
    i_                     \   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	 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. G d dejZ                        Z/d Z0dejb                  de2dejb                  fdZ3	 d;dejZ                  d ejb                  d!ejb                  d"ejb                  d#ejb                  dz  d$e4d%e4d&e$e&   fd'Z5d<d(Z6 G d) d*ejZ                        Z7 ed+       G d, d-ejZ                               Z8 G d. d/e      Z9e' G d0 d1e"             Z:e' G d2 d3e:             Z;e' G d4 d5e:e             Z< G d6 d7ee:      Z= G d8 d9ee:      Z>g d:Z?y)=    )Callable)OptionalN)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)maybe_autocast   )
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     p/home/obispo/Crisostomo_bridge/mision_env/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,   chunkr/   r-   )r1   r5   	up_statesgates       r3   forwardzPhi3MLP.forward;   sL    %%m4	#//!/4i 2 24 88	~~i((r4   )__name__
__module____qualname__r'   torchFloatTensorr>   __classcell__r2   s   @r3   r!   r!   2   s'    7)U%6%6 )5;L;L )r4   r!   c                        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 )Phi3RotaryEmbeddinginv_freqNr(   c                    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defaultrH   F)
persistentoriginal_inv_freq)r&   r'   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr(   rope_parametersrJ   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r1   r(   devicerope_init_fnrH   r2   s        r3   r'   zPhi3RotaryEmbedding.__init__G   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuUr4   rV   ztorch.deviceseq_lenr6   z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   r#   dtype)rV   r^   )rQ   getgetattrr*   num_attention_headsintrB   arangeint64tofloat)	r(   rV   rX   baser[   r\   r:   attention_factorrH   s	            r3   rR   z3Phi3RotaryEmbedding.compute_default_rope_parametersW   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
 )))r4   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   r8   r   mpscpuF)device_typeenabledr#   r9   r]   )rH   rf   expandshapere   rV   
isinstancetypestrr   	transposerB   catcosrS   sinr^   )
r1   xposition_idsinv_freq_expandedposition_ids_expandedrl   freqsembru   rv   s
             r3   r>   zPhi3RotaryEmbedding.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$N)NNN)r?   r@   rA   rB   Tensor__annotations__r   r'   staticmethodr   rb   tuplerf   rR   no_gradr   r>   rD   rE   s   @r3   rG   rG   D   s    llVz V  $(+/"*T!*(* t* 
~u$	%	* *> U]]_<  <r4   rG   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..Nr8   r#   r9   )ro   rB   rt   )rw   x1x2s      r3   rotate_halfr      sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r4   r5   n_repr6   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)ro   rn   reshape)r5   r   batchnum_key_value_headsslenr\   s         r3   	repeat_kvr      so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr4   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   r8   )r:   r^   )ptrainingr   )r   num_key_value_groupsrB   matmulrs   ro   r   
functionalsoftmaxfloat32re   r^   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r3   eager_attention_forwardr      s    3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#k1==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r4   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.
        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.
    r8   .Nr9   )	unsqueezero   rB   rt   r   )qkru   rv   unsqueeze_dim
rotary_dimq_rotq_passk_rotk_passq_embedk_embeds               r3   apply_rotary_pos_embr      s    $ --
&C
--
&C2Jc;J;&'3
+;)<6Ec;J;&'3
+;)<6Eii%#++e*<s*BCVLRTUGii%#++e*<s*BCVLRTUGGr4   c                   >    e Zd ZdZddededz  f fdZ	 	 ddej                  de	ej                  ej                  f   dej                  dz  d	e
dz  d
ej                  dz  dee   de	ej                  ej                  dz  e	ej                     dz  f   fdZ xZS )Phi3Attentionz=Multi-headed attention from 'Attention Is All You Need' paperNr(   	layer_idxc                 |   t         |           || _        || _        t	        |d|j
                  |j                  z        | _        |j                  |j                  z  | _	        |j                  | _        | j                  dz  | _
        |j                  | _        d| _        |j                  | j                  z  d|j                  | j                  z  z  z   }t        j                  |j                  | j                  z  |j
                  d      | _        t        j                  |j
                  |d      | _        y )Nr\   g      Tr#   Fr$   )r&   r'   r(   r   r`   r*   ra   r\   r   r   r   attention_dropout	is_causalr   r)   o_projqkv_proj)r1   r(   r   op_sizer2   s       r3   r'   zPhi3Attention.__init__   s    "
F4F4F&JdJd4de$*$>$>&B\B\$\!#)#=#= }}d*!'!9!9,,t}}<qFD^D^aeananDn?ooii : :T]] JFL^L^ejk		&"4"4gEJr4   r5   position_embeddingsr   past_key_valuescache_positionr   r6   c           
         |j                   d d }g |d| j                  }| j                  |      }	| j                  j                  | j                  z  }
|	dd |
f   }|	d|
|
| j
                  | j                  z  z   f   }|	d|
| j
                  | j                  z  z   d f   }|j                  |      j                  dd      }|j                  |      j                  dd      }|j                  |      j                  dd      }|\  }}t        ||||      \  }}|'|||d}|j                  ||| j                  |      \  }}t        j                  | j                  j                  t              } || ||||f| j                  sdn| j                   | j"                  t%        | j                  dd       d|\  }} |j&                  g |d j)                         }| j+                  |      }||fS )	Nr8   .r   r#   )rv   ru   r           sliding_window)r   r   r   )ro   r\   r   r(   ra   r   viewrs   r   updater   r   get_interface_attn_implementationr   r   r   r   r`   r   r   r   )r1   r5   r   r   r   r   r   input_shapehidden_shapeqkv	query_posquery_statesr   r   ru   rv   cache_kwargsattention_interfacer   r   s                       r3   r>   zPhi3Attention.forward   s    $))#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(?(M(MKK,,.E)
 %8
%
  $}}C$2H2HLL"4;;0@$G
%
 
%
!\ *k));;;;FFHkk+.L((r4   r}   )NN)r?   r@   rA   __doc__r   rb   r'   rB   r~   r   r	   
LongTensorr   r   r>   rD   rE   s   @r3   r   r      s    GKz KcDj K( )-260)||0) #5<<#=>0) t+	0)
 0) ((4/0) -.0) 
u||U\\D0%2E2LL	M0)r4   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   	ParameterrB   onesweightvariance_epsilon)r1   r*   epsr2   s      r3   r'   zPhi3RMSNorm.__init__  s1     	ll5::k#:; #r4   c                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )Nr#   r8   T)keepdim)	r^   re   rB   r   powmeanrsqrtr   r   )r1   r5   input_dtypevariances       r3   r>   zPhi3RMSNorm.forward!  sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r4   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)r   r   ro   r   )r1   s    r3   
extra_reprzPhi3RMSNorm.extra_repr(  s*    ))*+6$2G2G1HIIr4   )gư>)r?   r@   rA   r'   r>   r   rD   rE   s   @r3   r   r     s    $;Jr4   r   c                   d    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j                  dz  deej                  ej                  f   dz  dee   deej                  eej                  ej                  f   dz  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r1   r(   r   r2   s      r3   r'   zPhi3DecoderLayer.__init__-  s    !--&f	J6?*6+=+=6CVCVW(3F4F4FFL_L_(`%"$**V-?-?"@!#F,>,>!?r4   Nr5   r   rx   r   	use_cacher   r   r   r6   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	| j                  |      z   }|}	| j                  |      }| j	                  |      }|	| j                  |      z   }|S )N)r5   r   rx   r   r   r   r    )r   r   r   r   r   r   )r1   r5   r   rx   r   r   r   r   r   residualself_attn_weightss              r3   r>   zPhi3DecoderLayer.forward8  s     !,,];+94>> 	,
')%+) 3	,
 	,
(( !4#:#:=#II 55mD/ 4#9#9-#HHr4   )NNNFNN)r?   r@   rA   r   rb   r'   rB   r~   r   r	   boolr   r   r   rC   r>   rD   rE   s   @r3   r   r   ,  s    	@z 	@c 	@ /304(,!&26HL|| t+ &&-	
  $; ((4/ #5<<#=>E -. 
u  %(9(95;L;L(L"MPT"TT	Ur4   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   )r5   
attentionsz0.0.5N)r?   r@   rA   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_outputs_versionr   r4   r3   r   r   Y  sX    &*#+,#4"5N!"&)# Hr4   r   c                       e Zd Zdef fdZee	 	 	 	 	 	 	 ddej                  dz  dej                  dz  dej                  dz  de
dz  dej                  dz  d	edz  d
ej                  dz  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   normrG   
rotary_embgradient_checkpointing	post_initr   s      r3   r'   zPhi3Model.__init__o  s     !.. ++LL):):F<N<NPTP`P`ammBGH`H`BabYfi0b
   2 28K8KL	-V<&+# 	 cs   DN	input_idsr   rx   r   inputs_embedsr   r   r   r6   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   )rV   )r(   input_embedsr   r   r   rx   )rx   )r   rx   r   r   r   r   )last_hidden_stater   )
ValueErrorr  r
   r(   get_seq_lengthrB   rc   ro   rV   r   r   r   r   r  r  r  r  r   )r1   r  r   rx   r   r  r   r   r   past_seen_tokensmask_functionr   r5   r   decoder_layers                  r3   r>   zPhi3Model.forward  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,oW![[)H4;;+H+HI 
	M)	*) /#-$7	 	M
	 		-0&+/8O
 	
>B
 	
r4   )NNNNNNN)r?   r@   rA   r   r'   r   r   rB   r   r~   r	   rC   r   r   r   r   r>   rD   rE   s   @r3   r  r  m  s    z    .2.204(,26!%269
##d*9
 t+9
 &&-	9

 9
 ((4/9
 $;9
 ((4/9
 +,9
 
!9
  9
r4   r  c                   |    e Zd ZddiZddiZddgdgfiZ fdZee	 	 	 	 	 	 	 	 	 dd	e	j                  dz  d
e	j                  dz  de	j                  dz  dedz  de	j                  dz  de	j                  dz  dedz  de	j                  dz  dee	j                  z  dee   defd              Z	 	 	 	 	 	 	 d fd	Z xZS )Phi3ForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr5   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y )NFr$   )
r&   r'   r  r   r
  r   r)   r*   r!  r  r0   s     r3   r'   zPhi3ForCausalLM.__init__  sU     v&
 ++yy!3!3V5F5FUS 	r4   Nr  r   rx   r   r  labelsr   r   logits_to_keepr   r6   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   r5   r   r   )r   r  rp   rb   slicer!  loss_functionr(   r
  r   r   r5   r   )r1   r  r   rx   r   r  r%  r   r   r&  r   outputsr5   slice_indicesr#  r(  s                   r3   r>   zPhi3ForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r4   c	                     |r_t        | j                  d      rI|j                  d   | j                  j                  dz   k\  r |d   }
|
| j                  j                  k  rd }t	        |   d||||||||d|	}|S )N original_max_position_embeddingsr   r   )r  r   r   r  r   rx   r   r&  r   )hasattrr(   ro   r.  r&   prepare_inputs_for_generation)r1   r  r   r   r  r   rx   r   r&  r   past_lengthmodel_inputsr2   s               r3   r0  z-Phi3ForCausalLM.prepare_inputs_for_generation  s    $ %GH"dkk&R&RUV&VV(+KdkkJJJ"&w< 

+)')%)

 

 r4   )	NNNNNNNNr   )NNNNNTN)r?   r@   rA   _tied_weights_keys_tp_plan_pp_planr'   r   r   rB   r   r~   r	   rC   r   rb   r   r   r   r>   r0  rD   rE   s   @r3   r   r     sQ   *,GH23H_-z:;H  .2.204(,26*.!%26-.8
##d*8
 t+8
 &&-	8

 8
 ((4/8
   4'8
 $;8
 ((4/8
 ell*8
 +,8
 
 8
  8
z % %r4   r   c                       e Zd Zy)Phi3ForSequenceClassificationNr?   r@   rA   r   r4   r3   r7  r7  0      r4   r7  c                       e Zd Zy)Phi3ForTokenClassificationNr8  r   r4   r3   r;  r;  4  r9  r4   r;  )r   r  r   r7  r;  )r   )r   )@collections.abcr   typingr   rB   r   transformers.utils.genericr   activationsr   cache_utilsr	   r
   
generationr   integrationsr   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   configuration_phi3r   Moduler!   rG   r   r~   rb   r   rf   r   r   r   r   r   r   r  r   r7  r;  __all__r   r4   r3   <module>rO     s  , %    9 ! . ) 7 R B 
 P K F & I I + *)bii )$@<")) @<F(	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%4<B)BII B)J Y'J")) J (J(*1 *Z /  & L
# L
 L
^ o)? o od	$DFY 		!>@S 	r4   