
    <hO                        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
  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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$J%r%  SSK&J'r'  \" S5       " S S\RP                  5      5       r)S\RT                  S\+S\RT                  4S jr, S4S\RP                  S\RT                  S\RT                  S\RT                  S\\RT                     S\-S \-S!\ \   4S" jjr.S5S# jr/S$ r0 " S% S&\RP                  5      r1 " S' S(\RP                  5      r2 " S) S*\5      r3 " S+ S,\RP                  5      r4\" " S- S.\5      5       r5\" " S/ S0\55      5       r6\" " S1 S2\5\5      5       r7/ S3Qr8g)6    )CallableOptionalUnionN)TransformersKwargs   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)auto_docstringcan_return_tuple)check_model_inputs   )Olmo2ConfigRMSNormc                   8   ^  \ rS rSrSU 4S jjrS rS rSrU =r$ )Olmo2RMSNorm   c                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)z+
Olmo2RMSNorm is equivalent to T5LayerNorm
N)super__init__nn	Parametertorchonesweightvariance_epsilon)selfhidden_sizeeps	__class__s      `/var/www/html/shao/venv/lib/python3.13/site-packages/transformers/models/olmo2/modeling_olmo2.pyr!   Olmo2RMSNorm.__init__   s/     	ll5::k#:; #    c                    UR                   nUR                  [        R                  5      nUR	                  S5      R                  SSS9nU[        R                  " X0R                  -   5      -  nU R                  U-  R                  U5      $ )N   T)keepdim)	dtypetor$   float32powmeanrsqrtr'   r&   )r(   hidden_statesinput_dtypevariances       r,   forwardOlmo2RMSNorm.forward'   sw    #))%((7 $$Q',,R,>%H?T?T4T(UUm+//<<r.   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)tupler&   shaper'   r(   s    r,   
extra_reprOlmo2RMSNorm.extra_repr.   s*    ))*+6$2G2G1HIIr.   )r'   r&   )gư>)	__name__
__module____qualname____firstlineno__r!   r<   rB   __static_attributes____classcell__r+   s   @r,   r   r      s    $=J Jr.   r   r9   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)r@   expandreshape)r9   rK   batchnum_key_value_headsslenhead_dims         r,   	repeat_kvrT   2   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"  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$ )Nr0   r   r1   )dimr3   )ptrainingr   )rT   num_key_value_groupsr$   matmul	transposer@   r"   
functionalsoftmaxr5   r4   r3   r[   ra   
contiguous)rU   rV   rW   rX   rY   rZ   r[   r\   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r,   eager_attention_forwardrm   >   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$$r.   c                    U R                   UR                   pvU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$ )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.
)r3   	unsqueezerotate_halfr4   )
qkcossinposition_idsunsqueeze_dimq_typek_typeq_embedk_embeds
             r,   apply_rotary_pos_embr{   X   sv    ( WWaggF
--
&C
--
&Cw;q>C/0Gw;q>C/0G::fwzz&111r.   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$ )z*Rotates half the hidden dims of the input..Nr1   r0   r_   )r@   r$   cat)xx1x2s      r,   rp   rp   t   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r.   c                   P  ^  \ rS rSrSrSS\S\\   4U 4S jjjr  SS\	R                  S\\	R                  \	R                  4   S\\	R                     S	\\   S
\\	R                     S\\   S\\	R                  \\	R                     \\\	R                        4   4S jjrSrU =r$ )Olmo2Attention{   z=Multi-headed attention from 'Attention Is All You Need' paperconfig	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 )NrS   g      Tbias)r    r!   r   r   getattrr)   num_attention_headsrS   rQ   rb   rZ   attention_dropout	is_causalr"   Linearattention_biasq_projk_projv_projo_projr   rms_norm_epsq_normk_normr(   r   r   r+   s      r,   r!   Olmo2Attention.__init__~   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 #6#=#=#MvObObc"6#=#=#MvObObcr.   r9   position_embeddingsrY   past_key_valuecache_positionr\   rL   c                 |   UR                   S S n/ UQSPU R                  P7nU R                  U R                  U5      5      n	U R	                  U R                  U5      5      n
U R                  U5      nU	R                  U5      R                  SS5      n	U
R                  U5      R                  SS5      n
UR                  U5      R                  SS5      nUu  p[        XX5      u  pUb$  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$                  S.UD6u  nnUR&                  " / UQSP76 R)                  5       nU R+                  U5      nUU4$ )Nr1   r   r0   )rt   rs   r   eager        )r[   rZ   )r@   rS   r   r   r   r   r   viewrd   r{   updater   rm   r   _attn_implementationr   ra   r   rZ   rO   rg   r   )r(   r9   r   rY   r   r   r\   input_shapehidden_shapequery_statesrh   ri   rs   rt   cache_kwargsattention_interfacerl   rj   s                     r,   r<   Olmo2Attention.forward   s    $))#2.88b8$--8{{4;;}#=>[[]!;<
{{=1#((6@@AF__\2<<QB
#((6@@AF&#7RU#[ %#&nUL'5'<'<ZW[WeWegs't$J(?;;++w6"9$++:Z:Z"[$7	%
  $}}C$2H2HLL	%
 	%
!\ "));;;;FFHkk+.L((r.   )r   r   rS   r   r   r   r   rb   r   r   r   rZ   r   N)NN)rD   rE   rF   rG   __doc__r   r   intr!   r$   Tensorr?   r	   
LongTensorr   r   r<   rH   rI   rJ   s   @r,   r   r   {   s    Gd{ dx} d d< +/59-)||-) #5<<#=>-) !.	-)
 !-) !!1!12-) +,-) 
u||Xell3XeELL>Q5RR	S-) -)r.   r   c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )Olmo2MLP   c                   > [         TU ]  5         Xl        UR                  U l        UR                  U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l	        [        UR                     U l        g NFr   )r    r!   r   r)   intermediate_sizer"   r   	gate_projup_proj	down_projr   
hidden_actact_fnr(   r   r+   s     r,   r!   Olmo2MLP.__init__   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r.   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ r   )r   r   r   r   )r(   r   r   s      r,   r<   Olmo2MLP.forward   s6    NN4;;t~~a/@#ADLLQRO#ST	r.   )r   r   r   r   r)   r   r   )rD   rE   rF   rG   r!   r<   rH   rI   rJ   s   @r,   r   r      s    0 r.   r   c                   t  ^  \ rS rSrS\S\4U 4S jjr      SS\R                  S\	\R                     S\	\R                     S\	\   S	\	\   S
\	\R                     S\	\\R                  \R                  4      S\\   S\\R                   \	\\R                   \R                   4      4   4S jjrSrU =r$ )Olmo2DecoderLayer   r   r   c                   > [         TU ]  5         UR                  U l        [        XS9U l        [        U5      U l        [        UR                  UR                  S9U l	        [        UR                  UR                  S9U l
        g )N)r   r   r*   )r    r!   r)   r   	self_attnr   mlpr   r   post_attention_layernormpost_feedforward_layernormr   s      r,   r!   Olmo2DecoderLayer.__init__   sj    !--'vKF#(4V5G5GVM`M`(a%*6v7I7IvObOb*c'r.   r9   rY   ru   r   	use_cacher   r   r\   rL   c                     Un	U R                   " SUUUUUUUS.UD6u  pU R                  U5      nX-   nUn	U R                  U5      nU R                  U5      nX-   nU$ )N)r9   rY   ru   r   r   r   r    )r   r   r   r   )r(   r9   rY   ru   r   r   r   r   r\   residual_s              r,   r<   Olmo2DecoderLayer.forward   s     !>> 	
')%)) 3	
 	
 55mD 0 !/77F 0r.   )r)   r   r   r   r   )NNNFNN)rD   rE   rF   rG   r   r   r!   r$   r   r   r   r	   boolr?   r   r   FloatTensorr<   rH   rI   rJ   s   @r,   r   r      s   d{ ds d 2637*.$)59KO|| !. u//0	
 ! D> !!1!12 &eELL%,,,F&GH +, 
u  (51B1BEDUDU1U+V"WW	X r.   r   c                   l   ^  \ rS rSrSS\4U 4S jjjr\R                  " 5       \S 5       5       r	Sr
U =r$ )Olmo2RotaryEmbeddingi  r   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defaultinv_freqF)
persistent)r    r!   hasattr
isinstancer   dictgetr   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r(   r   devicer   r+   s       r,   r!   Olmo2RotaryEmbedding.__init__  s    6>**z&:M:Mt/T/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q((ZeD!%r.   c                    U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        R                  " USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	X4sS S S 5        $ ! , (       d  f       g = f)
Nr   r1   r   mpscpuF)device_typeenabledr0   r}   )r   floatrN   r@   r4   r   r   r   strr$   autocastrd   r~   rs   r   rt   )
r(   r   ru   inv_freq_expandedposition_ids_expandedr   freqsembrs   rt   s
             r,   r<   Olmo2RotaryEmbedding.forward  s)    !MM$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8 DCCs   $BE22
F )r   r   r   r   r   r   r   r   )rD   rE   rF   rG   r   r!   r$   no_gradr   r<   rH   rI   rJ   s   @r,   r   r     s6    /{ / /" ]]_
  
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	)
Olmo2PreTrainedModeli#  r   modelTr   past_key_values)r9   
attentionsr   N)rD   rE   rF   rG   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_outputsrH   r   r.   r,   r   r   #  sQ    &*#,-#4"5N!"&*$r.   r   c                     ^  \ rS rSrS\4U 4S jjr\\       SS\\	R                     S\\	R                     S\\	R                     S\\   S\\	R                     S	\\	R                     S
\\   S\\   S\4S jj5       5       rSrU =r$ )
Olmo2Modeli6  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      r,   r!   Olmo2Model.__init__8  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcCbiv1Cbc
 !!3!39L9LM	.f=&+# 	 ds   C>	input_idsrY   ru   r   inputs_embedsr   r   r\   rL   c           
      8   US L US L-  (       a  [        S5      eUc  U R                  U5      nU(       a  Uc
  [        5       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$ )Nz:You must specify exactly one of input_ids or inputs_embedsr   r   )r   )r   input_embedsrY   r   r   ru   )rY   ru   r   r   r   )last_hidden_stater   )
ValueErrorr	  r
   get_seq_lengthr$   aranger@   r   ro   r   r   r  r  r  r  r   )r(   r  rY   ru   r   r  r   r   r\   past_seen_tokensrk   r9   r   decoder_layers                 r,   r<   Olmo2Model.forwardH  sK    -t";<YZZ *.*;*;I*FM0*nO!CRC^==?de+0<< ]5H5H5K"KTaThTh,N )33A6L(;;&))+%
 &"oomJ![[)H4;;+H+HIM)*).-$7 M J 		-0&++
 	
r.   )r	  r  r  r  r  r  r  )NNNNNNN)rD   rE   rF   rG   r   r!   r   r   r   r$   r   r   r	   r   r   r   r   r   r<   rH   rI   rJ   s   @r,   r  r  6  s    {    151537+/5959$(8
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 !!1!128
 D>8
 +,8
 
!8
  8
r.   r  c                   ~  ^  \ rS rSrS/rSS0rSS/S/40rU 4S jrS rS	 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$ )Olmo2ForCausalLMi  zlm_head.weightlm_headcolwise_repr9   logitsc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g r   )
r    r!   r  r   r  r"   r   r)   r   r  r   s     r,   r!   Olmo2ForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r.   c                     Xl         g r   r   )r(   decoders     r,   set_decoderOlmo2ForCausalLM.set_decoder  s    
r.   c                     U R                   $ r   r&  rA   s    r,   get_decoderOlmo2ForCausalLM.get_decoder  s    zzr.   r  rY   ru   r   r  labelsr   r   logits_to_keepr\   rL   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$ )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  rY   ru   r   r  r   r   N)r"  r-  r  )lossr"  r   r9   r   r   )r   r  r   r   slicer   loss_functionr   r  r   r   r9   r   )r(   r  rY   ru   r   r  r-  r   r   r.  r\   outputsr9   slice_indicesr"  r0  s                   r,   r<   Olmo2ForCausalLM.forward  s    @ ,0:: 	,
)%+')	,
 	,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r.   )r   r   r  )	NNNNNNNNr   )rD   rE   rF   rG   _tied_weights_keys_tp_plan_pp_planr!   r(  r+  r   r   r   r$   r   r   r	   r   r   r   r   r   r   r   r<   rH   rI   rJ   s   @r,   r  r    s:   *+=)H_-z:;H  151537+/59-1$(59348
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 ))*8
 D>8
 !!1!128
 c5<</08
 +,8
 
 8
  8
r.   r  )r  r  r   )r   )Nr   )9typingr   r   r   r$   torch.nnr"   transformers.utils.genericr   activationsr   cache_utilsr	   r
   
generationr   integrationsr   masking_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   utils.genericr   configuration_olmo2r   Moduler   r   r   rT   r   rm   r{   rp   r   r   r   r   r   r  r  __all__r   r.   r,   <module>rK     s   - ,   9 ! . ) 7 / 9 O K F & 5 / , Y'J299 J (J(	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%428(I)RYY I)Xryy  (2 (V299 B ?  $ K
% K
 K
\ N
+_ N
 N
b Er.   