
     `isV                        d dl mZmZmZ d dlZd dlmZ ddlmZ ddl	m
Z
mZ ddlmZ ddlmZ ddlmZmZmZ dd	lmZmZ dd
lmZmZ ddlmZmZ ddlmZ ddlm Z m!Z!m"Z"m#Z# ddl$m%Z% ddl&m'Z' ddl(m)Z)  e#j*        e+          Z,d Z-d5dZ.dej/        de0dej/        fdZ1	 d6dej2        dej/        dej/        dej/        deej/                 de3de3d ee          fd!Z4 G d" d#ej2                  Z5 G d$ d%ej2                  Z6 G d& d'e          Z7 G d( d)ej2                  Z8e! G d* d+e                      Z9e! G d, d-e9                      Z:e! G d. d/e9e                      Z; G d0 d1ee9          Z< G d2 d3ee9          Z=g d4Z>dS )7    )CallableOptionalUnionN   )ACT2FN)CacheDynamicCache)GenerationMixin)create_causal_mask) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuplelogging)deprecate_kwarg)check_model_inputs   )	PhiConfigc                     | dd| j         d         dz  f         }| d| j         d         dz  df         }t          j        | |fd          S )z*Rotates half the hidden dims of the input..N   dim)shapetorchcat)xx1x2s      x/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/phi/modeling_phi.pyrotate_halfr*   "   s]    	
3"!'"+"""	#B	
3q """	#B9rc2YB''''    c                     |                     |          }|                     |          }| |z  t          |           |z  z   }||z  t          |          |z  z   }||fS )a  Applies Rotary Position Embedding to the query and key tensors.

    Args:
        q (`torch.Tensor`): The query tensor.
        k (`torch.Tensor`): The key tensor.
        cos (`torch.Tensor`): The cosine part of the rotary embedding.
        sin (`torch.Tensor`): The sine part of the rotary embedding.
        position_ids (`torch.Tensor`, *optional*):
            Deprecated and unused.
        unsqueeze_dim (`int`, *optional*, defaults to 1):
            The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
            sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
            that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and
            k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes
            cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have
            the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2.
    Returns:
        `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
    )	unsqueezer*   )qkcossinposition_idsunsqueeze_dimq_embedk_embeds           r)   apply_rotary_pos_embr6   )   sc    ( --
&
&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                             |||||          } |                     |||z  ||          S )z
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r   N)r#   expandreshape)r7   r8   batchnum_key_value_headsslenhead_dims         r)   	repeat_kvrA   D   s    
 2?1D.Ehzz!!!!QQQaaa"23::5BUW\^bdlmmM  (;e(CT8TTTr+           modulequerykeyvalueattention_maskscalingdropoutkwargsc                 R   t          || j                  }t          || j                  }	t          j        ||                    dd                    |z  }
|$|d d d d d d d |j        d         f         }|
|z   }
t          j                            |
dt          j	                  
                    |j                  }
t          j                            |
|| j                  }
t          j        |
|	          }|                    dd                                          }||
fS )Nr    r   r   )r"   dtype)ptrainingr   )rA   num_key_value_groupsr$   matmul	transposer#   nn
functionalsoftmaxfloat32torM   rI   rO   
contiguous)rC   rD   rE   rF   rG   rH   rI   rJ   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r)   eager_attention_forwardr^   P   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$$r+   c                       e Zd ZdZdedef fdZ eddd          	 	 dd
ej	        de
ej	        ej	        f         deej	                 dee         deej                 de
ej	        eej	                 f         fd            Z xZS )PhiAttentionz=Multi-headed attention from 'Attention Is All You Need' paperconfig	layer_idxc                    t                                                       || _        || _        t	          |d|j        |j        z            | _        |j        |j        z  | _	        | j        dz  | _
        |j        | _        d| _        t          j        |j        |j        | j        z  d          | _        t          j        |j        |j        | j        z  d          | _        t          j        |j        |j        | j        z  d          | _        t          j        |j        | j        z  |j        d          | _        t'          | j        |j        z            | _        |j        | _        | j        r^t          j        |j        |j        z  |j        d          | _        t          j        |j        |j        z  |j        d          | _        d S d S )Nr@   g      Tbias)epselementwise_affine)super__init__ra   rb   getattrhidden_sizenum_attention_headsr@   r>   rP   rH   attention_dropout	is_causalrS   Linearq_projk_projv_projdenseintpartial_rotary_factorrotary_ndimsqk_layernorm	LayerNormlayer_norm_epsq_layernormk_layernormselfra   rb   	__class__s      r)   ri   zPhiAttention.__init__m   s   "
F4F&Jd4dee$*$>&B\$\!}d*!'!9i 2F4NQUQ^4^eijjji 2F4NQUQ^4^eijjji 2F4NQUQ^4^eijjjYv9DMI6K]dhiii
0L LMM"/ 	!|"f&@@fF[pt     D  "|"f&@@fF[pt     D		 	r+   past_key_valuepast_key_values4.58new_nameversionNr7   position_embeddingsrG   cache_positionr9   c                    |j         d d         }g |d| j        R }|                     |                              |                              dd          }	|                     |                              |                              dd          }
|                     |                              |                              dd          }| j        r*|                     |	          }	| 	                    |
          }
|\  }}|	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        |          \  }
}t           }| j        j        dk    rt&          | j        j                 } || |	|
||f| j        sdn| j        | j        d	|\  }} |j        g |dR                                  }|                     |          }||fS )
Nr   r   r    .r!   )r1   r0   r   eagerrB   )rI   rH   )r#   r@   rp   viewrR   rq   rr   rw   rz   r{   rv   r6   r$   r%   updaterb   r^   ra   _attn_implementationr   rO   rm   rH   r<   rX   rs   )r}   r7   r   rG   r   r   rJ   input_shapehidden_shapequery_statesrY   rZ   r0   r1   	query_rot
query_passkey_rotkey_passcache_kwargsattention_interfacer]   r[   s                         r)   forwardzPhiAttention.forward   s    $)#2#.88b8$-88{{=1166|DDNNqRSTT[[//44\BBLLQPQRR
{{=1166|DDNNqRSTT 	6++L99L))*55J&S 1 1112d/1112 	
 s/d///0sD-///0 
 2)Wc3OO	7 y)Z!8bAAAY2;;;
&#&snUUL'6'='=j,X\Xfht'u'u$J(?;+w66"9$+:Z"[$7$7	%
  $}HCC$2HL	%
 	%
 	%
 	%
!\ *k);;;;;;FFHHjj--L((r+   )NN)__name__
__module____qualname____doc__r   rt   ri   r   r$   Tensortupler   r   
LongTensorr   __classcell__r~   s   @r)   r`   r`   j   s       GGy S      . _%0A6RRR ,059;) ;)|;) #5<#=>;) !.	;)
 "%;) !!12;) 
u|Xel33	4;) ;) ;) SR;) ;) ;) ;) ;)r+   r`   c                   B     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                  | _        d S N)rh   ri   ra   r   
hidden_actactivation_fnrS   ro   rk   intermediate_sizefc1fc2r}   ra   r~   s     r)   ri   zPhiMLP.__init__   sf    #F$569V/1IJJ9V5v7IJJr+   r7   r9   c                     |                      |          }|                     |          }|                     |          }|S r   )r   r   r   )r}   r7   s     r)   r   zPhiMLP.forward   s=    //**=99//r+   )r   r   r   ri   r$   r   r   r   r   s   @r)   r   r      sc        K K K K KU\ el        r+   r   c                   v    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         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 )PhiDecoderLayerra   rb   c                 "   t                                                       t          ||          | _        t	          |          | _        t          j        |j        |j	                  | _
        t          j        |j                  | _        d S )N)rb   rf   )rh   ri   r`   	self_attnr   mlprS   rx   rk   ry   input_layernormDropoutresid_pdropresid_dropoutr|   s      r)   ri   zPhiDecoderLayer.__init__   sr    %f	BBB&>>!|F,>FDYZZZZ(:;;r+   r   r   r   r   NFr7   rG   r2   output_attentions	use_cacher   r   r9   c	                    |}
|                      |          } | j        d||||||||d|	\  }}|                     |          }|                     |                     |                    }||z   |
z   }|f}|r||fz  }|S )N)r7   rG   r2   r   r   r   r   r    )r   r   r   r   )r}   r7   rG   r2   r   r   r   r   r   rJ   residualattn_outputsself_attn_weightsfeed_forward_hidden_statesoutputss                  r)   r   zPhiDecoderLayer.forward   s     !,,];; +9$. 
+
')%+/) 3
+
 
+
 
+
 
+
'' )),77%)%7%78O8O%P%P"$'AAHL " 	,)++Gr+   )NNNFFNN)r   r   r   r   rt   ri   r   r$   r   r   r   r   boolr   FloatTensorr   r   r   s   @r)   r   r      sN       <y <S < < < < < < _%0A6RRR 2637+/,1$)59KO% %|% !.% u/0	%
 "%% $D>% D>% !!12% &eEL%,,F&GH% 
u (51BEDU1U+V"WW	X% % % SR% % % % %r+   r   c                   |     e Zd ZU ej        ed<   ddef fdZ ej                    e	d                         Z
 xZS )PhiRotaryEmbeddinginv_freqNra   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)rh   ri   hasattr
isinstancer   dictgetr   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenra   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r}   ra   devicer   r~   s       r)   ri   zPhiRotaryEmbedding.__init__  s    6>** 	'z&:Mt/T/T 	'#044[&BUBYBYZ`BaBabbDNN&DN"("@$*$B!/?+/+<+<T[&+Q+Q($(ZeDDD!%r+   c                 X   | j         d d d d f                                                             |j        d         dd                              |j                  }|d d d d d f                                         }t          |j        j        t                    r|j        j        dk    r|j        j        nd}t          j
        |d          5  |                                |                                z                      dd          }t          j        ||fd	          }|                                | j        z  }|                                | j        z  }	d d d            n# 1 swxY w Y   |                    |j        
          |	                    |j        
          fS )Nr   r   r   mpscpuF)device_typeenabledr    r!   )rM   )r   floatr;   r#   rW   r   r   r   strr$   autocastrR   r%   r0   r   r1   rM   )
r}   r&   r2   inv_freq_expandedposition_ids_expandedr   freqsembr0   r1   s
             r)   r   zPhiRotaryEmbedding.forward  s    !M$4-8>>@@GGHZ[\H]_acdeehhijiqrr ,QQQaaaZ 8 > > @ @'1!(-'E'Ek!(-[`J`J`ahmmfk^UCCC 	5 	5&,,..1F1L1L1N1NNYYZ[]^__E)UEN333C''))d44C''))d44C		5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 vvAGv$$cff17f&;&;;;s   BE++E/2E/r   )r   r   r   r$   r   __annotations__r   ri   no_gradr   r   r   r   s   @r)   r   r     s         l/ /y / / / / / /" U]__< <  _< < < < <r+   r   c                   L    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S )PhiPreTrainedModelra   modelTr   r   )r7   
attentionsN)r   r   r   r   r   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r`   _can_record_outputsr   r+   r)   r   r   '  sl         &*#*+#4"5N!"&(" r+   r   c                   6    e Zd Zdef fdZee	 	 	 	 	 	 	 	 	 ddeej	                 deej
                 deej	                 dee         deej                 d	ee         d
ee         dee         deej	                 dee         defd                        Z xZS )PhiModelra   c                 $   t                                                     j        | _        j        | _        t          j        j        j        | j                  | _        t          j	        fdt          j                  D                       | _        t                    | _        d| _        t          j        j                  | _        t          j        j        j                  | _        |                                  d S )Nc                 0    g | ]}t          |          S r   )r   ).0rb   ra   s     r)   
<listcomp>z%PhiModel.__init__.<locals>.<listcomp>C  s#    aaaI_VY//aaar+   ra   Fr   )rh   ri   pad_token_idpadding_idx
vocab_sizerS   	Embeddingrk   embed_tokens
ModuleListrangenum_hidden_layerslayersr   
rotary_embgradient_checkpointingr   
embd_pdropembed_dropoutrx   ry   final_layernorm	post_initr   s    `r)   ri   zPhiModel.__init__<  s       !. +L):F<NPTP`aamaaaavG_A`A`aaa
 
 -F;;;&+#Z(9::!|F,>FDYZZZ 	r+   N	input_idsrG   r2   r   inputs_embedsr   r   output_hidden_statesr   rJ   r9   c
                    ||n| j         j        }||n| j         j        }||n| j         j        }|d u |d uz  rt	          d          | j        r%| j        r|rt                              d           d}|| 	                    |          }|r|t          | j                   }|	B||                                nd}t          j        |||j        d         z   |j                  }	||	                    d          }t#          | j         |||	||          }|                     |          }|}|                     ||          }|rd	nd }|rd	nd }| j        d | j         j                 D ]1}|r||fz  } ||f||||||	|d
|
}|d         }|r||d         fz  }2|                     |          }|r||fz  }t/          ||r|nd ||          S )Nz:You must specify exactly one of input_ids or inputs_embedszX`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.Fr   r   r   )r   )ra   input_embedsrG   r   r   r2   r   )rG   r2   r   r   r   r   r   )last_hidden_stater   r7   r   )ra   r   r  r   
ValueErrorr  rO   loggerwarning_oncer   r	   get_seq_lengthr$   aranger#   r   r-   r   r  r   r   r   r  r   )r}   r  rG   r2   r   r  r   r   r  r   rJ   past_seen_tokensr\   r7   r   all_hidden_statesall_self_attnsdecoder_layerlayer_outputss                      r)   r   zPhiModel.forwardM  s    2C1N--TXT_Tq$8$D  $+Jj 	 "+!6IIDK<Q	-t";< 	[YZZZ& 	4= 	Y 	j   I  --i88M 	?0*$+>>>O!CRC^==???de"\ "2]5H5K"KTaTh  N )33A66L(;&))+%
 
 
 **=99% #oom\JJ #7@BBD0:d![)H4;+H)HI 	6 	6M# 6!m%55!)M
*) /"3#-$7
 
 
 
M *!,M  6=#3"55,,];;   	2-!11&+/8BOOd+%	
 
 
 	
r+   )	NNNNNNNNN)r   r   r   r   ri   r   r   r   r$   r   r   r   r   r   r   r   r   r   r   r   s   @r)   r   r   :  sN       y      "  151537+/59$(,0/359^
 ^
E,-^
 !.^
 u/0	^

 "%^
   12^
 D>^
 $D>^
 'tn^
 !!12^
 +,^
 
!^
 ^
 ^
 ^ ^
 ^
 ^
 ^
 ^
r+   r   c                   f    e Zd ZdgZddiZddgdgfiZ fdZee	 	 	 	 	 	 	 	 	 dd	e	e
j                 d
e	e
j                 de	e
j                 de	e         de	e
j                 de	e
j                 de	e         de	e
j                 deee
j        f         dee         defd                        Z xZS )PhiForCausalLMzlm_head.weightlm_headcolwise_repr7   logitsc                     t                                          |           t          |          | _        |j        | _        t          j        |j        |j        d          | _        | 	                                 d S )NTrd   )
rh   ri   r   r   r   rS   ro   rk   r  r  r   s     r)   ri   zPhiForCausalLM.__init__  sj       f%%
 +y!3V5FTRRR 	r+   Nr   r  rG   r2   r   r  labelsr   r   logits_to_keeprJ   r9   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, PhiForCausalLM

        >>> model = PhiForCausalLM.from_pretrained("meta-phi/Phi-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-phi/Phi-2-7b-hf")

        >>> prompt = "Hey, are you conscious? Can you talk to me?"
        >>> inputs = tokenizer(prompt, return_tensors="pt")

        >>> # Generate
        >>> generate_ids = model.generate(inputs.input_ids, max_length=30)
        >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
        "Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
        ```)r  rG   r2   r   r  r   r   N)r  r  r   )lossr  r   r7   r   r   )r   r  r   rt   slicer  loss_functionra   r   r   r   r7   r   )r}   r  rG   r2   r   r  r  r   r   r  rJ   r   r7   slice_indicesr  r  s                   r)   r   zPhiForCausalLM.forward  s    @ ,64: 	,
)%+')	,
 	,
 	,
 	,
  18B>SV8W8Wk~ot444]kmAAA}aaa,?@AA%4%pVFt{OeppioppD%#3!/)
 
 
 	
r+   )	NNNNNNNNr   )r   r   r   _tied_weights_keys_tp_plan_pp_planri   r   r   r   r$   r   r   r   r   r   r   rt   r   r   r   r   r   r   s   @r)   r  r    sa       *+=)H_-z:;H      151537+/59-1$(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
 8
 8
 8
 8
r+   r  c                       e Zd ZdS )PhiForSequenceClassificationNr   r   r   r   r+   r)   r'  r'            Dr+   r'  c                       e Zd ZdS )PhiForTokenClassificationNr(  r   r+   r)   r+  r+     r)  r+   r+  )r   r   r  r'  r+  )Nr   )rB   )?typingr   r   r   r$   torch.nnrS   activationsr   cache_utilsr   r	   
generationr
   masking_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   utils.deprecationr   utils.genericr   configuration_phir   
get_loggerr   r  r*   r6   r   rt   rA   Moduler   r^   r`   r   r   r   r   r   r  r'  r+  __all__r   r+   r)   <module>r>     sD   - , , , , , , , , ,        ! ! ! ! ! ! . . . . . . . . ) ) ) ) ) ) / / / / / /         
 P O O O O O O O K K K K K K K K F F F F F F F F & & & & & & R R R R R R R R R R R R 0 0 0 0 0 0 / / / / / / ( ( ( ( ( ( 
	H	%	%( ( (   6	UU\ 	U# 	U%, 	U 	U 	U 	U& % %I%<% 
% <	%
 U\*% % % '(% % % %4V) V) V) V) V)29 V) V) V)r    RY   . . . . .0 . . .b!< !< !< !< !< !< !< !<H        $ r
 r
 r
 r
 r
! r
 r
 r
j H
 H
 H
 H
 H
' H
 H
 H
V	 	 	 	 	#CEW 	 	 		 	 	 	 	 =?Q 	 	 	  r+   