
    fTh	x                     z   S SK Jr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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  SSKJrJr  SSKJrJr  SSKJrJr  SSK J!r!  SSK"J#r#J$r$J%r%J&r&J'r'  SSK(J)r)  \&" 5       (       a  S SK*J+r+  SSK,J-r-  \'R\                  " \/5      r0\" S5       " S S\Rb                  5      5       r2S\Rf                  S\4S\Rf                  4S jr5 S6S\Rb                  S\Rf                  S\Rf                  S\Rf                  S\\Rf                     S \6S!\64S" jjr7S7S# jr8S$ r9 " S% S&\Rb                  5      r: " S' S(\Rb                  5      r; " S) S*\5      r< " S+ S,\Rb                  5      r=\$ " S- S.\5      5       r>\$ " S/ S0\>5      5       r? " S1 S2\\#5      r@\$ " S3 S4\>\5      5       rA/ S5QrBg)8    )CallableOptionalTupleUnionN   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)AttentionMaskConverter)FlashAttentionKwargs)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)
LossKwargsauto_docstringcan_return_tupleis_torch_flex_attn_availablelogging   )Olmo2Config)	BlockMask)make_flex_block_causal_maskRMSNormc                   8   ^  \ rS rSrSU 4S jjrS rS rSrU =r$ )Olmo2RMSNorm$   c                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)z+
Olmo2RMSNorm is equivalent to T5LayerNorm
N)super__init__nn	Parametertorchonesweightvariance_epsilon)selfhidden_sizeeps	__class__s      `/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/olmo2/modeling_olmo2.pyr&   Olmo2RMSNorm.__init__&   s/     	ll5::k#:; #    c                    UR                   nUR                  [        R                  5      nUR	                  S5      R                  SSS9nU[        R                  " X0R                  -   5      -  nU R                  U-  R                  U5      $ )N   T)keepdim)	dtypetor)   float32powmeanrsqrtr,   r+   )r-   hidden_statesinput_dtypevariances       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_repr5   s*    ))*+6$2G2G1HIIr3   )r,   r+   )gư>)	__name__
__module____qualname____firstlineno__r&   rA   rG   __static_attributes____classcell__r0   s   @r1   r"   r"   $   s    $=J Jr3   r"   r>   n_repreturnc                     U R                   u  p#pEUS:X  a  U $ 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      $ )z
This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
r   N)rE   expandreshape)r>   rP   batchnum_key_value_headsslenhead_dims         r1   	repeat_kvrY   9   s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr3   modulequerykeyvalueattention_maskscalingdropoutc                 @   [        X R                  5      n[        X0R                  5      n	[        R                  " XR	                  SS5      5      U-  n
Ub"  US S 2S S 2S S 2S UR
                  S   24   nX-   n
[        R                  R                  U
S[        R                  S9R                  UR                  5      n
[        R                  R                  XU R                  S9n
[        R                  " X5      nUR	                  SS5      R                  5       nX4$ )Nr5   r   r6   )dimr8   )ptrainingr   )rY   num_key_value_groupsr)   matmul	transposerE   r'   
functionalsoftmaxr:   r9   r8   r`   re   
contiguous)rZ   r[   r\   r]   r^   r_   r`   kwargs
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r1   eager_attention_forwardrr   E   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$$r3   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.
)r8   	unsqueezerotate_halfr9   )
qkcossinposition_ids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$ )z*Rotates half the hidden dims of the input..Nr6   r5   rc   )rE   r)   cat)xx1x2s      r1   ru   ru   {   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r3   c                   F  ^  \ rS rSrSrSS\S\\   4U 4S jjjr  SS\	R                  S\\	R                  \	R                  4   S\\	R                     S	\\   S
\\	R                     S\\	R                  \\	R                     \\\	R                        4   4S jjrSrU =r$ )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 )NrX   g      Tbias)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r-   r   r   r0   s      r1   r&   Olmo2Attention.__init__   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 #6#=#=#MvObObc"6#=#=#MvObObcr3   r>   position_embeddingsr^   past_key_valuecache_positionrQ   c                 
   UR                   S S n/ UQSPU R                  P7nU R                  U R                  U5      5      n	U R	                  U R                  U5      5      n
U R                  U5      nU	R                  U5      R                  SS5      n	U
R                  U5      R                  SS5      n
UR                  U5      R                  SS5      nUu  p[        XX5      u  pUb$  XUS.nUR                  XU R                  U5      u  p[        nU R                  R                  S:w  ad  U R                  R                  S:X  a-  UR                  SS5      (       a  [         R#                  S	5        O[$        U R                  R                     nU" U U	U
UU4U R&                  (       d  S
OU R(                  U R*                  S.UD6u  nnUR,                  " / UQSP76 R/                  5       nU R1                  U5      nUU4$ )Nr6   r   r5   )ry   rx   r   eagersdpaoutput_attentionsFz`torch.nn.functional.scaled_dot_product_attention` does not support `output_attentions=True`. Falling back to eager attention. This warning can be removed using the argument `attn_implementation="eager"` when loading the model.        )r`   r_   )rE   rX   r   r   r   r   r   viewrh   r   updater   rr   r   _attn_implementationgetloggerwarning_oncer   re   r   r_   rT   rk   r   )r-   r>   r   r^   r   r   rl   input_shapehidden_shapequery_statesrm   rn   rx   ry   cache_kwargsattention_interfacerq   ro   s                     r1   rA   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{{//69fjjI\^c>d>d##L
 '>dkk>^>^&_#$7	%
  $}}C$2H2HLL	%
 	%
!\ "));;;;FFHkk+.L((r3   )r   r   rX   r   r   r   r   rf   r   r   r   r_   r   N)NN)rI   rJ   rK   rL   __doc__r   r   intr&   r)   Tensorr   r	   
LongTensorrA   rM   rN   rO   s   @r1   r   r      s    Gd{ dx} d d< +/593)||3) #5<<#=>3) !.	3)
 !3) !!1!123) 
u||Xell3XeELL>Q5RR	S3) 3)r3   r   c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )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   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$ r   )r   r   r   r   )r-   r   r   s      r1   rA   Olmo2MLP.forward   s6    NN4;;t~~a/@#ADLLQRO#ST	r3   )r   r   r   r   r.   r   r   )rI   rJ   rK   rL   r&   rA   rM   rN   rO   s   @r1   r   r      s    0 r3   r   c                   v  ^  \ rS rSrS\S\4U 4S jjr       SS\R                  S\	\R                     S\	\R                     S\	\   S	\	\   S
\	\   S\	\R                     S\	\\R                  \R                  4      S\\R                  \	\\R                  \R                  4      4   4S jjrSrU =r$ )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      r1   r&   Olmo2DecoderLayer.__init__   sj    !--'vKF#(4V5G5GVM`M`(a%*6v7I7IvObOb*c'r3   r>   r^   rz   r   r   	use_cacher   r   rQ   c	                     Un
U R                   " SU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4nU(       a  X4-  nU$ )N)r>   r^   rz   r   r   r   r   r    )r   r   r   r   )r-   r>   r^   rz   r   r   r   r   r   rl   residualself_attn_weightsoutputss                r1   rA   Olmo2DecoderLayer.forward   s     ! ,0>> 
,
')%)/) 3
,
 
,
( 55mD 0 !/77F 0 "++Gr3   )r.   r   r   r   r   )NNNFFNN)rI   rJ   rK   rL   r   r   r&   r)   r   r   r   r	   boolr   FloatTensorrA   rM   rN   rO   s   @r1   r   r      s   d{ ds d 2637*.,1$)59KO'||' !.' u//0	'
 !' $D>' D>' !!1!12' &eELL%,,,F&GH' 
u  (51B1BEDUDU1U+V"WW	X' 'r3   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      (       aH  UR                  b;  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&   hasattrr   r   r   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   r0   s       r1   r&   Olmo2RotaryEmbedding.__init__  s    6>**v/B/B/N#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q((ZeD!%r3   c                    U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        R                  " USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	X4sS S S 5        $ ! , (       d  f       g = f)
Nr   r6   r   mpscpuF)device_typeenabledr5   r   )r   floatrS   rE   r9   r   
isinstancer   strr)   autocastrh   r   rx   r   ry   )
r-   r   rz   inv_freq_expandedposition_ids_expandedr   freqsembrx   ry   s
             r1   rA   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   )rI   rJ   rK   rL   r   r&   r)   no_gradr   rA   rM   rN   rO   s   @r1   r   r     s6    /{ / /" ]]_
  
r3   r   c                   N    \ rS rSr\rSrSrS/rS/r	Sr
SrSrSrSrSrSrS rSrg)	Olmo2PreTrainedModeli9  modelTr   past_key_valuesc                    U R                   R                  n[        U[        R                  5      (       aW  UR
                  R                  R                  SUS9  UR                  b%  UR                  R                  R                  5         g g [        U[        R                  5      (       ad  UR
                  R                  R                  SUS9  UR                  b2  UR
                  R                  UR                     R                  5         g g [        U[        5      (       a&  UR
                  R                  R                  S5        g g )Nr   )r<   stdg      ?)r   initializer_ranger   r'   r   r+   datanormal_r   zero_	Embeddingpadding_idxr"   fill_)r-   rZ   r   s      r1   _init_weights"Olmo2PreTrainedModel._init_weightsH  s    kk++fbii((MM&&CS&9{{&  &&( '--MM&&CS&9!!-""6#5#56<<> .--MM$$S) .r3   r   N)rI   rJ   rK   rL   r   config_classbase_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_2_supports_sdpa_supports_flex_attn_supports_cache_class_supports_quantized_cache_supports_static_cache_supports_attention_backendr  rM   r   r3   r1   r   r   9  sS    L&*#,-#4"5!N  $!"&*r3   r   c                     ^  \ rS rSrS\4U 4S jjrS rS r\\	         SS\
\R                     S\
\R                     S\
\R                     S	\
\   S
\
\R                     S\
\   S\
\   S\
\   S\
\R                     S\\   S\4S jj5       5       r SS\\R                  S4   S\R                  S\R                  S	\S\4
S jjr\S\R                  S\S\S\R2                  S\R                  S\4S j5       rSrU =r$ )
Olmo2ModeliV  r   c           	        > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [        UR                  UR                  S9U l        [#        US9U l        SU l        U R)                  5         g s  snf )Nr   )r   F)r%   r&   pad_token_idr  
vocab_sizer'   r  r.   embed_tokens
ModuleListrangenum_hidden_layersr   layersr"   r   normr   
rotary_embgradient_checkpointing	post_initr   s      r1   r&   Olmo2Model.__init__X  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcCbiv1Cbc
 !!3!39L9LM	.f=&+# 	 ds   C?c                     U R                   $ r   r  rF   s    r1   get_input_embeddingsOlmo2Model.get_input_embeddingsh  s       r3   c                     Xl         g r   r&  r-   r]   s     r1   set_input_embeddingsOlmo2Model.set_input_embeddingsk  s    !r3   	input_idsr^   rz   r   inputs_embedsr   r   output_hidden_statesr   flash_attn_kwargsrQ   c
                 J   Ub  UOU R                   R                  nUb  UOU R                   R                  nUb  UOU R                   R                  nUS L US L-  (       a  [	        S5      eU R
                  (       a/  U R                  (       a  U(       a  [        R                  S5        Sn[        U[        S 5      [        45      (       d  [	        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$                  S9n	Uc  U	R'                  S5      nU R)                  X%XU5      nUnU R+                  X5      nU(       a  SOS nU(       a  SOS nU R,                  S U R                   R.                    H7  nU(       a  X4-  nU" U4UUUUUU	US	.U
D6nUS   nU(       d  M.  UUS   4-  nM9     U R1                  U5      nU(       a  X4-  n[3        UU(       a  UOS UUS
9$ )Nz:You must specify exactly one of input_ids or inputs_embedszX`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.FzBThe `past_key_values` should be either a `Cache` object or `None`.r   r   r   r   )r^   rz   r   r   r   r   r   )last_hidden_stater   r>   
attentions)r   r   r/  r   
ValueErrorr"  re   r   r   r   r   r	   r  r
   get_seq_lengthr)   arangerE   r   rt   _update_causal_maskr!  r  r  r   r   )r-   r-  r^   rz   r   r.  r   r   r/  r   r0  past_seen_tokensrp   r>   r   all_hidden_statesall_self_attnsdecoder_layerlayer_outputss                      r1   rA   Olmo2Model.forwardn  sI    2C1N-TXT_T_TqTq$8$D $++JjJj 	 "+!6IDKK<Q<Q	-t";<YZZ&&4==Yj I /DJ+>??abb  --i8M0*nO!CRC^==?de"\\ ]5H5H5K"KTaThThN )33A6L..>L]
 & #oomJ #7BD0d![[)H4;;+H+HIM#!%55!)
*)."3#-$7
 $
M *!,M  =#3"55' J* 		-0  !11&+/8Od+%	
 	
r3   r   input_tensorc           	         U R                   R                  S:X  a  Ub  US:H  R                  5       (       a  U$ g U R                   R                  S:X  a,  [        U[        R
                  5      (       a  [        U5      nU$ Ub  UR                  5       OSnUb  UR                  OSnU R                   R                  S:X  a5  U(       d.  U(       d'  [        R                  " UUUU R                  S9(       a  g UR                  nUR                  S   n	U(       a  UR                  5       n
O5[        U[        R
                  5      (       a  UR                  S	   OXi-   S-   n
U R                  UU	U
UUUR                  S   S
9nU R                   R                  S:X  aZ  UbW  UR                   R"                  S;   a=  U(       d6  [        R$                  " U5      R&                  n[        R(                  " X5      nU$ )Nflash_attention_2r   flex_attentionr   Fr   )r.  past_key_values_lengthis_trainingr   r6   )sequence_lengthtarget_lengthr8   r   
batch_size)cudaxpunpu)r   r   anyr   r)   r   r   r6  is_compileabler   _ignore_causal_mask_sdpare   r8   rE   get_max_cache_shape5_prepare_4d_causal_attention_mask_with_cache_positionr   r   finfomin_unmask_unattended)r-   r^   r?  r   r   r   r9  using_compilable_cacher8   rE  rF  rp   	min_dtypes                r1   r8  Olmo2Model._update_causal_mask  s    ;;++/BB)~/D.I.I.K.K%%;;++/??.%,,77!<^!L!!
 @O?Z?99;`aCRC^!?!?di ;;++v5>T]n%>>*'7 MM	 ""&,,Q/!+??AM nell;; $$R(%7!;  PP+')#))!, Q 
 KK,,6*%%**.DD%
 E*..I0CCK[Kr3   rE  rF  r8   rG  c                    U b  U R                  5       S:X  a  U nU$ [        R                  " U5      R                  n[        R                  " X4XUR
                  S9nUS:w  a  [        R                  " USS9nU[        R                  " X$R
                  S9UR                  SS5      :  -  nUSSSS2SS24   R                  USSS5      nU b  UR                  5       nU R                  S   n	USS2SS2SS2SU	24   U SS2SSSS24   R                  UR
                  5      -   n
U
S:H  n
USS2SS2SS2SU	24   R                  X5      USS2SS2SS2SU	24'   U$ )	a  
Creates a causal 4D mask of shape `(batch_size, 1, query_length, key_value_length)` from a 2D mask of shape
`(batch_size, key_value_length)`, or if the input `attention_mask` is already 4D, do nothing.

Args:
    attention_mask (`torch.Tensor`):
        A 2D attention mask of shape `(batch_size, key_value_length)` or a 4D attention mask of shape
        `(batch_size, 1, query_length, key_value_length)`.
    sequence_length (`int`):
        The sequence length being processed.
    target_length (`int`):
        The target length: when generating with static cache, the mask should be as long as the static cache,
        to account for the 0 padding, the part of the cache that is not filled yet.
    dtype (`torch.dtype`):
        The dtype to use for the 4D attention mask.
    cache_position (`torch.Tensor`):
        Indices depicting the position of the input sequence tokens in the sequence.
    batch_size (`torch.Tensor`):
        Batch size.
N   )
fill_valuer8   r   r   )diagonalr2  r6   r   )rc   r)   rP  rQ  fullr   triur7  rT   rS   clonerE   r9   masked_fill)r^   rE  rF  r8   r   rG  rl   rp   rT  mask_lengthpadding_masks              r1   rO  @Olmo2Model._prepare_4d_causal_attention_mask_with_cache_position  s}   < %.*<*<*>!*C(K* ' E*..I** 0Y\j\q\qK !##jjqA5<<>S>STWeWmWmnprsWtttK%dD!Q&67>>z1bRTUK))//1,2226*1aL[L+@ANSTVZ\`bcScDdDgDg&&E    ,q05@Aq,;,AV5W5c5c 6Aq!\k\12 r3   )r  r"  r  r   r  r!  r  )	NNNNNNNNN)F)rI   rJ   rK   rL   r   r&   r'  r+  r   r   r   r)   r   r   r	   r   r   r   r   r   rA   r   r8  staticmethodr   r8   rO  rM   rN   rO   s   @r1   r  r  V  s   {  !"  151537+/59$(,0/359\
E,,-\
 !.\
 u//0	\

 "%\
   1 12\
 D>\
 $D>\
 'tn\
 !!1!12\
 $$89\
 
!\
  \
H #(BellK78B llB 	B
 B  BH 444 4 {{	4
 4 4 4r3   r  c                       \ rS rSrSrg)KwargsForCausalLMiJ  r   N)rI   rJ   rK   rL   rM   r   r3   r1   rc  rc  J  s    3r3   rc  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
 r
S rS rS r\\           SS\\R$                     S\\R&                     S\\R$                     S\\   S\\R*                     S\\R$                     S\\   S\\   S\\   S\\R$                     S\\\R&                  4   S\\   S\4S jj5       5       rSrU =r$ )Olmo2ForCausalLMiM  zlm_head.weightlm_headcolwise_repr>   logitsc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g r   )
r%   r&   r  r   r  r'   r   r.   rf  r#  r   s     r1   r&   Olmo2ForCausalLM.__init__S  sU     '
 ++yy!3!3V5F5FUS 	r3   c                 .    U R                   R                  $ r   r   r  rF   s    r1   r'  %Olmo2ForCausalLM.get_input_embeddings\  s    zz&&&r3   c                 $    XR                   l        g r   rl  r*  s     r1   r+  %Olmo2ForCausalLM.set_input_embeddings_  s    "'

r3   c                     U R                   $ r   rf  rF   s    r1   get_output_embeddings&Olmo2ForCausalLM.get_output_embeddingsb  s    ||r3   c                     Xl         g r   rq  )r-   new_embeddingss     r1   set_output_embeddings&Olmo2ForCausalLM.set_output_embeddingse  s    %r3   c                     Xl         g r   r   )r-   decoders     r1   set_decoderOlmo2ForCausalLM.set_decoderh  s    
r3   c                     U R                   $ r   ry  rF   s    r1   get_decoderOlmo2ForCausalLM.get_decoderk  s    zzr3   r-  r^   rz   r   r.  labelsr   r   r/  r   logits_to_keeprl   rQ   c                    Ub  UOU R                   R                  nU	b  U	OU R                   R                  n	U R                  " SUU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UX`R                   R                  S.UD6n[        UUUR                  UR                  UR                  S9$ )a  
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
    Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
    config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
    (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

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."
```N)	r-  r^   rz   r   r.  r   r   r/  r   )rh  r  r  )lossrh  r   r>   r4  r   )r   r   r/  r   r3  r   r   slicerf  loss_functionr  r   r   r>   r4  )r-   r-  r^   rz   r   r.  r  r   r   r/  r   r  rl   r   r>   slice_indicesrh  r  s                     r1   rA   Olmo2ForCausalLM.forwardn  s   N 2C1N-TXT_T_TqTq$8$D $++JjJj 	
 ,0:: ,
)%+'/!5),
 ,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVF{{OeOepiopD%#33!//))
 	
r3   )rf  r   r  )NNNNNNNNNNr   )rI   rJ   rK   rL   _tied_weights_keys_tp_plan_pp_planr&   r'  r+  rr  rv  r{  r~  r   r   r   r)   r   r   r	   r   r   r   r   r   rc  r   rA   rM   rN   rO   s   @r1   re  re  M  s   *+=)H_-z:;H'(&  151537+/59-1$(,0/35934G
E,,-G
 !.G
 u//0	G

 "%G
   1 12G
 ))*G
 D>G
 $D>G
 'tnG
 !!1!12G
 c5<</0G
 *+G
 
 G
  G
r3   re  )re  r  r   )r   )Nr   )Ctypingr   r   r   r   r)   torch.nnr'   activationsr   cache_utilsr	   r
   
generationr   integrationsr   modeling_attn_mask_utilsr   modeling_flash_attention_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   r   configuration_olmo2r   !torch.nn.attention.flex_attentionr   integrations.flex_attentionr   
get_loggerrI   r   Moduler"   r   r   rY   r   rr   r   ru   r   r   r   r   r   r  rc  re  __all__r   r3   r1   <module>r     s   4 3   ! . ) 7 > B 9 O K F & h h ,  !!;J 
		H	% Y'J299 J (J(	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % %428(O)RYY O)dryy  12 1h299 B *? * *8 p% p pf ?,j > i
+_ i
 i
X Er3   