
    Uh	x                     h   d dl mZ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mZ ddlmZ ddlm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mZ ddlmZmZ ddl m!Z! ddl"m#Z#m$Z$m%Z%m&Z&m'Z' ddl(m)Z)  e&       rd dl*m+Z+ ddl,m-Z-  e'j\                  e/      Z0 ed       G d dejb                               Z2dejf                  de4dejf                  fdZ5	 d6dejb                  dejf                  dejf                  dejf                  deejf                     d e6d!e6fd"Z7d7d#Z8d$ Z9 G d% d&ejb                        Z: G d' d(ejb                        Z; G d) d*e      Z< G d+ d,ejb                        Z=e$ G d- d.e             Z>e$ G d/ d0e>             Z? G d1 d2ee#      Z@e$ G d3 d4e>e             ZAg d5ZBy)8    )CallableOptionalTupleUnionN   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)AttentionMaskConverter)FlashAttentionKwargs)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)
LossKwargsauto_docstringcan_return_tupleis_torch_flex_attn_availablelogging   )Olmo2Config)	BlockMask)make_flex_block_causal_maskRMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )Olmo2RMSNormc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z;
        Olmo2RMSNorm is equivalent to T5LayerNorm
        N)super__init__nn	Parametertorchonesweightvariance_epsilon)selfhidden_sizeeps	__class__s      z/var/www/catia.catastroantioquia-mas.com/valormas/lib/python3.12/site-packages/transformers/models/olmo2/modeling_olmo2.pyr%   zOlmo2RMSNorm.__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       r0   forwardzOlmo2RMSNorm.forward.   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UUm+//<<r1   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tupler*   shaper+   r,   s    r0   
extra_reprzOlmo2RMSNorm.extra_repr5   s*    ))*+6$2G2G1HIIr1   )gư>)__name__
__module____qualname__r%   r?   rD   __classcell__r/   s   @r0   r"   r"   $   s    $=Jr1   r"   r<   n_repreturnc                     | j                   \  }}}}|dk(  r| S | dddddddddf   j                  |||||      } | j                  |||z  ||      S )z
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r   N)rB   expandreshape)r<   rJ   batchnum_key_value_headsslenhead_dims         r0   	repeat_kvrS   9   so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr1   modulequerykeyvalueattention_maskscalingdropoutc                 T   t        || j                        }t        || j                        }	t        j                  ||j	                  dd            |z  }
|#|d d d d d d d |j
                  d   f   }|
|z   }
t        j                  j                  |
dt        j                        j                  |j                        }
t        j                  j                  |
|| j                        }
t        j                  |
|	      }|j	                  dd      j                         }||
fS )Nr3   r   r4   )dimr6   )ptrainingr   )rS   num_key_value_groupsr(   matmul	transposerB   r&   
functionalsoftmaxr8   r7   r6   rZ   r_   
contiguous)rT   rU   rV   rW   rX   rY   rZ   kwargs
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r0   eager_attention_forwardrl   E   s    3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#k1==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r1   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.
    )r6   	unsqueezerotate_halfr7   )
qkcossinposition_idsunsqueeze_dimq_typek_typeq_embedk_embeds
             r0   apply_rotary_pos_embrz   _   s|    ( WWaggFF
--
&C
--
&C3w;q>C/0G3w;q>C/0G::fwzz&111r1   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..Nr4   r3   r]   )rB   r(   cat)xx1x2s      r0   ro   ro   {   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r1   c                   4    e Zd ZdZddedee   f fdZ	 	 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j                  eej                     ee
ej                        f   fdZ xZS )Olmo2Attentionz=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*                        | _        y )NrR   g      Tbias)r$   r%   r   r   getattrr-   num_attention_headsrR   rP   r`   rY   attention_dropout	is_causalr&   Linearattention_biasq_projk_projv_projo_projr"   rms_norm_epsq_normk_normr,   r   r   r/   s      r0   r%   zOlmo2Attention.__init__   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 #6#=#=#MvObObc"6#=#=#MvObObcr1   r<   position_embeddingsrX   past_key_valuecache_positionrK   c                    |j                   d d }g |d| j                  }| j                  | j                  |            }	| j	                  | j                  |            }
| j                  |      }|	j                  |      j                  dd      }	|
j                  |      j                  dd      }
|j                  |      j                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        }| j                  j                  dk7  r^| j                  j                  dk(  r(|j                  dd      rt         j#                  d	       nt$        | j                  j                     } || |	|
||f| j&                  sd
n| j(                  | j*                  d|\  }} |j,                  g |d j/                         }| j1                  |      }||fS )Nr4   r   r3   )rs   rr   r   eagersdpaoutput_attentionsFz`torch.nn.functional.scaled_dot_product_attention` does not support `output_attentions=True`. Falling back to eager attention. This warning can be removed using the argument `attn_implementation="eager"` when loading the model.        )rZ   rY   )rB   rR   r   r   r   r   r   viewrb   rz   updater   rl   r   _attn_implementationgetloggerwarning_oncer   r_   r   rY   rN   re   r   )r,   r<   r   rX   r   r   rf   input_shapehidden_shapequery_statesrg   rh   rr   rs   cache_kwargsattention_interfacerk   ri   s                     r0   r?   zOlmo2Attention.forward   s    $))#2.88b8$--8{{4;;}#=>[[]!;<
{{=1#((6@@AF__\2<<QB
#((6@@AF&S#7jRUWZ#[ j%#&snUL'5'<'<ZW[WeWegs't$J(?;;++w6{{//69fjjI\^c>d##L
 '>dkk>^>^&_#$7	%
  $}}C$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r1   N)NN)rE   rF   rG   __doc__r   r   intr%   r(   Tensorr   r	   
LongTensorr?   rH   rI   s   @r0   r   r      s    Gd{ dx} d< +/593)||3) #5<<#=>3) !.	3)
 !3) !!1!123) 
u||Xell3XeELL>Q5RR	S3)r1   r   c                   $     e Zd Z fdZd Z xZS )Olmo2MLPc                    t         |           || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _	        t        |j                     | _        y NFr   )r$   r%   r   r-   intermediate_sizer&   r   	gate_projup_proj	down_projr   
hidden_actact_fnr,   r   r/   s     r0   r%   zOlmo2MLP.__init__   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r1   c                     | j                  | j                  | j                  |            | j                  |      z        }|S r   )r   r   r   r   )r,   r~   r   s      r0   r?   zOlmo2MLP.forward   s6    NN4;;t~~a/@#ADLLQRO#ST	r1   )rE   rF   rG   r%   r?   rH   rI   s   @r0   r   r      s    0r1   r   c                   f    e Zd Zdedef fdZ	 	 	 	 	 	 	 ddej                  deej                     deej                     dee
   dee   d	ee   d
eej                     deeej                  ej                  f      deej                  eeej                  ej                  f      f   fdZ xZS )Olmo2DecoderLayerr   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        y )N)r   r   r.   )r$   r%   r-   r   	self_attnr   mlpr"   r   post_attention_layernormpost_feedforward_layernormr   s      r0   r%   zOlmo2DecoderLayer.__init__   sl    !--'vKF#(4V5G5GVM`M`(a%*6v7I7IvObOb*c'r1   r<   rX   rt   r   r   	use_cacher   r   rK   c	                     |}
 | j                   d||||||||d|	\  }}| j                  |      }|
|z   }|}
| j                  |      }| j                  |      }|
|z   }|f}|r||fz  }|S )N)r<   rX   rt   r   r   r   r   r    )r   r   r   r   )r,   r<   rX   rt   r   r   r   r   r   rf   residualself_attn_weightsoutputss                r0   r?   zOlmo2DecoderLayer.forward   s     ! ,:4>> 
,
')%)/) 3
,
 
,
(( 55mD =0 !/77F =0 ")++Gr1   )NNNFFNN)rE   rF   rG   r   r   r%   r(   r   r   r   r	   boolr   FloatTensorr?   rH   rI   s   @r0   r   r      s    d{ ds d 2637*.,1$)59KO'||' !.' u//0	'
 !' $D>' D>' !!1!12' &eELL%,,,F&GH' 
u  (51B1BEDUDU1U+V"WW	X'r1   r   c                   ^     e Zd Zddef fdZ ej                         ed               Z xZ	S )Olmo2RotaryEmbeddingr   c                    t         |           t        |d      rG|j                  ;|j                  j	                  d|j                  j	                  d            | _        nd| _        |j                  | _        |j                  | _        || _	        t        | j
                     | _        | j                  | j                  |      \  }| _        | j                  d|d       | j                  | _        y )Nrope_scaling	rope_typetypedefaultinv_freqF)
persistent)r$   r%   hasattrr   r   r   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r,   r   devicer   r/   s       r0   r%   zOlmo2RotaryEmbedding.__init__  s    6>*v/B/B/N#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r1   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   r4   r   mpscpuF)device_typeenabledr3   r|   )r   floatrM   rB   r7   r   
isinstancer   strr(   autocastrb   r}   rr   r   rs   )
r,   r~   rt   inv_freq_expandedposition_ids_expandedr   freqsembrr   rs   s
             r0   r?   zOlmo2RotaryEmbedding.forward*  s2    !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	 	 	s    BE22E;r   )
rE   rF   rG   r   r%   r(   no_gradr   r?   rH   rI   s   @r0   r   r     s3    /{ /" U]]_
  
r1   r   c                   F    e Zd ZeZdZdZdgZdgZdZ	dZ
dZdZdZdZdZd Zy)Olmo2PreTrainedModelmodelTr   past_key_valuesc                    | j                   j                  }t        |t        j                        rY|j
                  j                  j                  d|       |j                  %|j                  j                  j                          y y t        |t        j                        rf|j
                  j                  j                  d|       |j                  2|j
                  j                  |j                     j                          y y t        |t              r&|j
                  j                  j                  d       y y )Nr   )r:   stdg      ?)r   initializer_ranger   r&   r   r*   datanormal_r   zero_	Embeddingpadding_idxr"   fill_)r,   rT   r   s      r0   _init_weightsz"Olmo2PreTrainedModel._init_weightsH  s    kk++fbii(MM&&CS&9{{&  &&( '-MM&&CS&9!!-""6#5#56<<> .-MM$$S) .r1   N)rE   rF   rG   r   config_classbase_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_2_supports_sdpa_supports_flex_attn_supports_cache_class_supports_quantized_cache_supports_static_cache_supports_attention_backendr   r   r1   r0   r   r   9  sS    L&*#,-#4"5!N  $!"&*r1   r   c                       e Zd Zdef fdZd Zd Zee	 	 	 	 	 	 	 	 	 dde	e
j                     de	e
j                     de	e
j                     de	e   d	e	e
j                     d
e	e   de	e   de	e   de	e
j                     dee   defd              Z	 ddee
j                  df   de
j                  de
j                  dedef
dZede
j                  dedede
j0                  de
j                  defd       Z xZS )
Olmo2Modelr   c           	         t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |j                  |j                        | _        t#        |      | _        d| _        | j)                          y c c}w )Nr   )r   F)r$   r%   pad_token_idr   
vocab_sizer&   r   r-   embed_tokens
ModuleListrangenum_hidden_layersr   layersr"   r   normr   
rotary_embgradient_checkpointing	post_initr   s      r0   r%   zOlmo2Model.__init__X  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcivy1c
 !!3!39L9LM	.f=&+# 	 ds   Dc                     | j                   S r   r	  rC   s    r0   get_input_embeddingszOlmo2Model.get_input_embeddingsh  s       r1   c                     || _         y r   r  r,   rW   s     r0   set_input_embeddingszOlmo2Model.set_input_embeddingsk  s
    !r1   	input_idsrX   rt   r   inputs_embedsr   r   output_hidden_statesr   flash_attn_kwargsrK   c
                    ||n| j                   j                  }||n| j                   j                  }||n| j                   j                  }|d u |d uz  rt	        d      | j
                  r%| j                  r|rt        j                  d       d}t        |t        d       t        f      st	        d      || j                  |      }|r|
t               }|	F||j                         nd}t        j                   |||j"                  d   z   |j$                        }	||	j'                  d      }| j)                  |||	||      }|}| j+                  ||      }|rdnd }|rdnd }| j,                  d | j                   j.                   D ],  }|r||fz  } ||f||||||	|d	|
}|d   }|s$||d   fz  }. | j1                  |      }|r||fz  }t3        ||r|nd ||
      S )Nz:You must specify exactly one of input_ids or inputs_embedszX`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.FzBThe `past_key_values` should be either a `Cache` object or `None`.r   r   r   r   )rX   rt   r   r   r   r   r   )last_hidden_stater   r<   
attentions)r   r   r  r   
ValueErrorr  r_   r   r   r   r   r	   r	  r
   get_seq_lengthr(   arangerB   r   rn   _update_causal_maskr  r  r  r  r   )r,   r  rX   rt   r   r  r   r   r  r   r  past_seen_tokensrj   r<   r   all_hidden_statesall_self_attnsdecoder_layerlayer_outputss                      r0   r?   zOlmo2Model.forwardn  sT    2C1N-TXT_T_TqTq$8$D $++JjJj 	 "+!6IDKK<Q<Q	-t";<YZZ&&4==Yj I /DJ+>?abb  --i8M0*nO!CRC^==?de"\\ "2]5H5H5K"KTaThThN )33A6L..M>?L]
 & #oom\J #7BD0d![[)H4;;+H+HI 	6M#!m%55!)
*)."3#-$7
 $
M *!,M =#3"55'	6* 		-0  -!11&+/8Od+%	
 	
r1   r   input_tensorc           	         | j                   j                  dk(  r||dk(  j                         r|S y | j                   j                  dk(  r't        |t        j
                        rt        |      }|S ||j                         nd}||j                  nd}| j                   j                  dk(  r(|s&|s$t        j                  |||| j                        ry |j                  }|j                  d   }	|r|j                         }
n1t        |t        j
                        r|j                  d	   n||	z   dz   }
| j                  ||	|
|||j                  d   
      }| j                   j                  dk(  rQ|O|j                   j"                  dv r7|s5t	        j$                  |      j&                  }t        j(                  ||      }|S )Nflash_attention_2r   flex_attentionr   Fr   )r  past_key_values_lengthis_trainingr   r4   )sequence_lengthtarget_lengthr6   r   
batch_size)cudaxpunpu)r   r   anyr   r(   r   r   r!  is_compileabler   _ignore_causal_mask_sdpar_   r6   rB   get_max_cache_shape5_prepare_4d_causal_attention_mask_with_cache_positionr   r   finfomin_unmask_unattended)r,   rX   r)  r   r   r   r$  using_compilable_cacher6   r/  r0  rj   	min_dtypes                r0   r#  zOlmo2Model._update_causal_mask  s    ;;++/BB)~/D.I.I.K%%;;++/??.%,,7!<^!L!!
 @O?Z?99;`aCRC^!?!?di ;;++v5>T]n%>>*'7 MM	 ""&,,Q/!+??AM nell; $$R(%7!;  PP+')#))!, Q 
 KK,,6*%%**.DD%
 E*..I0CCKQZ[Kr1   r/  r0  r6   r1  c                    | | j                         dk(  r| }|S t        j                  |      j                  }t        j                  ||f|||j
                        }|dk7  rt        j                  |d      }|t        j                  ||j
                        |j                  dd      kD  z  }|ddddddf   j                  |ddd      }| |j                         }| j                  d   }	|ddddddd|	f   | ddddddf   j                  |j
                        z   }
|
dk(  }
|ddddddd|	f   j                  |
|      |ddddddd|	f<   |S )	aM  
        Creates a causal 4D mask of shape `(batch_size, 1, query_length, key_value_length)` from a 2D mask of shape
        `(batch_size, key_value_length)`, or if the input `attention_mask` is already 4D, do nothing.

        Args:
            attention_mask (`torch.Tensor`):
                A 2D attention mask of shape `(batch_size, key_value_length)` or a 4D attention mask of shape
                `(batch_size, 1, query_length, key_value_length)`.
            sequence_length (`int`):
                The sequence length being processed.
            target_length (`int`):
                The target length: when generating with static cache, the mask should be as long as the static cache,
                to account for the 0 padding, the part of the cache that is not filled yet.
            dtype (`torch.dtype`):
                The dtype to use for the 4D attention mask.
            cache_position (`torch.Tensor`):
                Indices depicting the position of the input sequence tokens in the sequence.
            batch_size (`torch.Tensor`):
                Batch size.
        N   )
fill_valuer6   r   r   )diagonalr  r4   r   )r]   r(   r:  r;  fullr   triur"  rN   rM   clonerB   r7   masked_fill)rX   r/  r0  r6   r   r1  rf   rj   r>  mask_lengthpadding_masks              r0   r9  z@Olmo2Model._prepare_4d_causal_attention_mask_with_cache_position  s   < %.*<*<*>!*C(K* ' E*..I** -0Ye\j\q\qK !##jjqA5<<n>S>STWeWmWmnprsWtttK%dD!Q&67>>z1bRTUK))//1,2226*1aL[L+@ANSTVZ\`bcScDdDgDg&&E    ,q05@Aq,;,AV5W5c5c )6Aq!\k\12 r1   )	NNNNNNNNN)F)rE   rF   rG   r   r%   r  r  r   r   r   r(   r   r   r	   r   r   r   r   r   r?   r   r#  staticmethodr   r6   r9  rH   rI   s   @r0   r  r  V  s   {  !"  151537+/59$(,0/359\
E,,-\
 !.\
 u//0	\

 "%\
   1 12\
 D>\
 $D>\
 'tn\
 !!1!12\
 $$89\
 
!\
  \
H #(BellK78B llB 	B
 B  BH 444 4 {{	4
 4 4 4r1   r  c                       e Zd Zy)KwargsForCausalLMN)rE   rF   rG   r   r1   r0   rK  rK  J  s    r1   rK  c                       e Zd ZdgZddiZddgdgfiZ fdZd Zd Zd	 Z	d
 Z
d Zd Zee	 	 	 	 	 	 	 	 	 	 	 ddeej"                     deej$                     deej"                     dee   deej(                     deej"                     dee   dee   dee   deej"                     deeej$                  f   dee   defd              Z xZS )Olmo2ForCausalLMzlm_head.weightlm_headcolwise_repr<   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y r   )
r$   r%   r  r   r  r&   r   r-   rN  r  r   s     r0   r%   zOlmo2ForCausalLM.__init__S  sU     '
 ++yy!3!3V5F5FUS 	r1   c                 .    | j                   j                  S r   r   r	  rC   s    r0   r  z%Olmo2ForCausalLM.get_input_embeddings\  s    zz&&&r1   c                 &    || j                   _        y r   rS  r  s     r0   r  z%Olmo2ForCausalLM.set_input_embeddings_  s    "'

r1   c                     | j                   S r   rN  rC   s    r0   get_output_embeddingsz&Olmo2ForCausalLM.get_output_embeddingsb  s    ||r1   c                     || _         y r   rV  )r,   new_embeddingss     r0   set_output_embeddingsz&Olmo2ForCausalLM.set_output_embeddingse  s	    %r1   c                     || _         y r   r   )r,   decoders     r0   set_decoderzOlmo2ForCausalLM.set_decoderh  s	    
r1   c                     | j                   S r   r\  rC   s    r0   get_decoderzOlmo2ForCausalLM.get_decoderk  s    zzr1   r  rX   rt   r   r  labelsr   r   r  r   logits_to_keeprf   rK   c                    ||n| j                   j                  }|	|	n| j                   j                  }	 | 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 )at  
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
            config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
            (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

        Example:

        ```python
        >>> from transformers import AutoTokenizer, Olmo2ForCausalLM

        >>> model = Olmo2ForCausalLM.from_pretrained("meta-olmo2/Olmo2-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-olmo2/Olmo2-2-7b-hf")

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

        >>> # Generate
        >>> generate_ids = model.generate(inputs.input_ids, max_length=30)
        >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
        "Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
        ```N)	r  rX   rt   r   r  r   r   r  r   )rP  ra  r  )lossrP  r   r<   r  r   )r   r   r  r   r  r   r   slicerN  loss_functionr  r   r   r<   r  )r,   r  rX   rt   r   r  ra  r   r   r  r   rb  rf   r   r<   slice_indicesrP  rd  s                     r0   r?   zOlmo2ForCausalLM.forwardn  s   N 2C1N-TXT_T_TqTq$8$D $++JjJj 	
 ,64:: ,
)%+'/!5),
 ,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r1   )NNNNNNNNNNr   )rE   rF   rG   _tied_weights_keys_tp_plan_pp_planr%   r  r  rW  rZ  r^  r`  r   r   r   r(   r   r   r	   r   r   r   r   r   rK  r   r?   rH   rI   s   @r0   rM  rM  M  s   *+=)H_-z:;H'(&  151537+/59-1$(,0/35934G
E,,-G
 !.G
 u//0	G

 "%G
   1 12G
 ))*G
 D>G
 $D>G
 'tnG
 !!1!12G
 c5<</0G
 *+G
 
 G
  G
r1   rM  )rM  r  r   )r   )Nr   )Ctypingr   r   r   r   r(   torch.nnr&   activationsr   cache_utilsr	   r
   
generationr   integrationsr   modeling_attn_mask_utilsr   modeling_flash_attention_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   r   configuration_olmo2r   !torch.nn.attention.flex_attentionr   integrations.flex_attentionr   
get_loggerrE   r   Moduler"   r   r   rS   r   rl   rz   ro   r   r   r   r   r   r  rK  rM  __all__r   r1   r0   <module>r     s   4 3   ! . ) 7 > B 9 O K F & h h ,  !;J 
		H	% Y'J299 J (J(	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % %428(O)RYY O)dryy  12 1h299 B *? * *8 p% p pf ?,j > i
+_ i
 i
X Er1   