
    Uhg                        d dl mZmZ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 dd
lmZ ddlmZ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! ddl"m#Z#m$Z$m%Z%m&Z&m'Z' ddl(m)Z)  e&       rd dl*m+Z+ ddl,m-Z-  e'j\                  e/      Z0 G d dejb                        Z2 G d dejb                        Z3 G d dejb                        Z4d Z5d;dZ6dejn                  de8dejn                  fdZ9	 d<d ejb                  d!ejn                  d"ejn                  d#ejn                  d$eejn                     d%e:d&e:fd'Z; G d( d)ejb                        Z< G d* d+e      Z=e$ G d, d-e             Z>e$ G d. d/e>             Z? G d0 d1ee#      Z@e$ G d2 d3e>e             ZA e$d45       G d6 d7e>             ZBe$ G d8 d9e>             ZCg d:ZDy)=    )CallableListOptionalTupleUnionN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)AttentionMaskConverter)FlashAttentionKwargs)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast SequenceClassifierOutputWithPastTokenClassifierOutput)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)
LossKwargsauto_docstringcan_return_tupleis_torch_flex_attn_availablelogging   )GemmaConfig)	BlockMask)make_flex_block_causal_maskc                   <     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      z/var/www/catia.catastroantioquia-mas.com/valormas/lib/python3.12/site-packages/transformers/models/gemma/modeling_gemma.pyr*   zGemmaRMSNorm.__init__8   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     r1   _normzGemmaRMSNorm._norm=   s4    5;;quuQx}}R}>IJJJr2   c                     | j                  |j                               }|d| j                  j                         z   z  }|j                  |      S )N      ?)r;   floatr.   type_as)r/   r:   outputs      r1   forwardzGemmaRMSNorm.forward@   sC    AGGI& 3!2!2!445~~a  r2   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tupler.   shaper&   r/   s    r1   
extra_reprzGemmaRMSNorm.extra_reprG   s'    ))*+6$((<<r2   )gư>)
__name__
__module____qualname__intr>   r*   r;   rA   rF   __classcell__r0   s   @r1   r$   r$   7   s&    5C 5e 5
K!=r2   r$   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/   rS   r0   s     r1   r*   zGemmaMLP.__init__L   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r2   c                     | j                  | j                  | j                  |            | j                  |      z        }|S r(   )rY   r[   rW   rX   )r/   r:   rY   s      r1   rA   zGemmaMLP.forwardV   s6    NN4;;t~~a/@#ADLLQRO#ST	r2   )rG   rH   rI   r*   rA   rK   rL   s   @r1   rN   rN   K   s    0r2   rN   c                   ^     e Zd Zddef fdZ ej                         ed               Z xZ	S )GemmaRotaryEmbeddingrS   c                    t         |           t        |d      rG|j                  ;|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*   hasattrra   getrb   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrS   r   rope_init_fnattention_scalingregister_bufferre   original_inv_freq)r/   rS   devicere   r0   s       r1   r*   zGemmaRotaryEmbedding.__init__\   s    6>*v/B/B/N#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r2   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   r5   r   mpscpuF)device_typeenabledr4   r%   dtype)re   r>   expandrD   torp   
isinstancerc   strr,   autocast	transposecatcosrm   sinrx   )
r/   r:   position_idsinv_freq_expandedposition_ids_expandedrt   freqsembr   r   s
             r1   rA   zGemmaRotaryEmbedding.forwardm   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(   )
rG   rH   rI   r    r*   r,   no_gradr   rA   rK   rL   s   @r1   r_   r_   [   s3    /{ /" U]]_<  <r2   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..Nr5   r4   rv   )rD   r,   r   )r:   x1x2s      r1   rotate_halfr   }   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r2   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kr   r   r   unsqueeze_dimq_embedk_embeds           r1   apply_rotary_pos_embr      sY    ( --
&C
--
&C3w;q>C/0G3w;q>C/0GGr2   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)rD   ry   reshape)r   r   batchnum_key_value_headsslenhead_dims         r1   	repeat_kvr      so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr2   modulequerykeyvalueattention_maskscalingdropoutc                 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 )Nr4   r	   r5   )r%   rx   )ptrainingr   )r   num_key_value_groupsr,   matmulr~   rD   r   
functionalsoftmaxfloat32rz   rx   r   r   
contiguous)r   r   r   r   r   r   r   kwargs
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r1   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$$r2   c                   6    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
ej                     e
e	ej                        f   fdZ xZS )GemmaAttentionz=Multi-headed attention from 'Attention Is All You Need' paperrS   	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      TrQ   )r)   r*   rS   r   getattrrT   num_attention_headsr   r   r   r   attention_dropout	is_causalr   rV   attention_biasq_projk_projv_projo_projr/   rS   r   r0   s      r1   r*   zGemmaAttention.__init__   sM   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r2   r   position_embeddingsr   past_key_valuecache_positionr   r   c                    |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        }| j                  j                  dk7  r^| j                  j                  dk(  r(|j                  dd      rt        j                  d	       nt         | j                  j                     } || |	|
||f| j"                  sd
n| j$                  | j&                  d|\  }} |j(                  g |d j+                         }| j-                  |      }||fS )Nr5   r   r4   )r   r   r   eagersdpaoutput_attentionsFz`torch.nn.functional.scaled_dot_product_attention` does not support `output_attentions=True`. Falling back to eager attention. This warning can be removed using the argument `attn_implementation="eager"` when loading the model.        )r   r   )rD   r   r   viewr~   r   r   r   updater   r   rS   _attn_implementationrh   loggerwarning_oncer   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                     r1   rA   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{{//69fjjI\^c>d##L
 '>dkk>^>^&_#$7	%
  $}}C$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r2   )NN)rG   rH   rI   __doc__r    rJ   r*   r,   Tensorr   r   r   
LongTensorr   r   rA   rK   rL   s   @r1   r   r      s    G
{ 
s 
8 +/590)||0) #5<<#=>0) !.	0)
 !0) !!1!120) -.0) 
u||Xell3XeELL>Q5RR	S0)r2   r   c                   p    e Zd Zdedef fdZ	 	 	 	 	 	 	 ddej                  deej                     deej                     dee
   dee   d	ee   d
eej                     deeej                  ej                  f      dee   deej                  eeej                  ej                  f      f   fdZ xZS )GemmaDecoderLayerrS   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        y )N)rS   r   r&   )r)   r*   rT   r   	self_attnrN   mlpr$   rms_norm_epsinput_layernormpost_attention_layernormr   s      r1   r*   zGemmaDecoderLayer.__init__  sl    !--'vKF#+F,>,>FDWDWX(4V5G5GVM`M`(a%r2   r   r   r   r   r   	use_cacher   r   r   r   c	                     |}
| j                  |      } | j                  d||||||||d|	\  }}|
|z   }|}
| j                  |      }| j                  |      }|
|z   }|f}|r||fz  }|S )N)r   r   r   r   r   r   r   r    )r   r   r   r   )r/   r   r   r   r   r   r   r   r   r   residualself_attn_weightsoutputss                r1   rA   zGemmaDecoderLayer.forward  s     !,,]; ,:4>> 
,
')%)/) 3
,
 
,
(( !=0 !55mD/ =0 ")++Gr2   )NNNFFNN)rG   rH   rI   r    rJ   r*   r,   r   r   r   r   boolr   r   r   FloatTensorrA   rK   rL   s   @r1   r   r     s   b{ bs b 2637*.,1$)59KO'||' !.' u//0	'
 !' $D>' D>' !!1!12' &eELL%,,,F&GH' -.' 
u  (51B1BEDUDU1U+V"WW	X'r2   r   c                   F    e Zd ZeZdZdZdgZdgZdZ	dZ
dZdZdZdZdZd Zy)GemmaPreTrainedModelmodelTr   past_key_valuesc                    | j                   j                  }t        |t        j                        rY|j
                  j                  j                  d|       |j                  %|j                  j                  j                          y y t        |t        j                        rf|j
                  j                  j                  d|       |j                  2|j
                  j                  |j                     j                          y y t        |t              r&|j
                  j                  j                  d       y y )Nr   )r9   stdr=   )rS   initializer_ranger{   r   rV   r.   datanormal_rR   zero_	Embeddingpadding_idxr$   fill_)r/   r   r   s      r1   _init_weightsz"GemmaPreTrainedModel._init_weightsV  s    kk++fbii(MM&&CS&9{{&  &&( '-MM&&CS&9!!-""6#5#56<<> .-MM$$S) .r2   N)rG   rH   rI   r    config_classbase_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_2_supports_sdpa_supports_flex_attn_supports_cache_class_supports_quantized_cache_supports_static_cache_supports_attention_backendr   r   r2   r1   r   r   G  sS    L&*#,-#4"5!N  $!"&*r2   r   c                       e Zd Zdef fdZd Zd Zee	 	 	 	 	 	 	 	 	 dde	e
j                     de	e
j                     de	e
j                     de	eeee
j                      f      d	e	e
j                      d
e	e   de	e   de	e   de	e
j                     defd              Z	 ddee
j                  df   de
j                  de
j                  dedef
dZede
j                  dedede
j.                  de
j                  defd       Z xZS )
GemmaModelrS   c           	         t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |j                  |j                        | _        t#        |      | _        d| _        | j)                          y c c}w )Nr   )rS   F)r)   r*   pad_token_idr   
vocab_sizer   r   rT   embed_tokens
ModuleListrangenum_hidden_layersr   layersr$   r   normr_   
rotary_embgradient_checkpointing	post_initr   s      r1   r*   zGemmaModel.__init__f  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcivy1c
 !!3!39L9LM	.f=&+# 	 ds   Dc                     | j                   S r(   r	  rE   s    r1   get_input_embeddingszGemmaModel.get_input_embeddingsv  s       r2   c                     || _         y r(   r  r/   r   s     r1   set_input_embeddingszGemmaModel.set_input_embeddingsy  s
    !r2   	input_idsr   r   r   inputs_embedsr   r   output_hidden_statesr   r   c
                    ||n| j                   j                  }||n| j                   j                  }||n| j                   j                  }|d u |d uz  rt	        d      | j
                  r%| j                  r|rt        j                  d       d}|| j                  |      }|r|
t               }|	F||j                         nd}t        j                  |||j                  d   z   |j                        }	||	j!                  d      }| j#                  |||	||      }|}| j%                  ||      }t        j&                  | j                   j(                  dz  |j*                        }||z  }|rd	nd }|rd	nd }| j,                  d | j                   j.                   D ]+  }|r||fz  } ||||||||	|
      }|d   }|s#||d   fz  }- | j1                  |      }|r||fz  }t3        ||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   rp   g      ?rw   r   )r   r   r   r   r   r   r   )last_hidden_stater   r   
attentions)rS   r   r  r   
ValueErrorr  r   r   r   r	  r   get_seq_lengthr,   arangerD   rp   r   _update_causal_maskr  tensorrT   rx   r  r  r  r   )r/   r  r   r   r   r  r   r   r  r   r   past_seen_tokensr   r   r   
normalizerall_hidden_statesall_self_attnsdecoder_layerlayer_outputss                       r1   rA   zGemmaModel.forward|  sU    2C1N-TXT_T_TqTq$8$D $++JjJj 	 "+!6IDKK<Q<Q	-t";<YZZ&&4==Yj I  --i8M0*nO!CRC^==?de"\\ "2]5H5H5K"KTaThThN )33A6L..M>?L]

 & #oom\J
 \\$++"9"93">mFYFYZ
%
2 #7BD0d![[)H4;;+H+HI 	6M#!m%55!)*)."3#-$7	M *!,M =#3"55%	6( 		-0  -!11&+/8Od+%	
 	
r2   r!   input_tensorc           	         | j                   j                  dk(  r||dk(  j                         r|S y | j                   j                  dk(  r't        |t        j
                        rt        |      }|S ||j                         nd}||j                  nd}| j                   j                  dk(  r(|s&|s$t        j                  |||| j                        ry |j                  }|j                  d   }	|r|j                         }
n1t        |t        j
                        r|j                  d	   n||	z   dz   }
| j                  ||	|
|||j                  d   
      }| j                   j                  dk(  rQ|O|j                   j"                  dv r7|s5t	        j$                  |      j&                  }t        j(                  ||      }|S )Nflash_attention_2r   flex_attentionr   Fr   )r  past_key_values_lengthis_trainingr   r5   )sequence_lengthtarget_lengthrx   r   
batch_size)cudaxpunpu)rS   r   anyr{   r,   r   r"   r   is_compileabler   _ignore_causal_mask_sdpar   rx   rD   get_max_cache_shape5_prepare_4d_causal_attention_mask_with_cache_positionrp   rc   finfomin_unmask_unattended)r/   r   r*  r   r   r   r$  using_compilable_cacherx   r0  r1  r   	min_dtypes                r1   r"  zGemmaModel._update_causal_mask  s    ;;++/BB)~/D.I.I.K%%;;++/??.%,,7!<^!L!!
 @O?Z?99;`aCRC^!?!?di ;;++v5>T]n%>>*'7 MM	 ""&,,Q/!+??AM nell; $$R(%7!;  PP+')#))!, Q 
 KK,,6*%%**.DD%
 E*..I0CCKQZ[Kr2   r0  r1  rx   r2  c                    | | j                         dk(  r| }|S t        j                  |      j                  }t        j                  ||f|||j
                        }|dk7  rt        j                  |d      }|t        j                  ||j
                        |j                  dd      kD  z  }|ddddddf   j                  |ddd      }| |j                         }| j                  d   }	|ddddddd|	f   | ddddddf   j                  |j
                        z   }
|
dk(  }
|ddddddd|	f   j                  |
|      |ddddddd|	f<   |S )	aM  
        Creates a causal 4D mask of shape `(batch_size, 1, query_length, key_value_length)` from a 2D mask of shape
        `(batch_size, key_value_length)`, or if the input `attention_mask` is already 4D, do nothing.

        Args:
            attention_mask (`torch.Tensor`):
                A 2D attention mask of shape `(batch_size, key_value_length)` or a 4D attention mask of shape
                `(batch_size, 1, query_length, key_value_length)`.
            sequence_length (`int`):
                The sequence length being processed.
            target_length (`int`):
                The target length: when generating with static cache, the mask should be as long as the static cache,
                to account for the 0 padding, the part of the cache that is not filled yet.
            dtype (`torch.dtype`):
                The dtype to use for the 4D attention mask.
            cache_position (`torch.Tensor`):
                Indices depicting the position of the input sequence tokens in the sequence.
            batch_size (`torch.Tensor`):
                Batch size.
        N   )
fill_valuerx   rp   r   )diagonalr  r5   r   )r%   r,   r;  r<  fullrp   triur!  r   ry   clonerD   rz   masked_fill)r   r0  r1  rx   r   r2  r   r   r?  mask_lengthpadding_masks              r1   r:  z@GemmaModel._prepare_4d_causal_attention_mask_with_cache_position"  s   < %.*<*<*>!*C(K* ' E*..I** -0Ye\j\q\qK !##jjqA5<<n>S>STWeWmWmnprsWtttK%dD!Q&67>>z1bRTUK))//1,2226*1aL[L+@ANSTVZ\`bcScDdDgDg&&E    ,q05@Aq,;,AV5W5c5c )6Aq!\k\12 r2   	NNNNNNNNN)F)rG   rH   rI   r    r*   r  r  r   r   r   r,   r   r   r   r   r   r   r   r   rA   r"  staticmethodrJ   rx   r:  rK   rL   s   @r1   r  r  d  s   {  !"  151537KO59$(,0/359^
E,,-^
 !.^
 u//0	^

 "%tE4E4E/F(F"GH^
   1 12^
 D>^
 $D>^
 'tn^
 !!1!12^
 
!^
  ^
L #(BellK78B llB 	B
 B  BH 444 4 {{	4
 4 4 4r2   r  c                       e Zd Zy)KwargsForCausalLMN)rG   rH   rI   r   r2   r1   rM  rM  Z  s    r2   rM  c                       e Zd ZdgZddiZddgdgfiZ fdZd Zd Zd	 Z	d
 Z
d Zd Zee	 	 	 	 	 	 	 	 	 	 	 ddeej"                     deej$                     deej"                     dee   deej(                     deej"                     dee   dee   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 rP   )
r)   r*   r  r   r  r   rV   rT   rP  r  r\   s     r1   r*   zGemmaForCausalLM.__init__c  sU     '
 ++yy!3!3V5F5FUS 	r2   c                 .    | j                   j                  S r(   r   r	  rE   s    r1   r  z%GemmaForCausalLM.get_input_embeddingsl      zz&&&r2   c                 &    || j                   _        y r(   rU  r  s     r1   r  z%GemmaForCausalLM.set_input_embeddingso      "'

r2   c                     | j                   S r(   rP  rE   s    r1   get_output_embeddingsz&GemmaForCausalLM.get_output_embeddingsr  s    ||r2   c                     || _         y r(   rZ  )r/   new_embeddingss     r1   set_output_embeddingsz&GemmaForCausalLM.set_output_embeddingsu  s	    %r2   c                     || _         y r(   r   )r/   decoders     r1   set_decoderzGemmaForCausalLM.set_decoderx  s	    
r2   c                     | j                   S r(   r`  rE   s    r1   get_decoderzGemmaForCausalLM.get_decoder{  s    zzr2   r  r   r   r   r  labelsr   r   r  r   logits_to_keepr   r   c                    ||n| j                   j                  }|	|	n| j                   j                  }	 | 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!  
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
            config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
            (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

        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?"
        ```N)	r  r   r   r   r  r   r   r  r   )rR  re  r  lossrR  r   r   r  r   )rS   r   r  r   r  r{   rJ   slicerP  loss_functionr  r   r   r   r  )r/   r  r   r   r   r  re  r   r   r  r   rf  r   r   r   slice_indicesrR  ri  s                     r1   rA   zGemmaForCausalLM.forward~  s   N 2C1N-TXT_T_TqTq$8$D $++JjJj 	
 ,64:: ,
)%+'/!5),
 ,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r2   )NNNNNNNNNNr   )rG   rH   rI   _tied_weights_keys_tp_plan_pp_planr*   r  r  r[  r^  rb  rd  r   r   r   r,   r   r   r   r   r   r   rJ   r   rM  r   rA   rK   rL   s   @r1   rO  rO  ]  s   *+=)H_-z:;H'(&  151537+/59-1$(,0/35934G
E,,-G
 !.G
 u//0	G

 "%G
   1 12G
 ))*G
 D>G
 $D>G
 'tnG
 !!1!12G
 c5<</0G
 *+G
 
 G
  G
r2   rO  a  
    The Gemma Model transformer with a sequence classification head on top (linear layer).

    [`GemmaForSequenceClassification`] uses the last token in order to do the classification, as other causal models
    (e.g. GPT-2) do.

    Since it does classification on the last token, it requires to know the position of the last token. If a
    `pad_token_id` is defined in the configuration, it finds the last token that is not a padding token in each row. If
    no `pad_token_id` is defined, it simply takes the last value in each row of the batch. Since it cannot guess the
    padding tokens when `inputs_embeds` are passed instead of `input_ids`, it does the same (take the last value in
    each row of the batch).
    )custom_introc                       e Zd 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   dee   defd              Z xZS )GemmaForSequenceClassificationc                     t         |   |       |j                  | _        t        |      | _        t        j                  |j                  | j                  d      | _        | j                          y rP   )
r)   r*   
num_labelsr  r   r   rV   rT   scorer  r\   s     r1   r*   z'GemmaForSequenceClassification.__init__  sS      ++'
YYv114??O
 	r2   c                 .    | j                   j                  S r(   rU  rE   s    r1   r  z3GemmaForSequenceClassification.get_input_embeddings  rV  r2   c                 &    || j                   _        y r(   rU  r  s     r1   r  z3GemmaForSequenceClassification.set_input_embeddings  rX  r2   r  r   r   r   r  re  r   r   r  r   c
           
         | j                  ||||||||	      }
|
j                  }| j                  |      }||j                  d   }n|j                  d   }| j                  j
                  |dk7  rt        d      | j                  j
                  d}n||| j                  j
                  k7  j                  |j                  t        j                        }t        j                  |j                  d   |j                  t        j                        }||z  j                  d      }n.d}t        j                  | j                  j                    d       |t        j                  ||j                  	      |f   }d}|| j#                  |||| j                  
      }t%        |||
j&                  |
j(                  |
j*                        S )  
        labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
            Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
            config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
            `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
        r   r   r   r  r   r   r  Nr   r   z=Cannot handle batch sizes > 1 if no padding token is defined.r5   )rp   rx   z will not detect padding tokens in `inputs_embeds`. Results may be unexpected if using padding tokens in conjunction with `inputs_embeds.`r  )rR  re  pooled_logitsrS   rh  )r   r  ru  rD   rS   r  r  rz   rp   r,   int32r!  argmaxr   r   r0   rG   rk  r   r   r   r  )r/   r  r   r   r   r  re  r   r   r  transformer_outputsr   rR  r2  last_non_pad_tokennon_pad_masktoken_indicesr{  ri  s                      r1   rA   z&GemmaForSequenceClassification.forward  s   * 8<zz)%+'/!5 8B 	8
 ,==M* "+J&,,Q/J;;##+
a\]];;##+!#"%)A)AAEEfmmUZU`U`aL!LL)<V]]Z_ZeZefM"/,">!F!Fr!J!#>>**+ ,Z Z
 u||Jv}}MOaab%%VFR_hlhshs%tD/ /??-;;*55
 	
r2   rJ  )rG   rH   rI   r*   r  r  r   r   r   r,   r   r   r   r   r   r   rA   rK   rL   s   @r1   rr  rr    s    '(  151537+/59-1$(,0/3A
E,,-A
 !.A
 u//0	A

 "%A
   1 12A
 ))*A
 D>A
 $D>A
 'tnA
 
*A
  A
r2   rr  c                       e Zd Z fdZd Zd Zee	 	 	 	 	 	 	 	 	 ddee	j                     dee	j                     dee	j                     dee   dee	j                     d	ee	j                     d
ee   dee   dee   defd              Z xZS )GemmaForTokenClassificationc                    t         |   |       |j                  | _        t        |      | _        t        |dd       |j                  }nt        |dd       |j                  }nd}t        j                  |      | _
        t        j                  |j                  |j                        | _        | j                          y )Nclassifier_dropouthidden_dropoutg?)r)   r*   rt  r  r   r   r  r  r   Dropoutr   rV   rT   ru  r  )r/   rS   r  r0   s      r1   r*   z$GemmaForTokenClassification.__init__0  s      ++'
6/6B!'!:!:V-t4@!'!6!6!$zz"45YYv1163D3DE
 	r2   c                 .    | j                   j                  S r(   rU  rE   s    r1   r  z0GemmaForTokenClassification.get_input_embeddings@  rV  r2   c                 &    || j                   _        y r(   rU  r  s     r1   r  z0GemmaForTokenClassification.set_input_embeddingsC  rX  r2   r  r   r   r   r  re  r   r   r  r   c
           
         | j                  ||||||||	      }
|
j                  }| j                  |      }| j                  |      }d}|| j	                  ||| j
                        }t        |||
j                  |
j                        S )ry  rz  N)ri  rR  r   r  )	r   r  r   ru  rk  rS   r   r   r  )r/   r  r   r   r   r  re  r   r   r  r   sequence_outputrR  ri  s                 r1   rA   z#GemmaForTokenClassification.forwardF  s    * ,0::)%+'/!5 ,6 	,
 "33,,7O,%%ffdkkBD$!//))	
 	
r2   rJ  )rG   rH   rI   r*   r  r  r   r   r   r,   r   r   r   r   r   r   rA   rK   rL   s   @r1   r  r  .  s     '(  151537+/59-1$(,0/3*
E,,-*
 !.*
 u//0	*

 "%*
   1 12*
 ))**
 D>*
 $D>*
 'tn*
 
*
  *
r2   r  )r  rO  rr  r  r   )Nr   )r   )Etypingr   r   r   r   r   r,   r   activationsr
   cache_utilsr   r   
generationr   modeling_attn_mask_utilsr   modeling_flash_attention_utilsr   modeling_layersr   modeling_outputsr   r   r   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   r   configuration_gemmar    !torch.nn.attention.flex_attentionr!   integrations.flex_attentionr"   
get_loggerrG   r   Moduler$   rN   r_   r   r   r   rJ   r   r>   r   r   r   r   r  rM  rO  rr  r  __all__r   r2   r1   <module>r     s  , : 9   ! . ) > B 9  L F & h h ,  !;J 
		H	%=299 =(ryy  <299 <D(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % %4J)RYY J)Z22 2j *? * *8 r% r rj ?,j > i
+_ i
 i
X S
%9 S
S
l C
"6 C
 C
Lr2   