
    3j#U                     x   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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$J%r%J&r&  SSK'J(r(J)r)  SSK*J+r+  SSK,J-r-  \" S5       " S S\R\                  5      5       r/ " S S\R\                  5      r0S\Rb                  S\2S\Rb                  4S jr3 S9S\R\                  S\Rb                  S \Rb                  S!\Rb                  S"\Rb                  S-  S#\4S$\4S%\#\   4S& jjr5\" S'5      S:S( j5       r6S) r7\" \65       " S* S+\R\                  5      5       r8 " S, S-\R\                  5      r9 " S. S/\5      r:\% " S0 S1\!5      5       r;\% " S2 S3\;5      5       r<\% " S4 S5\;\5      5       r= " S6 S7\\;5      r>/ S8Qr?g);    )Callable)OptionalN)TransformersKwargs   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernel_func_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$ )
Olmo2RMSNorm2   epsreturnNc                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)z+
Olmo2RMSNorm is equivalent to T5LayerNorm
N)super__init__nn	Parametertorchonesweightvariance_epsilon)selfhidden_sizer#   	__class__s      b/home/wildlama/miniconda3/lib/python3.13/site-packages/transformers/models/olmo2/modeling_olmo2.pyr'   Olmo2RMSNorm.__init__4   s/     	ll5::k#:; #    c                    UR                   nUR                  [        R                  5      nUR	                  S5      R                  SSS9nU[        R                  " X0R                  -   5      -  nU R                  U-  R                  U5      $ )N   T)keepdim)	dtypetor*   float32powmeanrsqrtr-   r,   )r.   hidden_statesinput_dtypevariances       r1   forwardOlmo2RMSNorm.forward<   sw    #))%((7 $$Q',,R,>%H?T?T4T(UUm+//<<r3   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)tupler,   shaper-   )r.   s    r1   
extra_reprOlmo2RMSNorm.extra_reprC   s*    ))*+6$2G2G1HIIr3   )r-   r,   )gư>)__name__
__module____qualname____firstlineno__floatr'   r*   TensorrA   rF   __static_attributes____classcell__r0   s   @r1   r!   r!   2   s7    $ $$ $ $= =J J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$ )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defaultrT   F)
persistentoriginal_inv_freq)r&   r'   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrU   rope_parametersrW   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r.   rU   devicerope_init_fnrT   r0   s        r1   r'   Olmo2RotaryEmbedding.__init__J   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L((ZeD0(..2BuUr3   rc   ztorch.deviceseq_lenr$   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   r5   )r8   )rc   r8   )	r^   getattrr/   num_attention_headsr*   arangeint64r9   rL   )rU   rc   rf   basedimattention_factorrT   s          r1   r_   4Olmo2RotaryEmbedding.compute_default_rope_parametersZ   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 ))r3   c                    U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        X4$ ! , (       d  f       WW	4$ = f)
Nr   r6   r   mpscpuF)device_typeenabledr5   ro   )rT   rL   expandrE   r9   rc   
isinstancetypestrr   	transposer*   catcosr`   sin)
r.   xposition_idsinv_freq_expandedposition_ids_expandedru   freqsembr~   r   s
             r1   rA   Olmo2RotaryEmbedding.forwardx   s7    !MM$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`   rU   r\   r]   rW   N)NNN)rH   rI   rJ   rK   r*   rM   __annotations__r   r'   staticmethodr   intrD   rL   r_   no_gradr   rA   rN   rO   rP   s   @r1   rR   rR   G   s    llV{ V V  %)+/"*d"*(* t* 
~u$	%	* *: ]]_
  
r3   rR   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      $ )z
This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
r   N)rE   rx   reshape)r>   r   batchnum_key_value_headsslenri   s         r1   	repeat_kvr      s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr3   modulequerykeyvalueattention_maskscalingdropoutkwargsc                    [        X R                  5      n[        X0R                  5      n	[        R                  " XR	                  SS5      5      U-  n
Ub  X-   n
[
        R                  R                  U
S[        R                  S9R                  UR                  5      n
[
        R                  R                  XU R                  S9n
[        R                  " X5      nUR	                  SS5      R                  5       nX4$ )Nr5   r   r6   )ro   r8   )ptrainingr   )r   num_key_value_groupsr*   matmulr|   r(   
functionalsoftmaxr:   r9   r8   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   rotary_pos_embc                    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.
)r8   	unsqueezerotate_halfr9   )	qkr~   r   unsqueeze_dimq_typek_typeq_embedk_embeds	            r1   apply_rotary_pos_embr      sv    & WWaggF
--
&C
--
&Cw;q>C/0Gw;q>C/0G::fwzz&111r3   c                     U SSU R                   S   S-  24   nU SU R                   S   S-  S24   n[        R                  " U* U4SS9$ )z*Rotates half the hidden dims of the input..Nr6   r5   rw   )rE   r*   r}   )r   x1x2s      r1   r   r      sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r3   c                     ^  \ rS rSrSrSS\S\S-  4U 4S jjjr SS\R                  S\
\R                  \R                  4   S	\R                  S-  S
\S-  S\\   S\
\R                  \R                  S-  4   4S jjrSrU =r$ )Olmo2Attention   z=Multi-headed attention from 'Attention Is All You Need' paperNrU   	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 )Nri   g      Tbias)r&   r'   rU   r   rj   r/   rk   ri   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.   rU   r   r0   s      r1   r'   Olmo2Attention.__init__   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 #6#=#=#MvObObc"6#=#=#MvObObcr3   r>   position_embeddingsr   past_key_valuesr   r$   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$                  U R&                  S.UD6u  pUR(                  " / UQSP76 R+                  5       nU R-                  U5      nX4$ )Nr6   r   r5           )r   r   )rE   ri   r   r   r   r   r   viewr|   r   updater   r   get_interfacerU   _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                   r1   rA   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$2H2HLL	%
 	%
! "));;;;FFHkk+.((r3   )r   rU   ri   r   r   r   r   r   r   r   r   r   r   r   )rH   rI   rJ   rK   __doc__r   r   r'   r*   rM   rD   r   r   r   rA   rN   rO   rP   s   @r1   r   r      s    Gd{ dsTz d d< )-*)||*) #5<<#=>*) t+	*)
 *) +,*) 
u||U\\D00	1*) *)r3   r   c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )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'   rU   r/   intermediate_sizer(   r   	gate_projup_proj	down_projr   
hidden_actact_fnr.   rU   r0   s     r1   r'   Olmo2MLP.__init__  s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r3   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ r   )r   r   r   r   )r.   r   r   s      r1   rA   Olmo2MLP.forward#  s6    NN4;;t~~a/@#ADLLQRO#ST	r3   )r   rU   r   r   r/   r   r   )rH   rI   rJ   rK   r'   rA   rN   rO   rP   s   @r1   r   r     s    0 r3   r   c                     ^  \ rS rSrS\S\4U 4S jjr     SS\R                  S\R                  S-  S\R                  S-  S	\
S-  S
\S-  S\\R                  \R                  4   S-  S\\   S\R                  4S jjrSrU =r$ )Olmo2DecoderLayeri(  rU   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)rU   r   r#   )r&   r'   r/   r   	self_attnr   mlpr!   r   post_attention_layernormpost_feedforward_layernormr   s      r1   r'   Olmo2DecoderLayer.__init__)  sj    !--'vKF#(4V5G5GVM`M`(a%*6v7I7IvObOb*c'r3   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
             r1   rA   Olmo2DecoderLayer.forward2  s     !>> 
')%+ 3
 
 55mD 0 !/77F 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    d{ ds d /304(,!&HL|| t+ &&-	
  $; #5<<#=>E +, 
 r3   r   c                   R    \ rS rSr% \\S'   SrSrS/rS/r	Sr
SrSrSrSr\\S.rSrg	)
Olmo2PreTrainedModeliQ  rU   modelTr   r   )r>   
attentionsr   N)rH   rI   rJ   rK   r   r   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsrN   r   r3   r1   r   r   Q  sQ    &*#,-#4"5N!"&*$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$ )
Olmo2Modelid  rU   c           	        > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [        UR                  UR                  S9U l        [#        US9U l        SU l        U R)                  5         g s  snf )Nr   rU   F)r&   r'   pad_token_idpadding_idx
vocab_sizer(   	Embeddingr/   embed_tokens
ModuleListrangenum_hidden_layersr   layersr!   r   normrR   
rotary_embgradient_checkpointing	post_initr   s      r1   r'   Olmo2Model.__init__f  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcCbiv1Cbc
 !!3!39L9LM	.f=&+# 	 ds   C?N	input_idsr   r   r   inputs_embedsr   r   r$   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$ )
Nz:You must specify exactly one of input_ids or inputs_embedsr	  r   r   )rc   )rU   r  r   r   r   )r   )r   r   r   r   r   )last_hidden_stater   )
ValueErrorr  r	   rU   get_seq_lengthr*   rl   rE   rc   r   r   r  r  r  r  r   )r.   r  r   r   r   r  r   r   past_seen_tokenscausal_maskr>   r   decoder_layers                r1   rA   Olmo2Model.forwardv  sF    -t";<YZZ *.*;*;I*FM0*$++>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  d  s    {     .2.204(,26!%2
##d*2
 t+2
 &&-	2

 2
 ((4/2
 $;2
 +,2
 
!2
    2
r3   r  c                   P  ^  \ rS rSrSS0rSS0rSS/S/40rU 4S jr\\	        SS
\
R                  S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\\
R                  -  S\\   S\4S jj5       5       rSrU =r$ )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     r1   r'   Olmo2ForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r3   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  ry   r   slicer%  loss_functionrU   r  r   r   r>   r   )r.   r  r   r   r   r  r*  r   r+  r   outputsr>   slice_indicesr'  r-  s                  r1   rA   Olmo2ForCausalLM.forward  s    > ,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23H_-z:;H  .2.204(,26*.!%-.6
##d*6
 t+6
 &&-	6

 6
 ((4/6
   4'6
 $;6
 ell*6
 +,6
 
 6
  6
r3   r$  c                       \ rS rSrSrg)Olmo2ForSequenceClassificationi  r   N)rH   rI   rJ   rK   rN   r   r3   r1   r7  r7    s    r3   r7  )r$  r7  r  r   )r   )r   )@collections.abcr   typingr   r*   torch.nnr(   transformers.utils.genericr   activationsr   cache_utilsr   r	   
generationr
   integrationsr   r   r   masking_utilsr   modeling_layersr   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   utils.genericr   r   utils.output_capturingr   configuration_olmo2r   Moduler!   rR   rM   r   r   rL   r   r   r   r   r   r   r   r  r$  r7  __all__r   r3   r1   <module>rL     s  4 %    9 ! . ) f f / [ O K F & 5 G 5 , Y'J299 J (J(=299 =@	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%2 *+2 ,24( )*F)RYY F) +F)Rryy  &2 &R ?  $ F
% F
 F
R F
+_ F
 F
R	%EG[ 	 gr3   