
    fThMv                     j   S SK JrJrJrJr  S SKrS SKJr  S SKJs  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%J&r&J'r'J(r(  SSK)J*r*  \'" 5       (       a  S SK+J,r,  SSK-J.r.  \(R^                  " \05      r1 " S S\Rd                  5      r3 " S S\Rd                  5      r4S r5S\Rl                  S\7S\Rl                  4S jr8 S4S\Rd                  S\Rl                  S\Rl                  S\Rl                  S \\Rl                     S!\9S"\94S# jjr:S5S$ jr; " S% S&\Rd                  5      r< " S' S(\5      r= " S) S*\Rd                  5      r>\% " S+ S,\ 5      5       r?\% " S- S.\?5      5       r@ " S/ S0\\$5      rA\% " S1 S2\?\5      5       rB/ S3QrCg)6    )CallableOptionalTupleUnionN   )ACT2FN)CacheDynamicCache)GenerationMixin)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   )
OlmoConfig)	BlockMask)make_flex_block_causal_maskc                   r   ^  \ rS rSrSrS\SS4U 4S jjrS\R                  S\R                  4S jr	S	r
U =r$ )
OlmoLayerNorm$   z/LayerNorm but with no learnable weight or bias.hidden_sizereturnNc                 2   > [         TU ]  5         U4U l        g N)super__init__normalized_shape)selfr"   	__class__s     ^/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/olmo/modeling_olmo.pyr'   OlmoLayerNorm.__init__'   s    !,    hidden_statesc                     UR                   n[        R                  " UR                  [        R
                  S9U R                  S S SS9R                  U5      $ )N)dtypegh㈵>)eps)r0   F
layer_normtotorchfloat32r(   )r)   r.   
orig_dtypes      r+   forwardOlmoLayerNorm.forward+   sO    "((
||M,,5==,A4CXCXZ^`djnorr
 	
r-   )r(   )__name__
__module____qualname____firstlineno____doc__intr'   r5   Tensorr8   __static_attributes____classcell__r*   s   @r+   r    r    $   s9    9/C /D /
U\\ 
ell 
 
r-   r    c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )OlmoMLP2   c                   > [         TU ]  5         Xl        UR                  U l        UR                  U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l	        [        UR                     U l        g NFbias)r&   r'   configr"   intermediate_sizennLinear	gate_projup_proj	down_projr   
hidden_actact_fnr)   rK   r*   s     r+   r'   OlmoMLP.__init__3   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r-   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ r%   )rQ   rS   rO   rP   )r)   xrQ   s      r+   r8   OlmoMLP.forward=   s6    NN4;;t~~a/@#ADLLQRO#ST	r-   )rS   rK   rQ   rO   r"   rL   rP   )r:   r;   r<   r=   r'   r8   rA   rB   rC   s   @r+   rE   rE   2   s    0 r-   rE   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$ )z*Rotates half the hidden dims of the input..N   dim)shaper5   cat)rW   x1x2s      r+   rotate_halfrb   B   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r-   r.   n_repr#   c                     U R                   u  p#pEUS:X  a  U $ 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      $ )z
This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
r   N)r^   expandreshape)r.   rc   batchnum_key_value_headsslenhead_dims         r+   	repeat_kvrk   I   s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr-   modulequerykeyvalueattention_maskscalingdropoutc                 @   [        X R                  5      n[        X0R                  5      n	[        R                  " XR	                  SS5      5      U-  n
Ub"  US S 2S S 2S S 2S UR
                  S   24   nX-   n
[        R                  R                  U
S[        R                  S9R                  UR                  5      n
[        R                  R                  XU R                  S9n
[        R                  " X5      nUR	                  SS5      R                  5       nX4$ )Nr[   r   rZ   )r]   r0   )ptrainingr   )rk   num_key_value_groupsr5   matmul	transposer^   rM   
functionalsoftmaxr6   r4   r0   rr   rv   
contiguous)rl   rm   rn   ro   rp   rq   rr   kwargs
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r+   eager_attention_forwardr   U   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.
)r0   	unsqueezerb   r4   )
qkcossinposition_idsunsqueeze_dimq_typek_typeq_embedk_embeds
             r+   apply_rotary_pos_embr   o   sv    ( WWaggF
--
&C
--
&Cw;q>C/0Gw;q>C/0G::fwzz&111r-   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
\\R                     S\
\R                  \\R                     \\
\R                        4   4S jjrSrU =r$ )OlmoAttention   z=Multi-headed attention from 'Attention Is All You Need' paperrK   	layer_idxc                 P  > [         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        g )Nrj   g      TrI   )r&   r'   rK   r   getattrr"   num_attention_headsrj   rh   rw   rq   attention_dropout	is_causalrM   rN   attention_biasq_projk_projv_projo_projr)   rK   r   r*   s      r+   r'   OlmoAttention.__init__   sI   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r-   r.   position_embeddingsrp   past_key_valuecache_positionr#   c                 R   UR                   S S n/ UQSPU R                  P7nU R                  U5      n	U R                  U5      n
U R	                  U5      nU R
                  R                  b  U	R                  U R
                  R                  * U R
                  R                  S9  U
R                  U R
                  R                  * U R
                  R                  S9  UR                  U R
                  R                  * U R
                  R                  S9  U	R                  U5      R                  SS5      n	U
R                  U5      R                  SS5      n
UR                  U5      R                  SS5      nUu  p[        XX5      u  pUb$  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[$        U R
                  R                     nU" U U	U
UU4U R&                  (       d  SOU R(                  U R*                  S.UD6u  nnUR,                  " / UQSP76 R/                  5       nU R1                  U5      nUU4$ )NrZ   )minmaxr   r[   )r   r   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.        )rr   rq   )r^   rj   r   r   r   rK   clip_qkvclamp_viewry   r   updater   r   _attn_implementationgetloggerwarning_oncer   rv   r   rq   rf   r|   r   )r)   r.   r   rp   r   r   r}   input_shapehidden_shapequery_statesr~   r   r   r   cache_kwargsattention_interfacer   r   s                     r+   r8   OlmoAttention.forward   sk    $))#2.88b8$--8{{=1[[/
{{=1;;+T[[%9%9$9t{{?S?ST4;;#7#7"7T[[=Q=QRT[[%9%9$9t{{?S?ST#((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$2H2HLL	%
 	%
!\ "));;;;FFHkk+.L((r-   )r   rK   rj   r   r   r   rw   r   r   rq   r   )NN)r:   r;   r<   r=   r>   r   r?   r'   r5   r@   r   r   r	   
LongTensorr8   rA   rB   rC   s   @r+   r   r      s    G
z 
c 
8 +/598)||8) #5<<#=>8) !.	8)
 !8) !!1!128) 
u||Xell3XeELL>Q5RR	S8) 8)r-   r   c                     ^  \ rS rSrS\S\4U 4S jjr       SS\R                  S\	\R                     S\	\R                     S\	\   S	\	\   S
\	\   S\	\R                     S\	\\R                  \R                  4      S\\   S\\R                   \	\\R                   \R                   4      4   4S jjrSrU =r$ )OlmoDecoderLayer   rK   r   c                    > [         TU ]  5         UR                  U l        [        XS9U l        [        U5      U l        [        UR                  5      U l        [        UR                  5      U l	        g )N)rK   r   )
r&   r'   r"   r   	self_attnrE   mlpr    input_layernormpost_attention_layernormr   s      r+   r'   OlmoDecoderLayer.__init__   sY    !--&fJ6?,V-?-?@(5f6H6H(I%r-   r.   rp   r   r   r   	use_cacher   r   r}   r#   c	                     Un
U R                  U5      nU R                  " SUUUUUUUUS.U	D6u  pX-   nUn
U R                  U5      nU R                  U5      nX-   nU4nU(       a  X4-  nU$ )N)r.   rp   r   r   r   r   r   r    )r   r   r   r   )r)   r.   rp   r   r   r   r   r   r   r}   residualself_attn_weightsoutputss                r+   r8   OlmoDecoderLayer.forward   s     !,,]; ,0>> 
,
')%)/) 3
,
 
,
( !0 !55mD/ 0 "++Gr-   )r"   r   r   r   r   )NNNFFNN)r:   r;   r<   r=   r   r?   r'   r5   r@   r   r   r	   boolr   r   r   FloatTensorr8   rA   rB   rC   s   @r+   r   r      s   Jz Jc J 2637*.,1$)59KO'||' !.' u//0	'
 !' $D>' 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$ )OlmoRotaryEmbeddingi  rK   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_lenrK   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r)   rK   devicer   r*   s       r+   r'   OlmoRotaryEmbedding.__init__  s    6>**v/B/B/N#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   rZ   r   mpscpuF)device_typeenabledr[   r\   )r   floatre   r^   r4   r   
isinstancer   strr5   autocastry   r_   r   r   r   )
r)   rW   r   inv_freq_expandedposition_ids_expandedr   freqsembr   r   s
             r+   r8   OlmoRotaryEmbedding.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   rK   r   r   r   r   r   r%   )r:   r;   r<   r=   r   r'   r5   no_gradr   r8   rA   rB   rC   s   @r+   r   r     s6    /z / /" ]]_
  
r-   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)	OlmoPreTrainedModeli5  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 g )Nr   )meanstd)rK   initializer_ranger   rM   rN   weightdatanormal_rJ   zero_	Embeddingpadding_idx)r)   rl   r   s      r+   _init_weights!OlmoPreTrainedModel._init_weightsD  s    kk++fbii((MM&&CS&9{{&  &&( '--MM&&CS&9!!-""6#5#56<<> . .r-   r   N)r:   r;   r<   r=   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   rA   r   r-   r+   r   r   5  sS    L&*#+,#4"5!N  $!"&	?r-   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$ )	OlmoModeliP  rK   c           	        > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [        UR                  5      U l        [!        US9U l        SU l        U R'                  5         g s  snf )N)rK   F)r&   r'   pad_token_idr   
vocab_sizerM   r   r"   embed_tokens
ModuleListrangenum_hidden_layersr   layersr    normr   
rotary_embgradient_checkpointing	post_initr   s      r+   r'   OlmoModel.__init__R  s     !.. ++LL):):F<N<NPTP`P`ammBGH`H`BabBaYf0Bab
 "&"4"45	-V<&+# 	 cs   C6c                     U R                   $ r%   r  r)   s    r+   get_input_embeddingsOlmoModel.get_input_embeddingsb  s       r-   c                     Xl         g r%   r  r)   ro   s     r+   set_input_embeddingsOlmoModel.set_input_embeddingse  s    !r-   	input_idsrp   r   r   inputs_embedsr   r   output_hidden_statesr   flash_attn_kwargsr#   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   )rp   r   r   r   r   r   r   )last_hidden_stater   r.   
attentions)rK   r   r$  r   
ValueErrorr  rv   r   r   r   r   r	   r  r
   get_seq_lengthr5   aranger^   r   r   _update_causal_maskr  r  r  r  r   )r)   r"  rp   r   r   r#  r   r   r$  r   r%  past_seen_tokensr   r.   r   all_hidden_statesall_self_attnsdecoder_layerlayer_outputss                      r+   r8   OlmoModel.forwardh  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+%	
 	
r-   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$ )Nflash_attention_2r   flex_attentionr   Fr   )r#  past_key_values_lengthis_trainingr   rZ   )sequence_lengthtarget_lengthr0   r   
batch_size)cudaxpunpu)rK   r   anyr   r5   r@   r   r+  is_compileabler   _ignore_causal_mask_sdparv   r0   r^   get_max_cache_shape5_prepare_4d_causal_attention_mask_with_cache_positionr   r   finfor   _unmask_unattended)r)   rp   r4  r   r   r   r.  using_compilable_cacher0   r:  r;  r   	min_dtypes                r+   r-  OlmoModel._update_causal_mask  s    ;;++/BB)~/D.I.I.K.K%%;;++/??.%,,77!<^!L!!
 @O?Z?99;`aCRC^!?!?di ;;++v5>T]n%>>*'7 MM	 ""&,,Q/!+??AM nell;; $$R(%7!;  PP+')#))!, Q 
 KK,,6*%%**.DD%
 E*..I0CCK[Kr-   r:  r;  r0   r<  c                    U b  U R                  5       S:X  a  U nU$ [        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_valuer0   r   r   )diagonalr'  rZ   r   )r]   r5   rE  r   fullr   triur,  rf   re   cloner^   r4   masked_fill)rp   r:  r;  r0   r   r<  r}   r   rH  mask_lengthpadding_masks              r+   rD  ?OlmoModel._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 r-   )r  r  r  r  r   r  r  )	NNNNNNNNN)F)r:   r;   r<   r=   r   r'   r  r   r   r   r   r5   r   r@   r	   r   r   r   r   r   r8   r   r-  staticmethodr?   r0   rD  rA   rB   rC   s   @r+   r  r  P  s   z  !"  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r-   r  c                       \ rS rSrSrg)KwargsForCausalLMiD  r   N)r:   r;   r<   r=   rA   r   r-   r+   rW  rW  D  s    3r-   rW  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$ )OlmoForCausalLMiG  zlm_head.weightlm_headcolwise_repr.   logitsc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g rH   )
r&   r'   r  r   r  rM   rN   r"   rZ  r  rT   s     r+   r'   OlmoForCausalLM.__init__M  sU     v&
 ++yy!3!3V5F5FUS 	r-   c                 .    U R                   R                  $ r%   r   r  r  s    r+   r  $OlmoForCausalLM.get_input_embeddingsV  s    zz&&&r-   c                 $    XR                   l        g r%   r`  r  s     r+   r   $OlmoForCausalLM.set_input_embeddingsY  s    "'

r-   c                     U R                   $ r%   rZ  r  s    r+   get_output_embeddings%OlmoForCausalLM.get_output_embeddings\  s    ||r-   c                     Xl         g r%   re  )r)   new_embeddingss     r+   set_output_embeddings%OlmoForCausalLM.set_output_embeddings_  s    %r-   c                     Xl         g r%   r   )r)   decoders     r+   set_decoderOlmoForCausalLM.set_decoderb  s    
r-   c                     U R                   $ r%   rm  r  s    r+   get_decoderOlmoForCausalLM.get_decodere  s    zzr-   r"  rp   r   r   r#  labelsr   r   r$  r   logits_to_keepr}   r#   c                    Ub  UOU R                   R                  nU	b  U	OU R                   R                  n	U R                  " SUUUUUUUU	U
S.	UD6nUR                  n[        U[        5      (       a  [        U* S5      OUnU R                  USS2USS24   5      nSnUb)  U R                  " SUX`R                   R                  S.UD6n[        UUUR                  UR                  UR                  S9$ )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, OlmoForCausalLM

>>> model = OlmoForCausalLM.from_pretrained("meta-olmo/Olmo-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-olmo/Olmo-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"  rp   r   r   r#  r   r   r$  r   )r\  rt  r  )lossr\  r   r.   r)  r   )rK   r   r$  r   r(  r   r?   slicerZ  loss_functionr  r   r   r.   r)  )r)   r"  rp   r   r   r#  rt  r   r   r$  r   ru  r}   r   r.   slice_indicesr\  rw  s                     r+   r8   OlmoForCausalLM.forwardh  s   N 2C1N-TXT_T_TqTq$8$D $++JjJj 	
 ,0:: ,
)%+'/!5),
 ,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVF{{OeOepiopD%#33!//))
 	
r-   )rZ  r   r  )NNNNNNNNNNr   )r:   r;   r<   r=   _tied_weights_keys_tp_plan_pp_planr'   r  r   rf  rj  ro  rr  r   r   r   r5   r   r@   r	   r   r   r   r?   r   rW  r   r8   rA   rB   rC   s   @r+   rY  rY  G  s   *+=)H_-z:;H'(&  151537+/59-1$(,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
r-   rY  )rY  r  r   )r   )Nr   )Dtypingr   r   r   r   r5   torch.nnrM   torch.nn.functionalrz   r2   activationsr   cache_utilsr	   r
   
generationr   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_olmor   !torch.nn.attention.flex_attentionr   integrations.flex_attentionr   
get_loggerr:   r   Moduler    rE   rb   r@   r?   rk   r   r   r   r   r   r   r   r  rW  rY  __all__r   r-   r+   <module>r     s   4 3     ! . ) > B 9 O K F & h h *  !!;J 
		H	%
BII 
bii  (	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % %428R)BII R)j11 1h")) B ?/ ? ?4 p# p pf ?,j > i
)? i
 i
X Br-   