
     `iQ                     t   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$m%Z% ddl&m'Z'm(Z(m)Z) ddl*m+Z+ ddl,m-Z-  G d dej.                  Z/d Z0d=dZ1dej2        de3dej2        fdZ4	 d>dej.        dej2        d ej2        d!ej2        d"eej2                 d#e5d$e5d%e%e'         fd&Z6 G d' d(ej.                  Z7 ed)           G d* d+ej.                              Z8 G d, d-e          Z9e( G d. d/e#                      Z: G d0 d1ej.                  Z;e( G d2 d3e:                      Z<e( G d4 d5e:e                      Z= G d6 d7ee:          Z> G d8 d9ee:          Z? G d: d;ee:          Z@g d<ZAdS )?    )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)deprecate_kwarg   )MistralConfigc                   $     e Zd Z fdZd Z xZS )
MistralMLPc                    t                                                       || _        |j        | _        |j        | _        t          j        | j        | j        d          | _        t          j        | j        | j        d          | _        t          j        | j        | j        d          | _	        t          |j                 | _        d S NFbias)super__init__confighidden_sizeintermediate_sizer   Linear	gate_projup_proj	down_projr	   
hidden_actact_fnselfr*   	__class__s     /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/mistral/modeling_mistral.pyr)   zMistralMLP.__init__$   s    !-!'!94#3T5KRWXXXy!143IPUVVV4#94;KRWXXXV./    c                     |                      |                     |                     |                    |                     |          z            }|S N)r0   r2   r.   r/   )r4   xr0   s      r6   forwardzMistralMLP.forward.   sA    NN4;;t~~a/@/@#A#ADLLQROO#STT	r7   )__name__
__module____qualname__r)   r;   __classcell__r5   s   @r6   r#   r#   #   sG        0 0 0 0 0      r7   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)r:   x1x2s      r6   rotate_halfrK   3   s]    	
3"!'"+"""	#B	
3q """	#B9rc2YB''''r7   c                     |                     |          }|                     |          }| |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.
    )	unsqueezerK   )qkcossinposition_idsunsqueeze_dimq_embedk_embeds           r6   apply_rotary_pos_embrV   :   sc    ( --
&
&C
--
&
&C3w;q>>C/0G3w;q>>C/0GGr7   hidden_statesn_repreturnc                     | j         \  }}}}|dk    r| S | dddddddddf                             |||||          } |                     |||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)rF   expandreshape)rW   rX   batchnum_key_value_headsslenhead_dims         r6   	repeat_kvra   U   s    
 2?1D.Ehzz!!!!QQQaaa"23::5BUW\^bdlmmM  (;e(CT8TTTr7           modulequerykeyvalueattention_maskscalingdropoutkwargsc                 R   t          || j                  }t          || j                  }	t          j        ||                    dd                    |z  }
|$|d d d d d d d |j        d         f         }|
|z   }
t          j                            |
dt          j	                  
                    |j                  }
t          j                            |
|| j                  }
t          j        |
|	          }|                    dd                                          }||
fS )NrC   r   rB   )rE   dtype)ptrainingr    )ra   num_key_value_groupsrG   matmul	transposerF   r   
functionalsoftmaxfloat32torm   ri   ro   
contiguous)rc   rd   re   rf   rg   rh   ri   rj   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r6   eager_attention_forwardr}   a   s    3 ;<<JUF$?@@L<z';';Aq'A'ABBWLL!$QQQ111.D
0@0D.D%DE#k1=((2U](SSVVW\WbccL=((6?([[L,|\::K''1--88::K$$r7   c                        e Zd ZdZdedef fdZ eddd          	 	 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	                 f         fd            Z xZS )MistralAttentionz=Multi-headed attention from 'Attention Is All You Need' paperr*   	layer_idxc                    t                                                       || _        || _        t	          |dd           p|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          | _        d S )Nr`   g      TFr&   )r(   r)   r*   r   getattrr+   num_attention_headsr`   r^   rp   rh   attention_dropout	is_causalr   r-   q_projk_projv_projo_projr4   r*   r   r5   s      r6   r)   zMistralAttention.__init__~   s    "
D99mV=OSYSm=m$*$>&B\$\!}d*!'!9i 2F4NQUQ^4^ejkkki 2F4NQUQ^4^ejkkki 2F4NQUQ^4^ejkkki :T] JFL^ejkkkr7   past_key_valuepast_key_values4.58new_nameversionNrW   position_embeddingsrg   cache_positionrj   rY   c           
      n   |j         d d         }g |d| j        R }|                     |                              |                              dd          }	|                     |                              |                              dd          }
|                     |                              |                              dd          }|\  }}t          |	|
||          \  }	}
|&|||d}|                    |
|| j	        |          \  }
}t          }| j        j        dk    rt          | j        j                 } || |	|
||f| j        sdn| j        | j        t#          | j        dd           d|\  }} |j        g |dR                                  }|                     |          }||fS )	NrB   r    rC   )rQ   rP   r   eagerrb   sliding_window)ri   rh   r   )rF   r`   r   viewrr   r   r   rV   updater   r}   r*   _attn_implementationr   ro   r   rh   r   r\   rw   r   )r4   rW   r   rg   r   r   rj   input_shapehidden_shapequery_statesrx   ry   rP   rQ   cache_kwargsattention_interfacer|   rz   s                     r6   r;   zMistralAttention.forward   s    $)#2#.88b8$-88{{=1166|DDNNqRSTT[[//44\BBLLQPQRR
{{=1166|DDNNqRSTT&S#7jRUWZ#[#[ j&#&snUUL'6'='=j,X\Xfht'u'u$J(?;+w66"9$+:Z"[$7$7
%
  $}HCC$2HL"4;0@$GG
%
 
%
 
%
 
%
!\ *k);;;;;;FFHHkk+..L((r7   )NN)r<   r=   r>   __doc__r!   intr)   r   rG   Tensortupler   r
   
LongTensorr   r   r;   r?   r@   s   @r6   r   r   {   s       GGl} l l l l l l l _%0A6RRR ,059*) *)|*) #5<#=>*) !.	*)
 "%*) !!12*) -.*) 
u|Xel33	4*) *) *) SR*) *) *) *) *)r7   r   RMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )MistralRMSNormư>c                     t                                                       t          j        t	          j        |                    | _        || _        dS )z=
        MistralRMSNorm is equivalent to T5LayerNorm
        N)r(   r)   r   	ParameterrG   onesweightvariance_epsilon)r4   r+   epsr5   s      r6   r)   zMistralRMSNorm.__init__   sD     	l5:k#:#:;; #r7   c                    |j         }|                    t          j                  }|                    d                              dd          }|t          j        || j        z             z  }| j        |                    |          z  S )NrC   rB   T)keepdim)	rm   rv   rG   ru   powmeanrsqrtr   r   )r4   rW   input_dtypevariances       r6   r;   zMistralRMSNorm.forward   s|    #)%((77 $$Q'',,R,>>%Ht?T4T(U(UU{]--k::::r7   c                 H    t          | j        j                   d| j         S )Nz, eps=)r   r   rF   r   )r4   s    r6   
extra_reprzMistralRMSNorm.extra_repr   s&    )**II$2GIIIr7   )r   )r<   r=   r>   r)   r;   r   r?   r@   s   @r6   r   r      sb        $ $ $ $ $ $; ; ;J J J J J J Jr7   r   c                   4    e Zd Zdedef fdZ eddd          	 	 	 	 	 	 dd
ej        de	ej                 de	ej
                 de	e         de	e         de	ej
                 de	eej        ej        f                  dee         dej        fd            Z xZS )MistralDecoderLayerr*   r   c                 4   t                                                       |j        | _        t          ||          | _        t          |          | _        t          |j        |j                  | _	        t          |j        |j                  | _
        d S )N)r*   r   r   )r(   r)   r+   r   	self_attnr#   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr   s      r6   r)   zMistralDecoderLayer.__init__   s    !-)9MMMf%%-f.@fFYZZZ(6v7IvOb(c(c(c%%%r7   r   r   r   r   NFrW   rg   rR   	use_cacher   r   rj   rY   c                     |}	|                      |          } | j        d|||||||d|\  }}
|	|z   }|}	|                     |          }|                     |          }|	|z   }|S )N)rW   rg   rR   r   r   r   r    )r   r   r   r   )r4   rW   rg   rR   r   r   r   r   rj   residual_s              r6   r;   zMistralDecoderLayer.forward   s     !,,];;)4> 	
')%+) 3	
 	
 	
 	
q !=0 !55mDD// =0r7   )NNNFNN)r<   r=   r>   r!   r   r)   r   rG   r   r   r   r
   boolr   r   r   r;   r?   r@   s   @r6   r   r      s5       d} d d d d d d d _%0A6RRR 2637+/$)59KO | !. u/0	
 "% D> !!12 &eEL%,,F&GH +, 
   SR    r7   r   c                   L    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dS )MistralPreTrainedModelr*   modelTr   r   )rW   
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   r7   r6   r   r      sl         &*#./#4"5N!"&,& r7   r   c                   |     e Zd ZU ej        ed<   ddef fdZ ej                    e	d                         Z
 xZS )MistralRotaryEmbeddinginv_freqNr*   c                    t                                                       t          |d          rSt          |j        t
                    r9|j                            d|j                            d                    | _        nd| _        |j        | _	        |j        | _
        || _        t          | j                 | _        |                     | j        |          \  }| _        |                     d|d           | j        | _        d S )Nrope_scaling	rope_typetypedefaultr   F)
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)r4   r*   devicer   r5   s       r6   r)   zMistralRotaryEmbedding.__init__  s    6>** 	'z&:Mt/T/T 	'#044[&BUBYBYZ`BaBabbDNN&DN"("@$*$B!/?+/+<+<T[&+Q+Q($(ZeDDD!%r7   c                 X   | j         d d d d f                                                             |j        d         dd                              |j                  }|d d d d d f                                         }t          |j        j        t                    r|j        j        dk    r|j        j        nd}t          j
        |d          5  |                                |                                z                      dd          }t          j        ||fd	          }|                                | j        z  }|                                | j        z  }	d d d            n# 1 swxY w Y   |                    |j        
          |	                    |j        
          fS )Nr   rB   r    mpscpuF)device_typeenabledrC   rD   )rm   )r   floatr[   rF   rv   r   r   r   strrG   autocastrr   rH   rP   r   rQ   rm   )
r4   r:   rR   inv_freq_expandedposition_ids_expandedr   freqsembrP   rQ   s
             r6   r;   zMistralRotaryEmbedding.forward"  s    !M$4-8>>@@GGHZ[\H]_acdeehhijiqrr ,QQQaaaZ 8 > > @ @'1!(-'E'Ek!(-[`J`J`ahmmfk^UCCC 	5 	5&,,..1F1L1L1N1NNYYZ[]^__E)UEN333C''))d44C''))d44C		5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 vvAGv$$cff17f&;&;;;s   BE++E/2E/r9   )r<   r=   r>   rG   r   r   r!   r)   no_gradr   r;   r?   r@   s   @r6   r   r     s         l/ /} / / / / / /" U]__< <  _< < < < <r7   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	        fdt          j                  D                       | _        t          j        j                  | _        t!                    | _        d| _        |                                  d S )Nc                 0    g | ]}t          |          S r   )r   ).0r   r*   s     r6   
<listcomp>z)MistralModel.__init__.<locals>.<listcomp>;  s$    eee	 33eeer7   r   r*   F)r(   r)   pad_token_idpadding_idx
vocab_sizer   	Embeddingr+   embed_tokens
ModuleListrangenum_hidden_layerslayersr   r   normr   
rotary_embgradient_checkpointing	post_initr3   s    `r6   r)   zMistralModel.__init__4  s       !. +L):F<NPTP`aameeeeU6KcEdEdeee
 
 #6#56;NOOO	0???&+# 	r7   N	input_idsrg   rR   r   inputs_embedsr   r   rj   rY   c                    |d u |d uz  rt          d          ||                     |          }|r|t          | j                  }|B||                                nd}	t          j        |	|	|j        d         z   |j                  }||	                    d          }| j        j
        t          nt          }
 |
| j        |||||          }|}|                     ||          }| j        d | j        j                 D ]} ||f||||||d|}|                     |          }t#          ||r|nd           S )	Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r    )r   )r*   input_embedsrg   r   r   rR   )rg   rR   r   r   r   r   )last_hidden_stater   )
ValueErrorr  r   r*   get_seq_lengthrG   arangerF   r   rM   r   r   r   r  r  r  r  r   )r4   r
  rg   rR   r   r  r   r   rj   past_seen_tokensmask_functionr{   rW   r   decoder_layers                  r6   r;   zMistralModel.forwardD  s    -t";< 	[YZZZ  --i88M 	?0*$+>>>O!CRC^==???de"\ "2]5H5K"KTaTh  N )33A66L.2k.H.P**Vw#m;&))+%
 
 
 &"oom\JJ![)H4;+H)HI 
	 
	M)M	*) /#-$7	 	 	 	MM 		-00&+/8BOOd
 
 
 	
r7   )NNNNNNN)r<   r=   r>   r!   r)   r   r   r   rG   r   r   r
   FloatTensorr   r   r   r   r;   r?   r@   s   @r6   r   r   2  s       }         151537+/59$(599
 9
E,-9
 !.9
 u/0	9

 "%9
   129
 D>9
 !!129
 +,9
 
!9
 9
 9
 ^ 9
 9
 9
 9
 9
r7   r   c                   f    e Zd ZdgZddiZddgdgfiZ 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
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_reprW   logitsc                     t                                          |           t          |          | _        |j        | _        t          j        |j        |j        d          | _        | 	                                 d S r%   )
r(   r)   r   r   r   r   r-   r+   r  r	  r3   s     r6   r)   zMistralForCausalLM.__init__  sj       !&))
 +y!3V5FUSSS 	r7   Nr   r
  rg   rR   r   r  labelsr   r   logits_to_keeprj   rY   c
                 R    | j         d|||||||d|
}|j        }t          |	t                    rt	          |	 d          n|	}|                     |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
  rg   rR   r   r  r   r   N)r  r  r   )lossr  r   rW   r   r   )r   r  r   r   slicer  loss_functionr*   r   r   r   rW   r   )r4   r
  rg   rR   r   r  r  r   r   r  rj   outputsrW   slice_indicesr  r  s                   r6   r;   zMistralForCausalLM.forward  s    @ ,64: 	,
)%+')	,
 	,
 	,
 	,
  18B>SV8W8Wk~ot444]kmAAA}aaa,?@AA%4%pVFt{OeppioppD%#3!/)
 
 
 	
r7   )	NNNNNNNNr   )r<   r=   r>   _tied_weights_keys_tp_plan_pp_planr)   r   r   r   rG   r   r   r
   r  r   r   r   r   r   r   r;   r?   r@   s   @r6   r  r    sa       *+=)H_-z:;H      151537+/59-1$(59348
 8
E,-8
 !.8
 u/0	8

 "%8
   128
 )*8
 D>8
 !!128
 c5</08
 +,8
 
 8
 8
 8
 ^ 8
 8
 8
 8
 8
r7   r  c                       e Zd ZdS )MistralForTokenClassificationNr<   r=   r>   r   r7   r6   r(  r(            Dr7   r(  c                       e Zd ZdS ) MistralForSequenceClassificationNr)  r   r7   r6   r,  r,    r*  r7   r,  c                       e Zd ZdS )MistralForQuestionAnsweringNr)  r   r7   r6   r.  r.    s          r7   r.  )r  r.  r   r   r,  r(  )Nr    )rb   )Btypingr   r   r   rG   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   utils.deprecationr   configuration_mistralr!   Moduler#   rK   rV   r   r   ra   r   r}   r   r   r   r   r   r   r  r(  r,  r.  __all__r   r7   r6   <module>rA     s   - , , , , , , , , ,        9 9 9 9 9 9 ! ! ! ! ! ! . . . . . . . . ) ) ) ) ) ) 7 7 7 7 7 7 R R R R R R R R B B B B B B            P O O O O O O O K K K K K K K K F F F F F F F F & & & & & & I I I I I I I I I I 0 0 0 0 0 0 0 0 0 0 0 0        ( ( (   6	UU\ 	U# 	U%, 	U 	U 	U 	U& % %I%<% 
% <	%
 U\*% % % '(% % % %4<) <) <) <) <)ry <) <) <)~ Y''J J J J JRY J J ('J() ) ) ) )4 ) ) )X     _   $!< !< !< !< !<RY !< !< !<H L
 L
 L
 L
 L
) L
 L
 L
^ H
 H
 H
 H
 H
/ H
 H
 H
V	 	 	 	 	$ACY 	 	 		 	 	 	 	'GI_ 	 	 	 \ [ [ [ ["=?U [ [ [  r7   