
    hV                     $   d dl mZmZmZ d dlZd dlmZ ddlmZ ddl	m
Z
mZ ddlmZ ddlmZ ddlmZmZmZ dd	lmZmZ dd
lmZmZ ddlmZmZ ddlmZ ddlm Z m!Z!m"Z"m#Z# ddl$m%Z% ddl&m'Z' ddl(m)Z)  e#jT                  e+      Z,d Z-d4dZ.dej^                  de0dej^                  fdZ1	 d5dejd                  dej^                  dej^                  dej^                  deej^                     de3de3dee    fd Z4 G d! d"ejd                        Z5 G d# d$ejd                        Z6 G d% d&e      Z7 G d' d(ejd                        Z8e! G d) d*e             Z9e! G d+ d,e9             Z:e! G d- d.e9e             Z; G d/ d0ee9      Z< G d1 d2ee9      Z=g d3Z>y)6    )CallableOptionalUnionN   )ACT2FN)CacheDynamicCache)GenerationMixin)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)deprecate_kwarg)check_model_inputs   )	PhiConfigc                     | 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)xx1x2s      b/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/transformers/models/phi/modeling_phi.pyrotate_halfr*   "   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''    c                     |j                  |      }|j                  |      }| |z  t        |       |z  z   }||z  t        |      |z  z   }||fS )a  Applies Rotary Position Embedding to the query and key tensors.

    Args:
        q (`torch.Tensor`): The query tensor.
        k (`torch.Tensor`): The key tensor.
        cos (`torch.Tensor`): The cosine part of the rotary embedding.
        sin (`torch.Tensor`): The sine part of the rotary embedding.
        position_ids (`torch.Tensor`, *optional*):
            Deprecated and unused.
        unsqueeze_dim (`int`, *optional*, defaults to 1):
            The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
            sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
            that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and
            k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes
            cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have
            the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2.
    Returns:
        `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
    )	unsqueezer*   )qkcossinposition_idsunsqueeze_dimq_embedk_embeds           r)   apply_rotary_pos_embr6   )   sY    ( --
&C
--
&C3w;q>C/0G3w;q>C/0GGr+   hidden_statesn_repreturnc                     | j                   \  }}}}|dk(  r| S | dddddddddf   j                  |||||      } | j                  |||z  ||      S )z
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r   N)r#   expandreshape)r7   r8   batchnum_key_value_headsslenhead_dims         r)   	repeat_kvrA   D   so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr+   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   r   )r"   dtype)ptrainingr   )rA   num_key_value_groupsr$   matmul	transposer#   nn
functionalsoftmaxfloat32torL   rH   rN   
contiguous)rB   rC   rD   rE   rF   rG   rH   rI   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r)   eager_attention_forwardr]   P   s    3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#k1==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r+   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j                  eej                     f   fd       Z xZS )PhiAttentionz=Multi-headed attention from 'Attention Is All You Need' paperconfig	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(                  z        | _        |j,                  | _        | j,                  r}t        j.                  |j
                  |j                  z  |j0                  d      | _        t        j.                  |j
                  |j                  z  |j0                  d      | _        y y )Nr@   g      Tbias)epselementwise_affine)super__init__r`   ra   getattrhidden_sizenum_attention_headsr@   r>   rO   rG   attention_dropout	is_causalrR   Linearq_projk_projv_projdenseintpartial_rotary_factorrotary_ndimsqk_layernorm	LayerNormlayer_norm_epsq_layernormk_layernormselfr`   ra   	__class__s      r)   rh   zPhiAttention.__init__m   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii 2 2F4N4NQUQ^Q^4^eijii 2 2F4N4NQUQ^Q^4^eijii 2 2F4N4NQUQ^Q^4^eijYYv99DMMI6K]K]dhi
0L0L LM"//!||""f&@&@@fF[F[pt D  "||""f&@&@@fF[F[pt D	 r+   past_key_valuepast_key_values4.58new_nameversionr7   position_embeddingsrF   cache_positionr9   c                    |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }| j                  r"| j                  |	      }	| j                  |
      }
|\  }}|	dd | j                  f   |	d| j                  d f   }}|
dd | j                  f   |
d| j                  d f   }}t        ||||      \  }}t        j                  ||fd      }	t        j                  ||fd      }
|'|||d}|j                  |
|| j                  |      \  }
}t         }| j"                  j$                  dk7  rt&        | j"                  j$                     } || |	|
||f| j(                  sdn| j*                  | j,                  d	|\  }} |j.                  g |d j1                         }| j3                  |      }||fS )
Nr   r   r    .r!   )r1   r0   r   eager        )rH   rG   )r#   r@   ro   viewrQ   rp   rq   rv   ry   rz   ru   r6   r$   r%   updatera   r]   r`   _attn_implementationr   rN   rl   rG   r<   rW   rr   )r|   r7   r   rF   r   r   rI   input_shapehidden_shapequery_statesrX   rY   r0   r1   	query_rot
query_passkey_rotkey_passcache_kwargsattention_interfacer\   rZ   s                         r)   forwardzPhiAttention.forward   so    $))#2.88b8$--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$J(?;;++w6"9$++:Z:Z"[$7	%
  $}}C$2H2HLL	%
 	%
!\ *k));;;;FFHjj-L((r+   )NN)__name__
__module____qualname____doc__r   rs   rh   r   r$   Tensortupler   r   
LongTensorr   __classcell__r}   s   @r)   r_   r_   j   s    Gy S . %0A6R ,059;)||;) #5<<#=>;) !.	;)
 "%;) !!1!12;) 
u||Xell33	4;) S;)r+   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 N)rg   rh   r`   r   
hidden_actactivation_fnrR   rn   rj   intermediate_sizefc1fc2r|   r`   r}   s     r)   rh   zPhiMLP.__init__   sd    #F$5$5699V//1I1IJ99V55v7I7IJr+   r7   r9   c                 l    | j                  |      }| j                  |      }| j                  |      }|S r   )r   r   r   )r|   r7   s     r)   r   zPhiMLP.forward   s4    /**=9/r+   )r   r   r   rh   r$   r   r   r   r   s   @r)   r   r      s$    KU\\ ell r+   r   c                       e Zd Zdedef fdZ eddd      	 	 	 	 	 	 	 ddej                  d	e	ej                     d
e	ej                     de	eej                        de	e   de	e   de	ej                     de	eej                  ej                  f      deej                  e	eej                  ej                  f      f   fd       Z xZS )PhiDecoderLayerr`   ra   c                    t         |           t        ||      | _        t	        |      | _        t        j                  |j                  |j                        | _
        t        j                  |j                        | _        y )N)ra   re   )rg   rh   r_   	self_attnr   mlprR   rw   rj   rx   input_layernormDropoutresid_pdropresid_dropoutr{   s      r)   rh   zPhiDecoderLayer.__init__   s]    %f	B&>!||F,>,>FDYDYZZZ(:(:;r+   r~   r   r   r   r7   rF   r2   output_attentions	use_cacher   r   r9   c	                     |}
| j                  |      } | j                  d||||||||d|	\  }}| j                  |      }| j                  | j                  |            }||z   |
z   }|f}|r||fz  }|S )N)r7   rF   r2   r   r   r   r   r    )r   r   r   r   )r|   r7   rF   r2   r   r   r   r   r   rI   residualattn_outputsself_attn_weightsfeed_forward_hidden_statesoutputss                  r)   r   zPhiDecoderLayer.forward   s     !,,]; +9$.. 
+
')%+/) 3
+
 
+
'' )),7%)%7%78O%P"$'AAHL ")++Gr+   )NNNFFNN)r   r   r   r   rs   rh   r   r$   r   r   r   r   boolFloatTensorr   r   r   s   @r)   r   r      s    <y <S < %0A6R 26379=,1$)59KO%||% !.% u//0	%
 "%"56% $D>% D>% !!1!12% &eELL%,,,F&GH% 
u  (51B1BEDUDU1U+V"WW	X% S%r+   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 )PhiRotaryEmbeddinginv_freqr`   c                    t         |           t        |d      rUt        |j                  t
              r;|j                  j                  d|j                  j                  d            | _        nd| _        |j                  | _	        |j                  | _
        || _        t        | j                     | _        | j                  | j                  |      \  }| _        | j                  d|d       | j                   | _        y )Nrope_scaling	rope_typetypedefaultr   F)
persistent)rg   rh   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)r|   r`   devicer   r}   s       r)   rh   zPhiRotaryEmbedding.__init__  s    6>*z&:M:Mt/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r+   c                 b   | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        j                  |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        j	                  |j                   
      	j	                  |j                   
      fS # 1 sw Y   AxY w)Nr   r   r   mpscpuF)device_typeenabledr    r!   )rL   )r   floatr;   r#   rV   r   r   r   strr$   autocastrQ   r%   r0   r   r1   rL   )
r|   r&   r2   inv_freq_expandedposition_ids_expandedr   freqsembr0   r1   s
             r)   r   zPhiRotaryEmbedding.forward  sV    !MM$4-8>>@GGHZHZ[\H]_acdehhijiqiqr ,QaZ 8 > > @'1!((--'E!((--[`J`ahhmmfk^^UC 	5&,,.1F1L1L1NNYYZ[]^_E))UEN3C'')d444C'')d444C		5 vvAGGv$cff177f&;;;	5 	5s    BF%%F.r   )r   r   r   r$   r   __annotations__r   rh   no_gradr   r   r   r   s   @r)   r   r     s=    ll/y /" U]]_<  <r+   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   )r7   
attentionsN)r   r   r   r   r   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   r+   r)   r   r   '  sQ    &*#*+#4"5N!"&("r+   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   d
ee   deej                     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$                        | _        t        j(                  |j                  |j*                        | _        | j/                          y c c}w )Nr`   Fr   )rg   rh   pad_token_idpadding_idx
vocab_sizerR   	Embeddingrj   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   
rotary_embgradient_checkpointingr   
embd_pdropembed_dropoutrw   rx   final_layernorm	post_initr{   s      r)   rh   zPhiModel.__init__<  s     !.. ++LL):):F<N<NPTP`P`ammAFvG_G_A`aI_VY/a
 -F;&+#ZZ(9(9:!||F,>,>FDYDYZ 	 bs   D/	input_idsrF   r2   r   inputs_embedsr   r   output_hidden_statesr   rI   r9   c
                    ||n| j                   j                  }||n| j                   j                  }||n| j                   j                  }|d u |d uz  rt	        d      | j
                  r%| j                  r|rt        j                  d       d}|| j                  |      }|r|t        | j                         }|	F||j                         nd}t        j                  |||j                  d   z   |j                        }	||	j!                  d      }t#        | j                   |||	||      }| j%                  |      }|}| j'                  ||      }|rd	nd }|rd	nd }| j(                  d | j                   j*                   D ],  }|r||fz  } ||f||||||	|d
|
}|d   }|s$||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   )r   )r`   input_embedsrF   r   r   r2   r   )rF   r2   r   r   r   r   r   )last_hidden_stater   r7   r   )r`   r   r  r   
ValueErrorr   rN   loggerwarning_oncer   r	   get_seq_lengthr$   aranger#   r   r-   r   r   r   r   r   r  r   )r|   r  rF   r2   r   r  r   r   r  r   rI   past_seen_tokensr[   r7   r   all_hidden_statesall_self_attnsdecoder_layerlayer_outputss                      r)   r   zPhiModel.forwardM  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\J #7BD0d![[)H4;;+H+HI 	6M#!m%55!)
*) /"3#-$7
 
M *!,M =#3"55'	6* ,,];  -!11&+/8Od+%	
 	
r+   )	NNNNNNNNN)r   r   r   r   rh   r   r   r   r$   r   r   r   r   r   r   r   r   r   r   r   s   @r)   r   r   :  s   y "  151537+/59$(,0/359^
E,,-^
 !.^
 u//0	^

 "%^
   1 12^
 D>^
 $D>^
 'tn^
 !!1!12^
 +,^
 
!^
  ^
r+   r   c                   d    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 )PhiForCausalLMzlm_head.weightlm_headcolwise_repr7   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y )NTrc   )
rg   rh   r   r   r   rR   rn   rj   r  r  r   s     r)   rh   zPhiForCausalLM.__init__  sU     f%
 ++yy!3!3V5F5FTR 	r+   r  rF   r2   r   r  labelsr   r   logits_to_keeprI   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  rF   r2   r   r  r   r   N)r  r  r   )lossr  r   r7   r   r   )r   r  r   rs   slicer  loss_functionr`   r   r   r   r7   r   )r|   r  rF   r2   r   r  r  r   r   r  rI   r   r7   slice_indicesr  r  s                   r)   r   zPhiForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r+   )	NNNNNNNNr   )r   r   r   _tied_weights_keys_tp_plan_pp_planrh   r   r   r   r$   r   r   r   r   r   r   rs   r   r   r   r   r   r   s   @r)   r  r    s0   *+=)H_-z:;H  151537+/59-1$(59348
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 ))*8
 D>8
 !!1!128
 c5<</08
 +,8
 
 8
  8
r+   r  c                       e Zd Zy)PhiForSequenceClassificationNr   r   r   r   r+   r)   r$  r$        r+   r$  c                       e Zd Zy)PhiForTokenClassificationNr%  r   r+   r)   r(  r(     r&  r+   r(  )r   r   r  r$  r(  )Nr   )r   )?typingr   r   r   r$   torch.nnrR   activationsr   cache_utilsr   r	   
generationr
   masking_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   utils.deprecationr   utils.genericr   configuration_phir   
get_loggerr   r
  r*   r6   r   rs   rA   Moduler   r]   r_   r   r   r   r   r   r  r$  r(  __all__r   r+   r)   <module>r;     s   - ,   ! . ) / 
 P K F & R R 0 / ( 
		H	%(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4V)299 V)rRYY .0 .b!< !<H   $ r
! r
 r
j H
' H
 H
V	#CEW 		 =?Q 	r+   