
    Uh                        d dl mZ d dlmZ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! ddl"m#Z#m$Z$m%Z%m&Z&m'Z' ddl(m)Z)  e&       rd dl*m+Z+ ddl,m-Z-  e'j\                  e/      Z0d Z1d8dZ2dejf                  de4dejf                  fdZ5	 d9de	jl                  dejf                  dejf                  dejf                  deejf                     de7de7fd Z8 G d! d"e	jl                        Z9 G d# d$e	jl                        Z: G d% d&e	jl                        Z; G d' d(e	jl                        Z<e$ G d) d*e             Z=e$ G d+ d,e=             Z> G d- d.ee#      Z?e$ G d/ d0e=e             Z@ e$d12       G d3 d4e=             ZAe$ G d5 d6e=             ZBg d7ZCy):    )partial)CallableOptionalTupleUnionN   )ACT2FN)CacheDynamicCache)GenerationMixin)AttentionMaskConverter)FlashAttentionKwargs)BaseModelOutputWithPastCausalLMOutputWithPast SequenceClassifierOutputWithPastTokenClassifierOutput)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)
LossKwargsauto_docstringcan_return_tupleis_torch_flex_attn_availablelogging   )	PhiConfig)	BlockMask)make_flex_block_causal_maskc                     | 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      v/var/www/catia.catastroantioquia-mas.com/valormas/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_embr9   /   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)r:   r;   batchnum_key_value_headsslenhead_dims         r,   	repeat_kvrD   J   so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr.   modulequerykeyvalueattention_maskscalingdropoutc                 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   )rD   num_key_value_groupsr'   matmul	transposer&   nn
functionalsoftmaxfloat32torN   rK   rP   
contiguous)rE   rF   rG   rH   rI   rJ   rK   kwargs
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r,   eager_attention_forwardr`   V   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	 	 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                     e
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 )NrC   g      Tbias)epselementwise_affine)super__init__rc   rd   getattrhidden_sizenum_attention_headsrC   rA   rQ   rJ   attention_dropout	is_causalrT   Linearq_projk_projv_projdenseintpartial_rotary_factorrotary_ndimsqk_layernorm	LayerNormlayer_norm_epsq_layernormk_layernormselfrc   rd   	__class__s      r,   rk   zPhiAttention.__init__s   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii 2 2F4N4NQUQ^Q^4^eijii 2 2F4N4NQUQ^Q^4^eijii 2 2F4N4NQUQ^Q^4^eijYYv99DMMI6K]K]dhi
0L0L LM"//!||""f&@&@@fF[F[pt D  "||""f&@&@@fF[F[pt D	 r.   r:   position_embeddingsrI   past_key_valuecache_positionr<   c                    |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }| j                  r"| j                  |	      }	| j                  |
      }
|\  }}|	dd | j                  f   |	d| j                  d f   }}|
dd | j                  f   |
d| j                  d f   }}t        ||||      \  }}t        j                  ||fd      }	t        j                  ||fd      }
|'|||d}|j                  |
|| j                  |      \  }
}t         }| j"                  j$                  dk7  r^| j"                  j$                  dk(  r(|j'                  d	d
      rt(        j+                  d       nt,        | j"                  j$                     } || |	|
||f| j.                  sdn| j0                  | j2                  d|\  }} |j4                  g |d j7                         }| j9                  |      }||fS )Nr"   r   r#   .r$   )r4   r3   r   eagersdpaoutput_attentionsFz`torch.nn.functional.scaled_dot_product_attention` does not support `output_attentions=True`. Falling back to eager attention. This warning can be removed using the argument `attn_implementation="eager"` when loading the model.        )rK   rJ   )r&   rC   rr   viewrS   rs   rt   ry   r|   r}   rx   r9   r'   r(   updaterd   r`   rc   _attn_implementationgetloggerwarning_oncer   rP   ro   rJ   r?   rY   ru   )r   r:   r   rI   r   r   rZ   input_shapehidden_shapequery_statesr[   r\   r3   r4   	query_rot
query_passkey_rotkey_passcache_kwargsattention_interfacer_   r]   s                         r,   forwardzPhiAttention.forward   s    $))#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'5'<'<ZW[WeWegs't$J(?;;++w6{{//69fjjI\^c>d##L
 '>dkk>^>^&_#$7	%
  $}}C$2H2HLL	%
 	%
!\ *k));;;;FFHjj-L((r.   )NN)__name__
__module____qualname____doc__r   rv   rk   r'   Tensorr   r   r
   
LongTensorr   __classcell__r   s   @r,   rb   rb   p   s    Gy S 8 +/59A)||A) #5<<#=>A) !.	A)
 !A) !!1!12A) 
u||Xell3XeELL>Q5RR	SA)r.   rb   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)rj   rk   rc   r	   
hidden_actactivation_fnrT   rq   rm   intermediate_sizefc1fc2r   rc   r   s     r,   rk   zPhiMLP.__init__   sd    #F$5$5699V//1I1IJ99V55v7I7IJr.   r:   r<   c                 l    | j                  |      }| j                  |      }| j                  |      }|S r   )r   r   r   )r   r:   s     r,   r   zPhiMLP.forward   s4    /**=9/r.   )r   r   r   rk   r'   r   r   r   r   s   @r,   r   r      s$    KU\\ ell r.   r   c                       e Zd Zdedef fdZ	 	 	 	 	 	 	 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 )PhiDecoderLayerrc   rd   c                    t         |           t        ||      | _        t	        |      | _        t        j                  |j                  |j                        | _
        t        j                  |j                        | _        y )N)rd   rh   )rj   rk   rb   	self_attnr   mlprT   rz   rm   r{   input_layernormDropoutresid_pdropresid_dropoutr~   s      r,   rk   zPhiDecoderLayer.__init__   s]    %f	B&>!||F,>,>FDYDYZZZ(:(:;r.   r:   rI   r5   r   r   	use_cacher   r   r<   c	                     |}
| j                  |      } | j                  d||||||||d|	\  }}| j                  |      }| j                  | j                  |            }||z   |
z   }|f}|r||fz  }|S )N)r:   rI   r5   r   r   r   r   r    )r   r   r   r   )r   r:   rI   r5   r   r   r   r   r   rZ   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   rv   rk   r'   r   r   r   r   boolFloatTensorr   r   r   s   @r,   r   r      s   <y <S < 26378<,1$)59KO%||% !.% u//0	%
 !u||!45% $D>% D>% !!1!12% &eELL%,,,F&GH% 
u  (51B1BEDUDU1U+V"WW	X%r.   r   c                   ^     e Zd Zddef fdZ ej                         ed               Z xZ	S )PhiRotaryEmbeddingrc   c                    t         |           t        |d      rG|j                  ;|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defaultinv_freqF)
persistent)rj   rk   hasattrr   r   r   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrc   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r   rc   devicer   r   s       r,   rk   zPhiRotaryEmbedding.__init__  s    6>*v/B/B/N#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$   )rN   )r   floatr>   r&   rX   r   
isinstancer   strr'   autocastrS   r(   r3   r   r4   rN   )
r   r)   r5   inv_freq_expandedposition_ids_expandedr   freqsembr3   r4   s
             r,   r   zPhiRotaryEmbedding.forward  sV    !MM$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   rk   r'   no_gradr   r   r   r   s   @r,   r   r     s3    /y /" U]]_<  <r.   r   c                   F    e Zd ZeZdZdZdgZdgZdZ	dZ
dZdZdZdZdZd Zy)PhiPreTrainedModelmodelTr   past_key_valuesc                    | j                   j                  }t        |t        j                        rY|j
                  j                  j                  d|       |j                  %|j                  j                  j                          y y t        |t        j                        rf|j
                  j                  j                  d|       |j                  2|j
                  j                  |j                     j                          y y t        |t        j                        rJ|j
                  j                  j                  d       |j                  j                  j                          y y )Nr   )meanstdg      ?)rc   initializer_ranger   rT   rq   weightdatanormal_rg   zero_	Embeddingpadding_idxrz   fill_)r   rE   r   s      r,   _init_weightsz PhiPreTrainedModel._init_weights>  s    kk++fbii(MM&&CS&9{{&  &&( '-MM&&CS&9!!-""6#5#56<<> .-MM$$S)KK""$ .r.   N)r   r   r   r   config_classbase_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_2_supports_sdpa_supports_flex_attn_supports_cache_class_supports_quantized_cache_supports_static_cache_supports_attention_backendr   r   r.   r,   r   r   /  sS    L&*#*+#4"5!N  $!"&%r.   r   c                       e Zd Zdef fdZd Zd Zee	 	 	 	 	 	 	 	 	 dde	e
j                     de	e
j                     de	e
j                     de	e   d	e	e
j                     d
e	e   de	e   de	e   de	e
j                     dee   defd              Z	 ddee
j                  df   de
j                  de
j                  dedef
dZede
j                  dedede
j0                  de
j                  defd       Z xZS )PhiModelrc   c           	      h   t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |      | _        d| _        t        j"                  |j$                        | _        t        j(                  |j                  |j*                        | _        | j/                          y c c}w )N)rc   Fr   )rj   rk   pad_token_idr   
vocab_sizerT   r   rm   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   
rotary_embgradient_checkpointingr   
embd_pdropembed_dropoutrz   r{   final_layernorm	post_initr~   s      r,   rk   zPhiModel.__init__O  s     !.. ++LL):):F<N<NPTP`P`ammAFvG_G_A`aI_VY/a
 -F;&+#ZZ(9(9:!||F,>,>FDYDYZ 	 bs   D/c                     | j                   S r   r  r   s    r,   get_input_embeddingszPhiModel.get_input_embeddings`  s       r.   c                     || _         y r   r  r   rH   s     r,   set_input_embeddingszPhiModel.set_input_embeddingsc  s
    !r.   	input_idsrI   r5   r   inputs_embedsr   r   output_hidden_statesr   flash_attn_kwargsr<   c
                 4   ||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               }|	F||j                         nd}t        j                  |||j                  d   z   |j                        }	||	j!                  d      }| j#                  |||	||      }| j%                  |      }|}| j'                  ||      }|rdnd }|rdnd }| j(                  d | j                   j*                   D ]r  }|r||fz  }| j
                  r:| j                  r.| j-                  t/        |j0                  fi |
|||||||	|	      }n ||f||||||	|d|
}|d   }|sj||d   fz  }t | j3                  |      }|r||fz  }t5        ||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   )rI   r5   r   r   r   r   r   )last_hidden_stater   r:   
attentions)rc   r   r  r   
ValueErrorr  rP   r   r   r  r   get_seq_lengthr'   aranger&   r   r0   _update_causal_maskr	  r  r  r  _gradient_checkpointing_funcr   __call__r
  r   )r   r  rI   r5   r   r  r   r   r  r   r  past_seen_tokensr^   r:   r   all_hidden_statesall_self_attnsdecoder_layerlayer_outputss                      r,   r   zPhiModel.forwardf  s    2C1N-TXT_T_TqTq$8$D $++JjJj 	 "+!6IDKK<Q<Q	-t";<YZZ&&4==Yj I  --i8M0*nO!CRC^==?de"\\ "2]5H5H5K"KTaThThN )33A6L..M>?L]
 **=9% #oom\J #7BD0d![[)H4;;+H+HI  	6M#!m%55!**t}} $ A AM22H6GH! #%"'
! !.!
!#.!-#2&7'#1(;
! (
! *!,M =#3"55A 	6D ,,];  -!11&+/8Od+%	
 	
r.   r   input_tensorc           	         | j                   j                  dk(  r||dk(  j                         r|S y | j                   j                  dk(  r't        |t        j
                        rt        |      }|S ||j                         nd}||j                  nd}| j                   j                  dk(  r(|s&|s$t        j                  |||| j                        ry |j                  }|j                  d   }	|r|j                         }
n1t        |t        j
                        r|j                  d	   n||	z   dz   }
| j                  ||	|
|||j                  d   
      }| j                   j                  dk(  rQ|O|j                   j"                  dv r7|s5t	        j$                  |      j&                  }t        j(                  ||      }|S )Nflash_attention_2r   flex_attentionr   Fr   )r  past_key_values_lengthis_trainingr   r"   )sequence_lengthtarget_lengthrN   r   
batch_size)cudaxpunpu)rc   r   anyr   r'   r   r    r  is_compileabler   _ignore_causal_mask_sdparP   rN   r&   get_max_cache_shape5_prepare_4d_causal_attention_mask_with_cache_positionr   r   finfomin_unmask_unattended)r   rI   r&  r   r   r   r!  using_compilable_cacherN   r,  r-  r^   	min_dtypes                r,   r  zPhiModel._update_causal_mask  s    ;;++/BB)~/D.I.I.K%%;;++/??.%,,7!<^!L!!
 @O?Z?99;`aCRC^!?!?di ;;++v5>T]n%>>*'7 MM	 ""&,,Q/!+??AM nell; $$R(%7!;  PP+')#))!, Q 
 KK,,6*%%**.DD%
 E*..I0CCKQZ[Kr.   r,  r-  rN   r.  c                    | | j                         dk(  r| }|S t        j                  |      j                  }t        j                  ||f|||j
                        }|dk7  rt        j                  |d      }|t        j                  ||j
                        |j                  dd      kD  z  }|ddddddf   j                  |ddd      }| |j                         }| j                  d   }	|ddddddd|	f   | ddddddf   j                  |j
                        z   }
|
dk(  }
|ddddddd|	f   j                  |
|      |ddddddd|	f<   |S )	aM  
        Creates a causal 4D mask of shape `(batch_size, 1, query_length, key_value_length)` from a 2D mask of shape
        `(batch_size, key_value_length)`, or if the input `attention_mask` is already 4D, do nothing.

        Args:
            attention_mask (`torch.Tensor`):
                A 2D attention mask of shape `(batch_size, key_value_length)` or a 4D attention mask of shape
                `(batch_size, 1, query_length, key_value_length)`.
            sequence_length (`int`):
                The sequence length being processed.
            target_length (`int`):
                The target length: when generating with static cache, the mask should be as long as the static cache,
                to account for the 0 padding, the part of the cache that is not filled yet.
            dtype (`torch.dtype`):
                The dtype to use for the 4D attention mask.
            cache_position (`torch.Tensor`):
                Indices depicting the position of the input sequence tokens in the sequence.
            batch_size (`torch.Tensor`):
                Batch size.
        N   )
fill_valuerN   r   r   )diagonalr  r"   r   )r%   r'   r7  r8  fullr   triur  r?   r>   cloner&   rX   masked_fill)rI   r,  r-  rN   r   r.  rZ   r^   r;  mask_lengthpadding_masks              r,   r6  z>PhiModel._prepare_4d_causal_attention_mask_with_cache_position  s   < %.*<*<*>!*C(K* ' E*..I** -0Ye\j\q\qK !##jjqA5<<n>S>STWeWmWmnprsWtttK%dD!Q&67>>z1bRTUK))//1,2226*1aL[L+@ANSTVZ\`bcScDdDgDg&&E    ,q05@Aq,;,AV5W5c5c )6Aq!\k\12 r.   	NNNNNNNNN)F)r   r   r   r   rk   r  r  r   r   r   r'   r   r   r
   r   r   r   r   r   r   r   r  staticmethodrv   rN   r6  r   r   s   @r,   r   r   M  s   y "!"  151537+/59$(,0/359f
E,,-f
 !.f
 u//0	f

 "%f
   1 12f
 D>f
 $D>f
 'tnf
 !!1!12f
 $$89f
 
!f
  f
\ #(BellK78B llB 	B
 B  BH 444 4 {{	4
 4 4 4r.   r   c                       e Zd Zy)KwargsForCausalLMN)r   r   r   r   r.   r,   rI  rI  L  s    r.   rI  c                       e Zd ZdgZddiZddgdgfiZ fdZd Zd Zd	 Z	d
 Z
d Zd Zee	 	 	 	 	 	 	 	 	 	 	 ddeej"                     deej$                     deej"                     dee   deej(                     deej"                     dee   dee   dee   deej"                     deeej$                  f   dee   defd              Z xZS )PhiForCausalLMzlm_head.weightlm_headcolwise_repr:   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y )NTrf   )
rj   rk   r   r   r   rT   rq   rm   rL  r  r   s     r,   rk   zPhiForCausalLM.__init__U  sU     f%
 ++yy!3!3V5F5FTR 	r.   c                 .    | j                   j                  S r   r   r  r  s    r,   r  z#PhiForCausalLM.get_input_embeddings^      zz&&&r.   c                 &    || j                   _        y r   rQ  r  s     r,   r  z#PhiForCausalLM.set_input_embeddingsa      "'

r.   c                     | j                   S r   rL  r  s    r,   get_output_embeddingsz$PhiForCausalLM.get_output_embeddingsd  s    ||r.   c                     || _         y r   rV  )r   new_embeddingss     r,   set_output_embeddingsz$PhiForCausalLM.set_output_embeddingsg  s	    %r.   c                     || _         y r   r   )r   decoders     r,   set_decoderzPhiForCausalLM.set_decoderj  s	    
r.   c                     | j                   S r   r\  r  s    r,   get_decoderzPhiForCausalLM.get_decoderm  s    zzr.   r  rI   r5   r   r  labelsr   r   r  r   logits_to_keeprZ   r<   c                    ||n| j                   j                  }|	|	n| j                   j                  }	 | 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 )ah  
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
            config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
            (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

        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."
        ```N)	r  rI   r5   r   r  r   r   r  r   )rN  ra  r   lossrN  r   r:   r  r   )rc   r   r  r   r  r   rv   slicerL  loss_functionr   r   r   r:   r  )r   r  rI   r5   r   r  ra  r   r   r  r   rb  rZ   r   r:   slice_indicesrN  re  s                     r,   r   zPhiForCausalLM.forwardp  s   N 2C1N-TXT_T_TqTq$8$D $++JjJj 	
 ,64:: ,
)%+'/!5),
 ,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r.   )NNNNNNNNNNr   )r   r   r   _tied_weights_keys_tp_plan_pp_planrk   r  r  rW  rZ  r^  r`  r   r   r   r'   r   r   r
   r   r   r   rv   r   rI  r   r   r   r   s   @r,   rK  rK  O  s   *+=)H_-z:;H'(&  151537+/59-1$(,0/35934G
E,,-G
 !.G
 u//0	G

 "%G
   1 12G
 ))*G
 D>G
 $D>G
 'tnG
 !!1!12G
 c5<</0G
 *+G
 
 G
  G
r.   rK  a  
    The Phi Model transformer with a sequence classification head on top (linear layer).

    [`PhiForSequenceClassification`] uses the last token in order to do the classification, as other causal models
    (e.g. GPT-2) do.

    Since it does classification on the last token, it requires to know the position of the last token. If a
    `pad_token_id` is defined in the configuration, it finds the last token that is not a padding token in each row. If
    no `pad_token_id` is defined, it simply takes the last value in each row of the batch. Since it cannot guess the
    padding tokens when `inputs_embeds` are passed instead of `input_ids`, it does the same (take the last value in
    each row of the batch).
    )custom_introc                       e Zd Z fdZd Z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e   defd              Z xZS )PhiForSequenceClassificationc                     t         |   |       |j                  | _        t        |      | _        t        j                  |j                  | j                  d      | _        | j                          y )NFrf   )
rj   rk   
num_labelsr   r   rT   rq   rm   scorer  r   s     r,   rk   z%PhiForSequenceClassification.__init__  sS      ++f%
YYv114??O
 	r.   c                 .    | j                   j                  S r   rQ  r  s    r,   r  z1PhiForSequenceClassification.get_input_embeddings  rR  r.   c                 &    || j                   _        y r   rQ  r  s     r,   r  z1PhiForSequenceClassification.set_input_embeddings  rT  r.   r  rI   r5   r   r  ra  r   r   r  r<   c
           
         | j                  ||||||||	      }
|
j                  }| j                  |      }||j                  d   }n|j                  d   }| j                  j
                  |dk7  rt        d      | j                  j
                  d}n||| j                  j
                  k7  j                  |j                  t        j                        }t        j                  |j                  d   |j                  t        j                        }||z  j                  d      }n.d}t        j                  | j                  j                    d       |t        j                  ||j                  	      |f   }d}|| j#                  |||| j                  
      }t%        |||
j&                  |
j(                  |
j*                        S )  
        labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
            Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
            config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
            `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
        rI   r5   r   r  r   r   r  Nr   r   z=Cannot handle batch sizes > 1 if no padding token is defined.r"   )r   rN   z will not detect padding tokens in `inputs_embeds`. Results may be unexpected if using padding tokens in conjunction with `inputs_embeds.`r  )rN  ra  pooled_logitsrc   rd  )r   r  rq  r&   rc   r   r  rX   r   r'   int32r  argmaxr   r   r   r   rg  r   r   r:   r  )r   r  rI   r5   r   r  ra  r   r   r  transformer_outputsr:   rN  r.  last_non_pad_tokennon_pad_masktoken_indicesrw  re  s                      r,   r   z$PhiForSequenceClassification.forward  s   * 8<zz)%+'/!5 8B 	8
 ,==M* "+J&,,Q/J;;##+
a\]];;##+!#"%)A)AAEEfmmUZU`U`aL!LL)<V]]Z_ZeZefM"/,">!F!Fr!J!#>>**+ ,Z Z
 u||Jv}}MOaab%%VFR_hlhshs%tD/ /??-;;*55
 	
r.   rF  )r   r   r   rk   r  r  r   r   r   r'   r   r   r
   r   r   r   r   r   r   s   @r,   rn  rn    s    '(  151537+/59-1$(,0/3A
E,,-A
 !.A
 u//0	A

 "%A
   1 12A
 ))*A
 D>A
 $D>A
 'tnA
 
*A
  A
r.   rn  c                       e Zd Z fdZd Zd Zee	 	 	 	 	 	 	 	 	 ddee	j                     dee	j                     dee	j                     dee   dee	j                     d	ee	j                     d
ee   dee   dee   defd              Z xZS )PhiForTokenClassificationc                    t         |   |       |j                  | _        t        |      | _        t        |dd       |j                  }nt        |dd       |j                  }nd}t        j                  |      | _
        t        j                  |j                  |j                        | _        | j                          y )Nclassifier_dropouthidden_dropoutg?)rj   rk   rp  r   r   rl   r  r  rT   r   rK   rq   rm   rq  r  )r   rc   r  r   s      r,   rk   z"PhiForTokenClassification.__init__"  s      ++f%
6/6B!'!:!:V-t4@!'!6!6!$zz"45YYv1163D3DE
 	r.   c                 .    | j                   j                  S r   rQ  r  s    r,   r  z.PhiForTokenClassification.get_input_embeddings2  rR  r.   c                 &    || j                   _        y r   rQ  r  s     r,   r  z.PhiForTokenClassification.set_input_embeddings5  rT  r.   r  rI   r5   r   r  ra  r   r   r  r<   c
           
         | j                  ||||||||	      }
|
j                  }| j                  |      }| j                  |      }d}|| j	                  ||| j
                        }t        |||
j                  |
j                        S )ru  rv  N)re  rN  r:   r  )	r   r  rK   rq  rg  rc   r   r:   r  )r   r  rI   r5   r   r  ra  r   r   r  r   sequence_outputrN  re  s                 r,   r   z!PhiForTokenClassification.forward8  s    * ,0::)%+'/!5 ,6 	,
 "33,,7O,%%ffdkkBD$!//))	
 	
r.   rF  )r   r   r   rk   r  r  r   r   r   r'   r   r   r
   r   r   r   r   r   r   s   @r,   r  r     s     '(  151537+/59-1$(,0/3*
E,,-*
 !.*
 u//0	*

 "%*
   1 12*
 ))**
 D>*
 $D>*
 'tn*
 
*
  *
r.   r  )r   r   rK  rn  r  )Nr   )r   )D	functoolsr   typingr   r   r   r   r'   torch.nnrT   activationsr	   cache_utilsr
   r   
generationr   modeling_attn_mask_utilsr   modeling_flash_attention_utilsr   modeling_outputsr   r   r   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   r   configuration_phir   !torch.nn.attention.flex_attentionr   integrations.flex_attentionr    
get_loggerr   r   r-   r9   r   rv   rD   Moduler   r`   rb   r   r   r   r   r   rI  rK  rn  r  __all__r   r.   r,   <module>r     s    3 3   ! . ) > B  L F & h h (  !;J 
		H	%(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % %4[)299 [)|RYY -bii -`< <D % % %: {! { {| ?,j > i
' i
 i
X S
#5 S
S
l C
 2 C
 C
Lr.   