
    謜i,                         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	m
Z
mZ ddlmZ ddlmZ ddlmZmZmZmZ  ej*                  e      Z G d	 d
ej0                        Ze G d d             Ze G d d             Ze G d d             Zy)    )partialN   )Cache)BaseModelOutputWithPastQuestionAnsweringModelOutput SequenceClassifierOutputWithPastTokenClassifierOutput)	AutoModel)Unpack)TransformersKwargsauto_docstringcan_return_tupleloggingc                   &     e Zd ZdZdZ fdZ xZS )GradientCheckpointingLayera  Base class for layers with gradient checkpointing.

    This class enables gradient checkpointing functionality for a layer. By default, gradient checkpointing is disabled
    (`gradient_checkpointing = False`). When `model.set_gradient_checkpointing()` is called, gradient checkpointing is
    enabled by setting `gradient_checkpointing = True` and assigning a checkpointing function to `_gradient_checkpointing_func`.

    Important:

        When using gradient checkpointing with `use_reentrant=True`, inputs that require gradients (e.g. hidden states)
        must be passed as positional arguments (`*args`) rather than keyword arguments to properly propagate gradients.

        Example:

            ```python
            >>> # Correct - hidden_states passed as positional arg
            >>> out = self.layer(hidden_states, attention_mask=attention_mask)

            >>> # Incorrect - hidden_states passed as keyword arg
            >>> out = self.layer(hidden_states=hidden_states, attention_mask=attention_mask)
            ```
    Fc                    | j                   r| j                  rd}| j                  j                  }d| d}d|v r|d   rd|d<   |dz  }d}d|v r|d   d |d<   |dz  }d}d	|v r|d	   d |d	<   |d
z  }d}d|v r|d   d |d<   |dz  }d}|r)|j	                  d      dz   }t
        j                  |        | j                  t        t        | (  fi |g| S t        | (  |i |S )NFz7Caching is incompatible with gradient checkpointing in z	. Setting	use_cachez `use_cache=False`,Tpast_key_valuez `past_key_value=None`,past_key_valuesz `past_key_values=None`,
layer_pastz `layer_past=None`,,.)gradient_checkpointingtraining	__class____name__rstriploggerwarning_once_gradient_checkpointing_funcr   super__call__)selfargskwargsdo_warn
layer_namemessager   s         X/mnt/e/genesis-system/.venv/lib/python3.12/site-packages/transformers/modeling_layers.pyr"   z#GradientCheckpointingLayer.__call__;   sM   &&4==G00JOPZ|[deGf$)<&+{#00  6)f5E.F.R+/'(44 F*v6G/H/T,0()55v%&*>*J'+|$00 !..-3##G,4444WUW=M5XQW5X`[_``w000    )r   
__module____qualname____doc__r   r"   __classcell__r   s   @r)   r   r   "   s    , #"1 "1r*   r   c                       e Zd Zd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   defd              Z xZS ) GenericForSequenceClassificationmodelc                    t         |   |       |j                  | _        t        | | j                  t        j                  |             t        j                  |j                  | j                  d      | _
        | j                          y )NF)bias)r!   __init__
num_labelssetattrbase_model_prefixr
   from_confignnLinearhidden_sizescore	post_initr#   configr   s     r)   r5   z)GenericForSequenceClassification.__init__d   sd      ++d,,i.C.CF.KLYYv114??O
 	r*   N	input_idsattention_maskposition_idsr   inputs_embedslabelsr   r%   returnc           	          t        | | j                        |f|||||d|}	|	j                  }
| j                  |
      }||j                  d   }n|j                  d   }| j
                  j                  |dk7  rt        d      | j
                  j                  d}n||| j
                  j                  k7  j                  |j                  t        j                        }t        j                  |j                  d   |j                  t        j                        }||z  j                  d      }n.d}t        j                  | j                   j"                   d       |t        j                  ||j                        |f   }d }|| j%                  |||| j
                  	      }t'        |||	j(                  |	j*                  |	j,                  
      S )NrB   rC   r   rD   r   r   r   z=Cannot handle batch sizes > 1 if no padding token is defined.)devicedtypez will not detect padding tokens in `inputs_embeds`. Results may be unexpected if using padding tokens in conjunction with `inputs_embeds.`)rJ   )logitsrE   pooled_logitsr@   )lossrL   r   hidden_states
attentions)getattrr8   last_hidden_stater=   shaper@   pad_token_id
ValueErrortorJ   torchint32arangeargmaxr   r   r   r   loss_functionr   r   rO   rP   )r#   rA   rB   rC   r   rD   rE   r   r%   transformer_outputsrO   rL   
batch_sizelast_non_pad_tokennon_pad_masktoken_indicesrM   rN   s                     r)   forwardz(GenericForSequenceClassification.forwardn   s    8]wtTE[E[7\8
)%+'8
 8
 ,==M* "+J&,,Q/J;;##+
a\]];;##+!#"%)A)AAEEfmmUZU`U`aL!LL)<V]]Z_ZeZefM"/,">!F!Fr!J!#>>**+ ,Z Z
 u||Jv}}MOaab%%VFR_hlhshs%tD/ /??-;;*55
 	
r*   NNNNNNN)r   r+   r,   r8   r5   r   r   rW   
LongTensorTensorr   FloatTensorboolr   r   r   ra   r.   r/   s   @r)   r1   r1   `   s      .2.204(,26*.!%8
##d*8
 t+8
 &&-	8

 8
 ((4/8
   4'8
 $;8
 +,8
 
*8
  8
r*   r1   c                   &    e Zd ZdZ fdZd Zd Zee	 	 	 	 	 	 	 dde	j                  dz  de	j                  dz  de	j                  dz  d	edz  d
e	j                  dz  de	j                  dz  de	j                  dz  dee   defd              Z xZS )GenericForQuestionAnsweringr2   c                     t         |   |       t        | | j                  t	        j
                  |             t        j                  |j                  d      | _	        | j                          y )N   )r!   r5   r7   r8   r
   r9   r:   r;   r<   
qa_outputsr>   r?   s     r)   r5   z$GenericForQuestionAnswering.__init__   sQ     d,,i.C.CF.KL))F$6$6: 	r*   c                 B    t        | | j                        j                  S NrQ   r8   embed_tokens)r#   s    r)   get_input_embeddingsz0GenericForQuestionAnswering.get_input_embeddings   s    tT334AAAr*   c                 :    |t        | | j                        _        y rm   rn   )r#   values     r)   set_input_embeddingsz0GenericForQuestionAnswering.set_input_embeddings   s    =Bd,,-:r*   NrA   rB   rC   r   rD   start_positionsend_positionsr%   rF   c                     t        | | j                        |f||||d|}	|	j                  }
| j                  |
      }|j	                  dd      \  }}|j                  d      j                         }|j                  d      j                         }d }|| | j                  ||||fi |}t        ||||	j                  |	j                        S )N)rB   rC   r   rD   r   rI   )dim)rN   start_logits
end_logitsrO   rP   )rQ   r8   rR   rk   splitsqueeze
contiguousr[   r   rO   rP   )r#   rA   rB   rC   r   rD   rt   ru   r%   outputssequence_outputrL   rx   ry   rN   s                  r)   ra   z#GenericForQuestionAnswering.forward   s     ,Q749O9O+P,
)%+',
 ,
 "331#)<<r<#: j#++B/::<''+668
&=+D%4%%lJQ^ibhiD+%!!//))
 	
r*   rb   )r   r+   r,   r8   r5   rp   rs   r   r   rW   rc   rd   r   re   r   r   r   ra   r.   r/   s   @r)   rh   rh      s    BC  .2.204(,263715%
##d*%
 t+%
 &&-	%

 %
 ((4/%
 ))D0%
 ''$.%
 +,%
 
&%
  %
r*   rh   c                       e Zd ZdZ fdZee	 	 	 	 	 	 	 ddej                  dz  dej                  dz  dej                  dz  de
dz  dej                  dz  d	ej                  dz  d
edz  dee   defd              Z xZS )GenericForTokenClassificationr2   c                    t         |   |       |j                  | _        t        | | j                  t        j                  |             t        |dd       |j                  }nt        |dd       |j                  }nd}t        j                  |      | _        t        j                  |j                  |j                        | _        | j!                          y )Nclassifier_dropouthidden_dropoutg?)r!   r5   r6   r7   r8   r
   r9   rQ   r   r   r:   Dropoutdropoutr;   r<   r=   r>   )r#   r@   r   r   s      r)   r5   z&GenericForTokenClassification.__init__   s      ++d,,i.C.CF.KL6/6B!'!:!:V-t4@!'!6!6!$zz"45YYv1163D3DE
 	r*   NrA   rB   rC   r   rD   rE   r   r%   rF   c           	      ,    t        | | j                        |f|||||d|}	|	j                  }
| j                  |
      }
| j	                  |
      }d }|| j                  ||| j                        }t        |||	j                  |	j                        S )NrH   )rN   rL   rO   rP   )
rQ   r8   rR   r   r=   r[   r@   r	   rO   rP   )r#   rA   rB   rC   r   rD   rE   r   r%   r}   r~   rL   rN   s                r)   ra   z%GenericForTokenClassification.forward   s     ,Q749O9O+P,
)%+',
 ,
 "33,,7O,%%ffdkkBD$!//))	
 	
r*   rb   )r   r+   r,   r8   r5   r   r   rW   rc   rd   r   re   rf   r   r   r	   ra   r.   r/   s   @r)   r   r      s    "  .2.204(,26*.!%!
##d*!
 t+!
 &&-	!

 !
 ((4/!
   4'!
 $;!
 +,!
 
!
  !
r*   r   )	functoolsr   rW   torch.nnr:   cache_utilsr   modeling_outputsr   r   r   r	   models.autor
   processing_utilsr   utilsr   r   r   r   
get_loggerr   r   Moduler   r1   rh   r    r*   r)   <module>r      s         # $ P P 
		H	%;1 ;1| G
 G
 G
T 9
 9
 9
x 7
 7
 7
r*   