
     `iP                        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	m
Z
 ddlm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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% ddl&m'Z' ddl(m)Z) ddl*m+Z+  e%j,        e-          Z. ed           G d dej/                              Z0 G d dej/                  Z1d Z2d<dZ3 G d dej/                  Z4dej5        de6dej5        fd Z7	 d=d"ej/        d#ej5        d$ej5        d%ej5        d&eej5                 d'e8d(e8d)e e"         fd*Z9 G d+ d,ej/                  Z: G d- d.e          Z;e# G d/ d0e                      Z<e# G d1 d2e<                      Z=e# G d3 d4e<e                      Z> G d5 d6ee<          Z? G d7 d8ee<          Z@ G d9 d:ee<          ZAg d;ZBdS )>    )CallableOptionalUnionN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask)GenericForQuestionAnswering GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuplelogging)deprecate_kwarg)check_model_inputs   )LlamaConfigRMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )LlamaRMSNormư>c                     t                                                       t          j        t	          j        |                    | _        || _        dS )z;
        LlamaRMSNorm is equivalent to T5LayerNorm
        N)super__init__r   	Parametertorchonesweightvariance_epsilon)selfhidden_sizeeps	__class__s      |/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/llama/modeling_llama.pyr'   zLlamaRMSNorm.__init__6   sD     	l5:k#:#:;; #    c                    |j         }|                    t          j                  }|                    d                              dd          }|t          j        || j        z             z  }| j        |                    |          z  S )N   T)keepdim)	dtypetor)   float32powmeanrsqrtr,   r+   )r-   hidden_statesinput_dtypevariances       r1   forwardzLlamaRMSNorm.forward>   s|    #)%((77 $$Q'',,R,>>%Ht?T4T(U(UU{]--k::::r2   c                 H    t          | j        j                   d| j         S )Nz, eps=)tupler+   shaper,   )r-   s    r1   
extra_reprzLlamaRMSNorm.extra_reprE   s&    )**II$2GIIIr2   )r$   )__name__
__module____qualname__r'   r@   rD   __classcell__r0   s   @r1   r#   r#   4   sb        $ $ $ $ $ $; ; ;J J J J J J Jr2   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 )LlamaRotaryEmbeddinginv_freqNconfigc                    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defaultrL   F)
persistent)r&   r'   hasattr
isinstancerO   dictgetrP   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrM   r   rope_init_fnattention_scalingregister_bufferrL   original_inv_freq)r-   rM   devicerL   r0   s       r1   r'   zLlamaRotaryEmbedding.__init__L   s    6>** 	'z&:Mt/T/T 	'#044[&BUBYBYZ`BaBabbDNN&DN"("@$*$B!/?+/+<+<T[&+Q+Q($(ZeDDD!%r2   c                 X   | j         d d d d f                                                             |j        d         dd                              |j                  }|d d d d d f                                         }t          |j        j        t                    r|j        j        dk    r|j        j        nd}t          j
        |d          5  |                                |                                z                      dd          }t          j        ||fd	          }|                                | j        z  }|                                | j        z  }	d d d            n# 1 swxY w Y   |                    |j        
          |	                    |j        
          fS )Nr   r5   r   mpscpuF)device_typeenabledr4   dim)r7   )rL   floatexpandrC   r8   r_   rU   rQ   strr)   autocast	transposecatcosr\   sinr7   )
r-   xposition_idsinv_freq_expandedposition_ids_expandedrc   freqsembrm   rn   s
             r1   r@   zLlamaRotaryEmbedding.forward]   s    !M$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/N)rE   rF   rG   r)   Tensor__annotations__r    r'   no_gradr   r@   rH   rI   s   @r1   rK   rK   I   s         l/ /{ / / / / / /" U]__< <  _< < < < <r2   rK   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..Nr5   r4   re   )rC   r)   rl   )ro   x1x2s      r1   rotate_halfr|   m   s]    	
3"!'"+"""	#B	
3q """	#B9rc2YB''''r2   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.
    )	unsqueezer|   )qkrm   rn   rp   unsqueeze_dimq_embedk_embeds           r1   apply_rotary_pos_embr   t   sc    ( --
&
&C
--
&
&C3w;q>>C/0G3w;q>>C/0GGr2   c                   $     e Zd Z fdZd Z xZS )LlamaMLPc                    t                                                       || _        |j        | _        |j        | _        t          j        | j        | j        |j                  | _        t          j        | j        | j        |j                  | _	        t          j        | j        | j        |j                  | _
        t          |j                 | _        d S )Nbias)r&   r'   rM   r.   intermediate_sizer   Linearmlp_bias	gate_projup_proj	down_projr   
hidden_actact_fnr-   rM   r0   s     r1   r'   zLlamaMLP.__init__   s    !-!'!94#3T5KRXRabbby!143IPVP_```4#94;KRXRabbbV./r2   c                     |                      |                     |                     |                    |                     |          z            }|S ru   )r   r   r   r   )r-   ro   r   s      r1   r@   zLlamaMLP.forward   sA    NN4;;t~~a/@/@#A#ADLLQROO#STT	r2   )rE   rF   rG   r'   r@   rH   rI   s   @r1   r   r      sG        0 0 0 0 0      r2   r   r=   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)rC   rh   reshape)r=   r   batchnum_key_value_headsslenhead_dims         r1   	repeat_kvr      s    
 2?1D.Ehzz!!!!QQQaaa"23::5BUW\^bdlmmM  (;e(CT8TTTr2           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 )Nr4   r   r5   )rf   r7   )ptrainingr   )r   num_key_value_groupsr)   matmulrk   rC   r   
functionalsoftmaxr9   r8   r7   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r1   eager_attention_forwardr      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$$r2   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j	        f         fd            Z xZS )LlamaAttentionz=Multi-headed attention from 'Attention Is All You Need' paperrM   	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                  | _        d S )Nr   g      Tr   )r&   r'   rM   r   getattrr.   num_attention_headsr   r   r   r   attention_dropout	is_causalr   r   attention_biasq_projk_projv_projo_projr-   rM   r   r0   s      r1   r'   zLlamaAttention.__init__   sB   "
F4F&Jd4dee$*$>&B\$\!}d*!'!9i :T] JQWQf
 
 
 i :T] JQWQf
 
 
 i :T] JQWQf
 
 
 i&68JQWQf
 
 
r2   past_key_valuepast_key_values4.58new_nameversionNr=   position_embeddingsr   cache_positionr   r   c                 D   |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        d|\  }} |j        g |dR                                  }|                     |          }||fS )Nr5   r   r4   )rn   rm   r   eagerr   )r   r   )rC   r   r   viewrk   r   r   r   updater   r   rM   _attn_implementationr   r   r   r   r   r   r   )r-   r=   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   rm   rn   cache_kwargsattention_interfacer   r   s                     r1   r@   zLlamaAttention.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	%
 	%
 	%
 	%
!\ *k);;;;;;FFHHkk+..L((r2   )NN)rE   rF   rG   __doc__r    intr'   r   r)   rv   rB   r   r	   
LongTensorr   r   r@   rH   rI   s   @r1   r   r      s       GG
{ 
s 
 
 
 
 
 
. _%0A6RRR ,059)) ))|)) #5<#=>)) !.	))
 "%)) !!12)) +,)) 
u|U\)	*)) )) )) SR)) )) )) )) ))r2   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 )LlamaDecoderLayerrM   r   c                 4   t                                                       |j        | _        t          ||          | _        t          |          | _        t          |j        |j                  | _	        t          |j        |j                  | _
        d S )N)rM   r   r/   )r&   r'   r.   r   	self_attnr   mlpr#   rms_norm_epsinput_layernormpost_attention_layernormr   s      r1   r'   zLlamaDecoderLayer.__init__  s    !-'vKKKF##+F,>FDWXXX(4V5GVM`(a(a(a%%%r2   r   r   r   r   NFr=   r   rp   	use_cacher   r   r   r   c                     |}	|                      |          } | j        d|||||||d|\  }}
|	|z   }|}	|                     |          }|                     |          }|	|z   }|S )N)r=   r   rp   r   r   r   r    )r   r   r   r   )r-   r=   r   rp   r   r   r   r   r   residual_s              r1   r@   zLlamaDecoderLayer.forward  s     !,,];;)4> 	
')%+) 3	
 	
 	
 	
q !=0 !55mDD// =0r2   )NNNFNN)rE   rF   rG   r    r   r'   r   r)   rv   r   r   r	   boolrB   r   r   r@   rH   rI   s   @r1   r   r     s5       b{ bs b b b b b b _%0A6RRR 2637+/$)59KO | !. u/0	
 "% D> !!12 &eEL%,,F&GH +, 
   SR    r2   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 )LlamaPreTrainedModelrM   modelTr   r   )r=   
attentionsN)rE   rF   rG   r    rw   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   r2   r1   r   r   :  sl         &*#,-#4"5N!"&*$ r2   r   c                       e Zd Zdef fdZee	 	 	 	 	 	 	 ddeej	                 deej
                 deej	                 dee         deej                 d	eej	                 d
ee         dee         defd                        Z xZS )
LlamaModelrM   c                    t                                                     j        | _        j        | _        t          j        j        j        | j                  | _        t          j	        fdt          j                  D                       | _        t          j        j                  | _        t!                    | _        d| _        |                                  d S )Nc                 0    g | ]}t          |          S r   )r   ).0r   rM   s     r1   
<listcomp>z'LlamaModel.__init__.<locals>.<listcomp>V  s$    cccivy11cccr2   r   rM   F)r&   r'   pad_token_idpadding_idx
vocab_sizer   	Embeddingr.   embed_tokens
ModuleListrangenum_hidden_layerslayersr#   r   normrK   
rotary_embgradient_checkpointing	post_initr   s    `r1   r'   zLlamaModel.__init__O  s       !. +L):F<NPTP`aamcccc5IaCbCbccc
 
 !!39LMMM	.f===&+# 	r2   N	input_idsr   rp   r   inputs_embedsr   r   r   r   c           
      N   |d u |d uz  rt          d          ||                     |          }|r|t          | j                  }|B||                                nd}	t          j        |	|	|j        d         z   |j                  }||	                    d          }t          | j        |||||          }
|}|                     ||          }| j        d | j        j                 D ]} ||f|
||||d|}|                     |          }t          ||          S )	Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r   )r_   )rM   input_embedsr   r   r   rp   )r   rp   r   r   r   )last_hidden_stater   )
ValueErrorr   r
   rM   get_seq_lengthr)   arangerC   r_   r~   r   r  r  r  r  r   )r-   r	  r   rp   r   r
  r   r   r   past_seen_tokensr   r=   r   decoder_layers                 r1   r@   zLlamaModel.forward_  s    -t";< 	[YZZZ *.*;*;I*F*FM 	?0*$+>>>O!CRC^==???de+0< "2]5H5K"KTaTh, , ,N )33A66L(;&))+%
 
 
 &"oom\JJ![)H4;+H)HI 		 		M)M*) /-$7   MM 		-00&++
 
 
 	
r2   )NNNNNNN)rE   rF   rG   r    r'   r   r   r   r)   r   rv   r	   FloatTensorr   r   r   r   r@   rH   rI   s   @r1   r   r   M  s       {         151537+/5959$(8
 8
E,-8
 !.8
 u/0	8

 "%8
   128
 !!128
 D>8
 +,8
 
!8
 8
 8
 ^ 8
 8
 8
 8
 8
r2   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 )LlamaForCausalLMzlm_head.weightlm_headcolwise_repr=   logitsc                     t                                          |           t          |          | _        |j        | _        t          j        |j        |j        d          | _        | 	                                 d S )NFr   )
r&   r'   r   r   r   r   r   r.   r  r  r   s     r1   r'   zLlamaForCausalLM.__init__  sj       ''
 +y!3V5FUSSS 	r2   Nr   r	  r   rp   r   r
  labelsr   r   logits_to_keepr   r   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, LlamaForCausalLM

        >>> model = LlamaForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-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	  r   rp   r   r
  r   r   N)r  r  r   )lossr  r   r=   r   r   )r   r  rU   r   slicer  loss_functionrM   r   r   r   r=   r   )r-   r	  r   rp   r   r
  r  r   r   r  r   outputsr=   slice_indicesr  r  s                   r1   r@   zLlamaForCausalLM.forward  s    @ ,64: 	,
)%+')	,
 	,
 	,
 	,
  18B>SV8W8Wk~ot444]kmAAA}aaa,?@AA%4%pVFt{OeppioppD%#3!/)
 
 
 	
r2   )	NNNNNNNNr   )rE   rF   rG   _tied_weights_keys_tp_plan_pp_planr'   r   r   r   r)   r   rv   r	   r  r   r   r   r   r   r   r@   rH   rI   s   @r1   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
r2   r  c                       e Zd ZdS )LlamaForSequenceClassificationNrE   rF   rG   r   r2   r1   r&  r&              r2   r&  c                       e Zd ZdZdS )LlamaForQuestionAnsweringtransformerN)rE   rF   rG   r   r   r2   r1   r*  r*    s        %r2   r*  c                       e Zd ZdS )LlamaForTokenClassificationNr'  r   r2   r1   r-  r-    r(  r2   r-  )r  r   r   r&  r*  r-  )Nr   )r   )Ctypingr   r   r   r)   r   activationsr   cache_utilsr	   r
   
generationr   integrationsr   masking_utilsr   modeling_layersr   r   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   utils.deprecationr   utils.genericr   configuration_llamar    
get_loggerrE   loggerModuler#   rK   r|   r   r   rv   r   r   rg   r   r   r   r   r   r  r&  r*  r-  __all__r   r2   r1   <module>rA     s  ( - , , , , , , , , ,        ! ! ! ! ! ! . . . . . . . . ) ) ) ) ) ) 7 7 7 7 7 7 / / / / / /                   L K K K K K K K F F F F F F F F & & & & & & R R R R R R R R R R R R 0 0 0 0 0 0 / / / / / / , , , , , , 
	H	%	% Y''J J J J J29 J J ('J(!< !< !< !< !<29 !< !< !<H( ( (   6    ry    	UU\ 	U# 	U%, 	U 	U 	U 	U& % %I%<% 
% <	%
 U\*% % % '(% % % %4D) D) D) D) D)RY D) D) D)N+ + + + +2 + + +\     ?   $ K
 K
 K
 K
 K
% K
 K
 K
\ H
 H
 H
 H
 H
+_ H
 H
 H
V b a a a a%EG[ a a a& & & & & ;=Q & & & \ [ [ [ ["?AU [ [ [  r2   