
    .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 ddlmZmZ ddlmZm Z  ddl!m"Z"m#Z# ddl$m%Z% ddl&m'Z'm(Z(m)Z) ddl*m+Z+m,Z, ddl-m.Z. ddl/m0Z0  G d dejb                        Z2 G d dejb                        Z3d Z4 ed      d7d       Z5dejl                  de7dejl                  fd Z8	 	 	 d8d!ejb                  d"ejl                  d#ejl                  d$ejl                  d%ejl                  dz  d&e9d'e9dz  d(e9dz  de:ejl                  ejl                  f   fd)Z; ee5       G d* d+ejb                               Z< G d, d-e      Z= G d. d/ejb                        Z>e( G d0 d1e#             Z?e( G d2 d3e?             Z@e( G d4 d5e?e             ZAg d6ZBy)9    )Callable)OptionalN   )initialization)ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_func_from_hubuse_kernelized_func)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs   )VaultGemmaConfigc                   <     e Zd Zddedef fdZd Zd Zd Z xZ	S )VaultGemmaRMSNormdimepsc                     t         |           || _        t        j                  t        j                  |            | _        y N)super__init__r#   nn	Parametertorchzerosweight)selfr"   r#   	__class__s      n/mnt/e/genesis-system/.venv/lib/python3.12/site-packages/transformers/models/vaultgemma/modeling_vaultgemma.pyr'   zVaultGemmaRMSNorm.__init__/   s.    ll5;;s#34    c                     |t        j                  |j                  d      j                  dd      | j                  z         z  S )N   T)keepdim)r*   rsqrtpowmeanr#   )r-   xs     r/   _normzVaultGemmaRMSNorm._norm4   s4    5;;quuQx}}R}>IJJJr0   c                     | j                  |j                               }|d| j                  j                         z   z  }|j                  |      S )N      ?)r9   floatr,   type_as)r-   r8   outputs      r/   forwardzVaultGemmaRMSNorm.forward7   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VaultGemmaRMSNorm.extra_repr>   s'    ))*+6$((<<r0   )gư>)
__name__
__module____qualname__intr<   r'   r9   r?   rC   __classcell__r.   s   @r/   r!   r!   .   s&    5C 5e 5
K!=r0   r!   c                   $     e Zd Z fdZd Z xZS )VaultGemmaMLPc                    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-   rP   r.   s     r/   r'   zVaultGemmaMLP.__init__C   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%   )rV   rX   rT   rU   )r-   r8   rV   s      r/   r?   zVaultGemmaMLP.forwardM   s6    NN4;;t~~a/@#ADLLQRO#ST	r0   )rD   rE   rF   r'   r?   rH   rI   s   @r/   rK   rK   B   s    7r0   rK   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"   )rB   r*   cat)r8   x1x2s      r/   rotate_halfr`   R   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r0   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kcossinunsqueeze_dimq_embedk_embeds          r/   apply_rotary_pos_embrk   Y   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)rB   expandreshape)rl   rm   batchnum_key_value_headsslenhead_dims         r/   	repeat_kvrv   s   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  }|||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   )ru   rv   num_key_value_groupsr*   matmul	transposetanhr(   
functionalsoftmaxfloat32tor   r|   r   
contiguous)rw   rx   ry   rz   r{   r|   r}   r~   kwargs
key_statesvalue_statesattn_weightsattn_outputs                r/   eager_attention_forwardr      s    //4'3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL#g-zz,/#g-!#n4 ==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r0   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 )VaultGemmaAttentionz=Multi-headed attention from 'Attention Is All You Need' paperrP   	layer_idxc                 B   t         |           t        |d      r|j                  |   nd | _        || _        || _        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
                  j0                  | _        | j                  dk(  r|j2                  | _        y d | _        y )Nlayer_typesru   r   TrN   sliding_attention)r&   r'   hasattrr   
layer_typerP   r   getattrrQ   num_attention_headsru   rs   r   query_pre_attn_scalarr}   attention_dropout	is_causalr(   rS   attention_biasq_projk_projv_projo_projattn_logit_softcappingsliding_windowr-   rP   r   r.   s      r/   r'   zVaultGemmaAttention.__init__   s   ;B6=;Y&,,Y7_c"
F4F4F&JdJd4de$*$>$>&B\B\$\!33T9!%!>!>ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 '+kk&H&H#7;J]7]f33cgr0   Nrl   position_embeddingsr{   past_key_valuescache_positionr   rn   c                 D   |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        j                  | j                  j                  t              } || |	|
||f| j                  r| j                   nd| j"                  | j$                  | j&                  d|\  }} |j(                  g |d j+                         }| j-                  |      }||fS )Nr3   r   r2   )rg   rf   r           )r|   r}   r   r~   )rB   ru   r   viewr   r   r   rk   updater   r   get_interfacerP   _attn_implementationr   r   r   r}   r   r   rq   r   r   )r-   rl   r   r{   r   r   r   input_shapehidden_shapequery_statesr   r   rf   rg   cache_kwargsattention_interfacer   r   s                     r/   r?   zVaultGemmaAttention.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((r0   NNNN)rD   rE   rF   __doc__r   rG   r'   r*   TensorrA   r   
LongTensorr   r   r?   rH   rI   s   @r/   r   r      s    Gh/ hC h: IM.2(,26+)||+) #5<<#=>E+) t+	+)
 +) ((4/+) -.+) 
u||U\\D0%2E2LL	M+)r0   r   c                   F    e Zd Zdedef fdZ	 	 	 	 ddej                  deej                  ej                  f   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 )VaultGemmaDecoderLayerrP   r   c                 V   t         |           |j                  | _        || _        |j                  |   | _        t        ||      | _        t        |      | _	        t        |j                  |j                        | _        t        |j                  |j                        | _        y )N)rP   r   r#   )r&   r'   rQ   rP   r   attention_typer   	self_attnrK   mlpr!   rms_norm_epsinput_layernormpre_feedforward_layernormr   s      r/   r'   zVaultGemmaDecoderLayer.__init__   s    !--$00;,FiP (01C1CI\I\]):6;M;MSYSfSf)g&r0   Nrl   r   r{   position_idsr   r   rn   c           
          |}| j                  |      } | j                  d||||||d|\  }}	||z   }|}| j                  |      }| j                  |      }||z   }|S )N)rl   r   r{   r   r   r    )r   r   r   r   )
r-   rl   r   r{   r   r   r   r   residual_s
             r/   r?   zVaultGemmaDecoderLayer.forward   s     !,,];)4>> 
' 3)%+)
 
q !=0 66}E/ =0r0   r   )rD   rE   rF   r   rG   r'   r*   r   rA   r   r   FloatTensorr?   rH   rI   s   @r/   r   r      s    	h/ 	hC 	h /304(,26|| #5<<#=> t+	
 &&-  ((4/ 
u  %(9(95;L;L(L"MPT"TT	Ur0   r   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 )VaultGemmaRotaryEmbeddinginv_freqNrP   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_lenrP   rope_parametersr   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r-   rP   devicerope_init_fnr   r.   s        r/   r'   z"VaultGemmaRotaryEmbedding.__init__  s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuUr0   r   ztorch.deviceseq_lenrn   z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_thetaru   Nr;   r   r2   r   )r   r   )	r   r   rQ   r   r*   arangeint64r   r<   )rP   r   r   baser"   attention_factorr   s          r/   r   z9VaultGemmaRotaryEmbedding.compute_default_rope_parameters,  s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r0   c                 N   | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        j	                  |j                   
      	j	                  |j                   
      fS # 1 sw Y   AxY w)Nr   r3   r   mpscpuF)device_typeenabledr2   r\   r   )r   r<   rp   rB   r   r   
isinstancetypestrr   r   r*   r]   rf   r   rg   r   )
r-   r8   r   inv_freq_expandedposition_ids_expandedr   freqsembrf   rg   s
             r/   r?   z!VaultGemmaRotaryEmbedding.forwardJ  sR    !MM$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)rD   rE   rF   r*   r   __annotations__r   r'   staticmethodr   rG   rA   r<   r   no_gradr   r?   rH   rI   s   @r/   r   r     s    llV/ V  *.+/"* 4'*(* t* 
~u$	%	* *: U]]_<  <r0   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 )VaultGemmaPreTrainedModelrP   modelTr   r   )rl   
attentionsc                     t         |   |       d|j                  j                  v r t	        j
                  |j                         y y )NRMSNorm)r&   _init_weightsr.   rD   initzeros_r,   )r-   rw   r.   s     r/   r   z'VaultGemmaPreTrainedModel._init_weightsl  s9    f%((111KK& 2r0   )rD   rE   rF   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   rH   rI   s   @r/   r   r   Z  sn    &*#12#4"5N!"&/)
 U]]_' 'r0   r   c                       e Zd Zdef fdZe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 )VaultGemmaModelrP   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(   	EmbeddingrQ   embed_tokens
ModuleListrangenum_hidden_layersr   layersr!   r   normr   
rotary_embgradient_checkpointing	post_initr   s      r/   r'   zVaultGemmaModel.__init__v  s     !.. ++LL):):F<N<NPTP`P`ammHMfNfNfHgh9#FI6h
 &f&8&8f>Q>QR	3F;&+# 	 is   D N	input_idsr{   r   r   inputs_embeds	use_cacher   r   rn   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)rP   r   r   )r   )rP   r  r{   r   r   r   )full_attentionr   g      ?r   )r{   r   r   r   r   )last_hidden_stater   r   )
ValueErrorr  r	   rP   get_seq_lengthr*   r   rB   r   rc   r   dictr   r   r  tensorrQ   r   r  r  r   r  r   )r-   r  r{   r   r   r  r  r   r   past_seen_tokenscausal_mask_mappingmask_kwargsrl   r   
normalizerdecoder_layers                   r/   r?   zVaultGemmaModel.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&++
 	
r0   )NNNNNNN)rD   rE   rF   r   r'   r   r   r   r*   r   r   r   r   boolr   r   r   r?   rH   rI   s   @r/   r  r  t  s    /     .2.204(,26!%26H
##d*H
 t+H
 &&-	H

 H
 ((4/H
 $;H
 ((4/H
 +,H
 
!H
    H
r0   r  c                   b    e Zd ZddiZddiZddgdgfiZ fdZee	 	 	 	 	 	 	 	 	 dd	e	j                  dz  d
e	j                  dz  de	j                  dz  dedz  de	j                  dz  de	j                  dz  dedz  de	j                  dz  dee	j                  z  dee   defd              Z xZS )VaultGemmaForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputrl   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y rM   )
r&   r'   r  r   r  r(   rS   rQ   r(  r  rY   s     r/   r'   zVaultGemmaForCausalLM.__init__  sU     $V,
 ++yy!3!3V5F5FUS 	r0   Nr  r{   r   r   r  labelsr  r   logits_to_keepr   rn   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, VaultGemmaForCausalLM

        >>> model = VaultGemmaForCausalLM.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)lossr*  r   rl   r   r   )r   r  r   rG   slicer(  rP   final_logit_softcappingr*   r   loss_functionr  r   r   rl   r   )r-   r  r{   r   r   r  r,  r  r   r-  r   outputsrl   slice_indicesr*  r/  s                   r/   r?   zVaultGemmaForCausalLM.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!//))
 	
r0   )	NNNNNNNNr   )rD   rE   rF   _tied_weights_keys_tp_plan_pp_planr'   r   r   r*   r   r   r   r   r%  rG   r   r   r   r?   rH   rI   s   @r/   r'  r'    s/   *,GH23H_-z:;H  .2.204(,26*.!%26-.=
##d*=
 t+=
 &&-	=

 =
 ((4/=
   4'=
 $;=
 ((4/=
 ell*=
 +,=
 
 =
  =
r0   r'  )r'  r  r   )r   )r   NN)Ccollections.abcr   typingr   r*   torch.nnr(    r   r   activationsr   cache_utilsr   r	   
generationr
   integrationsr   r   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   utils.output_capturingr   configuration_vaultgemmar   Moduler!   rK   r`   rk   r   rG   rv   r<   rA   r   r   r   r   r   r  r'  __all__r   r0   r/   <module>rM     s  , %    & ! . ) I R B 9 O K F & I I G 5 6=		 =(BII  ( *+ ,2	UU\\ 	U# 	U%,, 	U$   %II%<<% 
% <<	%
 LL4'% % T\% T\% 5<<%&%D )*H)")) H) +H)V)7 )X><		 ><B ' ' '2 \
/ \
 \
~ M
5 M
 M
` Tr0   