
    iJW                     `   d dl mZ d dlmZ d dl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 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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jV                        Z, ed       G d dejV                               Z- G d dejV                        Z.d Z/ ed      d8d       Z0dejb                  de2d ejb                  fd!Z3	 d9d"ejV                  d#ejb                  d$ejb                  d%ejb                  d&ejb                  dz  d'e4d(e4d)e!e#   fd*Z5 ee0       G d+ d,ejV                               Z6 G d- d.e      Z7e$ G d/ d0e             Z8e$ G d1 d2e8             Z9e$ G d3 d4e8e             Z: G d5 d6ee8      Z;g d7Z<y):    )Callable)OptionalN)nn   )ACT2CLSACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernel_func_from_hubuse_kernelized_func)create_causal_mask)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   )ApertusConfigc                   $     e Zd Z fdZd Z xZS )
ApertusMLPc                    t         |           || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _        t        |j                     | _        |j                  dk(  rt        d   |j                        | _        y y )NFbiasxieludtype)super__init__confighidden_sizeintermediate_sizer   Linearup_proj	down_projr   
hidden_actact_fnr   r'   selfr*   	__class__s     v/home/obispo/Crisostomo_bridge/mision_env/lib/python3.12/site-packages/transformers/models/apertus/modeling_apertus.pyr)   zApertusMLP.__init__+   s    !--!'!9!9yy!1!143I3IPUV4#9#94;K;KRWXV../'!'*>DK (    c                 `    | j                  | j                  | j                  |                  S N)r/   r1   r.   )r3   xs     r5   forwardzApertusMLP.forward6   s"    ~~dkk$,,q/:;;r6   )__name__
__module____qualname__r)   r:   __classcell__r4   s   @r5   r!   r!   *   s    	?<r6   r!   RMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )ApertusRMSNormc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z=
        ApertusRMSNorm is equivalent to T5LayerNorm
        N)r(   r)   r   	Parametertorchonesweightvariance_epsilon)r3   r+   epsr4   s      r5   r)   zApertusRMSNorm.__init__<   s1     	ll5::k#:; #r6   c                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )N   T)keepdim)	r'   torE   float32powmeanrsqrtrH   rG   )r3   hidden_statesinput_dtypevariances       r5   r:   zApertusRMSNorm.forwardD   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r6   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tuplerG   shaperH   )r3   s    r5   
extra_reprzApertusRMSNorm.extra_reprK   s*    ))*+6$2G2G1HIIr6   )gư>)r;   r<   r=   r)   r:   rY   r>   r?   s   @r5   rB   rB   :   s    $;Jr6   rB   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 )ApertusRotaryEmbeddinginv_freqNr*   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_lenr*   rope_parametersr^   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r3   r*   devicerope_init_fnr\   r4   s        r5   r)   zApertusRotaryEmbedding.__init__R   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuUr6   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_dimNg      ?r   rK   r&   )rj   r'   )	re   getattrr+   num_attention_headsrE   arangeint64rN   float)r*   rj   rl   basedimattention_factorr\   s          r5   rf   z6ApertusRotaryEmbedding.compute_default_rope_parametersb   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r6   c                 N   | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        j	                  |j                   
      	j	                  |j                   
      fS # 1 sw Y   AxY w)Nr   rL   r   mpscpuF)device_typeenabledrK   rw   r&   )r\   ru   expandrX   rN   rj   
isinstancetypestrr   	transposerE   catcosrg   sinr'   )
r3   r9   position_idsinv_freq_expandedposition_ids_expandedr|   freqsembr   r   s
             r5   r:   zApertusRotaryEmbedding.forward   sR    !MM$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$cff177f&;;;	5 	5s   BFF$r8   )NNN)r;   r<   r=   rE   Tensor__annotations__r   r)   staticmethodr   intrW   ru   rf   no_gradr   r:   r>   r?   s   @r5   r[   r[   O   s    llV} V  '++/"*$*(* t* 
~u$	%	* *: U]]_<  <r6   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..NrL   rK   r~   )rX   rE   r   )r9   x1x2s      r5   rotate_halfr      sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r6   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          r5   apply_rotary_pos_embr      sY    & --
&C
--
&C3w;q>C/0G3w;q>C/0GGr6   rS   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)rX   r   reshape)rS   r   batchnum_key_value_headsslenrp   s         r5   	repeat_kvr      so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr6   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 )NrK   r   rL   )rw   r'   )ptrainingr   )r   num_key_value_groupsrE   matmulr   rX   r   
functionalsoftmaxrO   rN   r'   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r5   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$$r6   c                       e Zd ZdZddededz  f fdZ	 	 ddej                  de	ej                  ej                  f   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 )ApertusAttentionz=Multi-headed attention from 'Attention Is All You Need' paperNr*   	layer_idxc                    t         |           || _        || _        t	        |d|j
                  |j                  z        | _        |j                  |j                  z  | _	        | j                  dz  | _
        |j                  | _        d| _        t        j                  |j
                  |j                  | j                  z  |j                        | _        t        j                  |j
                  |j                  | j                  z  |j                        | _        t        j                  |j
                  |j                  | j                  z  |j                        | _        t        j                  |j                  | j                  z  |j
                  |j                        | _        t)        | j                  |j*                        | _        t)        | j                  |j*                        | _        y )Nrp   g      Tr#   )r(   r)   r*   r   rq   r+   rr   rp   r   r   r   attention_dropout	is_causalr   r-   attention_biasq_projk_projv_projo_projrB   rms_norm_epsq_normk_normr3   r*   r   r4   s      r5   r)   zApertusAttention.__init__   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 %T]]F4G4GH$T]]F4G4GHr6   rS   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      }| j                  |	      }	| j                  |
      }
|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        j                  | j                  j                  t               } || |	|
||f| j"                  sdn| j$                  | j&                  d|\  }} |j(                  g |d j+                         }| j-                  |      }||fS )NrL   r   rK   )r   r   r           )r   r   )rX   rp   r   viewr   r   r   r   r   r   updater   r   get_interfacer*   _attn_implementationr   r   r   r   r   r   r   )r3   rS   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   r   r   cache_kwargsattention_interfacer   r   s                     r5   r:   zApertusAttention.forward   s    $))#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{{<0[[,
&S#7jRUWZ#[ j&#&snUL'6'='=j,X\XfXfht'u$J(?(M(MKK,,.E)
 %8	%
  $}}C$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r6   r8   )NN)r;   r<   r=   __doc__r   r   r)   rE   r   rW   r	   
LongTensorr   r   r:   r>   r?   s   @r5   r   r      s    GI} It I< )-26*)||*) #5<<#=>*) t+	*)
 *) ((4/*) +,*) 
u||U\\)	**)r6   r   c                   (    e Zd Zdedef fdZ	 	 	 	 	 	 ddej                  dej                  dz  dej                  dz  de	dz  d	e
dz  d
ej                  dz  deej                  ej                  f   dz  dee   deej                     fdZ xZS )ApertusDecoderLayerr*   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        y )N)r*   r   rI   )r(   r)   r+   r   	self_attnr!   mlprB   r   attention_layernormfeedforward_layernormr   s      r5   r)   zApertusDecoderLayer.__init__"  sl    !--)9Mf%#1&2D2D&J]J]#^ %3F4F4FFL_L_%`"r6   NrS   r   r   r   	use_cacher   r   r   rm   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)rS   r   r   r   r   r   r    )r   r   r   r   )r3   rS   r   r   r   r   r   r   r   residual_s              r5   r:   zApertusDecoderLayer.forward,  s     !00?)4>> 	
')%+) 3	
 	
q !=0 !22=A/ =0r6   )NNNFNN)r;   r<   r=   r   r   r)   rE   r   r   r	   boolrW   r   r   r:   r>   r?   s   @r5   r   r   !  s    a} a a /304(,!&26HL|| t+ &&-	
  $; ((4/ #5<<#=>E +, 
u||	r6   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)ApertusPreTrainedModelr*   modelTr   r   )rS   
attentionsN)r;   r<   r=   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   r6   r5   r   r   M  sQ    &*#./#4"5N!"&,&r6   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j                  dz  d
edz  dee   defd              Z xZS )ApertusModelr*   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   r*   F)r(   r)   pad_token_idpadding_idx
vocab_sizer   	Embeddingr+   embed_tokens
ModuleListrangenum_hidden_layersr   layersrB   r   normr[   
rotary_embgradient_checkpointing	post_initr   s      r5   r)   zApertusModel.__init__b  s     !.. ++LL):):F<N<NPTP`P`ammEJ6KcKcEde	 3e
 #6#5#56;N;NO	0?&+# 	 fs   DN	input_idsr   r   r   inputs_embedsr   r   r   rm   c                 D   |d u |d uz  rt        d      || j                  |      }|r|t        | j                        }|E||j	                         nd}	t        j                  |j                  d   |j                        |	z   }||j                  d      }t        | j                  |||||      }
|}| j                  ||      }| j                  d | j                  j                   D ]  } ||f|
|||||d|} | j                  |      }t        ||	      S )
Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r   )rj   )r*   input_embedsr   r   r   r   )r   )r   r   r   r   r   r   )last_hidden_stater   )
ValueErrorr   r
   r*   get_seq_lengthrE   rs   rX   rj   r   r   r  r  r  r  r   )r3   r  r   r   r   r	  r   r   r   past_seen_tokensr   rS   r   decoder_layers                 r5   r:   zApertusModel.forwardr  s]    -t";<YZZ *.*;*;I*FM0*$++>O!CRC^==?de]003M<P<PQTdd  )33A6L(;;&))+%
 &"oom,oW![[)H4;;+H+HI 
	M)	*$7) /#-	 	M
	 		-0&++
 	
r6   )NNNNNNN)r;   r<   r=   r   r)   r   r   rE   r   r   r	   FloatTensorr   r   r   r   r:   r>   r?   s   @r5   r   r   `  s    }    .2.204(,2626!%9
##d*9
 t+9
 &&-	9

 9
 ((4/9
 ((4/9
 $;9
 +,9
 
!9
  9
r6   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 )ApertusForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputrS   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y )NFr#   )
r(   r)   r   r   r   r   r-   r+   r  r  r2   s     r5   r)   zApertusForCausalLM.__init__  sU     !&)
 ++yy!3!3V5F5FUS 	r6   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 )an  
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
            config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
            (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

        Example:

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

        >>> model = ApertusForCausalLM.from_pretrained("swiss-ai/Apertus-8B")
        >>> tokenizer = AutoTokenizer.from_pretrained("swiss-ai/Apertus-8B")

        >>> prompt = "Hey, are you conscious? Can you talk to me?"
        >>> 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]
        "Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
        ```)r  r   r   r   r	  r   r   N)r  r  r   )lossr  r   rS   r   r   )r   r  r   r   slicer  loss_functionr*   r   r   r   rS   r   )r3   r  r   r   r   r	  r  r   r   r  r   outputsrS   slice_indicesr  r  s                   r5   r:   zApertusForCausalLM.forward  s    J ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r6   )	NNNNNNNNr   )r;   r<   r=   _tied_weights_keys_tp_plan_pp_planr)   r   r   rE   r   r   r	   r  r   r   r   r   r   r:   r>   r?   s   @r5   r  r    s/   *,GH23H_-z:;H  .2.204(,26*.!%26-.=
##d*=
 t+=
 &&-	=

 =
 ((4/=
   4'=
 $;=
 ((4/=
 ell*=
 +,=
 
 =
  =
r6   r  c                       e Zd Zy)ApertusForTokenClassificationN)r;   r<   r=   r   r6   r5   r$  r$    s    r6   r$  )r   r  r$  r   )r   )r   )=collections.abcr   typingr   rE   r   activationsr   r   cache_utilsr	   r
   
generationr   integrationsr   r   r   masking_utilsr   modeling_layersr   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   configuration_apertusr   Moduler!   rB   r[   r   r   r   r   r   ru   r   r   r   r   r   r  r$  __all__r   r6   r5   <module>r6     s  * %    * . ) f f / X O K F & I I ? 0< <  Y'JRYY J (J(><RYY ><B( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%4 )*F)ryy F) +F)R)4 )X _  $ L
) L
 L
^ M
/ M
 M
`	$ACY 	 lr6   