
    rhO                        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 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$m%Z% ddl&m'Z'  ed       G d dejP                               Z)dejT                  de+dejT                  fdZ,	 d4dejP                  dejT                  dejT                  dejT                  deejT                     de-d e-d!e e   fd"Z.d5d#Z/d$ Z0 G d% d&ejP                        Z1 G d' d(ejP                        Z2 G d) d*e      Z3 G d+ d,ejP                        Z4e" G d- d.e             Z5e" G d/ d0e5             Z6e" G d1 d2e5e             Z7g d3Z8y)6    )CallableOptionalUnionN)TransformersKwargs   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)auto_docstringcan_return_tuple)check_model_inputs   )Olmo2Config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      {/var/www/html/ai-insurance-compliance-backend/venv/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       r+   forwardzOlmo2RMSNorm.forward'   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Olmo2RMSNorm.extra_repr.   s*    ))*+6$2G2G1HIIr,   )gư>)__name__
__module____qualname__r    r:   r?   __classcell__r*   s   @r+   r   r      s    $=Jr,   r   r7   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)r7   rE   batchnum_key_value_headsslenhead_dims         r+   	repeat_kvrN   2   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 )Nr.   r   r/   )dimr1   )ptrainingr   )rN   num_key_value_groupsr#   matmul	transposer=   r!   
functionalsoftmaxr3   r2   r1   rU   r[   
contiguous)rO   rP   rQ   rR   rS   rT   rU   rV   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r+   eager_attention_forwardrg   >   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.
    )r1   	unsqueezerotate_halfr2   )
qkcossinposition_idsunsqueeze_dimq_typek_typeq_embedk_embeds
             r+   apply_rotary_pos_embru   X   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..Nr/   r.   rY   )r=   r#   cat)xx1x2s      r+   rj   rj   t   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r,   c                   >    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   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 )NrM   g      Tbias)r   r    r~   r   getattrr(   num_attention_headsrM   rK   r\   rT   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      r+   r    zOlmo2Attention.__init__~   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 #6#=#=#MvObObc"6#=#=#MvObObcr,   r7   position_embeddingsrS   past_key_valuecache_positionrV   rF   c                 |   |j                   d d }g |d| j                  }| j                  | j                  |            }	| j	                  | j                  |            }
| j                  |      }|	j                  |      j                  dd      }	|
j                  |      j                  dd      }
|j                  |      j                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        }| j                  j                  dk7  rt        | j                  j                     } || |	|
||f| j                   sdn| j"                  | j$                  d|\  }} |j&                  g |d j)                         }| j+                  |      }||fS )Nr/   r   r.   )rn   rm   r   eager        )rU   rT   )r=   rM   r   r   r   r   r   viewr^   ru   updater   rg   r~   _attn_implementationr   r[   r   rT   rI   ra   r   )r'   r7   r   rS   r   r   rV   input_shapehidden_shapequery_statesrb   rc   rm   rn   cache_kwargsattention_interfacerf   rd   s                     r+   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$J(?;;++w6"9$++:Z:Z"[$7	%
  $}}C$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r,   N)NN)r@   rA   rB   __doc__r   r   intr    r#   Tensorr<   r	   
LongTensorr   r   r:   rC   rD   s   @r+   r}   r}   {   s    Gd{ dx} d< +/59-)||-) #5<<#=>-) !.	-)
 !-) !!1!12-) +,-) 
u||Xell3XeELL>Q5RR	S-)r,   r}   c                   $     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     r+   r    zOlmo2MLP.__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 r   )r   r   r   r   )r'   ry   r   s      r+   r:   zOlmo2MLP.forward   s6    NN4;;t~~a/@#ADLLQRO#ST	r,   )r@   rA   rB   r    r:   rC   rD   s   @r+   r   r      s    0r,   r   c                   d    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j                     d
eeej                  ej                  f      dee   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      r+   r    zOlmo2DecoderLayer.__init__   sl    !--'vKF#(4V5G5GVM`M`(a%*6v7I7IvObOb*c'r,   r7   rS   ro   r   	use_cacher   r   rV   rF   c                     |}	 | j                   d|||||||d|\  }}
| j                  |      }|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r7   rS   ro   r   r   r   r    )r   r   r   r   )r'   r7   rS   ro   r   r   r   r   rV   residual_s              r+   r:   zOlmo2DecoderLayer.forward   s     !)4>> 	
')%)) 3	
 	
q 55mD =0 !/77F =0r,   )NNNFNN)r@   rA   rB   r   r   r    r#   r   r   r   r	   boolr<   r   r   FloatTensorr:   rC   rD   s   @r+   r   r      s    d{ ds d 2637*.$)59KO|| !. u//0	
 ! D> !!1!12 &eELL%,,,F&GH +, 
u  (51B1BEDUDU1U+V"WW	Xr,   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      rUt        |j                  t
              r;|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    hasattr
isinstancer   dictgetr   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       r+   r    zOlmo2RotaryEmbedding.__init__  s    6>*z&:M:Mt/T#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   r/   r   mpscpuF)device_typeenabledr.   rw   )r   floatrH   r=   r2   r   r   r   strr#   autocastr^   rx   rm   r   rn   )
r'   ry   ro   inv_freq_expandedposition_ids_expandedr   freqsembrm   rn   s
             r+   r:   zOlmo2RotaryEmbedding.forward  s2    !MM$4-8>>@GGHZHZ[\H]_acdehhijiqiqr ,QaZ 8 > > @'1!((--'E!((--[`J`ahhmmfk^^UC 	&,,.1F1L1L1NNYYZ[]^_E))UEN3C'')d444C'')d444C8	 	 	s    BE22E;r   )
r@   rA   rB   r   r    r#   no_gradr   r:   rC   rD   s   @r+   r   r     s3    /{ /" U]]_
  
r,   r   c                   J    e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedZy)Olmo2PreTrainedModelr~   modelTr   past_key_values)r7   
attentionsN)r@   rA   rB   r   __annotations__base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r}   _can_record_outputsr   r,   r+   r   r   #  sQ    &*#,-#4"5N!"&*$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 )
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_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Olmo2Model.__init__8  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcivy1c
 !!3!39L9LM	.f=&+# 	 ds   D	input_idsrS   ro   r   inputs_embedsr   r   rV   rF   c           
      *   |d u |d uz  rt        d      || j                  |      }|r|
t               }|F||j                         nd}	t	        j
                  |	|	|j                  d   z   |j                        }||j                  d      }t        | j                  |||||      }
|}| j                  ||      }| j                  d | j                  j                   D ]  } ||f|
||||d|} | j                  |      }t        ||      S )Nz:You must specify exactly one of input_ids or inputs_embedsr   r   )r   )r~   input_embedsrS   r   r   ro   )rS   ro   r   r   r   )last_hidden_stater   )
ValueErrorr   r
   get_seq_lengthr#   aranger=   r   ri   r   r~   r   r   r   r   r   )r'   r  rS   ro   r   r  r   r   rV   past_seen_tokensre   r7   r   decoder_layers                 r+   r:   zOlmo2Model.forwardH  sT    -t";<YZZ *.*;*;I*FM0*nO!CRC^==?de+0<< "2]5H5H5K"KTaThTh,N )33A6L(;;&))+%
 &"oom\J![[)H4;;+H+HI 		M)*).-$7 M		 		-0&++
 	
r,   )NNNNNNN)r@   rA   rB   r   r    r   r   r   r#   r   r   r	   r   r   r   r   r   r:   rC   rD   s   @r+   r   r   6  s    {    151537+/5959$(8
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 !!1!128
 D>8
 +,8
 
!8
  8
r,   r   c                   p    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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 )Olmo2ForCausalLMzlm_head.weightlm_headcolwise_repr7   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Olmo2ForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r,   c                     || _         y r   r   )r'   decoders     r+   set_decoderzOlmo2ForCausalLM.set_decoder  s	    
r,   c                     | j                   S r   r  r>   s    r+   get_decoderzOlmo2ForCausalLM.get_decoder  s    zzr,   r  rS   ro   r   r  labelsr   r   logits_to_keeprV   rF   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, 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."
        ```)r  rS   ro   r   r  r   r   N)r  r  r   )lossr  r   r7   r   r   )r   r  r   r   slicer  loss_functionr~   r   r   r   r7   r   )r'   r  rS   ro   r   r  r  r   r   r  rV   outputsr7   slice_indicesr  r  s                   r+   r:   zOlmo2ForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r,   )	NNNNNNNNr   )r@   rA   rB   _tied_weights_keys_tp_plan_pp_planr    r  r  r   r   r   r#   r   r   r	   r   r   r   r   r   r   r   r:   rC   rD   s   @r+   r  r    s:   *+=)H_-z:;H  151537+/59-1$(59348
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 ))*8
 D>8
 !!1!128
 c5<</08
 +,8
 
 8
  8
r,   r  )r  r   r   )r   )Nr   )9typingr   r   r   r#   torch.nnr!   transformers.utils.genericr   activationsr   cache_utilsr	   r
   
generationr   integrationsr   masking_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   utils.genericr   configuration_olmo2r   Moduler   r   r   rN   r   rg   ru   rj   r}   r   r   r   r   r   r  __all__r   r,   r+   <module>r4     s   - ,   9 ! . ) 7 / 9 O K F & 5 / , Y'J299 J (J(	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%428(I)RYY I)Xryy  (2 (V299 B ?  $ K
% K
 K
\ N
+_ N
 N
b Er,   