
     `iS                        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! ddl"m#Z# ddl$m%Z% ddl&m'Z'  G d dej(                  Z) G d dej(                  Z* G d dej(                  Z+d Z,d8dZ-dej.        de/dej.        fdZ0	 d9d ej(        d!ej.        d"ej.        d#ej.        d$eej.                 d%e1d&e1d'ee         fd(Z2 G d) d*ej(                  Z3 G d+ d,e          Z4e  G d- d.e                      Z5e  G d/ d0e5                      Z6e  G d1 d2e5e                      Z7 G d3 d4ee5          Z8 G d5 d6ee5          Z9g d7Z:dS ):    )CallableOptionalUnionN)nn   )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)deprecate_kwarg)check_model_inputs   )GemmaConfigc                   <     e Zd Zddedef fdZd Zd Zd Z xZ	S )	GemmaRMSNormư>dimepsc                     t                                                       || _        t          j        t          j        |                    | _        d S N)super__init__r"   r   	Parametertorchzerosweight)selfr!   r"   	__class__s      |/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/gemma/modeling_gemma.pyr&   zGemmaRMSNorm.__init__/   s?    l5;s#3#344    c                     |t          j        |                    d                              dd          | j        z             z  S )N   T)keepdim)r(   rsqrtpowmeanr"   )r+   xs     r-   _normzGemmaRMSNorm._norm4   s8    5;quuQxx}}R}>>IJJJJr.   c                     |                      |                                          }|d| j                                        z   z  }|                    |          S )Ng      ?)r7   floatr*   type_as)r+   r6   outputs      r-   forwardzGemmaRMSNorm.forward7   sL    AGGII&& 3!2!2!4!445~~a   r.   c                 H    t          | j        j                   d| j         S )Nz, eps=)tupler*   shaper"   )r+   s    r-   
extra_reprzGemmaRMSNorm.extra_repr>   s%    )**<<$(<<<r.   )r    )
__name__
__module____qualname__intr9   r&   r7   r<   r@   __classcell__r,   s   @r-   r   r   .   s        5 5C 5e 5 5 5 5 5 5
K K K! ! != = = = = = =r.   r   c                   $     e Zd Z fdZd Z xZS )GemmaMLPc                    t                                                       || _        |j        | _        |j        | _        t          j        | j        | j        d          | _        t          j        | j        | j        d          | _        t          j        | j        | j        d          | _	        t          |j                 | _        d S NFbias)r%   r&   confighidden_sizeintermediate_sizer   Linear	gate_projup_proj	down_projr   
hidden_actact_fnr+   rM   r,   s     r-   r&   zGemmaMLP.__init__C   s    !-!'!94#3T5KRWXXXy!143IPUVVV4#94;KRWXXXV./r.   c                     |                      |                     |                     |                    |                     |          z            }|S r$   )rS   rU   rQ   rR   )r+   r6   rS   s      r-   r<   zGemmaMLP.forwardM   sA    NN4;;t~~a/@/@#A#ADLLQROO#STT	r.   )rA   rB   rC   r&   r<   rE   rF   s   @r-   rH   rH   B   sG        0 0 0 0 0      r.   rH   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 )GemmaRotaryEmbeddinginv_freqNrM   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defaultrZ   F)
persistent)r%   r&   hasattr
isinstancer\   dictgetr]   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrM   r   rope_init_fnattention_scalingregister_bufferrZ   original_inv_freq)r+   rM   devicerZ   r,   s       r-   r&   zGemmaRotaryEmbedding.__init__U   s    6>** 	'z&:Mt/T/T 	'#044[&BUBYBYZ`BaBabbDNN&DN"("@$*$B!/?+/+<+<T[&+Q+Q($(ZeDDD!%r.   c                 X   | j         d d d d f                                                             |j        d         dd                              |j                  }|d d d d d f                                         }t          |j        j        t                    r|j        j        dk    r|j        j        nd}t          j
        |d          5  |                                |                                z                      dd          }t          j        ||fd	          }|                                | j        z  }|                                | j        z  }	d d d            n# 1 swxY w Y   |                    |j        
          |	                    |j        
          fS )Nr   r1   r   mpscpuF)device_typeenabledr0   r!   dtype)rZ   r9   expandr?   torl   rb   r^   strr(   autocast	transposecatcosri   sinrt   )
r+   r6   position_idsinv_freq_expandedposition_ids_expandedrp   freqsembr{   r|   s
             r-   r<   zGemmaRotaryEmbedding.forwardf   s    !M$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$   )rA   rB   rC   r(   Tensor__annotations__r   r&   no_gradr   r<   rE   rF   s   @r-   rY   rY   R   s         l/ /{ / / / / / /" U]__< <  _< < < < <r.   rY   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..Nr1   r0   rr   )r?   r(   rz   )r6   x1x2s      r-   rotate_halfr   v   s]    	
3"!'"+"""	#B	
3q """	#B9rc2YB''''r.   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kr{   r|   r}   unsqueeze_dimq_embedk_embeds           r-   apply_rotary_pos_embr   }   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?   ru   reshape)r   r   batchnum_key_value_headsslenhead_dims         r-   	repeat_kvr      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  }
|$|d d d d d d d |j        d         f         }|
|z   }
t          j                            |
dt          j	                  
                    |j                  }
t          j                            |
|| j                  }
t          j        |
|	          }|                    dd                                          }||
fS )Nr0   r   r1   )r!   rt   )ptrainingr   )r   num_key_value_groupsr(   matmulry   r?   r   
functionalsoftmaxfloat32rv   rt   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r-   eager_attention_forwardr      s    3 ;<<JUF$?@@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         de
ej	        ej	        f         fd            Z xZS )GemmaAttentionz=Multi-headed attention from 'Attention Is All You Need' paperrM   	layer_idxc                    t                                                       || _        || _        t	          |d|j        |j        z            | _        |j        |j        z  | _	        | j        dz  | _
        |j        | _        d| _        t          j        |j        |j        | j        z  |j                  | _        t          j        |j        |j        | j        z  |j                  | _        t          j        |j        |j        | j        z  |j                  | _        t          j        |j        | j        z  |j        |j                  | _        d S )Nr   g      TrK   )r%   r&   rM   r   getattrrN   num_attention_headsr   r   r   r   attention_dropout	is_causalr   rP   attention_biasq_projk_projv_projo_projr+   rM   r   r,   s      r-   r&   zGemmaAttention.__init__   sB   "
F4F&Jd4dee$*$>&B\$\!}d*!'!9i :T] JQWQf
 
 
 i :T] JQWQf
 
 
 i :T] JQWQf
 
 
 i&68JQWQf
 
 
r.   past_key_valuepast_key_values4.58new_nameversionNr   position_embeddingsr   cache_positionr   r   c                 D   |j         d d         }g |d| j        R }|                     |                              |                              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        d|\  }} |j        g |dR                                  }|                     |          }||fS )Nr1   r   r0   )r|   r{   r   eagerr   )r   r   )r?   r   r   viewry   r   r   r   updater   r   rM   _attn_implementationr   r   r   r   r   r   r   )r+   r   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   r{   r|   cache_kwargsattention_interfacer   r   s                     r-   r<   zGemmaAttention.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&S#7jRUWZ#[#[ j&#&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kk+..L((r.   )NN)rA   rB   rC   __doc__r   rD   r&   r   r(   r   r>   r   r	   
LongTensorr   r   r<   rE   rF   s   @r-   r   r      s       GG
{ 
s 
 
 
 
 
 
. _%0A6RRR ,059)) ))|)) #5<#=>)) !.	))
 "%)) !!12)) +,)) 
u|U\)	*)) )) )) SR)) )) )) )) ))r.   r   c                   4    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j        fd            Z xZS )GemmaDecoderLayerrM   r   c                 4   t                                                       |j        | _        t          ||          | _        t          |          | _        t          |j        |j                  | _	        t          |j        |j                  | _
        d S )N)rM   r   r"   )r%   r&   rN   r   	self_attnrH   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr   s      r-   r&   zGemmaDecoderLayer.__init__  s    !-'vKKKF##+F,>FDWXXX(4V5GVM`(a(a(a%%%r.   r   r   r   r   NFr   r   r}   	use_cacher   r   r   r   c                     |}	|                      |          } | j        d|||||||d|\  }}
|	|z   }|}	|                     |          }|                     |          }|	|z   }|S )N)r   r   r}   r   r   r   r    )r   r   r   r   )r+   r   r   r}   r   r   r   r   r   residual_s              r-   r<   zGemmaDecoderLayer.forward  s     !,,];;)4> 	
')%+) 3	
 	
 	
 	
q !=0 !55mDD// =0r.   )NNNFNN)rA   rB   rC   r   rD   r&   r   r(   r   r   r   r	   boolr>   r   r   r<   rE   rF   s   @r-   r   r     s5       b{ bs b b b b b b _%0A6RRR 2637+/$)59KO | !. u/0	
 "% D> !!12 &eEL%,,F&GH +, 
   SR    r.   r   c                   \     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 fdZ xZS )GemmaPreTrainedModelrM   modelTr   r   )r   
attentionsc                     t                                          |           d|j        j        v r |j        j                                         d S d S )NRMSNorm)r%   _init_weightsr,   rA   r*   datazero_)r+   r   r,   s     r-   r   z"GemmaPreTrainedModel._init_weightsE  sS    f%%% (111M$$&&&&& 21r.   )rA   rB   rC   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   rE   rF   s   @r-   r   r   3  s         &*#,-#4"5N!"&*$ 
' ' ' ' ' ' ' ' 'r.   r   c                       e Zd Zdef fdZee	 	 	 	 	 	 	 ddeej	                 deej
                 deej	                 dee         deej                 d	ee         d
eej	                 dee         defd                        Z xZS )
GemmaModelrM   c                    t                                                     j        | _        j        | _        t          j        j        j        | j                  | _        t          j	        fdt          j                  D                       | _        t          j        j                  | _        t!                    | _        d| _        |                                  d S )Nc                 0    g | ]}t          |          S r   )r   ).0r   rM   s     r-   
<listcomp>z'GemmaModel.__init__.<locals>.<listcomp>V  s$    cccivy11cccr.   r   rM   F)r%   r&   pad_token_idpadding_idx
vocab_sizer   	EmbeddingrN   embed_tokens
ModuleListrangenum_hidden_layerslayersr   r   normrY   
rotary_embgradient_checkpointing	post_initrV   s    `r-   r&   zGemmaModel.__init__O  s       !. +L):F<NPTP`aamcccc5IaCbCbccc
 
 !!39LMMM	.f===&+# 	r.   N	input_idsr   r}   r   inputs_embedsr   r   r   r   c                    |d u |d uz  rt          d          ||                     |          }|r|t          | j                  }|B||                                nd}	t          j        |	|	|j        d         z   |j                  }||	                    d          }t          | j        |||||          }
|}|                     ||          }t          j        | j        j        dz  |j                  }||z  }| 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   )rl   )rM   input_embedsr   r   r   r}   g      ?rs   )r   r}   r   r   r   r   )last_hidden_stater   )
ValueErrorr  r
   rM   get_seq_lengthr(   aranger?   rl   r   r   r	  tensorrN   rt   r  r  r  r   )r+   r  r   r}   r   r  r   r   r   past_seen_tokensr   r   r   
normalizerdecoder_layers                  r-   r<   zGemmaModel.forward_  s    -t";< 	[YZZZ  --i88M 	?0*$+>>>O!CRC^==???de"\ "2]5H5K"KTaTh  N )33A66L(;&))+%
 
 
 & #oom\JJ
 \$+"93">mFYZZZ
%
2![)H4;+H)HI 
	 
	M)M	*) /#-$7	 	 	 	MM 		-00&+/8BOOd
 
 
 	
r.   )NNNNNNN)rA   rB   rC   r   r&   r   r   r   r(   r   r   r	   FloatTensorr   r   r   r   r<   rE   rF   s   @r-   r   r   M  s*       {         151537+/59$(59A
 A
E,-A
 !.A
 u/0	A

 "%A
   12A
 D>A
 !!12A
 +,A
 
!A
 A
 A
 ^ A
 A
 A
 A
 A
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 )GemmaForCausalLMzlm_head.weightlm_headcolwise_repr   logitsc                     t                                          |           t          |          | _        |j        | _        t          j        |j        |j        d          | _        | 	                                 d S rJ   )
r%   r&   r   r   r  r   rP   rN   r  r  rV   s     r-   r&   zGemmaForCausalLM.__init__  sj       ''
 +y!3V5FUSSS 	r.   Nr   r  r   r}   r   r  labelsr   r   logits_to_keepr   r   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, GemmaForCausalLM

        >>> model = GemmaForCausalLM.from_pretrained("google/gemma-7b")
        >>> tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")

        >>> prompt = "What is your favorite condiment?"
        >>> 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]
        "What is your favorite condiment?"
        ```)r  r   r}   r   r  r   r   N)r  r  r  )lossr  r   r   r   r   )r   r  rb   rD   slicer  loss_functionrM   r  r   r   r   r   )r+   r  r   r}   r   r  r  r   r   r   r   outputsr   slice_indicesr  r"  s                   r-   r<   zGemmaForCausalLM.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   )rA   rB   rC   _tied_weights_keys_tp_plan_pp_planr&   r   r   r   r(   r   r   r	   r  r   r   rD   r   r   r   r<   rE   rF   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 )GemmaForSequenceClassificationNrA   rB   rC   r   r.   r-   r+  r+            Dr.   r+  c                       e Zd ZdS )GemmaForTokenClassificationNr,  r   r.   r-   r/  r/    r-  r.   r/  )r   r  r+  r/  r   )Nr   )r   );typingr   r   r   r(   r   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   utils.deprecationr   utils.genericr   configuration_gemmar   Moduler   rH   rY   r   r   r   rD   r   r9   r   r   r   r   r   r  r+  r/  __all__r   r.   r-   <module>r@     sV  , - , , , , , , , , ,        ! ! ! ! ! ! . . . . . . . . ) ) ) ) ) ) / / / / / /         
 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 / / / / / / , , , , , ,= = = = =29 = = =(    ry    !< !< !< !< !<29 !< !< !<H( ( (   6	UU\ 	U# 	U%, 	U 	U 	U 	U& % %I%<% 
% <	%
 U\*% % % '(% % % %4D) D) D) D) D)RY D) D) D)N+ + + + +2 + + +\ ' ' ' ' '? ' ' '2 T
 T
 T
 T
 T
% T
 T
 T
n H
 H
 H
 H
 H
+_ H
 H
 H
V	 	 	 	 	%EG[ 	 	 		 	 	 	 	"?AU 	 	 	  r.   