
    PhV                        d dl mZmZmZ d dlZd dlmZ d dlmZ ddl	m
Z
 ddlmZmZ ddlmZ ddlmZ dd	lmZmZ dd
lmZ ddlmZmZ ddlmZmZ ddlmZmZ ddl m!Z! ddl"m#Z#m$Z$ ddl%m&Z& ddl'm(Z( ddl)m*Z*  ed       G d dejV                               Z,dejZ                  de.dejZ                  fdZ/	 d5dejV                  dejZ                  dejZ                  dejZ                  deejZ                     d e0d!e0d"e!e   fd#Z1d6d$Z2d% Z3 G d& d'ejV                        Z4 G d( d)ejV                        Z5 G d* d+e      Z6 G d, d-ejV                        Z7e# G d. d/e             Z8e# G d0 d1e8             Z9e# G d2 d3e8e             Z:g d4Z;y)7    )CallableOptionalUnionN)TransformersKwargs   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask!create_sliding_window_causal_mask)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)auto_docstringcan_return_tuple)deprecate_kwarg)check_model_inputs   )Olmo3ConfigRMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )Olmo3RMSNormc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z;
        Olmo3RMSNorm is equivalent to T5LayerNorm
        N)super__init__nn	Parametertorchonesweightvariance_epsilon)selfhidden_sizeeps	__class__s      b/var/www/html/saasai/venv/lib/python3.12/site-packages/transformers/models/olmo3/modeling_olmo3.pyr"   zOlmo3RMSNorm.__init__/   s1     	ll5::k#:; #    c                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |z  j                  |      S )N   T)keepdim)	dtypetor%   float32powmeanrsqrtr(   r'   )r)   hidden_statesinput_dtypevariances       r-   forwardzOlmo3RMSNorm.forward7   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UUm+//<<r.   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tupler'   shaper(   )r)   s    r-   
extra_reprzOlmo3RMSNorm.extra_repr>   s*    ))*+6$2G2G1HIIr.   )gư>)__name__
__module____qualname__r"   r<   r@   __classcell__r,   s   @r-   r   r   -   s    $=Jr.   r   r9   n_repreturnc                     | j                   \  }}}}|dk(  r| S | dddddddddf   j                  |||||      } | j                  |||z  ||      S )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)r9   rF   batchnum_key_value_headsslenhead_dims         r-   	repeat_kvrO   B   so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr.   modulequerykeyvalueattention_maskscalingdropoutkwargsc                 T   t        || j                        }t        || j                        }	t        j                  ||j	                  dd            |z  }
|#|d d d d d d d |j
                  d   f   }|
|z   }
t        j                  j                  |
dt        j                        j                  |j                        }
t        j                  j                  |
|| j                        }
t        j                  |
|	      }|j	                  dd      j                         }||
fS )Nr0   r   r1   )dimr3   )ptrainingr   )rO   num_key_value_groupsr%   matmul	transposer?   r#   
functionalsoftmaxr5   r4   r3   rV   r\   
contiguous)rP   rQ   rR   rS   rT   rU   rV   rW   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r-   eager_attention_forwardrh   N   s    3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#k1==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r.   c                 
   | j                   |j                   }}|j                  |      }|j                  |      }| |z  t        |       |z  z   }||z  t        |      |z  z   }	|j                  |      |	j                  |      fS )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.
    )r3   	unsqueezerotate_halfr4   )
qkcossinposition_idsunsqueeze_dimq_typek_typeq_embedk_embeds
             r-   apply_rotary_pos_embrv   h   s|    ( WWaggFF
--
&C
--
&C3w;q>C/0G3w;q>C/0G::fwzz&111r.   c                     | dd| j                   d   dz  f   }| d| j                   d   dz  df   }t        j                  | |fd      S )z*Rotates half the hidden dims of the input..Nr1   r0   rZ   )r?   r%   cat)xx1x2s      r-   rk   rk      sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r.   c                   0    e Zd ZdZdedef fdZ eddd      	 	 dd	ej                  d
e
ej                  ej                  f   deej                     dee   deej                     dee   de
ej                  eej                     f   fd       Z xZS )Olmo3Attentionz=Multi-headed attention from 'Attention Is All You Need' paperconfig	layer_idxc                    t         |           || _        || _        t	        |d|j
                  |j                  z        | _        |j                  |j                  z  | _	        | j                  dz  | _
        |j                  | _        d| _        t        j                  |j
                  |j                  | j                  z  |j                        | _        t        j                  |j
                  |j                  | j                  z  |j                        | _        t        j                  |j
                  |j                  | j                  z  |j                        | _        t        j                  |j                  | j                  z  |j
                  |j                        | _        t)        |j                  | j                  z  |j*                        | _        t)        |j                  | j                  z  |j*                        | _        |j0                  J |j0                  |   | _        | j2                  dk(  r|j4                  | _        y d | _        y )NrN   g      Tbiassliding_attention)r!   r"   r   r   getattrr*   num_attention_headsrN   rL   r]   rU   attention_dropout	is_causalr#   Linearattention_biasq_projk_projv_projo_projr   rms_norm_epsq_normk_normlayer_typesattention_typesliding_windowr)   r   r   r,   s      r-   r"   zOlmo3Attention.__init__   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 #6#=#=#MvObObc"6#=#=#MvObObc!!---$00;7;7J7JNa7af33gkr.   past_key_valuepast_key_values4.58new_nameversionr9   position_embeddingsrT   cache_positionrW   rG   c                    |j                   d d }g |d| j                  }| j                  | j                  |            }	| j	                  | j                  |            }
| j                  |      }|	j                  |      j                  dd      }	|
j                  |      j                  dd      }
|j                  |      j                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        }| j                  j                  dk7  rt        | j                  j                     } || |	|
||f| j                   sdn| j"                  | j$                  | j&                  d|\  }} |j(                  g |d j+                         }| j-                  |      }||fS )Nr1   r   r0   )ro   rn   r   eager        )rV   rU   r   )r?   rN   r   r   r   r   r   viewr_   rv   updater   rh   r   _attn_implementationr   r\   r   rU   r   rJ   rb   r   )r)   r9   r   rT   r   r   rW   input_shapehidden_shapequery_statesrc   rd   rn   ro   cache_kwargsattention_interfacerg   re   s                     r-   r<   zOlmo3Attention.forward   s    $))#2.88b8$--8{{4;;}#=>[[]!;<
{{=1#((6@@AF__\2<<QB
#((6@@AF&S#7jRUWZ#[ j&#&snUL'6'='=j,X\XfXfht'u$J(?;;++w6"9$++:Z:Z"[$7
%
  $}}C$2H2HLL..
%
 
%
!\ *k));;;;FFHkk+.L((r.   NN)rA   rB   rC   __doc__r   intr"   r   r%   Tensorr>   r   r	   
LongTensorr   r   r<   rD   rE   s   @r-   r~   r~      s    Gl{ ls l8 %0A6R ,059.)||.) #5<<#=>.) !.	.)
 "%.) !!1!12.) +,.) 
u||Xell33	4.) S.)r.   r~   c                   $     e Zd Z fdZd Z xZS )Olmo3MLPc                    t         |           || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _	        t        |j                     | _        y NFr   )r!   r"   r   r*   intermediate_sizer#   r   	gate_projup_proj	down_projr   
hidden_actact_fnr)   r   r,   s     r-   r"   zOlmo3MLP.__init__   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r.   c                     | j                  | j                  | j                  |            | j                  |      z        }|S )N)r   r   r   r   )r)   rz   r   s      r-   r<   zOlmo3MLP.forward   s6    NN4;;t~~a/@#ADLLQRO#ST	r.   )rA   rB   rC   r"   r<   rD   rE   s   @r-   r   r      s    0r.   r   c                   >    e Zd Zdedef fdZ eddd      	 	 	 	 	 	 ddej                  d	e	ej                     d
e	ej                     de	e   de	e   de	ej                     de	eej                  ej                  f      dee   dej                  fd       Z xZS )Olmo3DecoderLayerr   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        y )N)r   r   r+   )r!   r"   r*   r~   	self_attnr   mlpr   r   post_attention_layernormpost_feedforward_layernormr   s      r-   r"   zOlmo3DecoderLayer.__init__   sl    !--'vKF#(4V5G5GVM`M`(a%*6v7I7IvObOb*c'r.   r   r   r   r   r9   rT   rp   	use_cacher   r   rW   rG   c                     |}	 | j                   d|||||||d|\  }}
| j                  |      }|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r9   rT   rp   r   r   r   r    )r   r   r   r   )r)   r9   rT   rp   r   r   r   r   rW   residual_s              r-   r<   zOlmo3DecoderLayer.forward   s     !)4>> 	
')%+) 3	
 	
q 55mD =0 !/77F =0r.   )NNNFNN)rA   rB   rC   r   r   r"   r   r%   r   r   r   r	   boolr>   r   r   r<   rD   rE   s   @r-   r   r      s    d{ ds d %0A6R 2637+/$)59KO|| !. u//0	
 "% D> !!1!12 &eELL%,,,F&GH +, 
 Sr.   r   c                        e Zd ZU ej                  ed<   ddedee   f fdZ	 ej                         ed               Z xZS )Olmo3RotaryEmbeddinginv_freqr   	rope_typec                 6   t         |           ||| _        nht        |d      rUt	        |j
                  t              r;|j
                  j                  d|j
                  j                  d            | _        nd| _        | j                  J |j                  | _	        |j                  | _
        || _        t        | j                     | _        | j                  | j                  |      \  }| _        | j                  d|d       | j                   | _        y )Nrope_scalingr   typedefaultr   F)
persistent)r!   r"   r   hasattr
isinstancer   dictget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   r   r,   s        r-   r"   zOlmo3RotaryEmbedding.__init__  s     &DNV^,F<O<OQU1V#0044[&BUBUBYBYZ`BabDN&DN~~)))"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r.   c                    | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        j                  |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	||	fcd d d        S # 1 sw Y   y xY w)
Nr   r1   r   mpscpuF)device_typeenabledr0   rx   )r   floatrI   r?   r4   r   r   r   strr%   autocastr_   ry   rn   r   ro   )
r)   rz   rp   inv_freq_expandedposition_ids_expandedr   freqsembrn   ro   s
             r-   r<   zOlmo3RotaryEmbedding.forward0  s*    !MM$4-8>>@GGHZHZ[\H]_acdehhijiqiqr ,QaZ 8 > > @'1!((--'E!((--[`J`ahhmmfk^^UC&,,.1F1L1L1NNYYZ[]^_E))UEN3C'')d444C'')d444C8 DCCs    BE22E;r   )rA   rB   rC   r%   r   __annotations__r   r   r   r"   no_gradr   r<   rD   rE   s   @r-   r   r     sH    ll/{ /HSM /* U]]_
  
r.   r   c                   J    e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedZy)Olmo3PreTrainedModelr   modelTr   r   )r9   
attentionsN)rA   rB   rC   r   r   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r~   _can_record_outputsr   r.   r-   r   r   ?  sQ    &*#,-#4"5N!"&*$r.   r   c                       e Zd Zdef fdZee	 	 	 	 	 	 	 ddeej                     deej                     deej                     dee   deej                     deej                     d	ee   d
ee   defd              Z xZS )
Olmo3Modelr   c           	      N   t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |j                  |j                        | _        d| _        t        j$                  t'        |d      t'        |      d      | _        | j+                          y c c}w )Nr   Fr   )r   r   r   r   full_attention)r!   r"   pad_token_idpadding_idx
vocab_sizer#   	Embeddingr*   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normgradient_checkpointing
ModuleDictr   rotary_embs	post_initr   s      r-   r"   zOlmo3Model.__init__T  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcCbivy1Cbc
 !!3!39L9LM	&+#==%9S\%]"6f"E
 	 ds   D"	input_idsrT   rp   r   inputs_embedsr   r   rW   rG   c           
         |d u |d uz  rt        d      || j                  |      }|r|t        | j                        }|F||j	                         nd}	t        j                  |	|	|j                  d   z   |j                        }||j                  d      }t        |x}
t              s*| j                  |||||d}t        di |t        di |d}
|} | j                  d   ||       | j                  d	   ||      d
}| j                  d | j                  j                    D ]?  } ||f|
|j"                  j$                     |||||j"                  j$                     d|}A | j'                  |      }t)        ||      S )Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r   )r   )r   input_embedsrT   r   r   rp   )r   r   r   r   r   )rT   rp   r   r   r   )last_hidden_stater   r   )
ValueErrorr  r
   r   get_seq_lengthr%   aranger?   r   rj   r   r   r   r   r  r  r  r   r   r  r   )r)   r  rT   rp   r   r  r   r   rW   past_seen_tokenscausal_mask_mappingmask_kwargsr9   position_embeddings_mappingdecoder_layers                  r-   r<   zOlmo3Model.forwardi  s    -t";<YZZ *.*;*;I*FM0*$++>O!CRC^==?de+0<< "2]5H5H5K"KTaThTh,N )33A6L ?-F ++ -"0"0#2 ,K #5"C{"C%F%U%U#
 &!F!1!12E!F}Vb!c@d../?@P\]'
#
 "[[)H4;;+H+HIM)2=3J3J3Y3YZ) /-$?@W@W@f@f$g M J 		-0&++
 	
r.   )NNNNNNN)rA   rB   rC   r   r"   r   r   r   r%   r   r   r	   FloatTensorr   r   r   r   r<   rD   rE   s   @r-   r   r   R  s    { *  151537+/5959$(C
E,,-C
 !.C
 u//0	C

 "%C
   1 12C
 !!1!12C
 D>C
 +,C
 
!C
  C
r.   r   c                   d    e Zd ZdgZddiZddgdgfiZ fdZee	 	 	 	 	 	 	 	 	 dde	e
j                     de	e
j                     d	e	e
j                     d
e	e   de	e
j                     de	e
j                     de	e   de	e
j                     deee
j                  f   dee   defd              Z xZS )Olmo3ForCausalLMzlm_head.weightlm_headcolwise_repr9   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y r   )
r!   r"   r   r   r  r#   r   r*   r  r  r   s     r-   r"   zOlmo3ForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r.   r  rT   rp   r   r  labelsr   r   logits_to_keeprW   rG   c
                 z    | j                   d|||||||d|
}|j                  }t        |	t              rt	        |	 d      n|	}| j                  |dd|ddf         }d}|* | j                  d||| j                  j                  d|
}t        |||j                  |j                  |j                        S )a  
        Example:

        ```python
        >>> from transformers import AutoTokenizer, Olmo3ForCausalLM

        >>> model = Olmo3ForCausalLM.from_pretrained("meta-olmo3/Olmo3-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-olmo3/Olmo3-2-7b-hf")

        >>> prompt = "Hey, are you conscious? Can you talk to me?"
        >>> inputs = tokenizer(prompt, return_tensors="pt")

        >>> # Generate
        >>> generate_ids = model.generate(inputs.input_ids, max_length=30)
        >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
        "Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
        ```)r  rT   rp   r   r  r   r   N)r  r!  r  )lossr  r   r9   r   r   )r   r  r   r   slicer  loss_functionr   r  r   r   r9   r   )r)   r  rT   rp   r   r  r!  r   r   r"  rW   outputsr9   slice_indicesr  r$  s                   r-   r<   zOlmo3ForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r.   )	NNNNNNNNr   )rA   rB   rC   _tied_weights_keys_tp_plan_pp_planr"   r   r   r   r%   r   r   r	   r  r   r   r   r   r   r   r<   rD   rE   s   @r-   r  r    s0   *+=)H_-z:;H  151537+/59-1$(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   )<typingr   r   r   r%   torch.nnr#   transformers.utils.genericr   activationsr   cache_utilsr	   r
   
generationr   integrationsr   masking_utilsr   r   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   utils.deprecationr   utils.genericr   configuration_olmo3r   Moduler   r   r   rO   r   rh   rv   rk   r~   r   r   r   r   r   r  __all__r   r.   r-   <module>r?     s  , - ,   9 ! . ) 7 R 9 O K F & 5 0 / , Y'J299 J (J(	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%428(N)RYY N)bryy  )2 )X$299 $N ?  $ [
% [
 [
| H
+_ H
 H
V Er.   