
    Z jT                     ^   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
  SSKJr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  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%  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\R`                  S\1S\R`                  4S jr2 S8S\RZ                  S\R`                  S \R`                  S!\R`                  S"\R`                  S-  S#\3S$\3S%\"\   4S& jjr4S9S' jr5S( r6\" \55       " S) S*\RZ                  5      5       r7 " S+ S,\RZ                  5      r8 " S- S.\5      r9\$ " S/ S0\ 5      5       r:\$ " S1 S2\:5      5       r;\$ " S3 S4\:\5      5       r< " S5 S6\\:5      r=/ S7Qr>g):    )Callable)OptionalN)TransformersKwargs   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernelized_func)create_causal_mask) GenericForSequenceClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)auto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs   )Olmo2ConfigRMSNormc                   `   ^  \ rS rSrS	S\SS4U 4S jjjrS\R                  4S jrS r	Sr
U =r$ )
Olmo2RMSNorm2   epsreturnNc                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)z+
Olmo2RMSNorm is equivalent to T5LayerNorm
N)super__init__nn	Parametertorchonesweightvariance_epsilon)selfhidden_sizer"   	__class__s      y/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/olmo2/modeling_olmo2.pyr&   Olmo2RMSNorm.__init__4   s/     	ll5::k#:; #    c                    UR                   nUR                  [        R                  5      nUR	                  S5      R                  SSS9nU[        R                  " X0R                  -   5      -  nU R                  U-  R                  U5      $ )N   T)keepdim)	dtypetor)   float32powmeanrsqrtr,   r+   )r-   hidden_statesinput_dtypevariances       r0   forwardOlmo2RMSNorm.forward<   sw    #))%((7 $$Q',,R,>%H?T?T4T(UUm+//<<r2   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)tupler+   shaper,   )r-   s    r0   
extra_reprOlmo2RMSNorm.extra_reprC   s*    ))*+6$2G2G1HIIr2   )r,   r+   )gư>)__name__
__module____qualname____firstlineno__floatr&   r)   Tensorr@   rE   __static_attributes____classcell__r/   s   @r0   r    r    2   s7    $ $$ $ $= =J Jr2   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$ )Olmo2RotaryEmbeddingG   inv_freqNconfigc                   > [         TU ]  5         UR                  U l        UR                  U l        Xl        U R
                  R                  S   U l        U R                  nU R                  S:w  a  [        U R                     nU" U R
                  U5      u  o@l
        U R                  SUSS9  U R                  SUR                  5       SS9  g )N	rope_typedefaultrS   F)
persistentoriginal_inv_freq)r%   r&   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrT   rope_parametersrV   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r-   rT   devicerope_init_fnrS   r/   s        r0   r&   Olmo2RotaryEmbedding.__init__J   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L((ZeD0(..2BuUr2   rb   ztorch.deviceseq_lenr#   ztorch.Tensorc           	         U R                   S   n[        U SS5      =(       d    U R                  U R                  -  nSnSU[        R
                  " SUS[        R                  S9R                  U[        R                  S9U-  -  -  nXe4$ )	aH  
Computes the inverse frequencies according to the original RoPE implementation
Args:
    config ([`~transformers.PreTrainedConfig`]):
        The model configuration.
    device (`torch.device`):
        The device to use for initialization of the inverse frequencies.
    seq_len (`int`, *optional*):
        The current sequence length. Unused for this type of RoPE.
Returns:
    Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
    post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).

rope_thetahead_dimNg      ?r   r4   )r7   )rb   r7   )	r]   getattrr.   num_attention_headsr)   arangeint64r8   rK   )rT   rb   re   basedimattention_factorrS   s          r0   r^   4Olmo2RotaryEmbedding.compute_default_rope_parametersZ   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 ))r2   c                    U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        X4$ ! , (       d  f       WW	4$ = f)
Nr   r5   r   mpscpuF)device_typeenabledr4   rn   )rS   rK   expandrD   r8   rb   
isinstancetypestrr   	transposer)   catcosr_   sin)
r-   xposition_idsinv_freq_expandedposition_ids_expandedrt   freqsembr}   r~   s
             r0   r@   Olmo2RotaryEmbedding.forwardx   s7    !MM$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
 x DC
 Cxs   BE&&
E7)r_   rT   r[   r\   rV   N)NNN)rG   rH   rI   rJ   r)   rL   __annotations__r   r&   staticmethodr   intrC   rK   r^   no_gradr   r@   rM   rN   rO   s   @r0   rQ   rQ   G   s    llV{ V V  %)+/"*d"*(* t* 
~u$	%	* *: ]]_
  
r2   rQ   r=   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)rD   rw   reshape)r=   r   batchnum_key_value_headsslenrh   s         r0   	repeat_kvr      s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr2   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$ )Nr4   r   r5   )rn   r7   )ptrainingr   )r   num_key_value_groupsr)   matmulr{   r'   
functionalsoftmaxr9   r8   r7   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightsattn_outputs               r0   eager_attention_forwardr      s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!#4==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r2   c                    U R                   UR                   peUR                  U5      nUR                  U5      nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nUR                  U5      UR                  U5      4$ )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.
)r7   	unsqueezerotate_halfr8   )	qkr}   r~   unsqueeze_dimq_typek_typeq_embedk_embeds	            r0   apply_rotary_pos_embr      sv    $ WWaggF
--
&C
--
&Cw;q>C/0Gw;q>C/0G::fwzz&111r2   c                     U SSU R                   S   S-  24   nU SU R                   S   S-  S24   n[        R                  " U* U4SS9$ )z*Rotates half the hidden dims of the input..Nr5   r4   rv   )rD   r)   r|   )r   x1x2s      r0   r   r      sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r2   c                     ^  \ rS rSrSrSS\S\S-  4U 4S j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$ )Olmo2Attention   z=Multi-headed attention from 'Attention Is All You Need' paperNrT   	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                  -  UR*                  5      U l        [)        UR                  U R                  -  UR*                  5      U l        g )Nrh   g      Tbias)r%   r&   rT   r   ri   r.   rj   rh   r   r   r   attention_dropout	is_causalr'   Linearattention_biasq_projk_projv_projo_projr    rms_norm_epsq_normk_normr-   rT   r   r/   s      r0   r&   Olmo2Attention.__init__   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 #6#=#=#MvObObc"6#=#=#MvObObcr2   r=   position_embeddingsr   past_key_valuesr   r#   c                 P   UR                   S S n/ UQSPU R                  P7nU R                  U R                  U5      5      nU R	                  U R                  U5      5      n	U R                  U5      n
UR                  U5      R                  SS5      nU	R                  U5      R                  SS5      n	U
R                  U5      R                  SS5      n
Uu  p[        XX5      u  pUb  UR                  XU R                  5      u  p[        R                  " U R                  R                  [         5      nU" U UU	U
U4U R"                  (       d  SOU R$                  U R&                  S.UD6u  pUR(                  " / UQSP76 R+                  5       nU R-                  U5      nX4$ )Nr5   r   r4           )r   r   )rD   rh   r   r   r   r   r   viewr{   r   updater   r   get_interfacerT   _attn_implementationr   r   r   r   r   r   r   )r-   r=   r   r   r   r   input_shapehidden_shapequery_statesr   r   r}   r~   attention_interfacer   r   s                   r0   r@   Olmo2Attention.forward   s    $))#2.88b8$--8{{4;;}#=>[[]!;<
{{=1#((6@@AF__\2<<QB
#((6@@AF&#7RU#[ &'6'='=jX\XfXf'g$J(?(M(MKK,,.E)
 %8	%
  $}}C$2H2HLL	%
 	%
! "));;;;FFHkk+.((r2   )r   rT   rh   r   r   r   r   r   r   r   r   r   r   r   )rG   rH   rI   rJ   __doc__r   r   r&   r)   rL   rC   r   r   r   r@   rM   rN   rO   s   @r0   r   r      s    Gd{ dsTz d d< )-*)||*) #5<<#=>*) t+	*)
 *) +,*) 
u||U\\D00	1*) *)r2   r   c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )Olmo2MLPi  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 NFr   )r%   r&   rT   r.   intermediate_sizer'   r   	gate_projup_proj	down_projr   
hidden_actact_fnr-   rT   r/   s     r0   r&   Olmo2MLP.__init__  s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r2   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ r   )r   r   r   r   )r-   r   r   s      r0   r@   Olmo2MLP.forward"  s6    NN4;;t~~a/@#ADLLQRO#ST	r2   )r   rT   r   r   r.   r   r   )rG   rH   rI   rJ   r&   r@   rM   rN   rO   s   @r0   r   r     s    0 r2   r   c                     ^  \ rS rSrS\S\4U 4S jjr     SS\R                  S\R                  S-  S\R                  S-  S	\
S-  S
\S-  S\\R                  \R                  4   S-  S\\   S\R                  4S jjrSrU =r$ )Olmo2DecoderLayeri'  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   r"   )r%   r&   r.   r   	self_attnr   mlpr    r   post_attention_layernormpost_feedforward_layernormr   s      r0   r&   Olmo2DecoderLayer.__init__(  sj    !--'vKF#(4V5G5GVM`M`(a%*6v7I7IvObOb*c'r2   Nr=   r   r   r   	use_cacher   r   r#   c           
          UnU R                   " SUUUUUUS.UD6u  pU R                  U5      nX-   nUnU R                  U5      nU R                  U5      nX-   nU$ )N)r=   r   r   r   r   r    )r   r   r   r   )
r-   r=   r   r   r   r   r   r   residual_s
             r0   r@   Olmo2DecoderLayer.forward1  s     !>> 
')%+ 3
 
 55mD 0 !/77F 0r2   )r.   r   r   r   r   )NNNFN)rG   rH   rI   rJ   r   r   r&   r)   rL   
LongTensorr   boolrC   r   r   r@   rM   rN   rO   s   @r0   r   r   '  s    d{ ds d /304(,!&HL|| t+ &&-	
  $; #5<<#=>E +, 
 r2   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	)
Olmo2PreTrainedModeliP  rT   modelTr   r   )r=   
attentionsr   N)rG   rH   rI   rJ   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_outputsrM   r   r2   r0   r   r   P  sQ    &*#,-#4"5N!"&*$r2   r   c                     ^  \ rS rSrS\4U 4S jjr\\\      SS\	R                  S-  S\	R                  S-  S\	R                  S-  S\S-  S	\	R                  S-  S
\S-  S\\   S\4S jj5       5       5       rSrU =r$ )
Olmo2Modelic  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 )Nr   rT   F)r%   r&   pad_token_idpadding_idx
vocab_sizer'   	Embeddingr.   embed_tokens
ModuleListrangenum_hidden_layersr   layersr    r   normrQ   
rotary_embgradient_checkpointing	post_initr   s      r0   r&   Olmo2Model.__init__e  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcCbiv1Cbc
 !!3!39L9LM	.f=&+# 	 d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$ )
Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r   )rb   )rT   r  r   r   r   )r   )r   r   r   r   r   )last_hidden_stater   )
ValueErrorr  r	   rT   get_seq_lengthr)   rk   rD   rb   r   r   r  r  r  r  r   )r-   r  r   r   r   r  r   r   past_seen_tokenscausal_maskr=   r   decoder_layers                r0   r@   Olmo2Model.forwardu  sF    -t";<YZZ *.*;*;I*FM0*$++>OCRC^==?de <<(;(;A(>}G[G[\_ooL'11!4L(;;')+%
 &"oomoW![[)H4;;+H+HIM)*$7) /# M J 		-0&++
 	
r2   )r  r  r  r  r	  r  r
  )NNNNNN)rG   rH   rI   rJ   r   r&   r   r   r   r)   r   rL   r   FloatTensorr   r   r   r   r@   rM   rN   rO   s   @r0   r  r  c  s    {     .2.204(,26!%2
##d*2
 t+2
 &&-	2

 2
 ((4/2
 $;2
 +,2
 
!2
    2
r2   r  c                   P  ^  \ rS rSrSS0rSS0rSS/S/40rU 4S jr\\	        SS
\
R                  S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\\
R                  -  S\\   S\4S jj5       5       rSrU =r$ )Olmo2ForCausalLMi  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'   r   r.   r#  r  r   s     r0   r&   Olmo2ForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r2   Nr  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$ )ao  
Example:

```python
>>> from transformers import AutoTokenizer, Olmo2ForCausalLM

>>> model = Olmo2ForCausalLM.from_pretrained("meta-olmo2/Olmo2-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-olmo2/Olmo2-2-7b-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  r   r   r   r  r   N)r%  r(  r
  )lossr%  r   r=   r   r   )r   r  rx   r   slicer#  loss_functionrT   r
  r   r   r=   r   )r-   r  r   r   r   r  r(  r   r)  r   outputsr=   slice_indicesr%  r+  s                  r0   r@   Olmo2ForCausalLM.forward  s    > ,0:: ,
)%+',
 ,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r2   )r#  r   r
  )NNNNNNNr   )rG   rH   rI   rJ   _tied_weights_keys_tp_plan_pp_planr&   r   r   r)   r   rL   r   r   r   r   r   r   r   r@   rM   rN   rO   s   @r0   r"  r"    s   *,GH23H_-z:;H  .2.204(,26*.!%-.6
##d*6
 t+6
 &&-	6

 6
 ((4/6
   4'6
 $;6
 ell*6
 +,6
 
 6
  6
r2   r"  c                       \ rS rSrSrg)Olmo2ForSequenceClassificationi  r   N)rG   rH   rI   rJ   rM   r   r2   r0   r5  r5    s    r2   r5  )r"  r5  r  r   )r   )r   )?collections.abcr   typingr   r)   torch.nnr'   transformers.utils.genericr   activationsr   cache_utilsr   r	   
generationr
   integrationsr   r   masking_utilsr   modeling_layersr   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   utils.genericr   r   utils.output_capturingr   configuration_olmo2r   Moduler    rQ   rL   r   r   rK   r   r   r   r   r   r   r   r  r"  r5  __all__r   r2   r0   <module>rJ     s  4 %    9 ! . ) L / [ O K F & 5 G 5 , Y'J299 J (J(=299 =@	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%224( )*F)RYY F) +F)Rryy  &2 &R ?  $ F
% F
 F
R F
+_ F
 F
R	%EG[ 	 gr2   