
    iU                     6   d dl mZ d dlmZ d dl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 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$m%Z%m&Z&m'Z' ddl(m)Z) ddl*m+Z+  ed       G d dejX                               Z-dej\                  de/dej\                  fdZ0	 d5dejX                  dej\                  dej\                  dej\                  dej\                  dz  d e1d!e1d"e e%   fd#Z2d6d$Z3d% Z4 ee3       G d& d'ejX                               Z5 G d( d)ejX                        Z6 G d* d+e      Z7 G d, d-ejX                        Z8e" G d. d/e             Z9e" G d0 d1e9             Z:e" G d2 d3e9e             Z;g d4Z<y)7    )Callable)OptionalN   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernelized_func)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)TransformersKwargsmaybe_autocastmerge_with_config_defaults)capture_outputs   )Olmo3ConfigRMSNormc                   P     e Zd Zddeddf fdZdej                  fdZd Z xZ	S )Olmo3RMSNormepsreturnNc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z;
        Olmo3RMSNorm is equivalent to T5LayerNorm
        N)super__init__nn	Parametertorchonesweightvariance_epsilon)selfhidden_sizer!   	__class__s      y/var/www/vps2.regionflexible.com/Desarrollo/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.forward5   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UUm+//<<r0   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tupler*   shaper+   )r,   s    r/   
extra_reprzOlmo3RMSNorm.extra_repr<   s*    ))*+6$2G2G1HIIr0   )gư>)
__name__
__module____qualname__floatr%   r(   Tensorr>   rB   __classcell__r.   s   @r/   r    r    +   s,    $ $$ $= =Jr0   r    r;   n_repr"   c                     | j                   \  }}}}|dk(  r| S | dddddddddf   j                  |||||      } | j                  |||z  ||      S )z
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r   N)rA   expandreshape)r;   rJ   batchnum_key_value_headsslenhead_dims         r/   	repeat_kvrR   @   so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr0   modulequerykeyvalueattention_maskscalingdropoutkwargsc                    t        || j                        }t        || j                        }	t        j                  ||j	                  dd            |z  }
||
|z   }
t
        j                  j                  |
dt        j                        j                  |j                        }
t
        j                  j                  |
|| j                        }
t        j                  |
|	      }|j	                  dd      j                         }||
fS )Nr2   r   r3   )dimr5   )ptrainingr   )rR   num_key_value_groupsr(   matmul	transposer&   
functionalsoftmaxr7   r6   r5   rY   r^   
contiguous)rS   rT   rU   rV   rW   rX   rY   rZ   
key_statesvalue_statesattn_weightsattn_outputs               r/   eager_attention_forwardri   L   s     3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!#n4==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r0   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.
        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.
    )r5   	unsqueezerotate_halfr6   )	qkcossinunsqueeze_dimq_typek_typeq_embedk_embeds	            r/   apply_rotary_pos_embrv   e   s|    $ WWaggFF
--
&C
--
&C3w;q>C/0G3w;q>C/0G::fwzz&111r0   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..Nr3   r2   r\   )rA   r(   cat)xx1x2s      r/   rl   rl      sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r0   c                        e Zd ZdZdedef fdZ	 ddej                  de	ej                  ej                  f   dej                  dz  d	e
dz  d
ee   de	ej                  ej                  dz  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                  |   | _        | j2                  dk(  r|j4                  | _        y d | _        y )NrQ   g      Tbiassliding_attention)r$   r%   r   r   getattrr-   num_attention_headsrQ   rO   r_   rX   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r0   Nr;   position_embeddingsrW   past_key_valuesrZ   r"   c                 h   |j                   d d }g |d| j                  }| j                  | j                  |            }| j	                  | j                  |            }	| j                  |      }
|j                  |      j                  dd      }|	j                  |      j                  dd      }	|
j                  |      j                  dd      }
|\  }}t        ||	||      \  }}	| |j                  |	|
| j                        \  }	}
t        j                  | j                  j                  t               } || ||	|
|f| j"                  sdn| j$                  | j&                  | j(                  d|\  }} |j*                  g |d j-                         }| j/                  |      }||fS )Nr3   r   r2           )rY   rX   r   )rA   rQ   r   r   r   r   r   viewra   rv   updater   r   get_interfacer   _attn_implementationri   r^   r   rX   r   rM   rd   r   )r,   r;   r   rW   r   rZ   input_shapehidden_shapequery_statesre   rf   ro   rp   attention_interfacerh   rg   s                   r/   r>   zOlmo3Attention.forward   s    $))#2.88b8$--8{{4;;}#=>[[]!;<
{{=1#((6@@AF__\2<<QB
#((6@@AF&S#7jRUWZ#[ j&'6'='=j,X\XfXf'g$J(?(M(MKK,,.E)
 %8
%
  $}}C$2H2HLL..
%
 
%
!\ *k));;;;FFHkk+.L((r0   N)rC   rD   rE   __doc__r   intr%   r(   rG   r@   r   r   r   r>   rH   rI   s   @r/   r~   r~      s    Gl{ ls l@ )-+)||+) #5<<#=>+) t+	+)
 +) +,+) 
u||U\\D00	1+)r0   r~   c                   $     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$   r%   r   r-   intermediate_sizer&   r   	gate_projup_proj	down_projr   
hidden_actact_fnr,   r   r.   s     r/   r%   zOlmo3MLP.__init__   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r0   c                     | j                  | j                  | j                  |            | j                  |      z        }|S r   )r   r   r   r   )r,   rz   r   s      r/   r>   zOlmo3MLP.forward   s6    NN4;;t~~a/@#ADLLQRO#ST	r0   )rC   rD   rE   r%   r>   rH   rI   s   @r/   r   r      s    0r0   r   c                       e Zd Zdedef fdZ	 	 	 	 	 ddej                  dej                  dz  dej                  dz  de	dz  d	e
dz  d
eej                  ej                  f   dz  dee   dej                  fdZ xZS )Olmo3DecoderLayerr   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        y )N)r   r   r!   )r$   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'r0   Nr;   rW   position_idsr   	use_cacher   rZ   r"   c           
          |} | j                   d||||||d|\  }}	| j                  |      }||z   }|}| j                  |      }| j                  |      }||z   }|S )N)r;   rW   r   r   r   r    )r   r   r   r   )
r,   r;   rW   r   r   r   r   rZ   residual_s
             r/   r>   zOlmo3DecoderLayer.forward   s     !)4>> 
')%+ 3
 
q 55mD =0 !/77F =0r0   )NNNFN)rC   rD   rE   r   r   r%   r(   rG   
LongTensorr   boolr@   r   r   r>   rH   rI   s   @r/   r   r      s    d{ ds d /304(,!&HL|| t+ &&-	
  $; #5<<#=>E +, 
r0   r   c                        e Zd ZU ej                  ed<   ddef fdZe	 	 	 ddedz  de	d   de
dz  ded	ef   fd
       Z ej                         ed               Z xZS )Olmo3RotaryEmbeddinginv_freqNr   c                    t         |           |j                  | _        |j                  | _        || _        | j
                  j                  d   | _        | j                  }| j                  dk7  rt        | j                     } || j
                  |      \  }| _
        | j                  d|d       | j                  d|j                         d       y )N	rope_typedefaultr   F)
persistentoriginal_inv_freq)r$   r%   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr   rope_parametersr   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r,   r   devicerope_init_fnr   r.   s        r/   r%   zOlmo3RotaryEmbedding.__init__  s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuUr0   r   ztorch.deviceseq_lenr"   ztorch.Tensorc                    | j                   d   }t        | dd      xs | j                  | j                  z  }d}d|t	        j
                  d|dt        j                        j                  |t        j                        |z  z  z  }||fS )	a  
        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_thetarQ   Ng      ?r   r2   r5   )r   r5   )	r   r   r-   r   r(   arangeint64r6   rF   )r   r   r   baser\   attention_factorr   s          r/   r   z4Olmo3RotaryEmbedding.compute_default_rope_parameters  s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r0   c                 N   | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        j	                  |j                   
      	j	                  |j                   
      fS # 1 sw Y   AxY w)Nr   r3   r   mpscpuF)device_typeenabledr2   rx   r   )r   rF   rL   rA   r6   r   
isinstancetypestrr   ra   r(   ry   ro   r   rp   r5   )
r,   rz   r   inv_freq_expandedposition_ids_expandedr   freqsembro   rp   s
             r/   r>   zOlmo3RotaryEmbedding.forward=  sR    !MM$4-8>>@GGHZHZ[\H]_acdehhijiqiqr ,QaZ 8 > > @'1!((--'E!((--[`J`ahhmmfkUC 	5&,,.1F1L1L1NNYYZ[]^_E))UEN3C'')d444C'')d444C		5 vvAGGv$cff177f&;;;	5 	5s   BFF$r   )NNN)rC   rD   rE   r(   rG   __annotations__r   r%   staticmethodr   r   r@   rF   r   no_gradr   r>   rH   rI   s   @r/   r   r     s    llV{ V  %)+/"*d"*(* t* 
~u$	%	* *: U]]_<  <r0   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   )r;   
attentionsN)rC   rD   rE   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   r0   r/   r   r   M  sQ    &*#,-#4"5N!"&*$r0   r   c                        e Zd Zdef fdZeee	 	 	 	 	 	 ddej                  dz  dej                  dz  dej                  dz  dedz  dej                  dz  d	edz  d
ee   defd                     Z xZS )
Olmo3Modelr   c           	         t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |j                  |j                        | _        t#        |      | _        d| _        | j)                          y c c}w )Nr   r   F)r$   r%   pad_token_idpadding_idx
vocab_sizer&   	Embeddingr-   embed_tokens
ModuleListrangenum_hidden_layersr   layersr    r   normr   
rotary_embgradient_checkpointing	post_initr   s      r/   r%   zOlmo3Model.__init__b  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcivy1c
 !!3!39L9LM	.f=&+# 	 ds   DN	input_idsrW   r   r   inputs_embedsr   rZ   r"   c           	         |d u |d uz  rt        d      || j                  |      }|r|t        | j                        }|V||j	                         nd}t        j                  |j                  d   |j                        |z   }|j                  d      }t        |x}	t              s)| j                  ||||d}
t        d
i |
t        d
i |
d}	|}| j                  ||      }t        | j                   d | j                  j"                         D ]-  \  }} ||f|	| j                  j$                  |      |||d|}/ | j'                  |      }t)        ||	      S )Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r   )r   )r   r
  rW   r   r   )full_attentionr   )rW   r   r   r   )last_hidden_stater   r   )
ValueErrorr   r   r   get_seq_lengthr(   r   rA   r   rk   r   dictr   r   r  	enumerater  r  r   r  r   )r,   r	  rW   r   r   r
  r   rZ   past_seen_tokenscausal_mask_mappingmask_kwargsr;   r   idecoder_layers                  r/   r>   zOlmo3Model.forwardr  s    -t";<YZZ *.*;*;I*FM0*$++>OCRC^==?de <<(;(;A(>}G[G[\_ooL'11!4L ?-F ++!."0#2 ,K #5"C{"C%F%U%U#
 &"oom\J )$++6U8U8U*V W 	A})24;;3J3J13MN) /$7 M	 		-0&++
 	
r0   )NNNNNN)rC   rD   rE   r   r%   r   r   r   r(   r   rG   r   FloatTensorr   r   r   r   r>   rH   rI   s   @r/   r   r   `  s    {     .2.204(,26!%9
##d*9
 t+9
 &&-	9

 9
 ((4/9
 $;9
 +,9
 
!9
    9
r0   r   c                   B    e Zd ZddiZddiZddgdgfiZ fdZee	 	 	 	 	 	 	 	 dd	e	j                  dz  d
e	j                  dz  de	j                  dz  dedz  de	j                  dz  de	j                  dz  dedz  dee	j                  z  dee   defd              Z xZS )Olmo3ForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr;   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y r   )
r$   r%   r   r   r   r&   r   r-   r  r  r   s     r/   r%   zOlmo3ForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r0   Nr	  rW   r   r   r
  labelsr   logits_to_keeprZ   r"   c	           
      x    | 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	  rW   r   r   r
  r   N)r  r  r   )lossr  r   r;   r   r   )r   r  r   r   slicer  loss_functionr   r   r   r   r;   r   )r,   r	  rW   r   r   r
  r  r   r  rZ   outputsr;   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!//))
 	
r0   )NNNNNNNr   )rC   rD   rE   _tied_weights_keys_tp_plan_pp_planr%   r   r   r(   r   rG   r   r  r   r   r   r   r   r>   rH   rI   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
 $;6
 ell*6
 +,6
 
 6
  6
r0   r  )r  r   r   )r   )r   )=collections.abcr   typingr   r(   torch.nnr&   activationsr   cache_utilsr   r   
generationr	   integrationsr
   r   masking_utilsr   r   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   utils.genericr   r   r   utils.output_capturingr   configuration_olmo3r   Moduler    rG   r   rR   rF   ri   rv   rl   r~   r   r   r   r   r   r  __all__r   r0   r/   <module>r<     s  * %    ! . ) L R 9 O K F & 5 [ [ 5 , Y'J299 J (J(	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%224( )*I)RYY I) +I)Xryy  &2 &R><299 ><B ?  $ M
% M
 M
` F
+_ F
 F
R Er0   