
     `iZ                     R   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j-                  Z.d Z/dej0        de1dej0        fdZ2	 d;dej-        dej0        dej0        d ej0        d!eej0                 d"e3d#e3d$e$e&         fd%Z4d<d&Z5 G d' d(ej-                  Z6 ed)           G d* d+ej-                              Z7 G d, d-e          Z8e' G d. d/e"                      Z9 G d0 d1ej-                  Z:e' G d2 d3e9                      Z;e' G d4 d5e9e                      Z< G d6 d7ee9          Z= G d8 d9ee9          Z>g d:Z?dS )=    )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                   B     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
                 | _        d S )N   Fbias)super__init__configr   Linearhidden_sizeintermediate_sizegate_up_proj	down_projr	   
hidden_actactivation_fnselfr)   	__class__s     z/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/phi3/modeling_phi3.pyr(   zPhi3MLP.__init__3   sz    If&8!f>V:V]bccc6#;V=OV[\\\#F$56    hidden_statesreturnc                     |                      |          }|                    dd          \  }}||                     |          z  }|                     |          S )Nr$   dim)r-   chunkr0   r.   )r2   r6   	up_statesgates       r4   forwardzPhi3MLP.forward;   sX    %%m44	#//!/44i 2 24 8 88	~~i(((r5   )__name__
__module____qualname__r(   torchFloatTensorr?   __classcell__r3   s   @r4   r"   r"   2   s`        7 7 7 7 7)U%6 )5;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$   r:   )shaperC   cat)xx1x2s      r4   rotate_halfrM   D   s]    	
3"!'"+"""	#B	
3q """	#B9rc2YB''''r5   r6   n_repr7   c                     | j         \  }}}}|dk    r| S | dddddddddf                             |||||          } |                     |||z  ||          S )z
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r   N)rH   expandreshape)r6   rN   batchnum_key_value_headsslenhead_dims         r4   	repeat_kvrV   K   s    
 2?1D.Ehzz!!!!QQQaaa"23::5BUW\^bdlmmM  (;e(CT8TTTr5           modulequerykeyvalueattention_maskscalingdropoutkwargsc                 R   t          || j                  }t          || j                  }	t          j        ||                    dd                    |z  }
|$|d d d d d d d |j        d         f         }|
|z   }
t          j                            |
dt          j	                  
                    |j                  }
t          j                            |
|| j                  }
t          j        |
|	          }|                    dd                                          }||
fS )Nr$   r   r9   )r;   dtype)ptrainingr   )rV   num_key_value_groupsrC   matmul	transposerH   r   
functionalsoftmaxfloat32torb   r^   rd   
contiguous)rX   rY   rZ   r[   r\   r]   r^   r_   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r4   eager_attention_forwardrr   W   s    3 ;<<JUF$?@@L<z';';Aq'A'ABBWLL!$QQQ111.D
0@0D.D%DE#k1=((2U](SSVVW\WbccL=((6?([[L,|\::K''1--88::K$$r5   c                    |                     |          }|                     |          }|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i%#++e*<*<s*BCVLRTUUUGi%#++e*<*<s*BCVLRTUUUGGr5   c                   R    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' 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          | _        d S )NrU   g      Tr$   Fr%   )r'   r(   r)   r   getattrr+   num_attention_headsrU   rS   re   r]   attention_dropout	is_causalr   r*   o_projqkv_proj)r2   r)   r   op_sizer3   s       r4   r(   zPhi3Attention.__init__   s    "
F4F&Jd4dee$*$>&B\$\!#)#= }d*!'!9,t}<qFD^aeanDn?ooi :T] JFL^ejkkk	&"4gEJJ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        R }|                     |          }	| j        j        | j        z  }
|	dd |
f         }|	d|
|
| j        | j        z  z   f         }|	d|
| j        | j        z  z   d f         }|                    |                              dd          }|                    |                              dd          }|                    |                              dd          }|\  }}t          ||||          \  }}|&|||d}|	                    ||| j
        |          \  }}t          }| j        j        dk    rt          | j        j                 } || ||||f| j        sdn| j        | j        t#          | j        dd           d	|\  }} |j        g |dR                                  }|                     |          }||fS )
Nr9   .r   r$   )rx   rw   r   eagerrW   sliding_window)r^   r]   r   )rH   rU   r   r)   r   rS   viewrg   r   updater   rr   _attn_implementationr   rd   r   r]   r   rQ   rl   r   )r2   r6   r   r\   r   r   r_   input_shapehidden_shapeqkv	query_posquery_statesrm   rn   rw   rx   cache_kwargsattention_interfacerq   ro   s                       r4   r?   zPhi3Attention.forward   s>    $)#2#.88b8$-88mmM**K3dmC	3

?+i)d6NQUQ^6^*^^^_
3	D,Dt},T T V VVW#((66@@AFF__\22<<QBB
#((66@@AFF&S#7jRUWZ#[#[ j&#&snUUL'6'='=j,X\Xfht'u'u$J(?;+w66"9$+:Z"[$7$7
%
  $}HCC$2HL"4;0@$GG
%
 
%
 
%
 
%
!\ *k);;;;;;FFH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      s3       GGK Kz Khsm K K K K K K _%0A6RRR ,0590) 0)|0) #5<#=>0) !.	0)
 "%0) !!120) -.0) 
u|Xel3XeEL>Q5RR	S0) 0) 0) SR0) 0) 0) 0) 0)r5   r   RMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )Phi3RMSNormư>c                     t                                                       t          j        t	          j        |                    | _        || _        dS )z:
        Phi3RMSNorm is equivalent to T5LayerNorm
        N)r'   r(   r   	ParameterrC   onesweightvariance_epsilon)r2   r+   epsr3   s      r4   r(   zPhi3RMSNorm.__init__   sD     	l5:k#:#:;; #r5   c                    |j         }|                    t          j                  }|                    d                              dd          }|t          j        || j        z             z  }| j        |                    |          z  S )Nr$   r9   T)keepdim)	rb   rk   rC   rj   powmeanrsqrtr   r   )r2   r6   input_dtypevariances       r4   r?   zPhi3RMSNorm.forward   s|    #)%((77 $$Q'',,R,>>%Ht?T4T(U(UU{]--k::::r5   c                 H    t          | j        j                   d| j         S )Nz, eps=)r   r   rH   r   )r2   s    r4   
extra_reprzPhi3RMSNorm.extra_repr   s&    )**II$2GIIIr5   )r   )r@   rA   rB   r(   r?   r   rE   rF   s   @r4   r   r      sb        $ $ $ $ $ $; ; ;J J J J J J Jr5   r   c                   t    e Zd Zdedef fdZ eddd          	 	 	 	 	 	 dd
ej        de	ej                 de	ej
                 de	e         de	e         de	ej
                 de	eej        ej        f                  dee         deej        e	eej        ej        f                  f         fd            Z xZS )Phi3DecoderLayerr)   r   c                    t                                                       |j        | _        t          ||          | _        t          |          | _        t          |j        |j                  | _	        t          |j        |j                  | _
        || _        t          j        |j                  | _        t          j        |j                  | _        d S )N)r)   r   r   )r'   r(   r+   r   	self_attnr"   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr)   r   Dropoutresid_pdropresid_attn_dropoutresid_mlp_dropout)r2   r)   r   r3   s      r4   r(   zPhi3DecoderLayer.__init__   s    !-&f	JJJ6??*6+=6CVWWW(3F4FFL_(`(`(`%"$*V-?"@"@!#F,>!?!?r5   r   r   r   r   NFr6   r\   ry   	use_cacher   r   r_   r7   c                    |}	|                      |          } | j        d|||||||d|\  }}
|	|                     |          z   }|}	|                     |          }|                     |          }|	|                     |          z   }|S )N)r6   r\   ry   r   r   r   r    )r   r   r   r   r   r   )r2   r6   r\   ry   r   r   r   r   r_   residualself_attn_weightss              r4   r?   zPhi3DecoderLayer.forward   s     !,,];;+94> 	,
')%+) 3	,
 	,
 	,
 	,
(( !4#:#:=#I#II 55mDD// 4#9#9-#H#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      sU       	@z 	@c 	@ 	@ 	@ 	@ 	@ 	@ _%0A6RRR 2637+/$)59KO | !. u/0	
 "% D> !!12 &eEL%,,F&GH -. 
u (51BEDU1U+V"WW	X   SR    r5   r   c                   P    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dS )	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     sq         &*#+,#4"5N!"&)#  HHHr5   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_freqNr)   c                    t                                                       t          |d          rSt          |j        t
                    r9|j                            d|j                            d                    | _        nd| _        |j        | _	        |j        | _
        || _        t          | j                 | _        |                     | j        |          \  }| _        |                     d|d           | j        | _        d S )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&:Mt/T/T 	'#044[&BUBYBYZ`BaBabbDNN&DN"("@$*$B!/?+/+<+<T[&+Q+Q($(ZeDDD!%r5   c                 X   | j         d d d d f                                                             |j        d         dd                              |j                  }|d d d d d f                                         }t          |j        j        t                    r|j        j        dk    r|j        j        nd}t          j
        |d          5  |                                |                                z                      dd          }t          j        ||fd	          }|                                | j        z  }|                                | j        z  }	d d d            n# 1 swxY w Y   |                    |j        
          |	                    |j        
          fS )Nr   r9   r   mpscpuF)device_typeenabledr$   r:   )rb   )r   floatrP   rH   rk   r   r   r   strrC   autocastrg   rI   rw   r   rx   rb   )
r2   rJ   ry   inv_freq_expandedposition_ids_expandedr   freqsembrw   rx   s
             r4   r?   zPhi3RotaryEmbedding.forwardB  s    !M$4-8>>@@GGHZ[\H]_acdeehhijiqrr ,QQQaaaZ 8 > > @ @'1!(-'E'Ek!(-[`J`J`ahmmfk^UCCC 	5 	5&,,..1F1L1L1N1NNYYZ[]^__E)UEN333C''))d44C''))d44C		5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 vvAGv$$cff17f&;&;;;s   BE++E/2E/r   )r@   rA   rB   rC   r   r   r    r(   no_gradr   r?   rE   rF   s   @r4   r   r   .  s         l/ /z / / / / / /" U]__< <  _< < < < <r5   r   c                       e Zd Zdef fdZee	 	 	 	 	 	 	 ddeej	                 deej
                 deej	                 dee         deej                 d	ee         d
eej	                 dee         defd                        Z xZS )	Phi3Modelr)   c                    t                                                     j        | _        j        | _        t          j        j        j        | j                  | _        t          j	        fdt          j                  D                       | _        t          j        j                  | _        t!                    | _        d| _        |                                  d S )Nc                 0    g | ]}t          |          S r   )r   ).0r   r)   s     r4   
<listcomp>z&Phi3Model.__init__.<locals>.<listcomp>[  s$    bbbYfi00bbbr5   r   r)   F)r'   r(   pad_token_idpadding_idx
vocab_sizer   	Embeddingr+   embed_tokens
ModuleListrangenum_hidden_layerslayersr   r   normr   
rotary_embgradient_checkpointing	post_initr1   s    `r4   r(   zPhi3Model.__init__T  s       !. +L):F<NPTP`aambbbb%H`BaBabbb
 
   28KLLL	-V<<<&+# 	r5   N	input_idsr\   ry   r   inputs_embedsr   r   r_   r7   c                    |d u |d uz  rt          d          ||                     |          }|r|t          | j                  }|B||                                nd}	t          j        |	|	|j        d         z   |j                  }||	                    d          }| j        j
        t          nt          }
 |
| j        |||||          }|}|                     ||          }| j        d | j        j                 D ]} ||f||||||d|}|                     |          }t#          ||r|nd           S )	Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r   )r   )r)   input_embedsr\   r   r   ry   )r\   ry   r   r   r   r   )last_hidden_stater   )
ValueErrorr  r   r)   get_seq_lengthrC   arangerH   r   rt   r   r   r   r  r  r  r  r   )r2   r  r\   ry   r   r  r   r   r_   past_seen_tokensmask_functionrp   r6   r   decoder_layers                  r4   r?   zPhi3Model.forwardd  s    -t";< 	[YZZZ  --i88M 	?0*$+>>>O!CRC^==???de"\ "2]5H5K"KTaTh  N )33A66L.2k.H.P**Vw#m;&))+%
 
 
 &"oom\JJ![)H4;+H)HI 
	 
	M)M	*) /#-$7	 	 	 	MM 		-00&+/8BOOd
 
 
 	
r5   )NNNNNNN)r@   rA   rB   r    r(   r   r   r   rC   r   r   r
   rD   r   r   r   r   r?   rE   rF   s   @r4   r  r  R  s       z         151537+/59$(599
 9
E,-9
 !.9
 u/0	9

 "%9
   129
 D>9
 !!129
 +,9
 
!9
 9
 9
 ^ 9
 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          | _        | 	                                 d S )NFr%   )
r'   r(   r  r   r
  r   r*   r+   r"  r  r1   s     r4   r(   zPhi3ForCausalLM.__init__  sj       v&&
 +y!3V5FUSSS 	r5   Nr   r  r\   ry   r   r  labelsr   r   logits_to_keepr_   r7   c
                 R    | j         d|||||||d|
}|j        }t          |	t                    rt	          |	 d          n|	}|                     |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\   ry   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\   ry   r   r  r&  r   r   r'  r_   outputsr6   slice_indicesr$  r)  s                   r4   r?   zPhi3ForCausalLM.forward  s    @ ,64: 	,
)%+')	,
 	,
 	,
 	,
  18B>SV8W8Wk~ot444]kmAAA}aaa,?@AA%4%pVFt{OeppioppD%#3!/)
 
 
 	
r5   Tc	                     |rD| j         j        r8|j        d         | j         j        dz   k    r|d         }
|
| j         j        k    rd } t	                      j        d||||||||d|	}|S )Nr   r   )r  r   r\   r  r   ry   r   r'  r   )r)   r   rH    original_max_position_embeddingsr'   prepare_inputs_for_generation)r2   r  r   r\   r  r   ry   r   r'  r_   past_lengthmodel_inputsr3   s               r4   r0  z-Phi3ForCausalLM.prepare_inputs_for_generation  s    $ 	'(	' "dk&RUV&VVV(+KdkJJJ"&<uww< 

+)')%)

 

 

 

 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?   r0  rE   rF   s   @r4   r!  r!    s       *+=)H_-z:;H      151537+/59-1$(59348
 8
E,-8
 !.8
 u/0	8

 "%8
   128
 )*8
 D>8
 !!128
 c5</08
 +,8
 
 8
 8
 8
 ^ 8
z % % % % % % % % % %r5   r!  c                       e Zd ZdS )Phi3ForSequenceClassificationNr@   rA   rB   r   r5   r4   r7  r7            Dr5   r7  c                       e Zd ZdS )Phi3ForTokenClassificationNr8  r   r5   r4   r;  r;    r9  r5   r;  )r   r  r!  r7  r;  )rW   )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   rr   r   r   r   r   r   r   r  r!  r7  r;  __all__r   r5   r4   <module>rN     s  . - , , , , , , , , ,        9 9 9 9 9 9 ! ! ! ! ! ! . . . . . . . . ) ) ) ) ) ) 7 7 7 7 7 7 R R R R R R R R B B B B B B         
 P O O O O O O O K K K K K K K K F F F F F F F F & & & & & & I I I I I I I I I I 0 0 0 0 0 0 * * * * * *) ) ) ) )bi ) ) )$( ( (	UU\ 	U# 	U%, 	U 	U 	U 	U& % %I%<% 
% <	%
 U\*% % % '(% % % %4   @C) C) C) C) C)BI C) C) C)L Y''J J J J J") J J ('J(+ + + + +1 + + +\     /   &!< !< !< !< !<") !< !< !<H L
 L
 L
 L
 L
# L
 L
 L
^ o o o o o)? o o od	 	 	 	 	$DFY 	 	 		 	 	 	 	!>@S 	 	 	  r5   