
    hZ                     X   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	 ddl
mZm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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* ddl+m,Z,  G d dejZ                        Z.d Z/dej`                  de1dej`                  fdZ2	 d:dejZ                  dej`                  dej`                  dej`                  d eej`                     d!e3d"e3d#e$e&   fd$Z4d;d%Z5 G d& d'ejZ                        Z6 ed(       G d) d*ejZ                               Z7 G d+ d,e      Z8e' G d- d.e"             Z9 G d/ d0ejZ                        Z:e' G d1 d2e9             Z;e' G d3 d4e9e             Z< G d5 d6ee9      Z= G d7 d8ee9      Z>g d9Z?y)<    )CallableOptionalUnionN)nn)check_model_inputs   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)deprecate_kwarg   )
Phi3Configc                   V     e Zd Z fdZdej
                  dej
                  fdZ xZS )Phi3MLPc                 *   t         |           || _        t        j                  |j
                  d|j                  z  d      | _        t        j                  |j                  |j
                  d      | _        t        |j                     | _        y )N   Fbias)super__init__configr   Linearhidden_sizeintermediate_sizegate_up_proj	down_projr	   
hidden_actactivation_fnselfr)   	__class__s     d/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/transformers/models/phi3/modeling_phi3.pyr(   zPhi3MLP.__init__3   sp    IIf&8&8!f>V>V:V]bc6#;#;V=O=OV[\#F$5$56    hidden_statesreturnc                     | j                  |      }|j                  dd      \  }}|| j                  |      z  }| j                  |      S )Nr$   dim)r-   chunkr0   r.   )r2   r6   	up_statesgates       r4   forwardzPhi3MLP.forward;   sL    %%m4	#//!/4i 2 24 88	~~i((r5   )__name__
__module____qualname__r(   torchFloatTensorr?   __classcell__r3   s   @r4   r"   r"   2   s'    7)U%6%6 )5;L;L )r5   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..Nr9   r$   r:   )shaperC   cat)xx1x2s      r4   rotate_halfrM   D   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r5   r6   n_repr7   c                     | j                   \  }}}}|dk(  r| S | dddddddddf   j                  |||||      } | j                  |||z  ||      S )z
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r   N)rH   expandreshape)r6   rN   batchnum_key_value_headsslenhead_dims         r4   	repeat_kvrV   K   so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr5   modulequerykeyvalueattention_maskscalingdropoutkwargsc                 T   t        || j                        }t        || j                        }	t        j                  ||j	                  dd            |z  }
|#|d d d d d d d |j
                  d   f   }|
|z   }
t        j                  j                  |
dt        j                        j                  |j                        }
t        j                  j                  |
|| j                        }
t        j                  |
|	      }|j	                  dd      j                         }||
fS )Nr$   r   r9   )r;   dtype)ptrainingr   )rV   num_key_value_groupsrC   matmul	transposerH   r   
functionalsoftmaxfloat32tora   r]   rc   
contiguous)rW   rX   rY   rZ   r[   r\   r]   r^   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r4   eager_attention_forwardrq   W   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$$r5   c                 `   |j                  |      }|j                  |      }|j                  d   }| dd|f   | d|df   }}|dd|f   |d|df   }
}	t        j                  ||z  t	        |      |z  z   |gd      }t        j                  |	|z  t	        |	      |z  z   |
gd      }||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.
    r9   .Nr:   )	unsqueezerH   rC   rI   rM   )qkcossinposition_idsunsqueeze_dim
rotary_dimq_rotq_passk_rotk_passq_embedk_embeds                r4   apply_rotary_pos_embr   q   s    ( --
&C
--
&C2Jc;J;&'3
+;)<6Ec;J;&'3
+;)<6Eii%#++e*<s*BCVLRTUGii%#++e*<s*BCVLRTUGGr5   c                   Z    e Zd ZdZddedee   f fdZ eddd      	 	 dd	e	j                  d
ee	j                  e	j                  f   dee	j                     dee   dee	j                     dee   dee	j                  ee	j                     eee	j                        f   fd       Z xZS )Phi3Attentionz=Multi-headed attention from 'Attention Is All You Need' paperr)   	layer_idxc                 |   t         |           || _        || _        t	        |d|j
                  |j                  z        | _        |j                  |j                  z  | _	        |j                  | _        | j                  dz  | _
        |j                  | _        d| _        |j                  | j                  z  d|j                  | j                  z  z  z   }t        j                  |j                  | j                  z  |j
                  d      | _        t        j                  |j
                  |d      | _        y )NrU   g      Tr$   Fr%   )r'   r(   r)   r   getattrr+   num_attention_headsrU   rS   rd   r\   attention_dropout	is_causalr   r*   o_projqkv_proj)r2   r)   r   op_sizer3   s       r4   r(   zPhi3Attention.__init__   s    "
F4F4F&JdJd4de$*$>$>&B\B\$\!#)#=#= }}d*!'!9!9,,t}}<qFD^D^aeananDn?ooii : :T]] JFL^L^ejk		&"4"4gEJr5   past_key_valuepast_key_values4.58new_nameversionr6   position_embeddingsr[   cache_positionr^   r7   c           
         |j                   d d }g |d| j                  }| j                  |      }	| j                  j                  | j                  z  }
|	dd |
f   }|	d|
|
| j
                  | j                  z  z   f   }|	d|
| j
                  | j                  z  z   d f   }|j                  |      j                  dd      }|j                  |      j                  dd      }|j                  |      j                  dd      }|\  }}t        ||||      \  }}|'|||d}|j                  ||| j                  |      \  }}t        }| j                  j                  dk7  rt        | j                  j                     } || ||||f| j                  sdn| j                  | j                   t#        | j                  dd       d	|\  }} |j$                  g |d j'                         }| j)                  |      }||fS )
Nr9   .r   r$   )rw   rv   r   eager        sliding_window)r]   r\   r   )rH   rU   r   r)   r   rS   viewrf   r   updater   rq   _attn_implementationr   rc   r   r\   r   rQ   rk   r   )r2   r6   r   r[   r   r   r^   input_shapehidden_shapeqkv	query_posquery_statesrl   rm   rv   rw   cache_kwargsattention_interfacerp   rn   s                       r4   r?   zPhi3Attention.forward   s$    $))#2.88b8$--8mmM*KK33dmmC	3

?+i)d6N6NQUQ^Q^6^*^^^_
3	D,D,Dt}},T T VVW#((6@@AF__\2<<QB
#((6@@AF&S#7jRUWZ#[ j&#&snUL'6'='=j,X\XfXfht'u$J(?;;++w6"9$++:Z:Z"[$7
%
  $}}C$2H2HLL"4;;0@$G
%
 
%
!\ *k));;;;FFHkk+.L((r5   N)NN)r@   rA   rB   __doc__r    r   intr(   r   rC   Tensortupler
   
LongTensorr   r   r?   rE   rF   s   @r4   r   r      s    GKz Khsm K %0A6R ,0590)||0) #5<<#=>0) !.	0)
 "%0) !!1!120) -.0) 
u||Xell3XeELL>Q5RR	S0) S0)r5   r   RMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )Phi3RMSNormc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z:
        Phi3RMSNorm is equivalent to T5LayerNorm
        N)r'   r(   r   	ParameterrC   onesweightvariance_epsilon)r2   r+   epsr3   s      r4   r(   zPhi3RMSNorm.__init__   s1     	ll5::k#:; #r5   c                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )Nr$   r9   T)keepdim)	ra   rj   rC   ri   powmeanrsqrtr   r   )r2   r6   input_dtypevariances       r4   r?   zPhi3RMSNorm.forward   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r5   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)r   r   rH   r   )r2   s    r4   
extra_reprzPhi3RMSNorm.extra_repr   s*    ))*+6$2G2G1HIIr5   )gư>)r@   rA   rB   r(   r?   r   rE   rF   s   @r4   r   r      s    $;Jr5   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   de	e   de	ej                     de	eej                  ej                  f      dee   deej                   e	eej                   ej                   f      f   fd       Z xZS )Phi3DecoderLayerr)   r   c                    t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        || _        t        j                  |j                        | _        t        j                  |j                        | _        y )N)r)   r   r   )r'   r(   r+   r   	self_attnr"   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr)   r   Dropoutresid_pdropresid_attn_dropoutresid_mlp_dropoutr2   r)   r   r3   s      r4   r(   zPhi3DecoderLayer.__init__   s    !--&f	J6?*6+=+=6CVCVW(3F4F4FFL_L_(`%"$**V-?-?"@!#F,>,>!?r5   r   r   r   r   r6   r[   rx   	use_cacher   r   r^   r7   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	| j                  |      z   }|}	| j                  |      }| j	                  |      }|	| j                  |      z   }|S )N)r6   r[   rx   r   r   r   r    )r   r   r   r   r   r   )r2   r6   r[   rx   r   r   r   r   r^   residualself_attn_weightss              r4   r?   zPhi3DecoderLayer.forward   s     !,,];+94>> 	,
')%+) 3	,
 	,
(( !4#:#:=#II 55mD/ 4#9#9-#HHr5   )NNNFNN)r@   rA   rB   r    r   r(   r   rC   r   r   r   r
   boolr   r   r   rD   r?   rE   rF   s   @r4   r   r      s   	@z 	@c 	@ %0A6R 2637+/$)59KO|| !. u//0	
 "% D> !!1!12 &eELL%,,,F&GH -. 
u  (51B1BEDUDU1U+V"WW	X Sr5   r   c                   N    e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedZdZy)	Phi3PreTrainedModelr)   modelTr   r   )r6   
attentionsz0.0.5N)r@   rA   rB   r    __annotations__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_outputs_versionr   r5   r4   r   r     sX    &*#+,#4"5N!"&)# Hr5   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 )Phi3RotaryEmbedding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)r'   r(   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)r2   r)   devicer   r3   s       r4   r(   zPhi3RotaryEmbedding.__init__1  s    6>*z&:M:Mt/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r5   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   r9   r   mpscpuF)device_typeenabledr$   r:   )ra   )r   floatrP   rH   rj   r   r   r   strrC   autocastrf   rI   rv   r   rw   ra   )
r2   rJ   rx   inv_freq_expandedposition_ids_expandedr   freqsembrv   rw   s
             r4   r?   zPhi3RotaryEmbedding.forwardB  sV    !MM$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@   rA   rB   rC   r   r   r    r(   no_gradr   r?   rE   rF   s   @r4   r   r   .  s=    ll/z /" U]]_<  <r5   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j                     d
ee   defd              Z xZS )	Phi3Modelr)   c           	         t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |j                  |j                        | _        t#        |      | _        d| _        | j)                          y c c}w )Nr   r)   F)r'   r(   pad_token_idpadding_idx
vocab_sizer   	Embeddingr+   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normr   
rotary_embgradient_checkpointing	post_initr   s      r4   r(   zPhi3Model.__init__T  s     !.. ++LL):):F<N<NPTP`P`ammBGH`H`BabYfi0b
   2 28K8KL	-V<&+# 	 cs   D	input_idsr[   rx   r   inputs_embedsr   r   r^   r7   c                    |d u |d uz  rt        d      || j                  |      }|r|t        | j                        }|F||j	                         nd}	t        j                  |	|	|j                  d   z   |j                        }||j                  d      }| j                  j                  t        nt        }
 |
| j                  |||||      }|}| j                  ||      }| j                  d | j                  j                   D ]  } ||f||||||d|} | j!                  |      }t#        ||r|      S d       S )	Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r   )r   )r)   input_embedsr[   r   r   rx   )r[   rx   r   r   r   r   )last_hidden_stater   )
ValueErrorr	  r   r)   get_seq_lengthrC   arangerH   r   rs   r   r   r   r  r  r  r  r   )r2   r  r[   rx   r   r  r   r   r^   past_seen_tokensmask_functionro   r6   r   decoder_layers                  r4   r?   zPhi3Model.forwardd  s    -t";<YZZ  --i8M0*$++>O!CRC^==?de"\\ "2]5H5H5K"KTaThThN )33A6L.2kk.H.H.P*Vw#;;&))+%
 &"oom\J![[)H4;;+H+HI 
	M)	*) /#-$7	 	M
	 		-0&+/8O
 	
>B
 	
r5   )NNNNNNN)r@   rA   rB   r    r(   r   r   r   rC   r   r   r
   rD   r   r   r   r   r?   rE   rF   s   @r4   r  r  R  s    z    151537+/59$(599
E,,-9
 !.9
 u//0	9

 "%9
   1 129
 D>9
 !!1!129
 +,9
 
!9
  9
r5   r  c                   ~    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	 	 	 	 	 	 	 d fd	Z xZS )Phi3ForCausalLMzlm_head.weightlm_headcolwise_repr6   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y )NFr%   )
r'   r(   r  r   r  r   r*   r+   r  r  r1   s     r4   r(   zPhi3ForCausalLM.__init__  sU     v&
 ++yy!3!3V5F5FUS 	r5   r  r[   rx   r   r  labelsr   r   logits_to_keepr^   r7   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, Phi3ForCausalLM

        >>> model = Phi3ForCausalLM.from_pretrained("meta-phi3/Phi3-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-phi3/Phi3-2-7b-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[   rx   r   r  r   r   N)r!  r#  r  )lossr!  r   r6   r   r   )r   r  r   r   slicer  loss_functionr)   r  r   r   r6   r   )r2   r  r[   rx   r   r  r#  r   r   r$  r^   outputsr6   slice_indicesr!  r&  s                   r4   r?   zPhi3ForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r5   c	                     |r_| j                   j                  rI|j                  d   | j                   j                  dz   k\  r |d   }
|
| j                   j                  k  rd }t	        |   d||||||||d|	}|S )Nr   r   )r  r   r[   r  r   rx   r   r$  r   )r)   r   rH    original_max_position_embeddingsr'   prepare_inputs_for_generation)r2   r  r   r[   r  r   rx   r   r$  r^   past_lengthmodel_inputsr3   s               r4   r-  z-Phi3ForCausalLM.prepare_inputs_for_generation  s    $ (("dkk&R&RUV&VV(+KdkkJJJ"&w< 

+)')%)

 

 r5   )	NNNNNNNNr   )NNNNNTN)r@   rA   rB   _tied_weights_keys_tp_plan_pp_planr(   r   r   r   rC   r   r   r
   rD   r   r   r   r   r   r   r?   r-  rE   rF   s   @r4   r  r    sR   *+=)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
z % %r5   r  c                       e Zd Zy)Phi3ForSequenceClassificationNr@   rA   rB   r   r5   r4   r4  r4        r5   r4  c                       e Zd Zy)Phi3ForTokenClassificationNr5  r   r5   r4   r8  r8    r6  r5   r8  )r   r  r  r4  r8  )r   )Nr   )@typingr   r   r   rC   r   transformers.utils.genericr   activationsr	   cache_utilsr
   r   
generationr   integrationsr   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.deprecationr   configuration_phi3r    Moduler"   rM   r   r   rV   r   rq   r   r   r   r   r   r   r  r  r4  r8  __all__r   r5   r4   <module>rK     s  . - ,   9 ! . ) 7 R B 
 P K F & I I 0 *)bii )$(	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4@C)BII C)L Y'J")) J (J(+1 +\ /  &!<")) !<H L
# L
 L
^ o)? o od	$DFY 		!>@S 	r5   