
    3joS                     h   S SK Jr  S SK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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#  SSK$J%r%J&r&J'r'  SSK(J)r)J*r*  SSK+J,r,  SSK-J.r.   " S S\R^                  5      r0 " S S\R^                  5      r1 " S S\R^                  5      r2S r3S\Rh                  S\5S\Rh                  4S jr6 S7S\R^                  S \Rh                  S!\Rh                  S"\Rh                  S#\Rh                  S-  S$\7S%\7S&\#\%   4S' jjr8\" S(5      S8S) j5       r9\" \95       " S* S+\R^                  5      5       r: " S, S-\5      r;\& " 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_func_from_hubuse_kernelized_func)create_causal_mask) GenericForSequenceClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs   )
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$ )
OlmoLayerNorm1   z/LayerNorm but with no learnable weight or bias.hidden_sizereturnNc                 2   > [         TU ]  5         U4U l        g N)super__init__normalized_shape)selfr!   	__class__s     `/home/wildlama/miniconda3/lib/python3.13/site-packages/transformers/models/olmo/modeling_olmo.pyr&   OlmoLayerNorm.__init__4   s    !,    hidden_statesc                     UR                   n[        R                  " UR                  [        R
                  S9U R                  S S SS9R                  U5      $ )Ndtypegh㈵>)eps)r0   F
layer_normtotorchfloat32r'   )r(   r-   
orig_dtypes      r*   forwardOlmoLayerNorm.forward8   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   1   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$ )OlmoMLP?   c                   > [         TU ]  5         Xl        UR                  U l        UR                  U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l	        [        UR                     U l        g NFbias)r%   r&   configr!   intermediate_sizennLinear	gate_projup_proj	down_projr   
hidden_actact_fnr(   rK   r)   s     r*   r&   OlmoMLP.__init__@   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r,   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ r$   )rQ   rS   rO   rP   )r(   xrQ   s      r*   r8   OlmoMLP.forwardJ   s6    NN4;;t~~a/@#ADLLQRO#ST	r,   )rS   rK   rQ   rO   r!   rL   rP   )r:   r;   r<   r=   r&   r8   rA   rB   rC   s   @r*   rE   rE   ?   s    0 r,   rE   c                      ^  \ rS rSr% \R
                  \S'   SS\4U 4S jjjr\	   SS\S-  S\
S   S\S-  S	\S
\4   4S jj5       r\R                  " 5       \S 5       5       rSrU =r$ )OlmoRotaryEmbeddingO   inv_freqNrK   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_lenrK   rope_parametersr^   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r(   rK   devicerope_init_fnr\   r)   s        r*   r&   OlmoRotaryEmbedding.__init__R   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L((ZeD0(..2BuUr,   rj   ztorch.deviceseq_lenr"   ztorch.Tensorc           	         U R                   S   n[        U SS5      =(       d    U R                  U R                  -  nSnSU[        R
                  " SUS[        R                  S9R                  U[        R                  S9U-  -  -  nXe4$ )	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_thetahead_dimNg      ?r      r/   )rj   r0   )	re   getattrr!   num_attention_headsr5   arangeint64r4   float)rK   rj   rm   basedimattention_factorr\   s          r*   rf   3OlmoRotaryEmbedding.compute_default_rope_parametersb   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 ))r,   c                    U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        X4$ ! , (       d  f       WW	4$ = f)
Nr   r   mpscpuF)device_typeenabledrq   rx   )r\   rv   expandshaper4   rj   
isinstancetypestrr   	transposer5   catcosrg   sin)
r(   rW   position_idsinv_freq_expandedposition_ids_expandedr   freqsembr   r   s
             r*   r8   OlmoRotaryEmbedding.forward   s7    !MM$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
 x DC
 Cxs   BE&&
E7)rg   rK   rc   rd   r^   r$   )NNN)r:   r;   r<   r=   r5   r@   __annotations__r   r&   staticmethodr   r?   tuplerv   rf   no_gradr   r8   rA   rB   rC   s   @r*   rZ   rZ   O   s    llVz V V  $(+/"*T!*(* t* 
~u$	%	* *: ]]_
  
r,   rZ   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$ )z*Rotates half the hidden dims of the input..Nr|   rq   r   )r   r5   r   )rW   x1x2s      r*   rotate_halfr      sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r,   r-   n_repr"   c                     U R                   u  p#pEUS:X  a  U $ 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      $ )z
This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
r   N)r   r   reshape)r-   r   batchnum_key_value_headsslenrp   s         r*   	repeat_kvr      s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr,   modulequerykeyvalueattention_maskscalingdropoutkwargsc                    [        X R                  5      n[        X0R                  5      n	[        R                  " XR	                  SS5      5      U-  n
Ub  X-   n
[
        R                  R                  U
S[        R                  S9R                  UR                  5      n
[
        R                  R                  XU R                  S9n
[        R                  " X5      nUR	                  SS5      R                  5       nX4$ )Nrq   r   r|   )rx   r0   )ptrainingr   )r   num_key_value_groupsr5   matmulr   rM   
functionalsoftmaxr6   r4   r0   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightsattn_outputs               r*   eager_attention_forwardr      s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!#4==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r,   rotary_pos_embc                    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.
)r0   	unsqueezer   r4   )	qkr   r   unsqueeze_dimq_typek_typeq_embedk_embeds	            r*   apply_rotary_pos_embr      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
\S-  S\
\R                  \R                  S-  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 )Nrp   g      TrI   )r%   r&   rK   r   rr   r!   rs   rp   r   r   r   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$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r,   Nr-   position_embeddingsr   past_key_valuesr"   c                    UR                   S S n/ UQSPU R                  P7nU R                  U5      nU R                  U5      n	U R	                  U5      n
U R
                  R                  b  UR                  U R
                  R                  * U R
                  R                  S9  U	R                  U R
                  R                  * U R
                  R                  S9  U
R                  U R
                  R                  * U R
                  R                  S9  UR                  U5      R                  SS5      nU	R                  U5      R                  SS5      n	U
R                  U5      R                  SS5      n
Uu  p[        XX5      u  pUb  UR                  XU R                  5      u  p[        R                  " U R
                  R                  [         5      nU" U UU	U
U4U R"                  (       d  SOU R$                  U R&                  S.UD6u  pUR(                  " / UQSP76 R+                  5       nU R-                  U5      nX4$ )Nr|   )minmaxr   rq           )r   r   )r   rp   r   r   r   rK   clip_qkvclamp_viewr   r   updater   r   get_interface_attn_implementationr   r   r   r   r   r   r   )r(   r-   r   r   r   r   input_shapehidden_shapequery_statesr   r   r   r   attention_interfacer   r   s                   r*   r8   OlmoAttention.forward   s    $))#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#[ &'6'='=jX\XfXf'g$J(?(M(MKK,,.E)
 %8	%
  $}}C$2H2HLL	%
 	%
! "));;;;FFHkk+.((r,   )r   rK   rp   r   r   r   r   r   r   r   r   r$   )r:   r;   r<   r=   r>   r   r?   r&   r5   r@   r   r   r8   rA   rB   rC   s   @r*   r   r      s    G
z 
c 
8 )-/)||/) #5<<#=>/) t+	/)
 /) 
u||U\\D00	1/) /)r,   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$ )OlmoDecoderLayeri#  rK   r   c                    > [         TU ]  5         UR                  U l        [        XS9U l        [        U5      U l        [        UR                  5      U l        [        UR                  5      U l	        g )N)rK   r   )
r%   r&   r!   r   	self_attnrE   mlpr   input_layernormpost_attention_layernormr   s      r*   r&   OlmoDecoderLayer.__init__$  sY    !--&fJ6?,V-?-?@(5f6H6H(I%r,   Nr-   r   r   r   	use_cacher   r   r"   c           
          UnU R                  U5      nU R                  " S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$ )N)r-   r   r   r   r   r    )r   r   r   r   )
r(   r-   r   r   r   r   r   r   residual_s
             r*   r8   OlmoDecoderLayer.forward-  s     !,,];>> 
')%+ 3
 
 !0 !55mD/ 0r,   )r!   r   r   r   r   )NNNFN)r:   r;   r<   r=   r   r?   r&   r5   r@   
LongTensorr   boolr   r   r   r8   rA   rB   rC   s   @r*   r   r   #  s    Jz Jc J /304(,!&HL|| t+ &&-	
  $; #5<<#=>E +, 
 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	)
OlmoPreTrainedModeliM  rK   modelTr   r   )r-   
attentionsr   N)r:   r;   r<   r=   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_outputsrA   r   r,   r*   r   r   M  sQ    &*#+,#4"5N!"&)#r,   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$ )	OlmoModeli`  rK   c           	        > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [        UR                  5      U l        [!        US9U l        SU l        U R'                  5         g s  snf )NrK   F)r%   r&   pad_token_idpadding_idx
vocab_sizerM   	Embeddingr!   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   normrZ   
rotary_embgradient_checkpointing	post_initr   s      r*   r&   OlmoModel.__init__b  s     !.. ++LL):):F<N<NPTP`P`ammBGH`H`BabBaYf0Bab
 "&"4"45	-V<&+# 	 cs   C6N	input_idsr   r   r   inputs_embedsr   r   r"   c           
      >   US L US L-  (       a  [        S5      eUc  U R                  U5      nU(       a  Uc  [        U R                  S9nUcU  Ub  UR	                  5       OSn[
        R                  " UR                  S   UR                  S9U-   nUR                  S5      n[        U R                  UUUUS9n	Un
U R                  XS9nU R                  S U R                  R                    H  nU" U
4U	UUUUS.UD6n
M     U R                  U
5      n
[        U
US	9$ )
Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r   )rj   )rK   r  r   r   r   )r   )r   r   r   r   r   )last_hidden_stater   )
ValueErrorr  r   rK   get_seq_lengthr5   rt   r   rj   r   r   r  r	  r  r
  r   )r(   r  r   r   r   r  r   r   past_seen_tokenscausal_maskr-   r   decoder_layers                r*   r8   OlmoModel.forwardr  sF    -t";<YZZ *.*;*;I*FM0*$++>OCRC^==?de <<(;(;A(>}G[G[\_ooL'11!4L(;;')+%
 &"oomoW![[)H4;;+H+HIM)*$7) /# M J 		-0&++
 	
r,   )r  r  r	  r
  r  r  r  )NNNNNN)r:   r;   r<   r=   r   r&   r   r   r   r5   r   r@   r   FloatTensorr   r   r   r   r8   rA   rB   rC   s   @r*   r   r   `  s    z     .2.204(,26!%2
##d*2
 t+2
 &&-	2

 2
 ((4/2
 $;2
 +,2
 
!2
    2
r,   r   c                   P  ^  \ rS rSrSS0rSS0rSS/S/40rU 4S jr\\	        SS
\
R                  S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\\
R                  -  S\\   S\4S jj5       5       rSrU =r$ )OlmoForCausalLMi  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 rH   )
r%   r&   r   r   r  rM   rN   r!   r  r  rT   s     r*   r&   OlmoForCausalLM.__init__  sU     v&
 ++yy!3!3V5F5FUS 	r,   Nr  r   r   r   r  labelsr   logits_to_keepr   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$ )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  r   r   r   r  r   N)r  r!  r  )lossr  r   r-   r   r   )r   r  r   r?   slicer  loss_functionrK   r  r   r   r-   r   )r(   r  r   r   r   r  r!  r   r"  r   outputsr-   slice_indicesr  r$  s                  r*   r8   OlmoForCausalLM.forward  s    > ,0:: ,
)%+',
 ,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r,   )r  r   r  )NNNNNNNr   )r:   r;   r<   r=   _tied_weights_keys_tp_plan_pp_planr&   r   r   r5   r   r@   r   r  r   r?   r   r   r   r8   rA   rB   rC   s   @r*   r  r    s   *,GH23H_-z:;H  .2.204(,26*.!%-.6
##d*6
 t+6
 &&-	6

 6
 ((4/6
   4'6
 $;6
 ell*6
 +,6
 
 6
  6
r,   r  c                       \ rS rSrSrg)OlmoForSequenceClassificationi  r   N)r:   r;   r<   r=   rA   r   r,   r*   r.  r.    s    r,   r.  )r  r.  r   r   )r   )r   )Acollections.abcr   typingr   r5   torch.nnrM   torch.nn.functionalr   r2   activationsr   cache_utilsr   r   
generationr	   integrationsr
   r   masking_utilsr   modeling_layersr   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   utils.output_capturingr   configuration_olmor   Moduler   rE   rZ   r   r@   r?   r   rv   r   r   r   r   r   r   r  r.  __all__r   r,   r*   <module>rC     s  4 %      ! . ) I / [ O K F & I I G 5 *
BII 
bii  =")) =@(	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%2 *+2 ,24 )*I)BII I) +I)X'1 'T /  $ F
# F
 F
R F
)? F
 F
R	$DFY 	 cr,   