
    rhtP                     h   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mZ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$m%Z% ddl&m'Z'm(Z(m)Z) ddl*m+Z+  G d dejX                        Z-d Z.d;dZ/dej`                  de1dej`                  fdZ2	 d<dejX                  dej`                  dej`                  dej`                  d eej`                     d!e3d"e3d#e%e'   fd$Z4 G d% d&ejX                        Z5 ed'       G d( d)ejX                               Z6 G d* d+e      Z7e( G d, d-e#             Z8 G d. d/ejX                        Z9e( G d0 d1e8             Z:e( G d2 d3e8e             Z; G d4 d5ee8      Z< G d6 d7ee8      Z= G d8 d9ee8      Z>g d:Z?y)=    )CallableOptionalUnionN)nn)check_model_inputs   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs)GenericForQuestionAnswering GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple   )MistralConfigc                   $     e Zd Z fdZd Z xZS )
MistralMLPc                    t         |           || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _	        t        |j                     | _        y NFbias)super__init__confighidden_sizeintermediate_sizer   Linear	gate_projup_proj	down_projr	   
hidden_actact_fnselfr)   	__class__s     /var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/mistral/modeling_mistral.pyr(   zMistralMLP.__init__#   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../    c                     | j                  | j                  | j                  |            | j                  |      z        }|S N)r/   r1   r-   r.   )r3   xr/   s      r5   forwardzMistralMLP.forward-   s6    NN4;;t~~a/@#ADLLQRO#ST	r6   )__name__
__module____qualname__r(   r:   __classcell__r4   s   @r5   r"   r"   "   s    0r6   r"   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..N   dim)shapetorchcat)r9   x1x2s      r5   rotate_halfrJ   2   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r6   c                     |j                  |      }|j                  |      }| |z  t        |       |z  z   }||z  t        |      |z  z   }||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.
    )	unsqueezerJ   )qkcossinposition_idsunsqueeze_dimq_embedk_embeds           r5   apply_rotary_pos_embrU   9   sY    ( --
&C
--
&C3w;q>C/0G3w;q>C/0GGr6   hidden_states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)rE   expandreshape)rV   rW   batchnum_key_value_headsslenhead_dims         r5   	repeat_kvr`   T   so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr6   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 )NrB   r   rA   )rD   dtype)ptrainingr   )r`   num_key_value_groupsrF   matmul	transposerE   r   
functionalsoftmaxfloat32tork   rg   rm   
contiguous)ra   rb   rc   rd   re   rf   rg   rh   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r5   eager_attention_forwardr{   `   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$$r6   c                   6    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
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 )MistralAttentionz=Multi-headed attention from 'Attention Is All You Need' paperr)   	layer_idxc                    t         |           || _        || _        t	        |dd       xs |j
                  |j                  z  | _        |j                  |j                  z  | _	        | j                  dz  | _
        |j                  | _        d| _        t        j                  |j
                  |j                  | j                  z  d      | _        t        j                  |j
                  |j                  | j                  z  d      | _        t        j                  |j
                  |j                  | j                  z  d      | _        t        j                  |j                  | j                  z  |j
                  d      | _        y )Nr_   g      TFr%   )r'   r(   r)   r~   getattrr*   num_attention_headsr_   r]   rn   rf   attention_dropout	is_causalr   r,   q_projk_projv_projo_projr3   r)   r~   r4   s      r5   r(   zMistralAttention.__init__}   s2   "
D9mV=O=OSYSmSm=m$*$>$>&B\B\$\!}}d*!'!9!9ii 2 2F4N4NQUQ^Q^4^ejkii 2 2F4N4NQUQ^Q^4^ejkii 2 2F4N4NQUQ^Q^4^ejkii : :T]] JFL^L^ejkr6   rV   position_embeddingsre   past_key_valuecache_positionrh   rX   c           
      `   |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        }| j                  j                  dk7  rt        | j                  j                     } || |	|
||f| j                  sdn| j                  | j                   t#        | j                  dd       d|\  }} |j$                  g |d j'                         }| j)                  |      }||fS )	NrA   r   rB   )rP   rO   r   eager        sliding_window)rg   rf   r   )rE   r_   r   viewrp   r   r   rU   updater~   r{   r)   _attn_implementationr   rm   r   rf   r   r[   ru   r   )r3   rV   r   re   r   r   rh   input_shapehidden_shapequery_statesrv   rw   rO   rP   cache_kwargsattention_interfacerz   rx   s                     r5   r:   zMistralAttention.forward   s    $))#2.88b8$--8{{=166|DNNqRST[[/44\BLLQPQR
{{=166|DNNqRST&S#7jRUWZ#[ j%#&snUL'5'<'<ZW[WeWegs't$J(?;;++w6"9$++:Z:Z"[$7
%
  $}}C$2H2HLL"4;;0@$G
%
 
%
!\ *k));;;;FFHkk+.L((r6   )NN)r;   r<   r=   __doc__r    intr(   rF   Tensortupler   r
   
LongTensorr   r   r:   r>   r?   s   @r5   r}   r}   z   s    Gl} l l& +/59*)||*) #5<<#=>*) !.	*)
 !*) !!1!12*) -.*) 
u||Xell3XeELL>Q5RR	S*)r6   r}   RMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )MistralRMSNormc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z=
        MistralRMSNorm is equivalent to T5LayerNorm
        N)r'   r(   r   	ParameterrF   onesweightvariance_epsilon)r3   r*   epsr4   s      r5   r(   zMistralRMSNorm.__init__   s1     	ll5::k#:; #r6   c                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )NrB   rA   T)keepdim)	rk   rt   rF   rs   powmeanrsqrtr   r   )r3   rV   input_dtypevariances       r5   r:   zMistralRMSNorm.forward   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r6   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)r   r   rE   r   r3   s    r5   
extra_reprzMistralRMSNorm.extra_repr   s*    ))*+6$2G2G1HIIr6   )gư>)r;   r<   r=   r(   r:   r   r>   r?   s   @r5   r   r      s    $;Jr6   r   c                   (    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                     fdZ xZS )MistralDecoderLayerr)   r~   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        y )N)r)   r~   r   )r'   r(   r*   r}   	self_attnr"   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr   s      r5   r(   zMistralDecoderLayer.__init__   sl    !--)9Mf%-f.@.@fFYFYZ(6v7I7IvObOb(c%r6   rV   re   rQ   r   	use_cacher   r   rh   rX   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)rV   re   rQ   r   r   r   r    )r   r   r   r   )r3   rV   re   rQ   r   r   r   r   rh   residual_s              r5   r:   zMistralDecoderLayer.forward   s     !,,];)4>> 	
')%)) 3	
 	
q !=0 !55mD/ =0r6   )NNNFNN)r;   r<   r=   r    r   r(   rF   r   r   r   r
   boolr   r   r   r:   r>   r?   s   @r5   r   r      s    d} d d 2637*.$)59KO|| !. u//0	
 ! D> !!1!12 &eELL%,,,F&GH +, 
u||	r6   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)MistralPreTrainedModelr)   modelTr   past_key_values)rV   
attentionsN)r;   r<   r=   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   r6   r5   r   r      sQ    &*#./#4"5N!"&,&r6   r   c                   ^     e Zd Zddef fdZ ej                         ed               Z xZ	S )MistralRotaryEmbeddingr)   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)r3   r)   devicer   r4   s       r5   r(   zMistralRotaryEmbedding.__init__  s    6>*z&:M:Mt/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r6   c                 b   | 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  }	d d d        j	                  |j                   
      	j	                  |j                   
      fS # 1 sw Y   AxY w)Nr   rA   r   mpscpuF)device_typeenabledrB   rC   )rk   )r   floatrZ   rE   rt   r   r   r   strrF   autocastrp   rG   rO   r   rP   rk   )
r3   r9   rQ   inv_freq_expandedposition_ids_expandedr   freqsembrO   rP   s
             r5   r:   zMistralRotaryEmbedding.forward  sV    !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.r8   )
r;   r<   r=   r    r(   rF   no_gradr   r:   r>   r?   s   @r5   r   r     s3    /} /" U]]_<  <r6   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   d	eej                     d
ee   defd              Z xZS )MistralModelr)   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      r5   r(   zMistralModel.__init__/  s     !.. ++LL):):F<N<NPTP`P`ammEJ6KcKcEde	 3e
 #6#5#56;N;NO	0?&+# 	 fs   D	input_idsre   rQ   r   inputs_embedsr   r   rh   rX   c                 |   |d u |d uz  rt        d      || j                  |      }|r|
t               }|F||j                         nd}	t	        j
                  |	|	|j                  d   z   |j                        }||j                  d      }| j                  j                  t        nt        }
 |
| j                  |||||      }|}| j                  ||      }| j                  d | j                  j                   D ]  } ||f||||||d|} | j!                  |      }t#        ||r|      S d       S )Nz:You must specify exactly one of input_ids or inputs_embedsr   r   )r   )r)   input_embedsre   r   r   rQ   )re   rQ   r   r   r   r   )last_hidden_stater   )
ValueErrorr   r   get_seq_lengthrF   arangerE   r   rL   r)   r   r   r   r   r   r   r   r   )r3   r  re   rQ   r   r  r   r   rh   past_seen_tokensmask_functionry   rV   r   decoder_layers                  r5   r:   zMistralModel.forward?  s~    -t";<YZZ  --i8M0*nO!CRC^==?de"\\ "2]5H5H5K"KTaThThN )33A6L.2kk.H.H.P*Vw#;;&))+%
 &"oom\J![[)H4;;+H+HI 
	M)	*).#-$7	 	M
	 		-0&+/8O
 	
>B
 	
r6   )NNNNNNN)r;   r<   r=   r    r(   r   r   r   rF   r   r   r
   FloatTensorr   r   r   r   r:   r>   r?   s   @r5   r   r   -  s    }    151537+/59$(599
E,,-9
 !.9
 u//0	9

 "%9
   1 129
 D>9
 !!1!129
 +,9
 
!9
  9
r6   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 )MistralForCausalLMzlm_head.weightlm_headcolwise_reprV   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y r$   )
r'   r(   r   r   r   r   r,   r*   r  r   r2   s     r5   r(   zMistralForCausalLM.__init__  sU     !&)
 ++yy!3!3V5F5FUS 	r6   c                     || _         y r8   r   )r3   decoders     r5   set_decoderzMistralForCausalLM.set_decoder  s	    
r6   c                     | j                   S r8   r  r   s    r5   get_decoderzMistralForCausalLM.get_decoder  s    zzr6   r  re   rQ   r   r  labelsr   r   logits_to_keeprh   rX   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, MistralForCausalLM

        >>> model = MistralForCausalLM.from_pretrained("meta-mistral/Mistral-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-mistral/Mistral-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  re   rQ   r   r  r   r   N)r  r  r   )lossr  r   rV   r   r   )r   r  r   r   slicer  loss_functionr)   r   r   r   rV   r   )r3   r  re   rQ   r   r  r  r   r   r  rh   outputsrV   slice_indicesr  r  s                   r5   r:   zMistralForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r6   )	NNNNNNNNr   )r;   r<   r=   _tied_weights_keys_tp_plan_pp_planr(   r  r  r   r   r   rF   r   r   r
   r  r   r   r   r   r   r   r:   r>   r?   s   @r5   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
r6   r  c                       e Zd Zy)MistralForTokenClassificationNr;   r<   r=   r   r6   r5   r%  r%        r6   r%  c                       e Zd Zy) MistralForSequenceClassificationNr&  r   r6   r5   r)  r)    r'  r6   r)  c                       e Zd Zy)MistralForQuestionAnsweringNr&  r   r6   r5   r+  r+    s    r6   r+  )r  r+  r   r   r)  r%  )Nr   )r   )@typingr   r   r   rF   r   transformers.utils.genericr   activationsr	   cache_utilsr
   r   
generationr   integrationsr   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   r   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   configuration_mistralr    Moduler"   rJ   rU   r   r   r`   r   r{   r}   r   r   r   r   r   r  r%  r)  r+  __all__r   r6   r5   <module>r=     s   - ,   9 ! . ) 7 R B  P K F & I I 0  (6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4;)ryy ;)| Y'JRYY J (J((4 (V _  $<RYY <D L
) L
 L
^ N
/ N
 N
b	$ACY 		'GI_ 	 \"=?U [r6   