
    rhQ                        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$m%Z%  G d dejL                        Z' G d dejL                        Z( G d dejL                        Z)d Z*d6dZ+dejX                  de-dejX                  fdZ.	 d7dejL                  dejX                  d ejX                  d!ejX                  d"eejX                     d#e/d$e/d%ee   fd&Z0 G d' d(ejL                        Z1 G d) d*e      Z2e  G d+ d,e             Z3e  G d- d.e3             Z4e  G d/ d0e3e             Z5 G d1 d2ee3      Z6 G d3 d4ee3      Z7g d5Z8y)8    )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)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 )GemmaRMSNormdimepsc                     t         |           || _        t        j                  t        j                  |            | _        y N)super__init__r    r   	Parametertorchzerosweight)selfr   r    	__class__s      {/var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/gemma/modeling_gemma.pyr$   zGemmaRMSNorm.__init__.   s.    ll5;;s#34    c                     |t        j                  |j                  d      j                  dd      | j                  z         z  S )N   T)keepdim)r&   rsqrtpowmeanr    )r)   xs     r+   _normzGemmaRMSNorm._norm3   s4    5;;quuQx}}R}>IJJJr,   c                     | j                  |j                               }|d| j                  j                         z   z  }|j                  |      S )Ng      ?)r5   floatr(   type_as)r)   r4   outputs      r+   forwardzGemmaRMSNorm.forward6   sC    AGGI& 3!2!2!445~~a  r,   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tupler(   shaper    r)   s    r+   
extra_reprzGemmaRMSNorm.extra_repr=   s'    ))*+6$((<<r,   )gư>)
__name__
__module____qualname__intr7   r$   r5   r:   r?   __classcell__r*   s   @r+   r   r   -   s&    5C 5e 5
K!=r,   r   c                   $     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                     | _        y NFbias)r#   r$   confighidden_sizeintermediate_sizer   Linear	gate_projup_proj	down_projr   
hidden_actact_fnr)   rL   r*   s     r+   r$   zGemmaMLP.__init__B   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r,   c                     | j                  | j                  | j                  |            | j                  |      z        }|S r"   )rR   rT   rP   rQ   )r)   r4   rR   s      r+   r:   zGemmaMLP.forwardL   s6    NN4;;t~~a/@#ADLLQRO#ST	r,   )r@   rA   rB   r$   r:   rD   rE   s   @r+   rG   rG   A   s    0r,   rG   c                   ^     e Zd Zddef fdZ ej                         ed               Z xZ	S )GemmaRotaryEmbeddingrL   c                    t         |           t        |d      rUt        |j                  t
              r;|j                  j                  d|j                  j                  d            | _        nd| _        |j                  | _	        |j                  | _
        || _        t        | j                     | _        | j                  | j                  |      \  }| _        | j                  d|d       | j                   | _        y )Nrope_scaling	rope_typetypedefaultinv_freqF)
persistent)r#   r$   hasattr
isinstancerZ   dictgetr[   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrL   r   rope_init_fnattention_scalingregister_bufferr^   original_inv_freq)r)   rL   devicer^   r*   s       r+   r$   zGemmaRotaryEmbedding.__init__R   s    6>*z&:M:Mt/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r,   c                 b   | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        j                  |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        j	                  |j                   
      	j	                  |j                   
      fS # 1 sw Y   AxY w)Nr   r/   r   mpscpuF)device_typeenabledr.   r   dtype)r^   r7   expandr=   tork   ra   r\   strr&   autocast	transposecatcosrh   sinrs   )
r)   r4   position_idsinv_freq_expandedposition_ids_expandedro   freqsembrz   r{   s
             r+   r:   zGemmaRotaryEmbedding.forwardc   sV    !MM$4-8>>@GGHZHZ[\H]_acdehhijiqiqr ,QaZ 8 > > @'1!((--'E!((--[`J`ahhmmfk^^UC 	5&,,.1F1L1L1NNYYZ[]^_E))UEN3C'')d444C'')d444C		5 vvAGGv$cff177f&;;;	5 	5s    BF%%F.r"   )
r@   rA   rB   r   r$   r&   no_gradr   r:   rD   rE   s   @r+   rX   rX   Q   s3    /{ /" U]]_<  <r,   rX   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..Nr/   r.   rq   )r=   r&   ry   )r4   x1x2s      r+   rotate_halfr   s   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r,   c                     |j                  |      }|j                  |      }| |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krz   r{   r|   unsqueeze_dimq_embedk_embeds           r+   apply_rotary_pos_embr   z   sY    ( --
&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   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)r=   rt   reshape)r   r   batchnum_key_value_headsslenhead_dims         r+   	repeat_kvr      so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr,   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   r/   )r   rs   )ptrainingr   )r   num_key_value_groupsr&   matmulrx   r=   r   
functionalsoftmaxfloat32ru   rs   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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$$r,   c                       e Zd ZdZdedef fdZ	 	 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' paperrL   	layer_idxc                 d   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                        | _        y )Nr   g      TrJ   )r#   r$   rL   r   getattrrM   num_attention_headsr   r   r   r   attention_dropout	is_causalr   rO   attention_biasq_projk_projv_projo_projr)   rL   r   r*   s      r+   r$   zGemmaAttention.__init__   sM   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r,   r   position_embeddingsr   past_key_valuecache_positionr   r   c                 4   |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        }| j                  j                  dk7  rt        | j                  j                     } || |	|
||f| j                  sdn| j                  | j                   d|\  }} |j"                  g |d j%                         }| j'                  |      }||fS )Nr/   r   r.   )r{   rz   r   eager        )r   r   )r=   r   r   viewrx   r   r   r   updater   r   rL   _attn_implementationr   r   r   r   r   r   r   )r)   r   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   rz   r{   cache_kwargsattention_interfacer   r   s                     r+   r:   zGemmaAttention.forward   s    $))#2.88b8$--8{{=166|DNNqRST[[/44\BLLQPQR
{{=166|DNNqRST&S#7jRUWZ#[ j%#&snUL'5'<'<ZW[WeWegs't$J(?;;++w6"9$++:Z:Z"[$7	%
  $}}C$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r,   )NN)r@   rA   rB   __doc__r   rC   r$   r&   Tensorr<   r   r	   
LongTensorr   r   r:   rD   rE   s   @r+   r   r      s    G
{ 
s 
8 +/59))||)) #5<<#=>)) !.	))
 !)) !!1!12)) +,)) 
u||U\\)	*))r,   r   c                   (    e Zd Zdedef fdZ	 	 	 	 	 	 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                     fdZ xZS )GemmaDecoderLayerrL   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        y )N)rL   r   r    )r#   r$   rM   r   	self_attnrG   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr   s      r+   r$   zGemmaDecoderLayer.__init__  sl    !--'vKF#+F,>,>FDWDWX(4V5G5GVM`M`(a%r,   r   r   r|   r   	use_cacher   r   r   r   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|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/ =0r,   )NNNFNN)r@   rA   rB   r   rC   r$   r&   r   r   r   r	   boolr<   r   r   r:   rD   rE   s   @r+   r   r     s    b{ bs b 2637*.$)59KO|| !. u//0	
 ! D> !!1!12 &eELL%,,,F&GH +, 
u||	r,   r   c                   J    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y)GemmaPreTrainedModelrL   modelTr   past_key_values)r   
attentionsN)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_outputsr   r,   r+   r   r   .  sQ    &*#,-#4"5N!"&*$r,   r   c                       e Zd Zdef fdZee	 	 	 	 	 	 	 ddeej                     deej                     deej                     dee   deej                     dee   d	eej                     d
ee   defd              Z xZS )
GemmaModelrL   c           	         t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |j                  |j                        | _        t#        |      | _        d| _        | j)                          y c c}w )Nr   )rL   F)r#   r$   pad_token_idpadding_idx
vocab_sizer   	EmbeddingrM   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normrX   
rotary_embgradient_checkpointing	post_initr   s      r+   r$   zGemmaModel.__init__C  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcivy1c
 !!3!39L9LM	.f=&+# 	 ds   D	input_idsr   r|   r   inputs_embedsr   r   r   r   c                    |d u |d uz  rt        d      || j                  |      }|r|
t               }|F||j                         nd}	t	        j
                  |	|	|j                  d   z   |j                        }||j                  d      }t        | j                  |||||      }
|}| j                  ||      }t	        j                  | j                  j                  dz  |j                        }||z  }| j                  d | j                  j                    D ]  } ||f|
|||||d|} | j#                  |      }t%        ||r|	      S d 	      S )
Nz:You must specify exactly one of input_ids or inputs_embedsr   r   )rk   )rL   input_embedsr   r   r   r|   g      ?rr   )r   r|   r   r   r   r   )last_hidden_stater   )
ValueErrorr   r
   get_seq_lengthr&   aranger=   rk   r   r   rL   r   tensorrM   rs   r   r   r   r   )r)   r   r   r|   r   r   r   r   r   past_seen_tokensr   r   r   
normalizerdecoder_layers                  r+   r:   zGemmaModel.forwardS  s    -t";<YZZ  --i8M0*nO!CRC^==?de"\\ "2]5H5H5K"KTaThThN )33A6L(;;&))+%
 & #oom\J
 \\$++"9"93">mFYFYZ
%
2![[)H4;;+H+HI 
	M)	*).#-$7	 	M
	 		-0&+/8O
 	
>B
 	
r,   )NNNNNNN)r@   rA   rB   r   r$   r   r   r   r&   r   r   r	   FloatTensorr   r   r   r   r:   rD   rE   s   @r+   r   r   A  s    {    151537+/59$(59A
E,,-A
 !.A
 u//0	A

 "%A
   1 12A
 D>A
 !!1!12A
 +,A
 
!A
  A
r,   r   c                   p    e Zd ZdgZddiZddgdgfiZ fdZd Z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      | _        | j                          y rI   )
r#   r$   r   r   r   r   rO   rM   r  r   rU   s     r+   r$   zGemmaForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r,   c                     || _         y r"   r   )r)   decoders     r+   set_decoderzGemmaForCausalLM.set_decoder  s	    
r,   c                     | j                   S r"   r  r>   s    r+   get_decoderzGemmaForCausalLM.get_decoder  s    zzr,   r   r   r|   r   r   labelsr   r   logits_to_keepr   r   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, 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  ra   rC   slicer  loss_functionrL   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18B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r,   )	NNNNNNNNr   )r@   rA   rB   _tied_weights_keys_tp_plan_pp_planr$   r  r  r   r   r   r&   r   r   r	   r
  r   r   rC   r   r   r   r:   rD   rE   s   @r+   r  r    s:   *+=)H_-z:;H  151537+/59-1$(59348
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 ))*8
 D>8
 !!1!128
 c5<</08
 +,8
 
 8
  8
r,   r  c                       e Zd Zy)GemmaForSequenceClassificationNr@   rA   rB   r   r,   r+   r#  r#        r,   r#  c                       e Zd Zy)GemmaForTokenClassificationNr$  r   r,   r+   r'  r'    r%  r,   r'  )r   r  r#  r'  r   )Nr   )r   )9typingr   r   r   r&   r   activationsr   cache_utilsr	   r
   
generationr   masking_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   configuration_gemmar   Moduler   rG   rX   r   r   r   rC   r   r7   r   r   r   r   r   r  r#  r'  __all__r   r,   r+   <module>r7     s  , - ,   ! . ) / 
 P K F & I I / ,=299 =(ryy  <299 <D(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4C)RYY C)L*2 *Z ?  $ T
% T
 T
n N
+_ N
 N
b	%EG[ 		"?AU 	r,   