
    iZ                     \   d dl mZ 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 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 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(m)Z) ddl*m+Z+  e&jX                  e-      Z. G d dej^                        Z0d Z1 ed      d6d       Z2dejf                  de4dejf                  fdZ5	 d7dej^                  dejf                  dejf                  dejf                  d ejf                  dz  d!e6d"e6d#e!e#   fd$Z7 ee2       G d% d&ej^                               Z8 G d' d(ej^                        Z9 G d) d*e      Z:e$ G d+ d,e             Z;e$ G d- d.e;             Z<e$ G d/ d0e;e             Z= G d1 d2ee;      Z> G d3 d4ee;      Z?g d5Z@y)8    )Callable)OptionalN   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_func_from_hubuse_kernelized_func)create_causal_mask) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuplelogging)check_model_inputsmaybe_autocast   )	PhiConfigc                        e Zd ZU ej                  ed<   ddef fdZe	 	 	 ddedz  de	d   de
dz  ded	ef   fd
       Z ej                         ed               Z xZS )PhiRotaryEmbeddinginv_freqNconfigc                    t         |           |j                  | _        |j                  | _        || _        | j
                  j                  d   | _        | j                  }| j                  dk7  rt        | j                     } || j
                  |      \  }| _
        | j                  d|d       | j                  d|j                         d       y )N	rope_typedefaultr!   F)
persistentoriginal_inv_freq)super__init__max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr"   rope_parametersr$   compute_default_rope_parametersr   attention_scalingregister_bufferclone)selfr"   devicerope_init_fnr!   	__class__s        n/home/obispo/Crisostomo_bridge/mision_env/lib/python3.12/site-packages/transformers/models/phi/modeling_phi.pyr)   zPhiRotaryEmbedding.__init__&   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuU    r3   ztorch.deviceseq_lenreturnztorch.Tensorc                 n   | j                   d   }| j                   j                  dd      }t        | dd      xs | j                  | j                  z  }t        ||z        }d}d|t        j                  d|dt        j                        j                  |t        j                  	      |z  z  z  }||fS )
a  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
            device (`torch.device`):
                The device to use for initialization of the inverse frequencies.
            seq_len (`int`, *optional*):
                The current sequence length. Unused for this type of RoPE.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        
rope_thetapartial_rotary_factorg      ?head_dimNr      dtype)r3   r@   )r-   getgetattrhidden_sizenum_attention_headsinttorcharangeint64tofloat)	r"   r3   r8   baser<   r=   dimattention_factorr!   s	            r6   r.   z2PhiRotaryEmbedding.compute_default_rope_parameters6   s    & %%l3 & 6 6 : :;RTW X6:t4h8J8JfNhNh8h(223 U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r7   c                 N   | 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        |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   r   mpscpuF)device_typeenabledr>   rL   r?   )r!   rJ   expandshaperI   r3   
isinstancetypestrr   	transposerF   catcosr/   sinr@   )
r2   xposition_idsinv_freq_expandedposition_ids_expandedrR   freqsembr\   r]   s
             r6   forwardzPhiRotaryEmbedding.forwardV   sR    !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$N)NNN)__name__
__module____qualname__rF   Tensor__annotations__r   r)   staticmethodr   rE   tuplerJ   r.   no_gradr   rd   __classcell__r5   s   @r6   r    r    #   s    llVy V  #'+/"*D *(* t* 
~u$	%	* *> U]]_<  <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..NrO   r>   rT   )rV   rF   r[   )r^   x1x2s      r6   rotate_halfrs   f   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r7   rotary_pos_embc                     |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.
        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.
    )	unsqueezers   )qkr\   r]   unsqueeze_dimq_embedk_embeds          r6   apply_rotary_pos_embr|   m   sY    & --
&C
--
&C3w;q>C/0G3w;q>C/0GGr7   hidden_statesn_repr9   c                     | 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)rV   rU   reshape)r}   r~   batchnum_key_value_headsslenr=   s         r6   	repeat_kvr      so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr7   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   rO   )rL   r@   )ptrainingr   )r   num_key_value_groupsrF   matmulrZ   rV   nn
functionalsoftmaxfloat32rI   r@   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r6   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$$r7   c                   
    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j                  dz  d	e
dz  d
ej                  dz  de	ej                  ej                  dz  f   fdZ xZS )PhiAttentionz=Multi-headed attention from 'Attention Is All You Need' paperr"   	layer_idxc                    t         |           || _        || _        t	        |d|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      | _        t'        | j                  |j(                  d   z        | _        |j,                  | _        | j,                  r}t        j.                  |j
                  |j                  z  |j0                  d      | _        t        j.                  |j
                  |j                  z  |j0                  d      | _        y y )Nr=   g      Tbiasr<   )epselementwise_affine)r(   r)   r"   r   rB   rC   rD   r=   r   r   r   attention_dropout	is_causalr   Linearq_projk_projv_projdenserE   r-   rotary_ndimsqk_layernorm	LayerNormlayer_norm_epsq_layernormk_layernormr2   r"   r   r5   s      r6   r)   zPhiAttention.__init__   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii 2 2F4N4NQUQ^Q^4^eijii 2 2F4N4NQUQ^Q^4^eijii 2 2F4N4NQUQ^Q^4^eijYYv99DMMI6K]K]dhi
0F0FG^0_ _`"//!||""f&@&@@fF[F[pt D  "||""f&@&@@fF[F[pt D	 r7   Nr}   position_embeddingsr   past_key_valuescache_positionr9   c                 p   |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }| j                  r"| j                  |	      }	| j                  |
      }
|\  }}|	dd | j                  f   |	d| j                  d f   }}|
dd | j                  f   |
d| j                  d f   }}t        ||||      \  }}t        j                  ||fd      }	t        j                  ||fd      }
|'|||d}|j                  |
|| j                  |      \  }
}t!        j"                  | j$                  j&                  t(              } || |	|
||f| j*                  sdn| j,                  | j.                  d|\  }} |j0                  g |d j3                         }| j5                  |      }||fS )	NrO   r   r>   .rT   )r]   r\   r           )r   r   )rV   r=   r   viewrZ   r   r   r   r   r   r   r|   rF   r[   updater   r   get_interfacer"   _attn_implementationr   r   r   r   r   r   r   )r2   r}   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   r\   r]   	query_rot
query_passkey_rotkey_passcache_kwargsattention_interfacer   r   s                         r6   rd   zPhiAttention.forward   se    $))#2.88b8$--8{{=166|DNNqRST[[/44\BLLQPQR
{{=166|DNNqRST++L9L))*5J&S 1 1 1112d//112 	
 s/d////0sD--//0 
 2)Wc3O	7 yy)Z!8bAYY2;
&#&snUL'6'='=j,X\XfXfht'u$J(?(M(MKK,,.E)
 %8	%
  $}}C$2H2HLL	%
 	%
!\ *k));;;;FFHjj-L((r7   )NN)rf   rg   rh   __doc__r   rE   r)   rF   ri   rl   r   
LongTensorrd   rn   ro   s   @r6   r   r      s    Gy S 8 )-26;)||;) #5<<#=>;) t+	;)
 ;) ((4/;) 
u||U\\D00	1;)r7   r   c                   V     e Zd Z fdZdej
                  dej
                  fdZ xZS )PhiMLPc                    t         |           || _        t        |j                     | _        t        j                  |j                  |j                        | _
        t        j                  |j                  |j                        | _        y re   )r(   r)   r"   r   
hidden_actactivation_fnr   r   rC   intermediate_sizefc1fc2r2   r"   r5   s     r6   r)   zPhiMLP.__init__  sd    #F$5$5699V//1I1IJ99V55v7I7IJr7   r}   r9   c                 l    | j                  |      }| j                  |      }| j                  |      }|S re   )r   r   r   )r2   r}   s     r6   rd   zPhiMLP.forward  s4    /**=9/r7   )rf   rg   rh   r)   rF   ri   rd   rn   ro   s   @r6   r   r     s$    KU\\ ell r7   r   c                   f    e Zd Zdedef fdZ	 	 	 	 	 	 	 ddej                  dej                  dz  dej                  dz  de	dz  d	e
dz  d
e
dz  dej                  dz  deej                  ej                  f   dz  deej                  eej                  ej                  f   dz  f   fdZ xZS )PhiDecoderLayerr"   r   c                    t         |           t        ||      | _        t	        |      | _        t        j                  |j                  |j                        | _
        t        j                  |j                        | _        y )N)r   r   )r(   r)   r   	self_attnr   mlpr   r   rC   r   input_layernormDropoutresid_pdropresid_dropoutr   s      r6   r)   zPhiDecoderLayer.__init__  s]    %f	B&>!||F,>,>FDYDYZZZ(:(:;r7   Nr}   r   r_   r   output_attentions	use_cacher   r   r9   c	                     |}
| j                  |      } | j                  d||||||||d|	\  }}| j                  |      }| j                  | j                  |            }||z   |
z   }|f}|r||fz  }|S )N)r}   r   r_   r   r   r   r   r    )r   r   r   r   )r2   r}   r   r_   r   r   r   r   r   r   residualattn_outputsself_attn_weightsfeed_forward_hidden_statesoutputss                  r6   rd   zPhiDecoderLayer.forward  s     !,,]; +9$.. 
+
')%+/) 3
+
 
+
'' )),7%)%7%78O%P"$'AAHL ")++Gr7   )NNNFFNN)rf   rg   rh   r   rE   r)   rF   ri   r   r   boolrl   FloatTensorrd   rn   ro   s   @r6   r   r     s    <y <S < /304(,).!&26HL%||% t+% &&-	%
 %  $;% $;% ((4/% #5<<#=>E% 
u  %(9(95;L;L(L"MPT"TT	U%r7   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)PhiPreTrainedModelr"   modelTr   r   )r}   
attentionsN)rf   rg   rh   r   rj   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   E  sQ    &*#*+#4"5N!"&("r7   r   c                        e Zd Zdef 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dz  d
edz  dedz  dej                  dz  dee   defd              Z xZS )PhiModelr"   c           	      h   t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |      | _        d| _        t        j"                  |j$                        | _        t        j(                  |j                  |j*                        | _        | j/                          y c c}w )Nr"   Fr   )r(   r)   pad_token_idpadding_idx
vocab_sizer   	EmbeddingrC   embed_tokens
ModuleListrangenum_hidden_layersr   layersr    
rotary_embgradient_checkpointingr   
embd_pdropembed_dropoutr   r   final_layernorm	post_initr   s      r6   r)   zPhiModel.__init__Z  s     !.. ++LL):):F<N<NPTP`P`ammAFvG_G_A`aI_VY/a
 -F;&+#ZZ(9(9:!||F,>,>FDYDYZ 	 bs   D/N	input_idsr   r_   r   inputs_embedsr   r   output_hidden_statesr   r   r9   c
                    ||n| j                   j                  }||n| j                   j                  }||n| j                   j                  }|d u |d uz  rt	        d      | j
                  r%| j                  r|rt        j                  d       d}|| j                  |      }|r|t        | j                         }|	F||j                         nd}t        j                  |||j                  d   z   |j                        }	||	j!                  d      }t#        | j                   |||	||      }| j%                  |      }|}| j'                  ||	      }|rd
nd }|rd
nd }| j(                  d | j                   j*                   D ],  }|r||fz  } ||f||||||	|d|
}|d   }|s$||d   fz  }. | j-                  |      }|r||fz  }t/        ||r|nd ||      S )Nz:You must specify exactly one of input_ids or inputs_embedszX`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.Fr   r   r   )r3   )r"   input_embedsr   r   r   r_   )r_   r   )r   r_   r   r   r   r   r   )last_hidden_stater   r}   r   )r"   r   r
  r   
ValueErrorr  r   loggerwarning_oncer   r   get_seq_lengthrF   rG   rV   r3   rv   r   r  r  r  r   r  r   )r2   r  r   r_   r   r	  r   r   r
  r   r   past_seen_tokensr   r}   r   all_hidden_statesall_self_attnsdecoder_layerlayer_outputss                      r6   rd   zPhiModel.forwardk  sP    2C1N-TXT_T_TqTq$8$D $++JjJj 	 "+!6IDKK<Q<Q	-t";<YZZ&&4==Yj I  --i8M0*$++>O!CRC^==?de"\\ "2]5H5H5K"KTaThThN )33A6L(;;&))+%
 **=9%"oom,oW #7BD0d![[)H4;;+H+HI 	6M#!m%55!)
*) /"3#-$7
 
M *!,M =#3"55'	6* ,,];  -!11&+/8Od+%	
 	
r7   )	NNNNNNNNN)rf   rg   rh   r   r)   r   r   rF   r   ri   r   r   r   r   r   r   rd   rn   ro   s   @r6   r   r   X  s   y "  .2.204(,26!%)-,026\
##d*\
 t+\
 &&-	\

 \
 ((4/\
 $;\
  $;\
 #Tk\
 ((4/\
 +,\
 
!\
  \
r7   r   c                   b    e Zd ZddiZddiZddgdgfi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	j                  dz  dee	j                  z  dee   defd              Z xZS )PhiForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr}   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y )NTr   )
r(   r)   r   r   r   r   r   rC   r  r  r   s     r6   r)   zPhiForCausalLM.__init__  sU     f%
 ++yy!3!3V5F5FTR 	r7   Nr  r   r_   r   r	  labelsr   r   logits_to_keepr   r9   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, PhiForCausalLM

        >>> model = PhiForCausalLM.from_pretrained("meta-phi/Phi-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-phi/Phi-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   r_   r   r	  r   r   N)r  r  r   )lossr  r   r}   r   r   )r   r  rW   rE   slicer  loss_functionr"   r   r   r   r}   r   )r2   r  r   r_   r   r	  r  r   r   r  r   r   r}   slice_indicesr  r   s                   r6   rd   zPhiForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r7   )	NNNNNNNNr   )rf   rg   rh   _tied_weights_keys_tp_plan_pp_planr)   r   r   rF   r   ri   r   r   r   rE   r   r   r   rd   rn   ro   s   @r6   r  r    s/   *,GH23H_-z:;H  .2.204(,26*.!%26-.8
##d*8
 t+8
 &&-	8

 8
 ((4/8
   4'8
 $;8
 ((4/8
 ell*8
 +,8
 
 8
  8
r7   r  c                       e Zd Zy)PhiForSequenceClassificationNrf   rg   rh   r   r7   r6   r(  r(        r7   r(  c                       e Zd Zy)PhiForTokenClassificationNr)  r   r7   r6   r,  r,    r*  r7   r,  )r   r   r  r(  r,  )r   )r   )Acollections.abcr   typingr   rF   torch.nnr   activationsr   cache_utilsr   r   
generationr	   integrationsr
   r   masking_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   utils.genericr   r   configuration_phir   
get_loggerrf   r  Moduler    rs   r|   ri   rE   r   rJ   r   r   r   r   r   r   r  r(  r,  __all__r   r7   r6   <module>r@     s   %    ! . ) I / 
 P K F & R R ? ( 
		H	%@< @<F( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%4 )*U)299 U) +U)pRYY -0 -`   $ p
! p
 p
f H
' H
 H
V	#CEW 		 =?Q 	r7   