
    i_                        d dl mZ d dlmZ d dlZd dlm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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-m.Z. ddl/m0Z0  G d dejb                        Z2 G d dejb                        Z3 G d dejb                        Z4d Z5 ed      d:d       Z6dejn                  de8d ejn                  fd!Z9	 	 	 d;d"ejb                  d#ejn                  d$ejn                  d%ejn                  d&ejn                  dz  d'e:d(e:dz  d)e:dz  d e;ejn                  ejn                  f   fd*Z< ee6       G d+ d,ejb                               Z= G d- d.e      Z>e* G d/ d0e%             Z?e* G d1 d2e?             Z@e* G d3 d4e?e             ZA G d5 d6ee?      ZB G d7 d8ee?      ZCg d9ZDy)<    )Callable)OptionalN   )initialization)ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_func_from_hubuse_kernelized_func)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)check_model_inputsmaybe_autocast   )Gemma2Configc                   <     e Zd Zddedef fdZd Zd Zd Z xZ	S )Gemma2RMSNormdimepsc                     t         |           || _        t        j                  t        j                  |            | _        y N)super__init__r$   nn	Parametertorchzerosweight)selfr#   r$   	__class__s      t/home/obispo/Crisostomo_bridge/mision_env/lib/python3.12/site-packages/transformers/models/gemma2/modeling_gemma2.pyr(   zGemma2RMSNorm.__init__1   s.    ll5;;s#34    c                     |t        j                  |j                  d      j                  dd      | j                  z         z  S )N   T)keepdim)r+   rsqrtpowmeanr$   )r.   xs     r0   _normzGemma2RMSNorm._norm6   s4    5;;quuQx}}R}>IJJJr1   c                     | j                  |j                               }|d| j                  j                         z   z  }|j                  |      S )N      ?)r:   floatr-   type_as)r.   r9   outputs      r0   forwardzGemma2RMSNorm.forward9   sC    AGGI& 3!2!2!445~~a  r1   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tupler-   shaper$   )r.   s    r0   
extra_reprzGemma2RMSNorm.extra_repr@   s'    ))*+6$((<<r1   )gư>)
__name__
__module____qualname__intr=   r(   r:   r@   rD   __classcell__r/   s   @r0   r"   r"   0   s&    5C 5e 5
K!=r1   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.   rQ   r/   s     r0   r(   zGemma2MLP.__init__E   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV556r1   c                     | j                  | j                  | j                  |            | j                  |      z        }|S r&   )rW   rY   rU   rV   )r.   r9   rW   s      r0   r@   zGemma2MLP.forwardO   s6    NN4;;t~~a/@#ADLLQRO#ST	r1   )rE   rF   rG   r(   r@   rI   rJ   s   @r0   rL   rL   D   s    7r1   rL   c                        e Zd ZU ej                  ed<   ddef fdZe	 	 	 ddedz  de	d   de
dz  ded	ef   fd
       Z ej                         ed               Z xZS )Gemma2RotaryEmbeddinginv_freqNrQ   c                    t         |           |j                  | _        |j                  | _        || _        | j
                  j                  d   | _        | j                  }| j                  dk7  rt        | j                     } || j
                  |      \  }| _
        | j                  d|d       | j                  d|j                         d       y )N	rope_typedefaultr^   F)
persistentoriginal_inv_freq)r'   r(   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrQ   rope_parametersr`   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r.   rQ   devicerope_init_fnr^   r/   s        r0   r(   zGemma2RotaryEmbedding.__init__W   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuUr1   rl   ztorch.deviceseq_lenreturnztorch.Tensorc                    | j                   d   }t        | dd      xs | j                  | j                  z  }d}d|t	        j
                  d|dt        j                        j                  |t        j                        |z  z  z  }||fS )	a  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
            device (`torch.device`):
                The device to use for initialization of the inverse frequencies.
            seq_len (`int`, *optional*):
                The current sequence length. Unused for this type of RoPE.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        
rope_thetahead_dimNr<   r   r3   dtype)rl   rt   )	rg   getattrrR   num_attention_headsr+   arangeint64tor=   )rQ   rl   rn   baser#   attention_factorr^   s          r0   rh   z5Gemma2RotaryEmbedding.compute_default_rope_parametersg   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r1   c                 N   | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        j	                  |j                   
      	j	                  |j                   
      fS # 1 sw Y   AxY w)Nr   r4   r   mpscpuF)device_typeenabledr3   r#   rs   )r^   r=   expandrC   ry   rl   
isinstancetypestrr   	transposer+   catcosri   sinrt   )
r.   r9   position_idsinv_freq_expandedposition_ids_expandedr   freqsembr   r   s
             r0   r@   zGemma2RotaryEmbedding.forward   sR    !MM$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&   )NNN)rE   rF   rG   r+   Tensor__annotations__r    r(   staticmethodr   rH   rB   r=   rh   no_gradr   r@   rI   rJ   s   @r0   r]   r]   T   s    llV| V  &*+/"*t#*(* t* 
~u$	%	* *: U]]_<  <r1   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..Nr4   r3   r   )rC   r+   r   )r9   x1x2s      r0   rotate_halfr      sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r1   rotary_pos_embc                     |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.
        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   unsqueeze_dimq_embedk_embeds          r0   apply_rotary_pos_embr      sY    & --
&C
--
&C3w;q>C/0G3w;q>C/0GGr1   hidden_statesn_repro   c                     | 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)rC   r   reshape)r   r   batchnum_key_value_headsslenrr   s         r0   	repeat_kvr      so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr1   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      r3   r   r4   )r#   rt   )ptrainingr   )rr   r   num_key_value_groupsr+   matmulr   tanhrC   r)   
functionalsoftmaxfloat32ry   rt   r   r   
contiguous)r   r   r   r   r   r   r   r   kwargs
key_statesvalue_statesattn_weightscausal_maskattn_outputs                 r0   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$$r1   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z  dej                  dz  d	e
dz  d
ej                  dz  dee   de	ej                  ej                  dz  e	ej                     dz  f   fdZ xZS )Gemma2Attentionz=Multi-headed attention from 'Attention Is All You Need' paperrQ   	layer_idxc                 Z   t         |           t        |d      r|j                  |   nd | _        || _        || _        t        |d|j                  |j                  z        | _
        |j                  |j                  z  | _        |j                  dz  | _        | j
                  j                  | _        t        |d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
                  j0                  | _        | j                  dk(  r|j2                  | _        y d | _        y )Nlayer_typesrr   r   use_bidirectional_attentionFrO   sliding_attention)r'   r(   hasattrr   
layer_typerQ   r   ru   rR   rv   rr   r   r   query_pre_attn_scalarr   attention_dropout	is_causalr)   rT   attention_biasq_projk_projv_projo_projattn_logit_softcappingsliding_windowr.   rQ   r   r/   s      r0   r(   zGemma2Attention.__init__   s   ;B6=;Y&,,Y7_c"
F4F4F&JdJd4de$*$>$>&B\B\$\!33T9!%!>!>$V-JERRii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 '+kk&H&H#7;J]7]f33cgr1   Nr   position_embeddingsr   past_key_valuescache_positionr   ro   c                 D   |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        j                  | j                  j                  t              } || |	|
||f| j                  r| j                   nd| j"                  | j$                  | j&                  d|\  }} |j(                  g |d j+                         }| j-                  |      }||fS )Nr4   r   r3   )r   r   r           )r   r   r   r   )rC   rr   r   viewr   r   r   r   updater   r   get_interfacerQ   _attn_implementationr   r   r   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                     r0   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$J(?(M(MKK,,.E)
 %8%
 /3mmD**LL..//%
 %
!\ *k));;;;FFHkk+.L((r1   )NNNN)rE   rF   rG   __doc__r    rH   r(   r+   r   rB   r   
LongTensorr   r   r@   rI   rJ   s   @r0   r   r      s    Gh| h h: IM.2(,26+)||+) #5<<#=>E+) t+	+)
 +) ((4/+) -.+) 
u||U\\D0%2E2LL	M+)r1   r   c                   N    e Zd Zdedef fdZ	 	 	 	 	 ddej                  deej                  ej                  f   dz  dej                  dz  dej                  dz  d	e
dz  d
ej                  dz  deej                  eej                  ej                  f   dz  f   fdZ xZS )Gemma2DecoderLayerrQ   r   c                    t         |           |j                  | _        || _        |j                  |   | _        t        ||      | _        t        |      | _	        t        |j                  |j                        | _        t        |j                  |j                        | _        t        |j                  |j                        | _        t        |j                  |j                        | _        y )N)rQ   r   r$   )r'   r(   rR   rQ   r   attention_typer   	self_attnrL   mlpr"   rms_norm_epsinput_layernormpost_attention_layernormpre_feedforward_layernormpost_feedforward_layernormr   s      r0   r(   zGemma2DecoderLayer.__init__2  s    !--$00;()LV$,V-?-?VEXEXY(5f6H6HfNaNa(b%)6v7I7IvObOb)c&*78J8JPVPcPc*d'r1   Nr   r   r   r   r   r   ro   c           
         |}| j                  |      } | j                  d||||||d|\  }}	| j                  |      }||z   }|}| j                  |      }| j	                  |      }| j                  |      }||z   }|S )N)r   r   r   r   r   r    )r   r   r   r   r   r   )
r.   r   r   r   r   r   r   r   residual_s
             r0   r@   zGemma2DecoderLayer.forward?  s     !,,]; *4>> 
' 3)%+)
 
q 55mD =0 66}E/77F =0r1   )NNNNN)rE   rF   rG   r    rH   r(   r+   r   rB   r   r   FloatTensorr@   rI   rJ   s   @r0   r   r   1  s    e| e e  IM.204(,26!||! #5<<#=>E! t+	!
 &&-! ! ((4/! 
u  %(9(95;L;L(L"MPT"TT	U!r1   r   c                        e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedZ ej$                          fd       Z xZS )Gemma2PreTrainedModelrQ   modelTr   r   )r   
attentionsc                     t         |   |       d|j                  j                  v r t	        j
                  |j                         y y )NRMSNorm)r'   _init_weightsr/   rE   initzeros_r-   )r.   r   r/   s     r0   r   z#Gemma2PreTrainedModel._init_weightsu  s9    f%((111KK& 2r1   )rE   rF   rG   r    r   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsr+   r   r   rI   rJ   s   @r0   r   r   c  sn    &*#-.#4"5N!"&+%
 U]]_' 'r1   r   c                       e Zd Zdef fdZee	 	 	 	 	 	 	 ddej                  dz  dej                  dz  dej                  dz  de
dz  dej                  dz  d	edz  d
ej                  dz  dee   defd              Z xZS )Gemma2ModelrQ   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   F)r'   r(   pad_token_idpadding_idx
vocab_sizer)   	EmbeddingrR   embed_tokens
ModuleListrangenum_hidden_layersr   layersr"   r   normr]   
rotary_embgradient_checkpointing	post_initr   s      r0   r(   zGemma2Model.__init__  s     !.. ++LL):):F<N<NPTP`P`ammDI&JbJbDcdy	2d
 "&"4"4&:M:MN	/7&+# 	 es   D N	input_idsr   r   r   inputs_embeds	use_cacher   r   ro   c           
         |d u |d uz  rt        d      || j                  |      }|r|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  |j"                  	      }||z  }| j$                  d | j                  j&                   D ]  } ||f|
|j(                     ||||d
|}  | j+                  |      }t-        ||      S )Nz:You must specify exactly one of input_ids or inputs_embeds)rQ   r   r   )rl   )rQ   input_embedsr   r   r   r   )full_attentionr   g      ?rs   )r   r   r   r   r   )last_hidden_stater   r   )
ValueErrorr  r	   rQ   get_seq_lengthr+   rw   rC   rl   r   r   dictr   r   r  tensorrR   rt   r  r  r   r  r   )r.   r  r   r   r   r  r  r   r   past_seen_tokenscausal_mask_mappingmask_kwargsr   r   
normalizerdecoder_layers                   r0   r@   zGemma2Model.forward  s    -t";<YZZ *.*;*;I*FM0*$++>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![[)H4;;+H+HI 		M)2=3O3OP$7) /- M		 		-0&++
 	
r1   )NNNNNNN)rE   rF   rG   r    r(   r   r   r+   r   r   r   r   boolr   r   r   r@   rI   rJ   s   @r0   r  r  }  s    |    .2.204(,26!%26H
##d*H
 t+H
 &&-	H

 H
 ((4/H
 $;H
 ((4/H
 +,H
 
!H
  H
r1   r  c                   b    e Zd ZddiZddiZddgdgfiZ fdZee	 	 	 	 	 	 	 	 	 dd	e	j                  dz  d
e	j                  dz  de	j                  dz  dedz  de	j                  dz  de	j                  dz  dedz  de	j                  dz  dee	j                  z  dee   defd              Z xZS )Gemma2ForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y rN   )
r'   r(   r  r   r  r)   rT   rR   r.  r  rZ   s     r0   r(   zGemma2ForCausalLM.__init__  sU      (
 ++yy!3!3V5F5FUS 	r1   Nr  r   r   r   r  labelsr  r   logits_to_keepr   ro   c
                     | 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  r   r   r   r  r  r   N)lossr0  r   r   r   r   )r   r!  r   rH   slicer.  rQ   final_logit_softcappingr+   r   loss_functionr  r   r   r   r   )r.   r  r   r   r   r  r2  r  r   r3  r   outputsr   slice_indicesr0  r5  s                   r0   r@   zGemma2ForCausalLM.forward  s   B ,64:: 	,
)%+')	,
 	,
  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!//))
 	
r1   )	NNNNNNNNr   )rE   rF   rG   _tied_weights_keys_tp_plan_pp_planr(   r   r   r+   r   r   r   r   r+  rH   r   r   r   r@   rI   rJ   s   @r0   r-  r-    s/   *,GH23H_-z:;H  .2.204(,26*.!%26-.=
##d*=
 t+=
 &&-	=

 =
 ((4/=
   4'=
 $;=
 ((4/=
 ell*=
 +,=
 
 =
  =
r1   r-  c                       e Zd Zy)Gemma2ForSequenceClassificationNrE   rF   rG   r   r1   r0   r?  r?  -      r1   r?  c                       e Zd Zy)Gemma2ForTokenClassificationNr@  r   r1   r0   rC  rC  1  rA  r1   rC  )r-  r  r   r?  rC  )r   )r   NN)Ecollections.abcr   typingr   r+   torch.nnr)    r   r   activationsr   cache_utilsr   r	   
generationr
   integrationsr   r   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   configuration_gemma2r    Moduler"   rL   r]   r   r   r   rH   r   r=   rB   r   r   r   r   r  r-  r?  rC  __all__r   r1   r0   <module>rX     s  * %    & ! . ) I R B 
 P K F & I I ? .=BII =(		  ><BII ><B( *+ ,2	UU\\ 	U# 	U%,, 	U$    %II %<< % 
 % <<	 %
 LL4' %  % T\ % T\ % 5<<%& %F )*H)bii H) +H)V/3 /d 'O ' '2 [
' [
 [
| M
- M
 M
`	&FH] 		#@BW 	r1   