
    iW                     j   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 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$m%Z%m&Z&m'Z' ddl(m)Z)m*Z* ddl+m,Z,  G d dejZ                        Z. G d dejZ                        Z/ G d dejZ                        Z0d Z1 ed      d:d       Z2dejf                  de4d ejf                  fd!Z5	 d;d"ejZ                  d#ejf                  d$ejf                  d%ejf                  d&ejf                  dz  d'e6d(e6d)e#e%   fd*Z7 ee2       G d+ d,ejZ                               Z8 G d- d.e      Z9e& G d/ d0e!             Z:e& G d1 d2e:             Z;e& G d3 d4e:e             Z< G d5 d6ee:      Z= G d7 d8ee:      Z>g d9Z?y)<    )Callable)OptionalN)nn   )initialization)ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_func_from_hubuse_kernelized_func)create_causal_mask) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)check_model_inputsmaybe_autocast   )GemmaConfigc                   <     e Zd Zddedef fdZd Zd Zd Z xZ	S )GemmaRMSNormdimepsc                     t         |           || _        t        j                  t        j                  |            | _        y N)super__init__r#   r   	Parametertorchzerosweight)selfr"   r#   	__class__s      r/home/obispo/Crisostomo_bridge/mision_env/lib/python3.12/site-packages/transformers/models/gemma/modeling_gemma.pyr'   zGemmaRMSNorm.__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     r.   _normzGemmaRMSNorm._norm6   s4    5;;quuQx}}R}>IJJJr/   c                     | j                  |j                               }|d| j                  j                         z   z  }|j                  |      S )N      ?)r8   floatr+   type_as)r,   r7   outputs      r.   forwardzGemmaRMSNorm.forward9   sC    AGGI& 3!2!2!445~~a  r/   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tupler+   shaper#   )r,   s    r.   
extra_reprzGemmaRMSNorm.extra_repr@   s'    ))*+6$((<<r/   )gư>)
__name__
__module____qualname__intr;   r'   r8   r>   rB   __classcell__r-   s   @r.   r!   r!   0   s&    5C 5e 5
K!=r/   r!   c                   $     e Zd Z fdZd Z xZS )GemmaMLPc                    t         |           || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _	        t        |j                     | _        y NFbias)r&   r'   confighidden_sizeintermediate_sizer   Linear	gate_projup_proj	down_projr   
hidden_actact_fnr,   rO   r-   s     r.   r'   zGemmaMLP.__init__E   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r/   c                     | j                  | j                  | j                  |            | j                  |      z        }|S r%   )rU   rW   rS   rT   )r,   r7   rU   s      r.   r>   zGemmaMLP.forwardO   s6    NN4;;t~~a/@#ADLLQRO#ST	r/   )rC   rD   rE   r'   r>   rG   rH   s   @r.   rJ   rJ   D   s    0r/   rJ   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 )GemmaRotaryEmbeddinginv_freqNrO   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_lenrO   rope_parametersr^   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r,   rO   devicerope_init_fnr\   r-   s        r.   r'   zGemmaRotaryEmbedding.__init__W   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuUr/   rj   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   r1   dtype)rj   rr   )	re   getattrrP   num_attention_headsr)   arangeint64tor;   )rO   rj   rl   baser"   attention_factorr\   s          r.   rf   z4GemmaRotaryEmbedding.compute_default_rope_parametersg   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r/   c                 N   | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        j	                  |j                   
      	j	                  |j                   
      fS # 1 sw Y   AxY w)Nr   r2   r   mpscpuF)device_typeenabledr1   r"   rq   )r\   r;   expandrA   rw   rj   
isinstancetypestrr   	transposer)   catcosrg   sinrr   )
r,   r7   position_idsinv_freq_expandedposition_ids_expandedr}   freqsembr   r   s
             r.   r>   zGemmaRotaryEmbedding.forward   sR    !MM$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)rC   rD   rE   r)   Tensor__annotations__r   r'   staticmethodr   rF   r@   r;   rf   no_gradr   r>   rG   rH   s   @r.   r[   r[   T   s    llV{ V  %)+/"*d"*(* t* 
~u$	%	* *: U]]_<  <r/   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..Nr2   r1   r   )rA   r)   r   )r7   x1x2s      r.   rotate_halfr      sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r/   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          r.   apply_rotary_pos_embr      sY    & --
&C
--
&C3w;q>C/0G3w;q>C/0GGr/   hidden_statesn_reprm   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)rA   r   reshape)r   r   batchnum_key_value_headsslenrp   s         r.   	repeat_kvr      so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr/   modulequerykeyvalueattention_maskscalingdropoutkwargsc                 T   t        || j                        }t        || j                        }	t        j                  ||j	                  dd            |z  }
|#|d d d d d d d |j
                  d   f   }|
|z   }
t        j                  j                  |
dt        j                        j                  |j                        }
t        j                  j                  |
|| j                        }
t        j                  |
|	      }|j	                  dd      j                         }||
fS )Nr1   r   r2   )r"   rr   )ptrainingr   )r   num_key_value_groupsr)   matmulr   rA   r   
functionalsoftmaxfloat32rw   rr   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r.   eager_attention_forwardr      s    3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#k1==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r/   c                       e Zd ZdZdedef fdZ	 	 	 	 ddej                  de	ej                  ej                  f   dz  dej                  dz  d	e
dz  d
ej                  dz  dee   de	ej                  ej                  f   fdZ xZS )GemmaAttentionz=Multi-headed attention from 'Attention Is All You Need' paperrO   	layer_idxc                 |   t         |           || _        || _        t	        |d|j
                  |j                  z        | _        |j                  |j                  z  | _	        | j                  dz  | _
        |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                        | _        y )Nrp   g      use_bidirectional_attentionFrM   )r&   r'   rO   r   rs   rP   rt   rp   r   r   r   attention_dropout	is_causalr   rR   attention_biasq_projk_projv_projo_projr,   rO   r   r-   s      r.   r'   zGemmaAttention.__init__   sZ   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9$V-JERRii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r/   Nr   position_embeddingsr   past_key_valuescache_positionr   rm   c                    |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        j                  | j                  j                  t              } || |	|
||f| j                  sdn| j                   | j"                  d|\  }} |j$                  g |d j'                         }| j)                  |      }||fS )Nr2   r   r1   )r   r   r           )r   r   )rA   rp   r   viewr   r   r   r   updater   r   get_interfacerO   _attn_implementationr   r   r   r   r   r   r   )r,   r   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   r   r   cache_kwargsattention_interfacer   r   s                     r.   r>   zGemmaAttention.forward   s    $))#2.88b8$--8{{=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	%
  $}}C$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r/   )NNNN)rC   rD   rE   __doc__r   rF   r'   r)   r   r@   r	   
LongTensorr   r   r>   rG   rH   s   @r.   r   r      s    G
{ 
s 
4 IM.2(,26))||)) #5<<#=>E)) t+	))
 )) ((4/)) +,)) 
u||U\\)	*))r/   r   c                   "    e Zd Zdedef fdZ	 	 	 	 	 	 ddej                  dej                  dz  dej                  dz  de	dz  d	e
dz  d
ej                  dz  deej                  ej                  f   dz  dee   dej                  fdZ xZS )GemmaDecoderLayerrO   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        y )N)rO   r   r#   )r&   r'   rP   r   	self_attnrJ   mlpr!   rms_norm_epsinput_layernormpost_attention_layernormr   s      r.   r'   zGemmaDecoderLayer.__init__$  sl    !--'vKF#+F,>,>FDWDWX(4V5G5GVM`M`(a%r/   Nr   r   r   r   	use_cacher   r   r   rm   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r   r   r   r   r   r   r    )r   r   r   r   )r,   r   r   r   r   r   r   r   r   residual_s              r.   r>   zGemmaDecoderLayer.forward.  s     !,,];)4>> 	
')%+) 3	
 	
q !=0 !55mD/ =0r/   )NNNFNN)rC   rD   rE   r   rF   r'   r)   r   r   r	   boolr@   r   r   r>   rG   rH   s   @r.   r   r   #  s    b{ bs b /304(,!&26HL|| t+ &&-	
  $; ((4/ #5<<#=>E +, 
r/   r   c                        e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedZ ej$                          fd       Z xZS )GemmaPreTrainedModelrO   modelTr   r   )r   
attentionsc                     t         |   |       d|j                  j                  v r t	        j
                  |j                         y y )NRMSNorm)r&   _init_weightsr-   rC   initzeros_r+   )r,   r   r-   s     r.   r   z"GemmaPreTrainedModel._init_weightsb  s9    f%((111KK& 2r/   )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)   r   r   rG   rH   s   @r.   r   r   P  sn    &*#,-#4"5N!"&*$
 U]]_' 'r/   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 )
GemmaModelrO   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GemmaModel.__init__l  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcivy1c
 !!3!39L9LM	.f=&+# 	 ds   DN	input_idsr   r   r   inputs_embedsr   r   r   rm   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        | j                  |||||      }
|}| j                  ||      }t        j                  | j                  j                  dz  |j                  	      }||z  }| j                  d | j                  j                    D ]  } ||f|
|||||d
|} | j#                  |      }t%        ||r|      S d       S )Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r   )rj   )rO   input_embedsr   r   r   r   )r   g      ?rq   )r   r   r   r   r   r   )last_hidden_stater   )
ValueErrorr  r
   rO   get_seq_lengthr)   ru   rA   rj   r   r   r  tensorrP   rr   r	  r  r
  r   )r,   r  r   r   r   r  r   r   r   past_seen_tokensr   r   r   
normalizerdecoder_layers                  r.   r>   zGemmaModel.forward|  s    -t";<YZZ  --i8M0*$++>O!CRC^==?de"\\ "2]5H5H5K"KTaThThN )33A6L(;;&))+%
 &"oom,oW
 \\$++"9"93">mFYFYZ
%
2![[)H4;;+H+HI 
	M)	*) /#-$7	 	M
	 		-0&+/8O
 	
>B
 	
r/   )NNNNNNN)rC   rD   rE   r   r'   r   r   r)   r   r   r	   FloatTensorr   r   r   r   r>   rG   rH   s   @r.   r   r   j  s    {    .2.204(,26!%26?
##d*?
 t+?
 &&-	?

 ?
 ((4/?
 $;?
 ((4/?
 +,?
 
!?
  ?
r/   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 )GemmaForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr   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GemmaForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r/   Nr  r   r   r   r  labelsr   r   logits_to_keepr   rm   c
                 z    | j                   d|||||||d|
}|j                  }t        |	t              rt	        |	 d      n|	}| j                  |dd|ddf         }d}|* | j                  d||| j                  j                  d|
}t        |||j                  |j                  |j                        S )a|  
        Example:

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

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

        >>> prompt = "What is your favorite condiment?"
        >>> inputs = tokenizer(prompt, return_tensors="pt")

        >>> # Generate
        >>> generate_ids = model.generate(inputs.input_ids, max_length=30)
        >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
        "What is your favorite condiment?"
        ```)r  r   r   r   r  r   r   N)r  r   r  )lossr  r   r   r   r   )r   r  r   rF   slicer  loss_functionrO   r  r   r   r   r   )r,   r  r   r   r   r  r   r   r   r!  r   outputsr   slice_indicesr  r#  s                   r.   r>   zGemmaForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r/   )	NNNNNNNNr   )rC   rD   rE   _tied_weights_keys_tp_plan_pp_planr'   r   r   r)   r   r   r	   r  r   rF   r   r   r   r>   rG   rH   s   @r.   r  r    s/   *,GH23H_-z:;H  .2.204(,26*.!%26-.8
##d*8
 t+8
 &&-	8

 8
 ((4/8
   4'8
 $;8
 ((4/8
 ell*8
 +,8
 
 8
  8
r/   r  c                       e Zd Zy)GemmaForSequenceClassificationNrC   rD   rE   r   r/   r.   r,  r,        r/   r,  c                       e Zd Zy)GemmaForTokenClassificationNr-  r   r/   r.   r0  r0    r.  r/   r0  )r   r  r,  r0  r   )r   )r   )@collections.abcr   typingr   r)   r    r   r   activationsr   cache_utilsr	   r
   
generationr   integrationsr   r   masking_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   configuration_gemmar   Moduler!   rJ   r[   r   r   r   rF   r   r;   r   r   r   r   r   r  r,  r0  __all__r   r/   r.   <module>rC     s  , %    & ! . ) I / 
 P K F & I I ? ,=299 =(ryy  ><299 ><B( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%4 )*C)RYY C) +C)L*2 *Z '? ' '2 R
% R
 R
j H
+_ H
 H
V	%EG[ 		"?AU 	r/   