   rK   s   @r.   rM   rM   @   s    	]| 	] r0   rM   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$ )z*Rotates half the hidden dims of the input..Nr3   r2   dim)rB   r&   cat)ra   x1x2s      r.   rotate_halfri   Q   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r0   c                     UR                  U5      nUR                  U5      nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nXg4$ )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.
)	unsqueezeri   )qkcossinposition_idsunsqueeze_dimq_embedk_embeds           r.   apply_rotary_pos_embrt   X   sS    ( --
&C
--
&Cw;q>C/0Gw;q>C/0Gr0   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)rB   expandreshape)r;   ru   batchnum_key_value_headsslenhead_dims         r.   	repeat_kvr~   s   s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr0   modulequerykeyvalueattention_maskscalingdropoutkwargsc                 @   [        X R                  5      n[        X0R                  5      n	[        R                  " XR	                  SS5      5      U-  n
Ub"  US S 2S S 2S S 2S UR
                  S   24   nX-   n
[        R                  R                  U
S[        R                  S9R                  UR                  5      n
[        R                  R                  XU R                  S9n
[        R                  " X5      nUR	                  SS5      R                  5       nX4$ )Nr2   r   r3   )re   r5   )ptrainingr   )r~   num_key_value_groupsr&   matmul	transposerB   r   
functionalsoftmaxr7   r6   r5   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r.   eager_attention_forwardr      s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#1==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r0   c                   :  ^  \ rS rSrSrS\S\4U 4S jjr\" SSSS	9  SS
\	R                  S\\	R                  \	R                  4   S\\	R                     S\\   S\\	R                     S\\   S\\	R                  \\	R                     4   4S jj5       rSrU =r$ )BitNetAttention   z=Multi-headed attention from 'Attention Is All You Need' paperrO   	layer_idxc                   > [         TU ]  5         Xl        X l        [	        USUR
                  UR                  -  5      U l        UR                  UR                  -  U l	        U R                  S-  U l
        UR                  U l        SU l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR                  U R                  -  UR
                  UR                  S9U l        [)        UR
                  UR*                  S9U l        g )Nr}   g      TrQ   rS   )r#   r$   rO   r   getattrr+   num_attention_headsr}   r{   r   r   attention_dropout	is_causalr   rU   attention_biasq_projk_projv_projo_projr    r[   attn_sub_normr*   rO   r   r-   s      r.   r$   BitNetAttention.__init__   sf   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 +6+=+=6CVCVWr0   past_key_valuepast_key_values4.58new_nameversionr;   position_embeddingsr   cache_positionr   rv   c                 V   UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
U R                  U5      R                  U5      R	                  SS5      nUu  p[        XX5      u  pUb$  XUS.nUR                  XU R                  U5      u  p[        nU R                  R                  S:w  a  [        U R                  R                     nU" U U	U
UU4U R                  (       d  SOU R                  U R                   S.UD6u  nnUR"                  " / UQSP76 R%                  5       nU R'                  U5      nU R)                  U5      nUU4$ )Nr3   r   r2   )ro   rn   r   eager        )r   r   )rB   r}   r   viewr   r   r   rt   updater   r   rO   _attn_implementationr   r   r   r   ry   r   r   r   )r*   r;   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   rn   ro   cache_kwargsattention_interfacer   r   s                     r.   r>   BitNetAttention.forward   s    $))#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'6'='=jX\XfXfht'u$J(?;;++w6"9$++:Z:Z"[$7	%
  $}}C$2H2HLL	%
 	%
!\ "));;;;FFH((5kk+.L((r0   )r   r   rO   r}   r   r   r   r   r   r   r   r   )NN)rE   rF   rG   rH   __doc__r   intr$   r   r&   TensorrA   r   r	   
LongTensorr   r   r>   rI   rJ   rK   s   @r.   r   r      s    GX| X X0 %0A6R ,059+)||+) #5<<#=>+) !.	+)
 "%+) !!1!12+) -.+) 
u||Xell33	4+) S+)r0   r   c                   H  ^  \ rS rSrS\S\4U 4S jjr\" SSSS9      SS	\R                  S
\
\R                     S\
\R                     S\
\   S\
\   S\
\R                     S\
\\R                  \R                  4      S\\   S\R                  4S jj5       rSrU =r$ )BitNetDecoderLayer   rO   r   c                   > [         TU ]  5         UR                  U l        [        XS9U l        [        U5      U l        [        UR                  UR                  S9U l	        [        UR                  UR                  S9U l
        g )N)rO   r   rS   )r#   r$   r+   r   	self_attnrM   mlpr    r[   input_layernormpost_attention_layernormr   s      r.   r$   BitNetDecoderLayer.__init__   sj    !--(LV$,V-?-?VEXEXY(5f6H6HfNaNa(b%r0   r   r   r   r   r;   r   rp   	use_cacher   r   r   rv   c                     Un	U R                  U5      nU R                  " S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$ )N)r;   r   rp   r   r   r   r    )r   r   r   r   )r*   r;   r   rp   r   r   r   r   r   residual_s              r.   r>   BitNetDecoderLayer.forward   s     !,,];>> 	
')%+) 3	
 	
 !0 !55mD/ 0r0   )r+   r   r   r   r   )NNNFNN)rE   rF   rG   rH   r   r   r$   r   r&   r   r   r   r	   boolrA   r   r   r>   rI   rJ   rK   s   @r.   r   r      s    c| c c %0A6R 2637+/$)59KO|| !. u//0	
 "% D> !!1!12 &eELL%,,,F&GH +, 
 Sr0   r   c                      ^  \ rS rSr% \R
                  \S'   SS\4U 4S jjjr\R                  " 5       \
S 5       5       rSrU =r$ )BitNetRotaryEmbeddingi  inv_freqrO   c                   > [         TU ]  5         [        US5      (       aZ  [        UR                  [
        5      (       a;  UR                  R                  SUR                  R                  S5      5      U l        OSU l        UR                  U l	        UR                  U l
        Xl        [        U R                     U l        U R                  U R                  U5      u  o0l        U R                  SUSS9  U R                   U l        g )Nrope_scaling	rope_typetypedefaultr   F)
persistent)r#   r$   hasattr
isinstancer   dictgetr   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrO   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r*   rO   devicer   r-   s       r.   r$   BitNetRotaryEmbedding.__init__  s    6>**z&:M:Mt/T/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q((ZeD!%r0   c                 b   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        R                  " USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r3   r   mpscpuF)device_typeenabledr2   rd   )r5   )r   floatrx   rB   r6   r   r   r   strr&   autocastr   rf   rn   r   ro   r5   )
r*   ra   rp   inv_freq_expandedposition_ids_expandedr   freqsembrn   ro   s
             r.   r>   BitNetRotaryEmbedding.forward%  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   $BF  
F.)r   rO   r   r   r   r   r   r`   )rE   rF   rG   rH   r&   r   __annotations__r   r$   no_gradr   r>   rI   rJ   rK   s   @r.   r   r     s@    ll/| / /" ]]_<  <r0   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	)
BitNetPreTrainedModeli5  rO   modelTr   r   )r;   
attentionsr   N)rE   rF   rG   rH   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_outputsrI   r   r0   r.   r   r   5  sQ    &*#-.#4"5N!"&+%r0   r   c                   "  ^  \ rS rSrS\4U 4S jjr\" 5       \       SS\\	R                     S\\	R                     S\\	R                     S\\   S\\	R                     S	\\	R                     S
\\   S\\   S\4S jj5       5       rSrU =r$ )BitNetModeliH  rO   c           	        > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [        UR                  UR                  S9U l        [#        US9U l        SU l        U R)                  5         g s  snf )NrS   rO   F)r#   r$   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      r.   r$   BitNetModel.__init__J  s     !.. ++LL):):F<N<NPTP`P`ammDI&JbJbDcdDcy2Dcd
 "&"4"4&:M:MN	/v>&+# 	 es   C?	input_idsr   rp   r   inputs_embedsr   r   r   rv   c           
      J   US L US L-  (       a  [        S5      eUc  U R                  U5      nU(       a  Uc  [        U R                  S9nUcD  Ub  UR	                  5       OSn	[
        R                  " XUR                  S   -   UR                  S9nUc  UR                  S5      n[        U R                  UUUUUS9n
UnU R                  X5      nU R                  S U R                  R                    H  nU" U4U
UUUUS.UD6nM     U R                  U5      n[        UUS9$ )	Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r   )r   )rO   input_embedsr   r   r   rp   )r   rp   r   r   r   )last_hidden_stater   )
ValueErrorr  r
   rO   get_seq_lengthr&   arangerB   r   rk   r   r  r  r  r  r   )r*   r  r   rp   r   r  r   r   r   past_seen_tokensr   r;   r   decoder_layers                 r.   r>   BitNetModel.forwardZ  sR    -t";<YZZ *.*;*;I*FM0*$++>O!CRC^==?de+0<< ]5H5H5K"KTaThTh,N )33A6L(;;&))+%
 &"oomJ![[)H4;;+H+HIM)*) /-$7 M J 		-0&++
 	
r0   )r  r  r  r  r  r  r	  )NNNNNNN)rE   rF   rG   rH   r   r$   r   r   r   r&   r   r   r	   FloatTensorr   r   r   r   r>   rI   rJ   rK   s   @r.   r  r  H  s    |    151537+/5959$(8
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 !!1!128
 D>8
 +,8
 
!8
  8
r0   r  c                   b  ^  \ rS rSrS/rSrSrU 4S jr\\	         SS\
\R                     S\
\R                     S\
\R                     S\
\   S	\
\R                     S
\
\R                     S\
\   S\
\R                     S\\\R                  4   S\\   S\4S jj5       5       rSrU =r$ )BitNetForCausalLMi  zlm_head.weightNc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g )NFrQ   )
r#   r$   r  r   r	  r   rU   r+   lm_headr  r]   s     r.   r$   BitNetForCausalLM.__init__  sU      (
 ++yy!3!3V5F5FUS 	r0   r  r   rp   r   r  labelsr   r   logits_to_keepr   rv   c
                 ~   U R                   " SUUUUUUUS.U
D6nUR                  n[        U	[        5      (       a  [	        U	* S5      OU	nU R                  USS2USS24   5      nSnUb)  U R                  " SXU R                  R                  S.U
D6n[        UUUR                  UR                  UR                  S9$ )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   rp   r   r  r   r   N)logitsr&  r	  )lossr)  r   r;   r   r   )r   r  r   r   slicer$  loss_functionrO   r	  r   r   r;   r   )r*   r  r   rp   r   r  r&  r   r   r'  r   outputsr;   slice_indicesr)  r*  s                   r.   r>   BitNetForCausalLM.forward  s    J ,0:: 	,
)%+')	,
 	,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r0   )r$  r   r	  )	NNNNNNNNr   )rE   rF   rG   rH   _tied_weights_keys_tp_plan_pp_planr$   r   r   r   r&   r   r   r	   r   r   r   r   r   r   r   r>   rI   rJ   rK   s   @r.   r"  r"    s   *+HH  151537+/59-1$(5934=
E,,-=
 !.=
 u//0	=

 "%=
   1 12=
 ))*=
 D>=
 !!1!12=
 c5<</0=
 +,=
 
 =
  =
r0   r"  )r"  r  r   )Nr   )r   );typingr   r   r   r&   r   activationsr   cache_utilsr	   r
   
generationr   integrationsr   masking_utilsr   modeling_flash_attention_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.deprecationr   utils.genericr   configuration_bitnetr   Moduler    rM   ri   rt   r   r   r~   r   r   r   r   r   r   r  r"  __all__r   r0   r.   <module>rE     s  * - ,   ! . ) 7 / B 9 O K F & I I 0 / . Y'JBII J (J(		 "(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4G)bii G)T+3 +\!<BII !<H O  $ K
' K
 K
\ M
- M
 M
` Hr0   