
    Z jWV                     Z   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  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Jr  SSK J!r!  SSK"J#r#J$r$  SSK%J&r&J'r'J(r(  SSK)J*r*  SSK+J,r,  \" S5       " S S\RZ                  5      5       r.S\R^                  S\0S\R^                  4S jr1 S7S\RZ                  S\R^                  S\R^                  S\R^                  S\R^                  S-  S \2S!\2S"\!\&   4S# jjr3S8S$ jr4S% r5\" \45       " S& S'\RZ                  5      5       r6 " S( S)\RZ                  5      r7 " S* S+\5      r8 " S, S-\RZ                  5      r9\# " S. S/\5      5       r:\# " S0 S1\:5      5       r;\# " S2 S3\:\5      5       r< " S4 S5\\:5      r=/ S6Qr>g)9    )Callable)OptionalN   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernelized_func)create_causal_mask!create_sliding_window_causal_mask) GenericForSequenceClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)auto_docstringcan_return_tuple)TransformersKwargsmaybe_autocastmerge_with_config_defaults)capture_outputs   )Olmo3Config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$ )
Olmo3RMSNorm+   epsreturnNc                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)z+
Olmo3RMSNorm is equivalent to T5LayerNorm
N)super__init__nn	Parametertorchonesweightvariance_epsilon)selfhidden_sizer#   	__class__s      y/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/olmo3/modeling_olmo3.pyr'   Olmo3RMSNorm.__init__-   s/     	ll5::k#:; #    c                    UR                   nUR                  [        R                  5      nUR	                  S5      R                  SSS9nU[        R                  " X0R                  -   5      -  nU R                  U-  R                  U5      $ )N   T)keepdim)	dtypetor*   float32powmeanrsqrtr-   r,   )r.   hidden_statesinput_dtypevariances       r1   forwardOlmo3RMSNorm.forward5   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Olmo3RMSNorm.extra_repr<   s*    ))*+6$2G2G1HIIr3   )r-   r,   )gư>)__name__
__module____qualname____firstlineno__floatr'   r*   TensorrA   rF   __static_attributes____classcell__r0   s   @r1   r!   r!   +   s7    $ $$ $ $= =J Jr3   r!   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      $ )z
This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
r   N)rE   expandreshape)r>   rQ   batchnum_key_value_headsslenhead_dims         r1   	repeat_kvrY   @   s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr3   modulequerykeyvalueattention_maskscalingdropoutkwargsc                    [        X R                  5      n[        X0R                  5      n	[        R                  " XR	                  SS5      5      U-  n
Ub  X-   n
[
        R                  R                  U
S[        R                  S9R                  UR                  5      n
[
        R                  R                  XU R                  S9n
[        R                  " X5      nUR	                  SS5      R                  5       nX4$ )Nr5   r   r6   )dimr8   )ptrainingr   )rY   num_key_value_groupsr*   matmul	transposer(   
functionalsoftmaxr:   r9   r8   r`   re   
contiguous)rZ   r[   r\   r]   r^   r_   r`   ra   
key_statesvalue_statesattn_weightsattn_outputs               r1   eager_attention_forwardrp   L   s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!#4==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r3   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.
)r8   	unsqueezerotate_halfr9   )	qkcossinunsqueeze_dimq_typek_typeq_embedk_embeds	            r1   apply_rotary_pos_embr}   e   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   rc   )rE   r*   cat)xx1x2s      r1   rs   rs      sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r3   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$ )Olmo3Attention   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        UR0                  U   U l        U R2                  S:X  a  UR4                  U l        g S U l        g )NrX   g      Tbiassliding_attention)r&   r'   r   r   getattrr/   num_attention_headsrX   rV   rf   r_   attention_dropout	is_causalr(   Linearattention_biasq_projk_projv_projo_projr!   rms_norm_epsq_normk_normlayer_typesattention_typesliding_windowr.   r   r   r0   s      r1   r'   Olmo3Attention.__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$00;7;7J7JNa7af33gkr3   Nr>   position_embeddingsr^   past_key_valuesra   r$   c                 f   UR                   S S n/ UQSPU R                  P7nU R                  U R                  U5      5      nU R	                  U R                  U5      5      n	U R                  U5      n
UR                  U5      R                  SS5      nU	R                  U5      R                  SS5      n	U
R                  U5      R                  SS5      n
Uu  p[        XX5      u  pUb  UR                  XU R                  5      u  p[        R                  " U R                  R                  [         5      nU" U UU	U
U4U R"                  (       d  SOU R$                  U R&                  U R(                  S.UD6u  pUR*                  " / UQSP76 R-                  5       nU R/                  U5      nX4$ )Nr6   r   r5           )r`   r_   r   )rE   rX   r   r   r   r   r   viewrh   r}   updater   r   get_interfacer   _attn_implementationrp   re   r   r_   r   rT   rk   r   )r.   r>   r   r^   r   ra   input_shapehidden_shapequery_statesrl   rm   rv   rw   attention_interfacero   rn   s                   r1   rA   Olmo3Attention.forward   s    $))#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$2H2HLL..
%
 
%
! "));;;;FFHkk+.((r3   )r   r   r   rX   r   r   r   r   rf   r   r   r   r_   r   r   N)rH   rI   rJ   rK   __doc__r   intr'   r*   rM   rD   r   r   r   rA   rN   rO   rP   s   @r1   r   r      s    Gl{ ls l@ )-+)||+) #5<<#=>+) t+	+)
 +) +,+) 
u||U\\D00	1+) +)r3   r   c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )Olmo3MLP   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   r0   s     r1   r'   Olmo3MLP.__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$ r   )r   r   r   r   )r.   r   r   s      r1   rA   Olmo3MLP.forward   s6    NN4;;t~~a/@#ADLLQRO#ST	r3   )r   r   r   r   r/   r   r   )rH   rI   rJ   rK   r'   rA   rN   rO   rP   s   @r1   r   r      s    0 r3   r   c                     ^  \ rS rSrS\S\4U 4S jjr     SS\R                  S\R                  S-  S\R                  S-  S	\
S-  S
\S-  S\\R                  \R                  4   S-  S\\   S\R                  4S jjrSrU =r$ )Olmo3DecoderLayer   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      r1   r'   Olmo3DecoderLayer.__init__   sj    !--'vKF#(4V5G5GVM`M`(a%*6v7I7IvObOb*c'r3   Nr>   r^   position_idsr   	use_cacher   ra   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   ra   residual_s
             r1   rA   Olmo3DecoderLayer.forward   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+ &&-	
  $; #5<<#=>E +, 
 r3   r   c                      ^  \ rS rSr% \R
                  \S'   SS\4U 4S jjjr\	   SS\S-  S\
S   S\S-  S	\S
\4   4S jj5       r\R                  " 5       \S 5       5       rSrU =r$ )Olmo3RotaryEmbeddingi  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)r.   r   devicerope_init_fnr   r0   s        r1   r'   Olmo3RotaryEmbedding.__init__  s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L((ZeD0(..2BuUr3   r   ztorch.deviceseq_lenr$   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_thetarX   Ng      ?r   r5   r8   )r   r8   )	r   r   r/   r   r*   arangeint64r9   rL   )r   r   r   baserc   attention_factorr   s          r1   r   4Olmo3RotaryEmbedding.compute_default_rope_parameters  s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 ))r3   c                 L   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r6   r   mpscpuF)device_typeenabledr5   r   r   )r   rL   rS   rE   r9   r   
isinstancetypestrr   rh   r*   r   rv   r   rw   r8   )
r.   r   r   inv_freq_expandedposition_ids_expandedr   freqsembrv   rw   s
             r1   rA   Olmo3RotaryEmbedding.forward=  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)rH   rI   rJ   rK   r*   rM   __annotations__r   r'   staticmethodr   r   rD   rL   r   no_gradr   rA   rN   rO   rP   s   @r1   r   r     s    llV{ V V  %)+/"*d"*(* t* 
~u$	%	* *: ]]_<  <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	)
Olmo3PreTrainedModeliM  r   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   M  sQ    &*#,-#4"5N!"&*$r3   r   c                     ^  \ rS rSrS\4U 4S jjr\\\      SS\	R                  S-  S\	R                  S-  S\	R                  S-  S\S-  S	\	R                  S-  S
\S-  S\\   S\4S jj5       5       5       rSrU =r$ )
Olmo3Modeli`  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      r1   r'   Olmo3Model.__init__b  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   ra   r$   c           	         US L US L-  (       a  [        S5      eUc  U R                  U5      nU(       a  Uc  [        U R                  S9nUcU  Ub  UR	                  5       OSn[
        R                  " UR                  S   UR                  S9U-   nUR                  S5      n[        U=n	[        5      (       d)  U R                  UUUUS.n
[        S
0 U
D6[        S
0 U
D6S.n	UnU R                  X5      n[        U R                   S U R                  R"                   5       H,  u  pU" U4XR                  R$                  U      UUUS.UD6nM.     U R'                  U5      n[)        UUS	9$ )Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r   )r   )r   r  r^   r   r   )full_attentionr   )r^   r   r   r   )last_hidden_stater   r   )
ValueErrorr  r   r   get_seq_lengthr*   r   rE   r   rr   r   dictr   r   r  	enumerater  r  r   r  r   )r.   r  r^   r   r   r  r   ra   past_seen_tokenscausal_mask_mappingmask_kwargsr>   r   idecoder_layers                  r1   rA   Olmo3Model.forwardr  s    -t";<YZZ *.*;*;I*FM0*$++>OCRC^==?de <<(;(;A(>}G[G[\_ooL'11!4L ?-FF ++!."0#2 ,K #5"C{"C%F%U%U#
 &"oomJ )$++6U8U8U*V WA)2;;3J3J13MN) /$7 M !X 		-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  `  s    {     .2.204(,26!%9
##d*9
 t+9
 &&-	9

 9
 ((4/9
 $;9
 +,9
 
!9
    9
r3   r  c                   P  ^  \ rS rSrSS0rSS0rSS/S/40rU 4S jr\\	        SS
\
R                  S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\\
R                  -  S\\   S\4S jj5       5       rSrU =r$ )Olmo3ForCausalLMi  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'   Olmo3ForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r3   Nr  r^   r   r   r  labelsr   logits_to_keepra   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, Olmo3ForCausalLM

>>> model = Olmo3ForCausalLM.from_pretrained("meta-olmo3/Olmo3-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-olmo3/Olmo3-2-7b-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)r1  r4  r  )lossr1  r   r>   r   r   )r   r!  r   r   slicer/  loss_functionr   r  r   r   r>   r   )r.   r  r^   r   r   r  r4  r   r5  ra   outputsr>   slice_indicesr1  r7  s                  r1   rA   Olmo3ForCausalLM.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
 $;6
 ell*6
 +,6
 
 6
  6
r3   r.  c                       \ rS rSrSrg)Olmo3ForSequenceClassificationi  r   N)rH   rI   rJ   rK   rN   r   r3   r1   rA  rA    s    r3   rA  )r.  rA  r  r   )r   )r   )?collections.abcr   typingr   r*   torch.nnr(   activationsr   cache_utilsr   r   
generationr	   integrationsr
   r   masking_utilsr   r   modeling_layersr   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   utils.genericr   r   r   utils.output_capturingr   configuration_olmo3r   Moduler!   rM   r   rY   rL   rp   r}   rs   r   r   r   r   r   r  r.  rA  __all__r   r3   r1   <module>rU     s  * %    ! . ) L R [ O K F & 5 [ [ 5 , Y'J299 J (J(	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%224( )*I)RYY I) +I)Xryy  &2 &R><299 ><B ?  $ M
% M
 M
` F
+_ F
 F
R	%EG[ 	 gr3   