
    hc                        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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&jZ                  e.      Z/ G d dej`                        Z1 G d dej`                        Z2d Z3d7dZ4dejj                  de6dejj                  fdZ7	 	 	 d8dej`                  dejj                  dejj                  d ejj                  d!eejj                     d"e8d#ee8   d$ee8   de9ejj                  ejj                  f   fd%Z: G d& d'ej`                        Z; G d( d)e      Z< G d* d+ej`                        Z=e$ G d, d-e             Z>e$ G d. d/e>             Z?e$ G d0 d1e>e             Z@ G d2 d3ee>      ZA G d4 d5ee>      ZBg d6ZCy)9    )CallableOptionalUnionN   )ACT2FN)CacheDynamicCache)GenerationMixin)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuplelogging)deprecate_kwarg)check_model_inputs   )Gemma2Configc                   <     e Zd Zddedef fdZd Zd Zd Z xZ	S )Gemma2RMSNormdimepsc                     t         |           || _        t        j                  t        j                  |            | _        y N)super__init__r#   nn	Parametertorchzerosweight)selfr"   r#   	__class__s      h/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/transformers/models/gemma2/modeling_gemma2.pyr'   zGemma2RMSNorm.__init__3   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Gemma2RMSNorm._norm8   s4    5;;quuQx}}R}>IJJJr0   c                     | j                  |j                               }|d| j                  j                         z   z  }|j                  |      S )Ng      ?)r9   floatr,   type_as)r-   r8   outputs      r/   forwardzGemma2RMSNorm.forward;   sC    AGGI& 3!2!2!445~~a  r0   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tupler,   shaper#   )r-   s    r/   
extra_reprzGemma2RMSNorm.extra_reprB   s'    ))*+6$((<<r0   )gư>)
__name__
__module____qualname__intr;   r'   r9   r>   rB   __classcell__r.   s   @r/   r!   r!   2   s&    5C 5e 5
K!=r0   r!   c                   $     e Zd Z fdZd Z xZS )	Gemma2MLPc                    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_activationact_fnr-   rO   r.   s     r/   r'   zGemma2MLP.__init__G   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV556r0   c                     | j                  | j                  | j                  |            | j                  |      z        }|S r%   )rU   rW   rS   rT   )r-   r8   rU   s      r/   r>   zGemma2MLP.forwardQ   s6    NN4;;t~~a/@#ADLLQRO#ST	r0   )rC   rD   rE   r'   r>   rG   rH   s   @r/   rJ   rJ   F   s    7r0   rJ   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..Nr3   r2   r"   )rA   r*   cat)r8   x1x2s      r/   rotate_halfr_   V   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r0   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kcossinposition_idsunsqueeze_dimq_embedk_embeds           r/   apply_rotary_pos_embrj   ]   sY    ( --
&C
--
&C3w;q>C/0G3w;q>C/0GGr0   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)rA   expandreshape)rk   rl   batchnum_key_value_headsslenhead_dims         r/   	repeat_kvru   x   so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr0   modulequerykeyvalueattention_maskdropoutscalingsoftcapc                    || j                   dz  }t        || j                        }	t        || j                        }
t        j                  ||	j                  dd            |z  }|||z  }t        j                  |      }||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 )	N      r2   r   r3   )r"   dtype)ptrainingr   )rt   ru   num_key_value_groupsr*   matmul	transposetanhrA   r(   
functionalsoftmaxfloat32tor   r{   r   
contiguous)rv   rw   rx   ry   rz   r{   r|   r}   kwargs
key_statesvalue_statesattn_weightscausal_maskattn_outputs                 r/   eager_attention_forwardr      sA    //4'3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL#g-zz,/#g-!$Q1.D
0@0@0D.D%DE#k1 ==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r0   c                   R    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ej                     ee
ej                        f   fd       Z xZS )Gemma2Attentionz=Multi-headed attention from 'Attention Is All You Need' paperrO   	layer_idxc                    t         |           || _        || _        t	        |d|j
                  |j                  z        | _        |j                  |j                  z  | _	        |j                  dz  | _        | j                  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                         | _        | j                  j*                  | _        |j,                  |   dk(  r|j.                  | _        y d | _        y )Nrt   r   TrM   sliding_attention)r&   r'   rO   r   getattrrP   num_attention_headsrt   rr   r   query_pre_attn_scalarr|   attention_dropout	is_causalr(   rR   attention_biasq_projk_projv_projo_projattn_logit_softcappinglayer_typessliding_windowr-   rO   r   r.   s      r/   r'   zGemma2Attention.__init__   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!33T9!%!>!>ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 '+kk&H&H#7=7I7I)7TXk7kf33qur0   past_key_valuepast_key_values4.58new_nameversionrk   position_embeddingsrz   cache_positionr   rm   c                 `   |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        }| j                  j                  dk7  rt        | j                  j                     } || |	|
||f| j                  r| j                  nd| j                   | j"                  | j$                  d|\  }} |j&                  g |d j)                         }| j+                  |      }||fS )Nr3   r   r2   )re   rd   r   eager        )r{   r|   r   r}   )rA   rt   r   viewr   r   r   rj   updater   r   rO   _attn_implementationr   r   r   r|   r   r   rp   r   r   )r-   rk   r   rz   r   r   r   input_shapehidden_shapequery_statesr   r   rd   re   cache_kwargsattention_interfacer   r   s                     r/   r>   zGemma2Attention.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'6'='=j,X\XfXfht'u$J(?;;++w6"9$++:Z:Z"[$7%
 /3mmD**LL..//%
 %
!\ *k));;;;FFHkk+.L((r0   )NN)rC   rD   rE   __doc__r   rF   r'   r   r*   Tensorr@   r   r   
LongTensorr   r   r>   rG   rH   s   @r/   r   r      s    Gv| v v2 %0A6R ,059+)||+) #5<<#=>+) !.	+)
 "%+) !!1!12+) -.+) 
u||Xell3XeELL>Q5RR	S+) S+)r0   r   c                   z    e 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j                     de
e   de
e   de
e   de
ej                     de	ej                  e
e	ej                  ej                  f      f   fd       Z xZS )Gemma2DecoderLayerrO   r   c                    t         |           |j                  | _        || _        |j                  |   | _        t        ||      | _        t        |      | _	        t        |j                  |j                        | _        t        |j                  |j                        | _        t        |j                  |j                        | _        t        |j                  |j                        | _        y )N)rO   r   r#   )r&   r'   rP   rO   r   attention_typer   	self_attnrJ   mlpr!   rms_norm_epsinput_layernormpost_attention_layernormpre_feedforward_layernormpost_feedforward_layernormr   s      r/   r'   zGemma2DecoderLayer.__init__   s    !--$00;()LV$,V-?-?VEXEXY(5f6H6HfNaNa(b%)6v7I7IvObOb)c&*78J8JPVPcPc*d'r0   r   r   r   r   rk   r   rz   rf   output_attentions	use_cacher   rm   c	                    |}
| j                  |      } | j                  d||||||||d|	\  }}| j                  |      }|
|z   }|}
| j                  |      }| j	                  |      }| j                  |      }|
|z   }|f}|r||fz  }|S )N)rk   r   rz   rf   r   r   r   r    )r   r   r   r   r   r   )r-   rk   r   rz   rf   r   r   r   r   r   residualself_attn_weightsoutputss                r/   r>   zGemma2DecoderLayer.forward   s     !,,]; ,:4>> 
,
' 3)%+/)
,
 
,
(( 55mD =0 66}E/77F =0 ")++Gr0   )NNNFFN)rC   rD   rE   r   rF   r'   r   r*   r   r@   r   r   r   boolFloatTensorr>   rG   rH   s   @r/   r   r      s   e| e e %0A6R
 2637+/,1$)59*||* #5<<#=>* !.	*
 u//0* "%* $D>* D>* !!1!12* 
u  (51B1BEDUDU1U+V"WW	X* S*r0   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 )Gemma2RotaryEmbeddinginv_freqrO   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defaultr   F)
persistent)r&   r'   hasattr
isinstancer   dictgetr   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrO   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r-   rO   devicer   r.   s       r/   r'   zGemma2RotaryEmbedding.__init__1  s    6>*z&:M:Mt/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r0   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   r3   r   mpscpuF)device_typeenabledr2   r[   r   )r   r;   ro   rA   r   r   r   r   strr*   autocastr   r\   rd   r   re   r   )
r-   r8   rf   inv_freq_expandedposition_ids_expandedr   freqsembrd   re   s
             r/   r>   zGemma2RotaryEmbedding.forwardB  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%   )rC   rD   rE   r*   r   __annotations__r   r'   no_gradr   r>   rG   rH   s   @r/   r   r   .  s=    ll/| /" U]]_<  <r0   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)Gemma2PreTrainedModelrO   modelTr   r   )rk   
attentionsN)rC   rD   rE   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   r0   r/   r   r   R  sQ    &*#-.#4"5N!"&+%r0   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   d
ee   deej                     dee   defd              Z xZS )Gemma2ModelrO   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   rO   F)r&   r'   pad_token_idpadding_idx
vocab_sizer(   	EmbeddingrP   embed_tokens
ModuleListrangenum_hidden_layersr   layersr!   r   normr   
rotary_embgradient_checkpointing	post_initr   s      r/   r'   zGemma2Model.__init__g  s     !.. ++LL):):F<N<NPTP`P`ammDI&JbJbDcdy	2d
 "&"4"4&:M:MN	/v>&+# 	 es   D	input_idsrz   rf   r   inputs_embedsr   r   output_hidden_statesr   r   rm   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$|"| j                  st        | j                         }|	F||j                         nd}t        j                  |||j                  d   z   |j                        }	||	j!                  d      }t#        |x}t$              s*| j                   |||	||d}t'        di |t)        di |d	}|}| j+                  ||      }t        j,                  | j                   j.                  d
z  |j0                        }||z  }|rdnd }|rdnd }| j2                  d | j                   j4                   D ]9  }|r||fz  } ||f|||j6                     |||||	d|
}|d   }|s1||d   fz  }; | j9                  |      }|r||fz  }t;        ||||      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   )rO   input_embedsrz   r   r   rf   )full_attentionr   g      ?r   r   )r   rz   rf   r   r   r   r   )last_hidden_stater   rk   r   )rO   r   r  r   
ValueErrorr  r   loggerwarning_oncer  r	   get_seq_lengthr*   arangerA   r   ra   r   r   r   r   r  tensorrP   r   r  r  r   r  r   )r-   r  rz   rf   r   r  r   r   r  r   r   past_seen_tokenscausal_mask_mappingmask_kwargsrk   r   
normalizerall_hidden_statesall_self_attnsdecoder_layerlayer_outputss                        r/   r>   zGemma2Model.forwardw  s    2C1N-TXT_T_TqTq$8$D $++JjJj 	 "+!6IDKK<Q<Q	-t";<YZZ&&4==Yj I  --i8M0*$++>O!CRC^==?de"\\ "2]5H5H5K"KTaThThN )33A6L ?-F ++ -"0"0#2 ,K #5"C{"C%F%U%U# & #oom\J
 \\$++"9"93">mFYFYZ
%
2 #7BD0d![[)H4;;+H+HI 	6M#!m%55!)
$72=3O3OP) /"3#-
 
M *!,M =#3"55'	6* 		-0-!11&+++%	
 	
r0   )	NNNNNNNNN)rC   rD   rE   r   r'   r   r   r   r*   r   r   r   r   r   r   r   r   r>   rG   rH   s   @r/   r  r  e  s   |    151537+/59$(,0/359k
E,,-k
 !.k
 u//0	k

 "%k
   1 12k
 D>k
 $D>k
 'tnk
 !!1!12k
 +,k
 
!k
  k
r0   r  c                   r    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   de	e   de	e
j                     deee
j                  f   defd              Z xZS )Gemma2ForCausalLMzlm_head.weightlm_headcolwise_reprk   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y rL   )
r&   r'   r  r   r	  r(   rR   rP   r+  r  rX   s     r/   r'   zGemma2ForCausalLM.__init__  sU      (
 ++yy!3!3V5F5FUS 	r0   r  rz   rf   r   r  labelsr   r   r  r   logits_to_keeprm   c                 .   | j                   rF| j                  j                  dk7  r-t        j	                  d| j                  j                   d       ||n| j                  j
                  }|	|	n| j                  j                  }	 | j                  d||||||||	|
d	|}|j                  }t        |t              rt        | d      n|}| j                  |dd|ddf         }| j                  j                  G|| j                  j                  z  }t        j                  |      }|| j                  j                  z  }d}| | j                   ||| j"                  fi |}t%        |||j&                  |j(                  |j*                        S )a  
        Example:

        ```python
        >>> from transformers import AutoTokenizer, Gemma2ForCausalLM

        >>> model = Gemma2ForCausalLM.from_pretrained("google/gemma-2-9b")
        >>> tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b")

        >>> 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   zhIt is strongly recommended to train Gemma2 models with the `eager` attention implementation instead of `zp`. Use `eager` with `AutoModelForCausalLM.from_pretrained('<path-to-checkpoint>', attn_implementation='eager')`.N)	r  rz   rf   r   r  r   r   r  r   )lossr-  r   rk   r   r   )r   rO   r   r  r  r   r  r   r  r   rF   slicer+  final_logit_softcappingr*   r   loss_functionr	  r   r   rk   r   )r-   r  rz   rf   r   r  r/  r   r   r  r   r0  r   r   rk   slice_indicesr-  r2  s                     r/   r>   zGemma2ForCausalLM.forward  s   F ==T[[==H#{{??@  Aqr 2C1N-TXT_T_TqTq$8$D $++JjJj 	 ,64:: ,
)%+'/!5),
 ,
  118B>SV8W~ot4]kmA}a,?@A;;..:dkkAAAFZZ'FdkkAAAF%4%%ffdooPPD%#33!//))
 	
r0   )NNNNNNNNNNr   )rC   rD   rE   _tied_weights_keys_tp_plan_pp_planr'   r   r   r   r*   r   r   r   r   r   r   rF   r   r>   rG   rH   s   @r/   r*  r*    sP   *+=)H_-z:;H  151537+/59-1$(,0/35934K
E,,-K
 !.K
 u//0	K

 "%K
   1 12K
 ))*K
 D>K
 $D>K
 'tnK
 !!1!12K
 c5<</0K
 
 K
  K
r0   r*  c                       e Zd Zy)Gemma2ForSequenceClassificationNrC   rD   rE   r   r0   r/   r;  r;  F      r0   r;  c                       e Zd Zy)Gemma2ForTokenClassificationNr<  r   r0   r/   r?  r?  J  r=  r0   r?  )r*  r  r   r;  r?  )Nr   )r   NN)Dtypingr   r   r   r*   torch.nnr(   activationsr   cache_utilsr   r	   
generationr
   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   utils.deprecationr   utils.genericr   configuration_gemma2r   
get_loggerrC   r  Moduler!   rJ   r_   rj   r   rF   ru   r;   r@   r   r   r   r   r   r  r*  r;  r?  __all__r   r0   r/   <module>rS     s  , - ,   ! . ) R B 
 P K F & R R 0 / . 
		H	%=BII =(		  (6	UU\\ 	U# 	U%,, 	U$ ## %II %<< % 
 % <<	 %
 U\\* %  % e_ % e_ % 5<<%& %FH)bii H)V93 9x!<BII !<H O  $ ~
' ~
 ~
B [
- [
 [
|	&FH] 		#@BW 	r0   