
    <hM                        S SK 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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#  SSK$J%r%  SSK&J'r'   " S S\RP                  5      r) " S S\RP                  5      r*S r+S\RX                  S\-S\RX                  4S jr. S1S\RP                  S\RX                  S\RX                  S\RX                  S\\RX                     S\/S \/S!\\!   4S" jjr0S2S# jr1 " S$ S%\RP                  5      r2 " S& S'\5      r3 " S( S)\RP                  5      r4\" " S* S+\5      5       r5\" " S, S-\55      5       r6\" " S. S/\5\5      5       r7/ S0Qr8g)3    )CallableOptionalUnionN   )ACT2FN)CacheDynamicCache)GenerationMixin)create_causal_mask)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)check_model_inputs   )
OlmoConfigc                   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$ )
OlmoLayerNorm   z/LayerNorm but with no learnable weight or bias.hidden_sizereturnNc                 2   > [         TU ]  5         U4U l        g N)super__init__normalized_shape)selfr   	__class__s     ^/var/www/html/shao/venv/lib/python3.13/site-packages/transformers/models/olmo/modeling_olmo.pyr"   OlmoLayerNorm.__init__   s    !,    hidden_statesc                     UR                   n[        R                  " UR                  [        R
                  S9U R                  S S SS9R                  U5      $ )N)dtypegh㈵>)eps)r+   F
layer_normtotorchfloat32r#   )r$   r)   
orig_dtypes      r&   forwardOlmoLayerNorm.forward"   sO    "((
||M,,5==,A4CXCXZ^`djnorr
 	
r(   )r#   )__name__
__module____qualname____firstlineno____doc__intr"   r0   Tensorr3   __static_attributes____classcell__r%   s   @r&   r   r      s9    9/C /D /
U\\ 
ell 
 
r(   r   c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )OlmoMLP)   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$   rF   r%   s     r&   r"   OlmoMLP.__init__*   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r(   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ r    )rL   rN   rJ   rK   )r$   xrL   s      r&   r3   OlmoMLP.forward4   s6    NN4;;t~~a/@#ADLLQRO#ST	r(   )rN   rF   rL   rJ   r   rG   rK   )r5   r6   r7   r8   r"   r3   r<   r=   r>   s   @r&   r@   r@   )   s    0 r(   r@   c                     U SSU R                   S   S-  24   nU SU R                   S   S-  S24   n[        R                  " U* U4SS9$ )z*Rotates half the hidden dims of the input..N   dim)shaper0   cat)rR   x1x2s      r&   rotate_halfr]   9   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)rY   expandreshape)r)   r^   batchnum_key_value_headsslenhead_dims         r&   	repeat_kvrf   @   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$ )NrV   r   rU   )rX   r+   )ptrainingr   )rf   num_key_value_groupsr0   matmul	transposerY   rH   
functionalsoftmaxr1   r/   r+   rm   rr   
contiguous)rg   rh   ri   rj   rk   rl   rm   rn   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r&   eager_attention_forwardr~   L   s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!$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.
)r+   	unsqueezer]   r/   )
qkcossinposition_idsunsqueeze_dimq_typek_typeq_embedk_embeds
             r&   apply_rotary_pos_embr   f   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$ )OlmoAttention   z=Multi-headed attention from 'Attention Is All You Need' paperrF   	layer_idxc                 P  > [         TU ]  5         Xl        X l        [	        USUR
                  UR                  -  5      U l        UR                  UR                  -  U l	        U R                  S-  U l
        UR                  U l        SU l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR                  U R                  -  UR
                  UR                  S9U l        g )Nre   g      TrD   )r!   r"   rF   r   getattrr   num_attention_headsre   rc   rs   rl   attention_dropout	is_causalrH   rI   attention_biasq_projk_projv_projo_projr$   rF   r   r%   s      r&   r"   OlmoAttention.__init__   sI   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r(   r)   position_embeddingsrk   past_key_valuecache_positionr   c                    UR                   S S n/ UQSPU R                  P7nU R                  U5      n	U R                  U5      n
U R	                  U5      nU R
                  R                  b  U	R                  U R
                  R                  * U R
                  R                  S9  U
R                  U R
                  R                  * U R
                  R                  S9  UR                  U R
                  R                  * U R
                  R                  S9  U	R                  U5      R                  SS5      n	U
R                  U5      R                  SS5      n
UR                  U5      R                  SS5      nUu  p[        XX5      u  pUb$  XUS.nUR                  XU R                  U5      u  p[        nU R
                  R                  S:w  a  [        U R
                  R                     nU" U U	U
UU4U R                   (       d  SOU R"                  U R$                  S.UD6u  nnUR&                  " / UQSP76 R)                  5       nU R+                  U5      nUU4$ )	NrU   )minmaxr   rV   )r   r   r   eager        )rm   rl   )rY   re   r   r   r   rF   clip_qkvclamp_viewru   r   updater   r~   _attn_implementationr   rr   r   rl   ra   rx   r   )r$   r)   r   rk   r   r   rn   input_shapehidden_shapequery_statesry   rz   r   r   cache_kwargsattention_interfacer}   r{   s                     r&   r3   OlmoAttention.forward   s1    $))#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$J(?;;++w6"9$++:Z:Z"[$7	%
  $}}C$2H2HLL	%
 	%
!\ "));;;;FFHkk+.L((r(   )r   rF   re   r   r   r   rs   r   r   rl   r   )NN)r5   r6   r7   r8   r9   r   r:   r"   r0   r;   tupler   r   
LongTensorr3   r<   r=   r>   s   @r&   r   r      s    G
z 
c 
8 +/592)||2) #5<<#=>2) !.	2)
 !2) !!1!122) 
u||Xell3XeELL>Q5RR	S2) 2)r(   r   c                   8  ^  \ rS rSrS\S\4U 4S jjr      SS\R                  S\	\R                     S\	\R                     S\	\   S	\	\   S
\	\R                     S\	\\R                  \R                  4      S\\   S\\R                     4S jjrSrU =r$ )OlmoDecoderLayer   rF   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)rF   r   )
r!   r"   r   r   	self_attnr@   mlpr   input_layernormpost_attention_layernormr   s      r&   r"   OlmoDecoderLayer.__init__   sY    !--&fJ6?,V-?-?@(5f6H6H(I%r(   r)   rk   r   r   	use_cacher   r   rn   r   c                     Un	U R                  U5      nU R                  " S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$ )N)r)   rk   r   r   r   r   r    )r   r   r   r   )r$   r)   rk   r   r   r   r   r   rn   residual_s              r&   r3   OlmoDecoderLayer.forward   s     !,,];>> 	
')%)) 3	
 	
 !0 !55mD/ 0r(   )r   r   r   r   r   )NNNFNN)r5   r6   r7   r8   r   r:   r"   r0   r;   r   r   r   boolr   r   r   r3   r<   r=   r>   s   @r&   r   r      s    Jz Jc J 2637*.$)59KO|| !. u//0	
 ! D> !!1!12 &eELL%,,,F&GH +, 
u||	 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$ )OlmoRotaryEmbedding   rF   c                   > [         TU ]  5         [        US5      (       aZ  [        UR                  [
        5      (       a;  UR                  R                  SUR                  R                  S5      5      U l        OSU l        UR                  U l	        UR                  U l
        Xl        [        U R                     U l        U R                  U R                  U5      u  o0l        U R                  SUSS9  U R                   U l        g )Nrope_scaling	rope_typetypedefaultinv_freqF)
persistent)r!   r"   hasattr
isinstancer   dictgetr   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrF   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r$   rF   devicer   r%   s       r&   r"   OlmoRotaryEmbedding.__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   rU   r   mpscpuF)device_typeenabledrV   rW   )r   floatr`   rY   r/   r   r   r   strr0   autocastru   rZ   r   r   r   )
r$   rR   r   inv_freq_expandedposition_ids_expandedr   freqsembr   r   s
             r&   r3   OlmoRotaryEmbedding.forward  s)    !MM$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   $BE22
F )r   rF   r   r   r   r   r   r    )r5   r6   r7   r8   r   r"   r0   no_gradr   r3   r<   r=   r>   s   @r&   r   r      s6    /z / /" ]]_
  
r(   r   c                   R    \ rS rSr% \\S'   SrSrS/rS/r	Sr
SrSrSrSr\\S.rSrg	)
OlmoPreTrainedModeli  rF   modelTr   past_key_values)r)   
attentionsr   N)r5   r6   r7   r8   r   __annotations__base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsr<   r   r(   r&   r   r     sQ    &*#+,#4"5N!"&)#r(   r   c                     ^  \ rS rSrS\4U 4S jjr\\       SS\\	R                     S\\	R                     S\\	R                     S\\   S\\	R                     S	\\	R                     S
\\   S\\   S\4S jj5       5       rSrU =r$ )	OlmoModeli1  rF   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)rF   F)r!   r"   pad_token_idpadding_idx
vocab_sizerH   	Embeddingr   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   normr   
rotary_embgradient_checkpointing	post_initr   s      r&   r"   OlmoModel.__init__3  s     !.. ++LL):):F<N<NPTP`P`ammBGH`H`BabBaYf0Bab
 "&"4"45	-V<&+# 	 cs   C5	input_idsrk   r   r   inputs_embedsr   r   rn   r   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$ )Nz:You must specify exactly one of input_ids or inputs_embedsr   r   )r   )rF   input_embedsrk   r   r   r   )rk   r   r   r   r   )last_hidden_stater   )
ValueErrorr   r	   get_seq_lengthr0   arangerY   r   r   r   rF   r  r  r   r  r   )r$   r  rk   r   r   r  r   r   rn   past_seen_tokensr|   r)   r   decoder_layers                 r&   r3   OlmoModel.forwardC  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)*).-$7 M J 		-0&++
 	
r(   )r   r  r  r  r   r  r   )NNNNNNN)r5   r6   r7   r8   r   r"   r   r   r   r0   r   r;   r   FloatTensorr   r   r   r   r3   r<   r=   r>   s   @r&   r   r   1  s    z    151537+/5959$(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$ )OlmoForCausalLMi  zlm_head.weightlm_headcolwise_repr)   logitsc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g rC   )
r!   r"   r   r   r   rH   rI   r   r  r  rO   s     r&   r"   OlmoForCausalLM.__init__  sU     v&
 ++yy!3!3V5F5FUS 	r(   c                     Xl         g r    r   )r$   decoders     r&   set_decoderOlmoForCausalLM.set_decoder  s    
r(   c                     U R                   $ r    r  )r$   s    r&   get_decoderOlmoForCausalLM.get_decoder  s    zzr(   r  rk   r   r   r  labelsr   r   logits_to_keeprn   r   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$ )ai  
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."
```)r  rk   r   r   r  r   r   N)r  r"  r   )lossr  r   r)   r   r   )r   r  r   r:   slicer  loss_functionrF   r   r   r   r)   r   )r$   r  rk   r   r   r  r"  r   r   r#  rn   outputsr)   slice_indicesr  r%  s                   r&   r3   OlmoForCausalLM.forward  s    @ ,0:: 	,
)%+')	,
 	,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r(   )r  r   r   )	NNNNNNNNr   )r5   r6   r7   r8   _tied_weights_keys_tp_plan_pp_planr"   r  r   r   r   r   r0   r   r;   r   r  r   r   r:   r   r   r   r3   r<   r=   r>   s   @r&   r  r    s:   *+=)H_-z:;H  151537+/59-1$(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   r0   torch.nnrH   torch.nn.functionalrv   r-   activationsr   cache_utilsr   r	   
generationr
   masking_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   configuration_olmor   Moduler   r@   r]   r;   r:   rf   r   r~   r   r   r   r   r   r   r  __all__r   r(   r&   <module>r?     s   - ,     ! . ) / 9 O K F & I I / *
BII 
bii  (	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%428L)BII L)^)1 )X")) B /  $ K
# K
 K
\ N
)? N
 N
b Br(   