
    hR                     ,   d dl mZmZmZ d dlZd dlmZ ddlmZ ddlm	Z	m
Z
 ddlmZ ddlmZ 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$Z$ ddl%m&Z& ddl'm(Z(  G d dejR                        Z* ed       G d dejR                               Z+ G d dejR                        Z,d Z-d7dZ.dej^                  de0dej^                  fd Z1	 d8d!ejR                  d"ej^                  d#ej^                  d$ej^                  d%eej^                     d&e2d'e2d(ee    fd)Z3 G d* d+ejR                        Z4 G d, d-e      Z5e! G d. d/e             Z6e! G d0 d1e6             Z7e! G d2 d3e6e             Z8 G d4 d5ee6      Z9g d6Z:y)9    )CallableOptionalUnionN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask)GenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)deprecate_kwarg)check_model_inputs   )ApertusConfigc                   $     e Zd Z fdZd Z xZS )
ApertusMLPc                 h   t         |           || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _        t        |j                     | _        y NFbias)super__init__confighidden_sizeintermediate_sizer   Linearup_proj	down_projr   
hidden_actact_fnselfr&   	__class__s     j/var/www/html/eduruby.in/venv/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../    c                 `    | j                  | j                  | j                  |                  S N)r+   r-   r*   )r/   xs     r1   forwardzApertusMLP.forward5   s"    ~~dkk$,,q/:;;r2   )__name__
__module____qualname__r%   r6   __classcell__r0   s   @r1   r   r   +   s    0<r2   r   RMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )ApertusRMSNormc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z=
        ApertusRMSNorm is equivalent to T5LayerNorm
        N)r$   r%   r   	Parametertorchonesweightvariance_epsilon)r/   r'   epsr0   s      r1   r%   zApertusRMSNorm.__init__;   s1     	ll5::k#:; #r2   c                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )N   T)keepdim)	dtypetorA   float32powmeanrsqrtrD   rC   )r/   hidden_statesinput_dtypevariances       r1   r6   zApertusRMSNorm.forwardC   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r2   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tuplerC   shaperD   )r/   s    r1   
extra_reprzApertusRMSNorm.extra_reprJ   s*    ))*+6$2G2G1HIIr2   )gư>)r7   r8   r9   r%   r6   rV   r:   r;   s   @r1   r>   r>   9   s    $;Jr2   r>   c                   ~     e Zd ZU ej                  ed<   ddef fdZ ej                         e	d               Z
 xZS )ApertusRotaryEmbeddinginv_freqr&   c                    t         |           t        |d      rUt        |j                  t
              r;|j                  j                  d|j                  j                  d            | _        nd| _        |j                  | _	        |j                  | _
        || _        t        | j                     | _        | j                  | j                  |      \  }| _        | j                  d|d       | j                   | _        y )Nrope_scaling	rope_typetypedefaultrY   F)
persistent)r$   r%   hasattr
isinstancer[   dictgetr\   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr&   r   rope_init_fnattention_scalingregister_bufferrY   original_inv_freq)r/   r&   devicerY   r0   s       r1   r%   zApertusRotaryEmbedding.__init__Q   s    6>*z&:M:Mt/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r2   c                 b   | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        j                  |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        j	                  |j                   
      	j	                  |j                   
      fS # 1 sw Y   AxY w)Nr   rH   r   mpscpuF)device_typeenabledrG   dim)rJ   )rY   floatexpandrU   rK   rk   ra   r]   strrA   autocast	transposecatcosrh   sinrJ   )
r/   r5   position_idsinv_freq_expandedposition_ids_expandedro   freqsembry   rz   s
             r1   r6   zApertusRotaryEmbedding.forwardb   sV    !MM$4-8>>@GGHZHZ[\H]_acdehhijiqiqr ,QaZ 8 > > @'1!((--'E!((--[`J`ahhmmfk^^UC 	5&,,.1F1L1L1NNYYZ[]^_E))UEN3C'')d444C'')d444C		5 vvAGGv$cff177f&;;;	5 	5s    BF%%F.r4   )r7   r8   r9   rA   Tensor__annotations__r   r%   no_gradr   r6   r:   r;   s   @r1   rX   rX   N   s=    ll/} /" U]]_<  <r2   rX   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..NrH   rG   rq   )rU   rA   rx   )r5   x1x2s      r1   rotate_halfr   r   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r2   c                     |j                  |      }|j                  |      }| |z  t        |       |z  z   }||z  t        |      |z  z   }||fS )a  Applies Rotary Position Embedding to the query and key tensors.

    Args:
        q (`torch.Tensor`): The query tensor.
        k (`torch.Tensor`): The key tensor.
        cos (`torch.Tensor`): The cosine part of the rotary embedding.
        sin (`torch.Tensor`): The sine part of the rotary embedding.
        position_ids (`torch.Tensor`, *optional*):
            Deprecated and unused.
        unsqueeze_dim (`int`, *optional*, defaults to 1):
            The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
            sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
            that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and
            k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes
            cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have
            the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2.
    Returns:
        `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
    )	unsqueezer   )qkry   rz   r{   unsqueeze_dimq_embedk_embeds           r1   apply_rotary_pos_embr   y   sY    ( --
&C
--
&C3w;q>C/0G3w;q>C/0GGr2   rP   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)rU   rt   reshape)rP   r   batchnum_key_value_headsslenhead_dims         r1   	repeat_kvr      so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr2   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 )NrG   r   rH   )rr   rJ   )ptrainingr   )r   num_key_value_groupsrA   matmulrw   rU   r   
functionalsoftmaxrL   rK   rJ   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r1   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$$r2   c                   2    e Zd ZdZddedee   f fdZ eddd      	 	 dd	e	j                  d
ee	j                  e	j                  f   dee	j                     dee   dee	j                     dee   dee	j                  e	j                  f   fd       Z xZS )ApertusAttentionz=Multi-headed attention from 'Attention Is All You Need' paperr&   	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 )Nr   g      Tr"   )r$   r%   r&   r   getattrr'   num_attention_headsr   r   r   r   attention_dropout	is_causalr   r)   attention_biasq_projk_projv_projo_projr>   rms_norm_epsq_normk_normr/   r&   r   r0   s      r1   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r2   past_key_valuepast_key_values4.58new_nameversionrP   position_embeddingsr   cache_positionr   r   c                 x   |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                  dk7  rt        | j                  j                     } || |	|
||f| j                   sdn| j"                  | j$                  d|\  }} |j&                  g |d j)                         }| j+                  |      }||fS )NrH   r   rG   )rz   ry   r   eager        )r   r   )rU   r   r   viewrw   r   r   r   r   r   updater   r   r&   _attn_implementationr   r   r   r   r   r   r   )r/   rP   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   ry   rz   cache_kwargsattention_interfacer   r   s                     r1   r6   zApertusAttention.forward   s    $))#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$J(?;;++w6"9$++:Z:Z"[$7	%
  $}}C$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r2   r4   )NN)r7   r8   r9   __doc__r   r   intr%   r   rA   r   rT   r	   
LongTensorr   r   r6   r:   r;   s   @r1   r   r      s    GI} I# I2 %0A6R ,059*)||*) #5<<#=>*) !.	*)
 "%*) !!1!12*) +,*) 
u||U\\)	**) S*)r2   r   c                   D    e Zd Zdedef fdZ eddd      	 	 	 	 	 	 ddej                  d	e	ej                     d
e	ej                     de	e   de	e   de	ej                     de	eej                  ej                  f      dee   deej                     fd       Z xZS )ApertusDecoderLayerr&   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        y )N)r&   r   rE   )r$   r%   r'   r   	self_attnr   mlpr>   r   attention_layernormfeedforward_layernormr   s      r1   r%   zApertusDecoderLayer.__init__  sl    !--)9Mf%#1&2D2D&J]J]#^ %3F4F4FFL_L_%`"r2   r   r   r   r   rP   r   r{   	use_cacher   r   r   r   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)rP   r   r{   r   r   r   r    )r   r   r   r   )r/   rP   r   r{   r   r   r   r   r   residual_s              r1   r6   zApertusDecoderLayer.forward  s     !00?)4>> 	
')%+) 3	
 	
q !=0 !22=A/ =0r2   )NNNFNN)r7   r8   r9   r   r   r%   r   rA   r   r   r   r	   boolrT   r   r   r6   r:   r;   s   @r1   r   r     s    a} a a %0A6R 2637+/$)59KO|| !. u//0	
 "% D> !!1!12 &eELL%,,,F&GH +, 
u||	 Sr2   r   c                   J    e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedZy)ApertusPreTrainedModelr&   modelTr   r   )rP   
attentionsN)r7   r8   r9   r   r   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsr   r2   r1   r   r   1  sQ    &*#./#4"5N!"&,&r2   r   c                       e Zd Zdef fdZee	 	 	 	 	 	 	 ddeej                     deej                     deej                     dee   deej                     deej                     d	ee   d
ee   defd              Z xZS )ApertusModelr&   c           	         t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |j                  |j                        | _        t#        |      | _        d| _        | j)                          y c c}w )Nr   r&   F)r$   r%   pad_token_idpadding_idx
vocab_sizer   	Embeddingr'   embed_tokens
ModuleListrangenum_hidden_layersr   layersr>   r   normrX   
rotary_embgradient_checkpointing	post_initr   s      r1   r%   zApertusModel.__init__F  s     !.. ++LL):):F<N<NPTP`P`ammEJ6KcKcEde	 3e
 #6#5#56;N;NO	0?&+# 	 fs   D	input_idsr   r{   r   inputs_embedsr   r   r   r   c           
      B   |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                  ||      }| j                  d | j                  j                   D ]  } ||f|
||||d|} | j                  |      }t        ||      S )	Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r   )rk   )r&   input_embedsr   r   r   r{   )r   r{   r   r   r   )last_hidden_stater   )
ValueErrorr   r
   r&   get_seq_lengthrA   arangerU   rk   r   r   r   r   r   r   r   )r/   r  r   r{   r   r  r   r   r   past_seen_tokensr   rP   r   decoder_layers                 r1   r6   zApertusModel.forwardV  s[    -t";<YZZ *.*;*;I*FM0*$++>O!CRC^==?de+0<< "2]5H5H5K"KTaThTh,N )33A6L(;;&))+%
 &"oom\J![[)H4;;+H+HI 		M)*) /-$7 M		 		-0&++
 	
r2   )NNNNNNN)r7   r8   r9   r   r%   r   r   r   rA   r   r   r	   FloatTensorr   r   r   r   r6   r:   r;   s   @r1   r   r   D  s    }    151537+/5959$(8
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 !!1!128
 D>8
 +,8
 
!8
  8
r2   r   c                   d    e Zd ZdgZddiZddgdgfiZ fdZee	 	 	 	 	 	 	 	 	 dde	e
j                     de	e
j                     d	e	e
j                     d
e	e   de	e
j                     de	e
j                     de	e   de	e
j                     deee
j                  f   dee   defd              Z xZS )ApertusForCausalLMzlm_head.weightlm_headcolwise_reprP   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y r!   )
r$   r%   r   r   r   r   r)   r'   r  r  r.   s     r1   r%   zApertusForCausalLM.__init__  sU     !&)
 ++yy!3!3V5F5FUS 	r2   r  r   r{   r   r  labelsr   r   logits_to_keepr   r   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   rP   r   r   )r   r  ra   r   slicer  loss_functionr&   r   r   r   rP   r   )r/   r  r   r{   r   r  r  r   r   r  r   outputsrP   slice_indicesr  r  s                   r1   r6   zApertusForCausalLM.forward  s    J ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r2   )	NNNNNNNNr   )r7   r8   r9   _tied_weights_keys_tp_plan_pp_planr%   r   r   r   rA   r   r   r	   r  r   r   r   r   r   r   r6   r:   r;   s   @r1   r  r    s0   *+=)H_-z:;H  151537+/59-1$(5934=
E,,-=
 !.=
 u//0	=

 "%=
   1 12=
 ))*=
 D>=
 !!1!12=
 c5<</0=
 +,=
 
 =
  =
r2   r  c                       e Zd Zy)ApertusForTokenClassificationN)r7   r8   r9   r   r2   r1   r   r     s    r2   r   )r   r  r   r   )Nr   )r   );typingr   r   r   rA   r   activationsr   cache_utilsr	   r
   
generationr   integrationsr   masking_utilsr   modeling_layersr   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.deprecationr   utils.genericr   configuration_apertusr   Moduler   r>   rX   r   r   r   r   r   rs   r   r   r   r   r   r  r   __all__r   r2   r1   <module>r2     s  , - ,   ! . ) 7 / X O K F & I I 0 / 0< < Y'JRYY J (J(!<RYY !<H(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4G)ryy G)T*4 *Z _  $ K
) K
 K
\ M
/ M
 M
`	$ACY 	 lr2   