
    Z jR                        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Jr  SSKJr  SSKJr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"J#r#  SSK$J%r%  SSK&J'r'J(r(J)r)  SSK*J+r+J,r,  SSK-J.r.  SSK/J0r0   " S S\Rb                  5      r2S r3\" S5      S>S j5       r4S\Rj                  S\6S\Rj                  4S jr7 S?S\Rb                  S \Rj                  S!\Rj                  S"\Rj                  S#\Rj                  S-  S$\8S%\8S&\%\'   4S' jjr9\" \45       " S( S)\Rb                  5      5       r:\" S*5       " S+ S,\Rb                  5      5       r; " S- S.\5      r<\( " S/ S0\#5      5       r= " S1 S2\Rb                  5      r>\( " S3 S4\=5      5       r?\( " S5 S6\=\5      5       r@ " S7 S8\\=5      rA " S9 S:\\=5      rB " S; S<\\=5      rC/ S=QrDg)@    )Callable)OptionalN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernel_func_from_hubuse_kernelized_func)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs)GenericForQuestionAnswering GenericForSequenceClassificationGenericForTokenClassification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   )MistralConfigc                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )
MistralMLP#   c                   > [         TU ]  5         Xl        UR                  U l        UR                  U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l	        [        UR                     U l        g NFbias)super__init__confighidden_sizeintermediate_sizer   Linear	gate_projup_proj	down_projr   
hidden_actact_fnselfr-   	__class__s     }/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/mistral/modeling_mistral.pyr,   MistralMLP.__init__$   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../    c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ N)r3   r5   r1   r2   )r7   xr3   s      r9   forwardMistralMLP.forward.   s6    NN4;;t~~a/@#ADLLQRO#ST	r;   )r5   r-   r3   r1   r.   r/   r2   )__name__
__module____qualname____firstlineno__r,   r?   __static_attributes____classcell__r8   s   @r9   r%   r%   #   s    0 r;   r%   c                     U SSU R                   S   S-  24   nU SU R                   S   S-  S24   n[        R                  " U* U4SS9$ )z*Rotates half the hidden dims of the input..N   dim)shapetorchcat)r>   x1x2s      r9   rotate_halfrR   3   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r;   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.
)	unsqueezerR   )qkcossinunsqueeze_dimq_embedk_embeds          r9   apply_rotary_pos_embr]   :   sS    & --
&C
--
&Cw;q>C/0Gw;q>C/0Gr;   hidden_states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)rM   expandreshape)r^   r_   batchnum_key_value_headsslenhead_dims         r9   	repeat_kvrh   T   s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr;   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$ )NrJ   r   rI   )rL   dtype)ptrainingr"   )rh   num_key_value_groupsrN   matmul	transposer   
functionalsoftmaxfloat32torr   ro   rt   
contiguous)ri   rj   rk   rl   rm   rn   ro   rp   
key_statesvalue_statesattn_weightsattn_outputs               r9   eager_attention_forwardr   `   s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!#4==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r;   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$ )MistralAttentiony   z=Multi-headed attention from 'Attention Is All You Need' paperr-   	layer_idxc                   > [         TU ]  5         Xl        X l        [	        USS 5      =(       d    UR
                  UR                  -  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                  -  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        g )Nrg   g      TFr)   )r+   r,   r-   r   getattrr.   num_attention_headsrg   re   ru   rn   attention_dropout	is_causalr   r0   q_projk_projv_projo_projr7   r-   r   r8   s      r9   r,   MistralAttention.__init__}   s.   "
D9mV=O=OSYSmSm=m$*$>$>&B\B\$\!}}d*!'!9!9ii 2 2F4N4NQUQ^Q^4^ejkii 2 2F4N4NQUQ^Q^4^ejkii 2 2F4N4NQUQ^Q^4^ejkii : :T]] JFL^L^ejkr;   Nr^   position_embeddingsrm   past_key_valuesrp   r`   c           
      4   UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
Uu  p[        XX5      u  pUb  UR                  XU R                  5      u  p[        R                  " U R                  R                  [        5      nU" U UU	U
U4U R                  (       d  SOU R                   U R"                  [%        U R                  SS 5      S.UD6u  pUR&                  " / UQSP76 R)                  5       nU R+                  U5      nX4$ )NrI   r"   rJ           sliding_window)ro   rn   r   )rM   rg   r   viewrw   r   r   r]   updater   r   get_interfacer-   _attn_implementationr   rt   r   rn   r   rc   r|   r   )r7   r^   r   rm   r   rp   input_shapehidden_shapequery_statesr}   r~   rX   rY   attention_interfacer   r   s                   r9   r?   MistralAttention.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$2H2HLL"4;;0@$G
%
 
%
! "));;;;FFHkk+.((r;   )r   r-   rg   r   r   r   ru   r   r   rn   r   r=   )rA   rB   rC   rD   __doc__r#   intr,   rN   Tensortupler   r   r   r?   rE   rF   rG   s   @r9   r   r   y   s    Gl} l l& )-')||') #5<<#=>') t+	')
 ') -.') 
u||U\\D00	1') ')r;   r   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$ )MistralRMSNorm   epsr`   Nc                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)z-
MistralRMSNorm is equivalent to T5LayerNorm
N)r+   r,   r   	ParameterrN   onesweightvariance_epsilon)r7   r.   r   r8   s      r9   r,   MistralRMSNorm.__init__   s/     	ll5::k#:; #r;   r^   c                    UR                   nUR                  [        R                  5      nUR	                  S5      R                  SSS9nU[        R                  " X0R                  -   5      -  nU R                  UR                  U5      -  $ )NrJ   rI   T)keepdim)	rr   r{   rN   rz   powmeanrsqrtr   r   )r7   r^   input_dtypevariances       r9   r?   MistralRMSNorm.forward   sw    #))%((7 $$Q',,R,>%H?T?T4T(UU{{]--k:::r;   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)r   r   rM   r   )r7   s    r9   
extra_reprMistralRMSNorm.extra_repr   s*    ))*+6$2G2G1HIIr;   )r   r   )gư>)rA   rB   rC   rD   floatr,   rN   r   r?   r   rE   rF   rG   s   @r9   r   r      sB    $ $$ $ $;U\\ ;ell ;J Jr;   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$ )MistralDecoderLayer   r-   r   c                   > [         TU ]  5         UR                  U l        [        XS9U l        [        U5      U l        [        UR                  UR                  S9U l	        [        UR                  UR                  S9U l
        g )N)r-   r   r   )r+   r,   r.   r   	self_attnr%   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr   s      r9   r,   MistralDecoderLayer.__init__   sj    !--)Mf%-f.@.@fFYFYZ(6v7I7IvObOb(c%r;   Nr^   rm   position_idsr   	use_cacher   rp   r`   c           
          UnU R                  U5      nU R                  " SUUUUUUS.UD6u  pX-   nUnU R                  U5      nU R                  U5      nX-   nU$ )N)r^   rm   r   r   r   r    )r   r   r   r   )
r7   r^   rm   r   r   r   r   rp   residual_s
             r9   r?   MistralDecoderLayer.forward   s     !,,];>> 
')%+ 3
 
 !0 !55mD/ 0r;   )r.   r   r   r   r   )NNNFN)rA   rB   rC   rD   r#   r   r,   rN   r   
LongTensorr   boolr   r   r   r?   rE   rF   rG   s   @r9   r   r      s    d} d d /304(,!&HL|| t+ &&-	
  $; #5<<#=>E +, 
 r;   r   c                   R    \ rS rSr% \\S'   SrSrS/rS/r	Sr
SrSrSrSr\\S.rSrg	)
MistralPreTrainedModel   r-   modelTr   r   )r^   
attentionsr   N)rA   rB   rC   rD   r#   __annotations__base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsrE   r   r;   r9   r   r      sQ    &*#./#4"5N!"&,&r;   r   c                      ^  \ rS rSr% \R
                  \S'   SS\4U 4S jjjr\	   SS\S-  S\
S   S\S-  S	\S
\4   4S jj5       r\R                  " 5       \S 5       5       rSrU =r$ )MistralRotaryEmbeddingi  inv_freqNr-   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_lenr-   rope_parametersr   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r7   r-   devicerope_init_fnr   r8   s        r9   r,   MistralRotaryEmbedding.__init__	  s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L((ZeD0(..2BuUr;   r   ztorch.deviceseq_lenr`   ztorch.Tensorc           	         U R                   S   n[        U SS5      =(       d    U R                  U R                  -  nSnSU[        R
                  " SUS[        R                  S9R                  U[        R                  S9U-  -  -  nXe4$ )	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_thetarg   Ng      ?r   rJ   rr   )r   rr   )	r   r   r.   r   rN   arangeint64r{   r   )r-   r   r   baserL   attention_factorr   s          r9   r   6MistralRotaryEmbedding.compute_default_rope_parameters  s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 ))r;   c                 L   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   rI   r"   mpscpuF)device_typeenabledrJ   rK   r   )r   r   rb   rM   r{   r   
isinstancetypestrr   rw   rN   rO   rX   r   rY   rr   )
r7   r>   r   inv_freq_expandedposition_ids_expandedr   freqsembrX   rY   s
             r9   r?   MistralRotaryEmbedding.forward7  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   r-   r   r   r   r=   )NNN)rA   rB   rC   rD   rN   r   r   r#   r,   staticmethodr   r   r   r   r   no_gradr   r?   rE   rF   rG   s   @r9   r   r     s    llV} V V  '++/"*$*(* t* 
~u$	%	* *: ]]_<  <r;   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$ )MistralModeliG  r-   c           	        > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [        UR                  UR                  S9U l        [#        US9U l        SU l        U R)                  5         g s  snf )Nr   r-   F)r+   r,   pad_token_idpadding_idx
vocab_sizer   	Embeddingr.   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normr   
rotary_embgradient_checkpointing	post_initr   s      r9   r,   MistralModel.__init__I  s     !.. ++LL):):F<N<NPTP`P`ammEJ6KcKcEdeEd	 3Ede
 #6#5#56;N;NO	0?&+# 	 fs   C?N	input_idsrm   r   r   inputs_embedsr   rp   r`   c           
         US L US L-  (       a  [        S5      eUc  U R                  U5      nU(       a  Uc  [        U R                  S9nUcU  Ub  UR	                  5       OSn[
        R                  " UR                  S   UR                  S9U-   nUR                  S5      nU R                  R                  c  [        O[        n	U	" U R                  UUUUS9n
UnU R                  XS9nU R                  S U R                  R                    H  nU" U4U
UUUUS.UD6nM     U R!                  U5      n[#        UU(       a  US	9$ S S	9$ )
Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r"   )r   )r-   r  rm   r   r   )r   )rm   r   r   r   r   )last_hidden_stater   )
ValueErrorr  r	   r-   get_seq_lengthrN   r   rM   r   rU   r   r   r   r  r  r  r  r   )r7   r  rm   r   r   r  r   rp   past_seen_tokensmask_functioncausal_maskr^   r   decoder_layers                 r9   r?   MistralModel.forwardY  sm    -t";<YZZ  --i8M0*$++>OCRC^==?de <<(;(;A(>}G[G[\_ooL'11!4L.2kk.H.H.P*Vw#;;')+%
 &"oomoW![[)H4;;+H+HIM)*) /#$7 M J 		-0&+/8O
 	
>B
 	
r;   )r  r  r  r  r  r  r  )NNNNNN)rA   rB   rC   rD   r#   r,   r    r!   r   rN   r   r   r   FloatTensorr   r   r   r   r?   rE   rF   rG   s   @r9   r
  r
  G  s    }     .2.204(,26!%2
##d*2
 t+2
 &&-	2

 2
 ((4/2
 $;2
 +,2
 
!2
    2
r;   r
  c                   P  ^  \ rS rSrSS0rSS0rSS/S/40rU 4S jr\\	        SS
\
R                  S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\\
R                  -  S\\   S\4S jj5       5       rSrU =r$ )MistralForCausalLMi  zlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr^   logitsc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g r(   )
r+   r,   r
  r   r  r   r0   r.   r)  r  r6   s     r9   r,   MistralForCausalLM.__init__  sU     !&)
 ++yy!3!3V5F5FUS 	r;   Nr  rm   r   r   r  labelsr   logits_to_keeprp   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{  
Example:

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

>>> model = MistralForCausalLM.from_pretrained("meta-mistral/Mistral-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-mistral/Mistral-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."
```)r  rm   r   r   r  r   N)r+  r.  r  )lossr+  r   r^   r   r   )r   r  r   r   slicer)  loss_functionr-   r  r   r   r^   r   )r7   r  rm   r   r   r  r.  r   r/  rp   outputsr^   slice_indicesr+  r1  s                  r9   r?   MistralForCausalLM.forward  s    > ,0:: ,
)%+',
 ,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r;   )r)  r   r  )NNNNNNNr   )rA   rB   rC   rD   _tied_weights_keys_tp_plan_pp_planr,   r   r   rN   r   r   r   r&  r   r   r   r   r   r?   rE   rF   rG   s   @r9   r(  r(    s   *,GH23H_-z:;H  .2.204(,26*.!%-.6
##d*6
 t+6
 &&-	6

 6
 ((4/6
   4'6
 $;6
 ell*6
 +,6
 
 6
  6
r;   r(  c                       \ rS rSrSrg)MistralForTokenClassificationi  r   NrA   rB   rC   rD   rE   r   r;   r9   r;  r;        r;   r;  c                       \ rS rSrSrg) MistralForSequenceClassificationi  r   Nr<  r   r;   r9   r?  r?    r=  r;   r?  c                       \ rS rSrSrg)MistralForQuestionAnsweringi  r   Nr<  r   r;   r9   rA  rA    s    X[r;   rA  )r(  rA  r
  r   r?  r;  )r"   )r   )Ecollections.abcr   typingr   rN   r   activationsr   cache_utilsr   r	   
generationr
   integrationsr   r   r   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   r   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r    utils.output_capturingr!   configuration_mistralr#   Moduler%   rR   r]   r   r   rh   r   r   r   r   r   r   r   r
  r(  r;  r?  rA  __all__r   r;   r9   <module>rU     s   %    ! . ) f f R B  P K F & I I G 5 0  ( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%2 )*8)ryy 8) +8)v Y'JRYY J (J(&4 &R _  $><RYY ><B F
) F
 F
R F
/ F
 F
R	$ACY 		'GI_ 	 \"=?U [r;   