
    iZ                     h   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% ddl&m'Z'm(Z(m)Z) ddl*m+Z+ ddl,m-Z-  e%j\                  e/      Z0 G d dejb                        Z2d Z3 ed      d7d       Z4dejj                  de6dejj                  fdZ7	 d8dejb                  dejj                  dejj                  d ejj                  d!ejj                  dz  d"e8d#e8d$e!e#   fd%Z9 ee4       G d& d'ejb                               Z: G d( d)ejb                        Z; G d* d+e      Z<e$ G d, d-e             Z=e$ G d. d/e=             Z>e$ G d0 d1e=e             Z? G d2 d3ee=      Z@ G d4 d5ee=      ZAg d6ZBy)9    )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logging)can_return_tuplemaybe_autocastmerge_with_config_defaults)capture_outputs   )	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        `/mnt/e/genesis-system/.venv/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    r4   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)r4   rA   )r.   getgetattrhidden_sizenum_attention_headsinttorcharangeint64tofloat)	r#   r4   r9   baser=   r>   dimattention_factorr"   s	            r7   r/   z2PhiRotaryEmbedding.compute_default_rope_parameters7   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
 )))r8   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?   rM   r@   )r"   rK   expandshaperJ   r4   
isinstancetypestrr   	transposerG   catcosr0   sinrA   )
r3   xposition_idsinv_freq_expandedposition_ids_expandedrS   freqsembr]   r^   s
             r7   forwardzPhiRotaryEmbedding.forwardW   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$N)NNN)__name__
__module____qualname__rG   Tensor__annotations__r   r*   staticmethodr   rF   tuplerK   r/   no_gradr   re   __classcell__r6   s   @r7   r!   r!   $   s    llVy V  #'+/"*D *(* t* 
~u$	%	* *> U]]_<  <r8   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..NrP   r?   rU   )rW   rG   r\   )r_   x1x2s      r7   rotate_halfrt   g   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r8   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.
    )	unsqueezert   )qkr]   r^   unsqueeze_dimq_embedk_embeds          r7   apply_rotary_pos_embr}   n   sY    & --
&C
--
&C3w;q>C/0G3w;q>C/0GGr8   hidden_statesn_repr:   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)rW   rV   reshape)r~   r   batchnum_key_value_headsslenr>   s         r7   	repeat_kvr      so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr8   modulequerykeyvalueattention_maskscalingdropoutkwargsc                    t        || j                        }t        || j                        }	t        j                  ||j	                  dd            |z  }
||
|z   }
t
        j                  j                  |
dt        j                        j                  |j                        }
t
        j                  j                  |
|| j                        }
t        j                  |
|	      }|j	                  dd      j                         }||
fS )Nr?   r   rP   )rM   rA   )ptrainingr   )r   num_key_value_groupsrG   matmulr[   nn
functionalsoftmaxfloat32rJ   rA   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightsattn_outputs               r7   eager_attention_forwardr      s     3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!#n4==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r8   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   rC   rD   rE   r>   r   r   r   attention_dropout	is_causalr   Linearq_projk_projv_projdenserF   r.   rotary_ndimsqk_layernorm	LayerNormlayer_norm_epsq_layernormk_layernormr3   r#   r   r6   s      r7   r*   zPhiAttention.__init__   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii 2 2F4N4NQUQ^Q^4^eijii 2 2F4N4NQUQ^Q^4^eijii 2 2F4N4NQUQ^Q^4^eijYYv99DMMI6K]K]dhi
0F0FG^0_ _`"//!||""f&@&@@fF[F[pt D  "||""f&@&@@fF[F[pt D	 r8   Nr~   position_embeddingsr   past_key_valuescache_positionr:   c                 p   |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }| j                  r"| j                  |	      }	| j                  |
      }
|\  }}|	dd | j                  f   |	d| j                  d f   }}|
dd | j                  f   |
d| j                  d f   }}t        ||||      \  }}t        j                  ||fd      }	t        j                  ||fd      }
|'|||d}|j                  |
|| j                  |      \  }
}t!        j"                  | j$                  j&                  t(              } || |	|
||f| j*                  sdn| j,                  | j.                  d|\  }} |j0                  g |d j3                         }| j5                  |      }||fS )	NrP   r   r?   .rU   )r^   r]   r           )r   r   )rW   r>   r   viewr[   r   r   r   r   r   r   r}   rG   r\   updater   r   get_interfacer#   _attn_implementationr   r   r   r   r   r   r   )r3   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                         r7   re   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((r8   )NN)rg   rh   ri   __doc__r   rF   r*   rG   rj   rm   r   
LongTensorre   ro   rp   s   @r7   r   r      s    Gy S 8 )-26;)||;) #5<<#=>;) t+	;)
 ;) ((4/;) 
u||U\\D00	1;)r8   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 rf   )r)   r*   r#   r   
hidden_actactivation_fnr   r   rD   intermediate_sizefc1fc2r3   r#   r6   s     r7   r*   zPhiMLP.__init__  sd    #F$5$5699V//1I1IJ99V55v7I7IJr8   r~   r:   c                 l    | j                  |      }| j                  |      }| j                  |      }|S rf   )r   r   r   )r3   r~   s     r7   re   zPhiMLP.forward  s4    /**=9/r8   )rg   rh   ri   r*   rG   rj   re   ro   rp   s   @r7   r   r     s$    KU\\ ell r8   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   rD   r   input_layernormDropoutresid_pdropresid_dropoutr   s      r7   r*   zPhiDecoderLayer.__init__  s]    %f	B&>!||F,>,>FDYDYZZZ(:(:;r8   Nr~   r   r`   r   output_attentions	use_cacher   r   r:   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   )r3   r~   r   r`   r   r   r   r   r   r   residualattn_outputsself_attn_weightsfeed_forward_hidden_statesoutputss                  r7   re   zPhiDecoderLayer.forward  s     !,,]; +9$.. 
+
')%+/) 3
+
 
+
'' )),7%)%7%78O%P"$'AAHL ")++Gr8   )NNNFFNN)rg   rh   ri   r   rF   r*   rG   rj   r   r   boolrm   FloatTensorre   ro   rp   s   @r7   r   r     s    <y <S < /304(,).!&26HL%||% t+% &&-	%
 %  $;% $;% ((4/% #5<<#=>E% 
u  %(9(95;L;L(L"MPT"TT	U%r8   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)rg   rh   ri   r   rk   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   r8   r7   r   r   E  sQ    &*#*+#4"5N!"&("r8   r   c                   *    e Zd Zdef fdZe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$                        | _        t        j(                  |j                  |j*                        | _        | j/                          y c c}w )Nr#   Fr   )r)   r*   pad_token_idpadding_idx
vocab_sizer   	EmbeddingrD   embed_tokens
ModuleListrangenum_hidden_layersr   layersr!   
rotary_embgradient_checkpointingr   
embd_pdropembed_dropoutr   r   final_layernorm	post_initr   s      r7   r*   zPhiModel.__init__Z  s     !.. ++LL):):F<N<NPTP`P`ammAFvG_G_A`aI_VY/a
 -F;&+#ZZ(9(9:!||F,>,>FDYDYZ 	 bs   D/N	input_idsr   r`   r   inputs_embedsr   r   output_hidden_statesr   r   r:   c
                    ||n| j                   j                  }||n| j                   j                  }||n| j                   j                  }|d u |d uz  rt	        d      | j
                  r%| j                  r|rt        j                  d       d}|| j                  |      }|r|t        | j                         }|	F||j                         nd}t        j                  |||j                  d   z   |j                        }	||	j!                  d      }t#        | j                   |||	||      }| j%                  |      }|}| j'                  ||	      }|rd
nd }|rd
nd }| j(                  d | j                   j*                   D ],  }|r||fz  } ||f||||||	|d|
}|d   }|s$||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   )r4   )r#   r  r   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_lengthrG   rH   rW   r4   rw   r   r  r  r   r   r  r   )r3   r  r   r`   r   r  r   r   r	  r   r   past_seen_tokenscausal_maskr~   r   all_hidden_statesall_self_attnsdecoder_layerlayer_outputss                      r7   re   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+%	
 	
r8   )	NNNNNNNNN)rg   rh   ri   r   r*   r   r   r   rG   r   rj   r   r   r   r   r   r   re   ro   rp   s   @r7   r   r   X  s   y "   .2.204(,26!%)-,026\
##d*\
 t+\
 &&-	\

 \
 ((4/\
 $;\
  $;\
 #Tk\
 ((4/\
 +,\
 
!\
    \
r8   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   rD   r  r  r   s     r7   r*   zPhiForCausalLM.__init__  sU     f%
 ++yy!3!3V5F5FTR 	r8   Nr  r   r`   r   r  labelsr   r   logits_to_keepr   r:   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  rX   rF   slicer  loss_functionr#   r   r   r   r~   r   )r3   r  r   r`   r   r  r  r   r   r  r   r   r~   slice_indicesr  r  s                   r7   re   zPhiForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r8   )	NNNNNNNNr   )rg   rh   ri   _tied_weights_keys_tp_plan_pp_planr*   r   r   rG   r   rj   r   r   r   rF   r   r   r   re   ro   rp   s   @r7   r  r    s/   *,GH23H_-z:;H  .2.204(,26*.!%26-.8
##d*8
 t+8
 &&-	8

 8
 ((4/8
   4'8
 $;8
 ((4/8
 ell*8
 +,8
 
 8
  8
r8   r  c                       e Zd Zy)PhiForSequenceClassificationNrg   rh   ri   r   r8   r7   r'  r'        r8   r'  c                       e Zd Zy)PhiForTokenClassificationNr(  r   r8   r7   r+  r+    r)  r8   r+  )r   r   r  r'  r+  )r   )r   )Ccollections.abcr   typingr   rG   torch.nnr   activationsr   cache_utilsr   r   
generationr	   integrationsr
   r   masking_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   r   utils.output_capturingr   configuration_phir   
get_loggerrg   r  Moduler!   rt   r}   rj   rF   r   rK   r   r   r   r   r   r   r  r'  r+  __all__r   r8   r7   <module>r@     s   %    ! . ) I / 
 P K F & @ @ Y Y 5 ( 
		H	%@< @<F( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%2 )*U)299 U) +U)pRYY -0 -`   $ q
! q
 q
h H
' H
 H
V	#CEW 		 =?Q 	r8   