
    UhE                        d dl Z d dlmZ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 dd
lmZ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" ddl#m$Z$m%Z%m&Z&m'Z'm(Z( ddl)m*Z*  e'       rd dl+m,Z, ddl-m.Z.  e(j^                  e0      Z1 G d dejd                        Z3 G d dejd                        Z4 G d dejd                        Z5dejl                  de7dejl                  fdZ8	 d:dejd                  dejl                  dejl                  d ejl                  d!eejl                     d"e9d#e9fd$Z:d% Z;d;d&Z< G d' d(ejd                        Z= G d) d*e      Z>e% G d+ d,e              Z?e% G d- d.e?             Z@ G d/ d0ee$      ZAe% G d1 d2e?e             ZB e%d34       G d5 d6e?             ZCe% G d7 d8e?             ZDg d9ZEy)<    N)CallableOptionalTupleUnion   )ACT2FN)CacheDynamicCache)GenerationMixin)AttentionMaskConverter)FlashAttentionKwargs)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast SequenceClassifierOutputWithPastTokenClassifierOutput)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)
LossKwargsauto_docstringcan_return_tupleis_torch_flex_attn_availablelogging   )HeliumConfig)	BlockMask)make_flex_block_causal_maskc                   ,     e Zd Zd fd	Zd Zd Z xZS )HeliumRMSNormc                     t         |           t        j                  t	        j
                  |            | _        || _        y N)super__init__nn	Parametertorchonesweightvariance_epsilon)selfhidden_sizeeps	__class__s      |/var/www/catia.catastroantioquia-mas.com/valormas/lib/python3.12/site-packages/transformers/models/helium/modeling_helium.pyr&   zHeliumRMSNorm.__init__9   s/    ll5::k#:; #    c                 \   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  j                  t        j                        |z  j                  |      S )N   T)keepdim)	dtypetor)   float32powmeanrsqrtr,   r+   )r-   hidden_statesinput_dtypevariances       r1   forwardzHeliumRMSNorm.forward>   s    #))%((7 $$Q',,R,>%Ht?T?T4T(UUu}}-=AA+NNr2   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tupler+   shaper,   r-   s    r1   
extra_reprzHeliumRMSNorm.extra_reprE   s*    ))*+6$2G2G1HIIr2   )gư>)__name__
__module____qualname__r&   r@   rE   __classcell__r0   s   @r1   r"   r"   8   s    $
OJr2   r"   c                   ^     e Zd Zddef fdZ ej                         ed               Z xZ	S )HeliumRotaryEmbeddingconfigc                    t         |           t        |d      rG|j                  ;|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defaultinv_freqF)
persistent)r%   r&   hasattrrO   getrP   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrM   r   rope_init_fnattention_scalingregister_bufferrS   original_inv_freq)r-   rM   devicerS   r0   s       r1   r&   zHeliumRotaryEmbedding.__init__J   s    6>*v/B/B/N#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   r5   r   mpscpuF)device_typeenabledr4   dim)r7   )rS   floatexpandrC   r8   r^   
isinstancerQ   strr)   autocast	transposecatcosr[   sinr7   )
r-   xposition_idsinv_freq_expandedposition_ids_expandedrb   freqsembrm   rn   s
             r1   r@   zHeliumRotaryEmbedding.forward[   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.r$   )
rF   rG   rH   r   r&   r)   no_gradr   r@   rI   rJ   s   @r1   rL   rL   I   s3    /| /" U]]_<  <r2   rL   c                   $     e Zd Z fdZd Z xZS )	HeliumMLPc                    t         |           || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  |j                        | _        t        j                  | j                  | j                  |j                        | _	        t        j                  | j                  | j                  |j                        | _
        t        |j                     | _        y )Nbias)r%   r&   rM   r.   intermediate_sizer'   Linearmlp_bias	gate_projup_proj	down_projr   
hidden_actact_fnr-   rM   r0   s     r1   r&   zHeliumMLP.__init__l   s    !--!'!9!94#3#3T5K5KRXRaRabyy!1!143I3IPVP_P_`4#9#94;K;KRXRaRabV../r2   c                     | j                  | j                  | j                  |            | j                  |      z        }|S r$   )r   r   r~   r   )r-   ro   r   s      r1   r@   zHeliumMLP.forwardv   s6    NN4;;t~~a/@#ADLLQRO#ST	r2   )rF   rG   rH   r&   r@   rI   rJ   s   @r1   rw   rw   k   s    0r2   rw   r=   n_repreturnc                     | j                   \  }}}}|dk(  r| S | dddddddddf   j                  |||||      } | j                  |||z  ||      S )z
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r   N)rC   rg   reshape)r=   r   batchnum_key_value_headsslenhead_dims         r1   	repeat_kvr   {   so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr2   modulequerykeyvalueattention_maskscalingdropoutc                 T   t        || j                        }t        || j                        }	t        j                  ||j	                  dd            |z  }
|#|d d d d d d d |j
                  d   f   }|
|z   }
t        j                  j                  |
dt        j                        j                  |j                        }
t        j                  j                  |
|| j                        }
t        j                  |
|	      }|j	                  dd      j                         }||
fS )Nr4   r   r5   )re   r7   )ptrainingr   )r   num_key_value_groupsr)   matmulrk   rC   r'   
functionalsoftmaxr9   r8   r7   r   r   
contiguous)r   r   r   r   r   r   r   kwargs
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r1   eager_attention_forwardr      s    3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!$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                 |    | ddddf   }| ddddf   }t        j                  | |fd      j                  d      S )	z*Rotates half the hidden dims of the input..r   Nr4   r   r5   rd   r   )r)   stackflatten)ro   x1x2s      r1   rotate_halfr      sJ    	
319B	
319B;;Ryb)11"55r2   c                 F   |j                  |      }|j                  |      }|dd|j                  d   dz  f   j                  dd      }|dd|j                  d   dz  f   j                  dd      }| |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.
    .Nr5   r4   rd   )	unsqueezerC   repeat_interleaver   )qkrm   rn   rp   unsqueeze_dimq_embedk_embeds           r1   apply_rotary_pos_embr      s    ( --
&C
--
&C c'SYYr]a'''
(
:
:1"
:
EC
c'SYYr]a'''
(
:
:1"
:
EC3w;q>C/0G3w;q>C/0GGr2   c                   >    e Zd ZdZddedee   f fdZ	 	 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ej                     ee
ej                        f   fdZ xZS )HeliumAttentionz=Multi-headed attention from 'Attention Is All You Need' paperrM   	layer_idxc                 \   t         |           || _        || _        t	        |d|j
                  |j                  z        | _        |j                  |j                  z  | _	        dt        j                  | j                        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
                  d      | _        y )Nr   r   Try   F)r%   r&   rM   r   getattrr.   num_attention_headsr   r   r   mathsqrtr   attention_dropout	is_causalr'   r|   attention_biasq_projk_projv_projo_projr-   rM   r   r0   s      r1   r&   zHeliumAttention.__init__   sC   "
F4F4F&JdJd4de$*$>$>&B\B\$\!499T]]33!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii 2 2F4F4FUSr2   r=   position_embeddingsr   past_key_valuecache_positionr   r   c                    |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        }| j                  j                  dk7  r^| j                  j                  dk(  r(|j                  dd      rt        j                  d	       nt         | j                  j                     } || |	|
||f| j"                  sd
n| j$                  | j&                  d|\  }} |j(                  g |d j+                         }| j-                  |      }||fS )Nr5   r   r4   )rn   rm   r   eagersdpaoutput_attentionsFz`torch.nn.functional.scaled_dot_product_attention` does not support `output_attentions=True`. Falling back to eager attention. This warning can be removed using the argument `attn_implementation="eager"` when loading the model.        )r   r   )rC   r   r   viewrk   r   r   r   updater   r   rM   _attn_implementationrV   loggerwarning_oncer   r   r   r   r   r   r   )r-   r=   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   rm   rn   cache_kwargsattention_interfacer   r   s                     r1   r@   zHeliumAttention.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'5'<'<ZW[WeWegs't$J(?;;++w6{{//69fjjI\^c>d##L
 '>dkk>^>^&_#$7	%
  $}}C$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r2   r$   )NN)rF   rG   rH   __doc__r   r   intr&   r)   Tensorr   r	   
LongTensorr   r   r@   rI   rJ   s   @r1   r   r      s    GT| T T4 +/590)||0) #5<<#=>0) !.	0)
 !0) !!1!120) -.0) 
u||Xell3XeELL>Q5RR	S0)r2   r   c                   x    e Zd Zddedee   f fdZ	 	 	 	 	 	 	 ddej                  deej                     deej                     dee
   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                  eeej                  ej                  f      f   fdZ xZS )HeliumDecoderLayerrM   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        y )N)rM   r   r/   )r%   r&   r.   r   	self_attnrw   mlpr"   rms_norm_epsinput_layernormpost_attention_layernormr   s      r1   r&   zHeliumDecoderLayer.__init__  sl    !--()LV$,V-?-?VEXEXY(5f6H6HfNaNa(b%r2   r=   r   rp   r   r   	use_cacher   r   r   r   c	                     |}
| j                  |      } | j                  d||||||||d|	\  }}|
|z   }|}
| j                  |      }| j                  |      }|
|z   }|f}|r||fz  }|S )N)r=   r   rp   r   r   r   r   r    )r   r   r   r   )r-   r=   r   rp   r   r   r   r   r   r   residualself_attn_weightsoutputss                r1   r@   zHeliumDecoderLayer.forward  s     !,,]; ,:4>> 
,
')%)/) 3
,
 
,
(( !=0 !55mD/ =0 ")++Gr2   r$   )NNNFFNN)rF   rG   rH   r   r   r   r&   r)   r   r   r	   boolr   r   r   FloatTensorr@   rI   rJ   s   @r1   r   r     s   c| c c 2637*.,1$)59KO'||' !.' u//0	'
 !' $D>' D>' !!1!12' &eELL%,,,F&GH' -.' 
u  (51B1BEDUDU1U+V"WW	X'r2   r   c                   F    e Zd ZeZdZdZdgZdgZdZ	dZ
dZdZdZdZdZd Zy)HeliumPreTrainedModelmodelTr   past_key_valuesc                    | j                   j                  }t        |t        j                        rY|j
                  j                  j                  d|       |j                  %|j                  j                  j                          y y t        |t        j                        rf|j
                  j                  j                  d|       |j                  2|j
                  j                  |j                     j                          y y t        |t              r&|j
                  j                  j                  d       y y )Nr   )r;   stdg      ?)rM   initializer_rangerh   r'   r|   r+   datanormal_rz   zero_	Embeddingpadding_idxr"   fill_)r-   r   r   s      r1   _init_weightsz#HeliumPreTrainedModel._init_weightsX  s    kk++fbii(MM&&CS&9{{&  &&( '-MM&&CS&9!!-""6#5#56<<> ..MM$$S) /r2   N)rF   rG   rH   r   config_classbase_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_2_supports_sdpa_supports_flex_attn_supports_cache_class_supports_quantized_cache_supports_static_cache_supports_attention_backendr   r   r2   r1   r   r   I  sS    L&*#-.#4"5!N  $!"&*r2   r   c                       e Zd Zdef fdZd Zd Zee	 	 	 	 	 	 	 	 	 dde	e
j                     de	e
j                     de	e
j                     de	e   d	e	e
j                     d
e	e   de	e   de	e   de	e
j                     dee   defd              Z	 ddee
j                  df   de
j                  de
j                  dedef
dZede
j                  dedede
j0                  de
j                  defd       Z xZS )HeliumModelrM   c           	      
   t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |j                  |j                        | _        t#        |      | _        d| _        | j)                          y c c}w )Nr   F)r%   r&   pad_token_idr   
vocab_sizer'   r   r.   embed_tokens
ModuleListrangenum_hidden_layersr   layersr"   r   normrL   
rotary_embgradient_checkpointing	post_initr   s      r1   r&   zHeliumModel.__init__h  s     !.. ++LL):):F<N<NPTP`P`ammDI&JbJbDcdy	2d
 "&"4"4&:M:MN	/7&+# 	 es   D c                     | j                   S r$   r
  rD   s    r1   get_input_embeddingsz HeliumModel.get_input_embeddingsx  s       r2   c                     || _         y r$   r  r-   r   s     r1   set_input_embeddingsz HeliumModel.set_input_embeddings{  s
    !r2   	input_idsr   rp   r   inputs_embedsr   r   output_hidden_statesr   flash_attn_kwargsr   c
                    ||n| j                   j                  }||n| j                   j                  }||n| j                   j                  }|d u |d uz  rt	        d      | j
                  r%| j                  r|rt        j                  d       d}t        |t        d       t        f      st	        d      || j                  |      }|r|
t               }|	F||j                         nd}t        j                   |||j"                  d   z   |j$                        }	||	j'                  d      }| j)                  |||	||      }|}| j+                  ||      }|rdnd }|rdnd }| j,                  d | j                   j.                   D ],  }|r||fz  } ||f||||||	|d	|
}|d   }|s$||d   fz  }. | j1                  |      }|r||fz  }t3        ||r|nd ||
      S )Nz:You must specify exactly one of input_ids or inputs_embedszX`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.FzBThe `past_key_values` should be either a `Cache` object or `None`.r   r   r^   r   )r   rp   r   r   r   r   r   )last_hidden_stater   r=   
attentions)rM   r   r  r   
ValueErrorr  r   r   r   rh   rQ   r	   r
  r
   get_seq_lengthr)   arangerC   r^   r   _update_causal_maskr  r  r  r  r   )r-   r  r   rp   r   r  r   r   r  r   r  past_seen_tokensr   r=   r   all_hidden_statesall_self_attnsdecoder_layerlayer_outputss                      r1   r@   zHeliumModel.forward~  sT    2C1N-TXT_T_TqTq$8$D $++JjJj 	 "+!6IDKK<Q<Q	-t";<YZZ&&4==Yj I /DJ+>?abb  --i8M0*nO!CRC^==?de"\\ "2]5H5H5K"KTaThThN )33A6L..M>?L]
 & #oom\J #7BD0d![[)H4;;+H+HI 	6M#!m%55!)
*)."3#-$7
 $
M *!,M =#3"55'	6* 		-0  -!11&+/8Od+%	
 	
r2   r   input_tensorc           	         | j                   j                  dk(  r||dk(  j                         r|S y | j                   j                  dk(  r't        |t        j
                        rt        |      }|S ||j                         nd}||j                  nd}| j                   j                  dk(  r(|s&|s$t        j                  |||| j                        ry |j                  }|j                  d   }	|r|j                         }
n1t        |t        j
                        r|j                  d	   n||	z   dz   }
| j                  ||	|
|||j                  d   
      }| j                   j                  dk(  rQ|O|j                   j"                  dv r7|s5t	        j$                  |      j&                  }t        j(                  ||      }|S )Nflash_attention_2r   flex_attentionr   Fr   )r  past_key_values_lengthis_trainingr   r5   )sequence_lengthtarget_lengthr7   r   
batch_size)cudaxpunpu)rM   r   anyrh   r)   r   r    r"  is_compileabler   _ignore_causal_mask_sdpar   r7   rC   get_max_cache_shape5_prepare_4d_causal_attention_mask_with_cache_positionr^   rQ   finfomin_unmask_unattended)r-   r   r*  r   r   r   r%  using_compilable_cacher7   r0  r1  r   	min_dtypes                r1   r$  zHeliumModel._update_causal_mask  s    ;;++/BB)~/D.I.I.K%%;;++/??.%,,7!<^!L!!
 @O?Z?99;`aCRC^!?!?di ;;++v5>T]n%>>*'7 MM	 ""&,,Q/!+??AM nell; $$R(%7!;  PP+')#))!, Q 
 KK,,6*%%**.DD%
 E*..I0CCKQZ[Kr2   r0  r1  r7   r2  c                    | | j                         dk(  r| }|S t        j                  |      j                  }t        j                  ||f|||j
                        }|dk7  rt        j                  |d      }|t        j                  ||j
                        |j                  dd      kD  z  }|ddddddf   j                  |ddd      }| |j                         }| j                  d   }	|ddddddd|	f   | ddddddf   j                  |j
                        z   }
|
dk(  }
|ddddddd|	f   j                  |
|      |ddddddd|	f<   |S )	aM  
        Creates a causal 4D mask of shape `(batch_size, 1, query_length, key_value_length)` from a 2D mask of shape
        `(batch_size, key_value_length)`, or if the input `attention_mask` is already 4D, do nothing.

        Args:
            attention_mask (`torch.Tensor`):
                A 2D attention mask of shape `(batch_size, key_value_length)` or a 4D attention mask of shape
                `(batch_size, 1, query_length, key_value_length)`.
            sequence_length (`int`):
                The sequence length being processed.
            target_length (`int`):
                The target length: when generating with static cache, the mask should be as long as the static cache,
                to account for the 0 padding, the part of the cache that is not filled yet.
            dtype (`torch.dtype`):
                The dtype to use for the 4D attention mask.
            cache_position (`torch.Tensor`):
                Indices depicting the position of the input sequence tokens in the sequence.
            batch_size (`torch.Tensor`):
                Batch size.
        N   )
fill_valuer7   r^   r   )diagonalr  r5   r   )re   r)   r;  r<  fullr^   triur#  r   rg   clonerC   r8   masked_fill)r   r0  r1  r7   r   r2  r   r   r?  mask_lengthpadding_masks              r1   r:  zAHeliumModel._prepare_4d_causal_attention_mask_with_cache_position"  s   < %.*<*<*>!*C(K* ' E*..I** -0Ye\j\q\qK !##jjqA5<<n>S>STWeWmWmnprsWtttK%dD!Q&67>>z1bRTUK))//1,2226*1aL[L+@ANSTVZ\`bcScDdDgDg&&E    ,q05@Aq,;,AV5W5c5c )6Aq!\k\12 r2   	NNNNNNNNN)F)rF   rG   rH   r   r&   r  r  r   r   r   r)   r   r   r	   r   r   r   r   r   r@   r   r$  staticmethodr   r7   r:  rI   rJ   s   @r1   r  r  f  s   |  !"  151537+/59$(,0/359\
E,,-\
 !.\
 u//0	\

 "%\
   1 12\
 D>\
 $D>\
 'tn\
 !!1!12\
 $$89\
 
!\
  \
H #(BellK78B llB 	B
 B  BH 444 4 {{	4
 4 4 4r2   r  c                       e Zd Zy)KwargsForCausalLMN)rF   rG   rH   r   r2   r1   rM  rM  Z  s    r2   rM  c                       e Zd ZdgZddiZddgdgfiZdef fdZd Zd	 Z	d
 Z
d Zd Z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$                     dee   dee   dee   deej$                     deeej&                  f   dee   defd              Z xZS )HeliumForCausalLMzlm_head.weightlm_headcolwise_repr=   logitsrM   c                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y NFry   )
r%   r&   r  r   r	  r'   r|   r.   rP  r  r   s     r1   r&   zHeliumForCausalLM.__init__c  sU      (
 ++yy!3!3V5F5FUS 	r2   c                 .    | j                   j                  S r$   r   r
  rD   s    r1   r  z&HeliumForCausalLM.get_input_embeddingsl      zz&&&r2   c                 &    || j                   _        y r$   rV  r  s     r1   r  z&HeliumForCausalLM.set_input_embeddingso      "'

r2   c                     | j                   S r$   rP  rD   s    r1   get_output_embeddingsz'HeliumForCausalLM.get_output_embeddingsr  s    ||r2   c                     || _         y r$   r[  )r-   new_embeddingss     r1   set_output_embeddingsz'HeliumForCausalLM.set_output_embeddingsu  s	    %r2   c                     || _         y r$   r   )r-   decoders     r1   set_decoderzHeliumForCausalLM.set_decoderx  s	    
r2   c                     | j                   S r$   ra  rD   s    r1   get_decoderzHeliumForCausalLM.get_decoder{  s    zzr2   r  r   rp   r   r  labelsr   r   r  r   logits_to_keepr   r   c                    ||n| j                   j                  }|	|	n| j                   j                  }	 | 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%  
        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, HeliumForCausalLM

        >>> model = HeliumForCausalLM.from_pretrained("google/helium-7b")
        >>> tokenizer = AutoTokenizer.from_pretrained("google/helium-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?"
        ```N)	r  r   rp   r   r  r   r   r  r   )rR  rf  r	  lossrR  r   r=   r   r   )rM   r   r  r   r  rh   r   slicerP  loss_functionr	  r   r   r=   r   )r-   r  r   rp   r   r  rf  r   r   r  r   rg  r   r   r=   slice_indicesrR  rj  s                     r1   r@   zHeliumForCausalLM.forward~  s   N 2C1N-TXT_T_TqTq$8$D $++JjJj 	
 ,64:: ,
)%+'/!5),
 ,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r2   )NNNNNNNNNNr   )rF   rG   rH   _tied_weights_keys_tp_plan_pp_planr   r&   r  r  r\  r_  rc  re  r   r   r   r)   r   r   r	   r   r   r   r   r   rM  r   r@   rI   rJ   s   @r1   rO  rO  ]  s   *+=)H_-z:;H| '(&  151537+/59-1$(,0/35934G
E,,-G
 !.G
 u//0	G

 "%G
   1 12G
 ))*G
 D>G
 $D>G
 'tnG
 !!1!12G
 c5<</0G
 *+G
 
 G
  G
r2   rO  a  
    The Helium Model transformer with a sequence classification head on top (linear layer).

    [`HeliumForSequenceClassification`] uses the last token in order to do the classification, as other causal models
    (e.g. GPT-2) do.

    Since it does classification on the last token, it requires to know the position of the last token. If a
    `pad_token_id` is defined in the configuration, it finds the last token that is not a padding token in each row. If
    no `pad_token_id` is defined, it simply takes the last value in each row of the batch. Since it cannot guess the
    padding tokens when `inputs_embeds` are passed instead of `input_ids`, it does the same (take the last value in
    each row of the batch).
    )custom_introc                   "    e Zd Zdef fdZd Z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	e   defd              Z xZS )HeliumForSequenceClassificationrM   c                     t         |   |       |j                  | _        t        |      | _        t        j                  |j                  | j                  d      | _        | j                          y rT  )
r%   r&   
num_labelsr  r   r'   r|   r.   scorer  r   s     r1   r&   z(HeliumForSequenceClassification.__init__  sS      ++ (
YYv114??O
 	r2   c                 .    | j                   j                  S r$   rV  rD   s    r1   r  z4HeliumForSequenceClassification.get_input_embeddings  rW  r2   c                 &    || j                   _        y r$   rV  r  s     r1   r  z4HeliumForSequenceClassification.set_input_embeddings  rY  r2   r  r   rp   r   r  rf  r   r   r  r   c
           
         | j                  ||||||||	      }
|
j                  }| j                  |      }||j                  d   }n|j                  d   }| j                  j
                  |dk7  rt        d      | j                  j
                  d}n||| j                  j
                  k7  j                  |j                  t        j                        }t        j                  |j                  d   |j                  t        j                        }||z  j                  d      }n.d}t        j                  | j                  j                    d       |t        j                  ||j                  	      |f   }d}|| j#                  |||| j                  
      }t%        |||
j&                  |
j(                  |
j*                        S )  
        labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
            Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
            config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
            `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
        r   rp   r   r  r   r   r  Nr   r   z=Cannot handle batch sizes > 1 if no padding token is defined.r5   )r^   r7   z will not detect padding tokens in `inputs_embeds`. Results may be unexpected if using padding tokens in conjunction with `inputs_embeds.`r  )rR  rf  pooled_logitsrM   ri  )r   r  rv  rC   rM   r  r!  r8   r^   r)   int32r#  argmaxr   r   r0   rF   rl  r   r   r=   r   )r-   r  r   rp   r   r  rf  r   r   r  transformer_outputsr=   rR  r2  last_non_pad_tokennon_pad_masktoken_indicesr|  rj  s                      r1   r@   z'HeliumForSequenceClassification.forward  s   * 8<zz)%+'/!5 8B 	8
 ,==M* "+J&,,Q/J;;##+
a\]];;##+!#"%)A)AAEEfmmUZU`U`aL!LL)<V]]Z_ZeZefM"/,">!F!Fr!J!#>>**+ ,Z Z
 u||Jv}}MOaab%%VFR_hlhshs%tD/ /??-;;*55
 	
r2   rJ  )rF   rG   rH   r   r&   r  r  r   r   r   r)   r   r   r	   r   r   r   r@   rI   rJ   s   @r1   rs  rs    s   | '(  151537+/59-1$(,0/3A
E,,-A
 !.A
 u//0	A

 "%A
   1 12A
 ))*A
 D>A
 $D>A
 'tnA
 
*A
  A
r2   rs  c                   "    e Zd Zdef fdZd Zd Zee	 	 	 	 	 	 	 	 	 dde	e
j                     de	e
j                     de	e
j                     de	e   d	e	e
j                     d
e	e
j                     de	e   de	e   de	e   defd              Z xZS )HeliumForTokenClassificationrM   c                    t         |   |       |j                  | _        t        |      | _        t        |dd       |j                  }nt        |dd       |j                  }nd}t        j                  |      | _
        t        j                  |j                  |j                        | _        | j                          y )Nclassifier_dropouthidden_dropoutg?)r%   r&   ru  r  r   r   r  r  r'   Dropoutr   r|   r.   rv  r  )r-   rM   r  r0   s      r1   r&   z%HeliumForTokenClassification.__init__0  s      ++ (
6/6B!'!:!:V-t4@!'!6!6!$zz"45YYv1163D3DE
 	r2   c                 .    | j                   j                  S r$   rV  rD   s    r1   r  z1HeliumForTokenClassification.get_input_embeddings@  rW  r2   c                 &    || j                   _        y r$   rV  r  s     r1   r  z1HeliumForTokenClassification.set_input_embeddingsC  rY  r2   r  r   rp   r   r  rf  r   r   r  r   c
           
         | j                  ||||||||	      }
|
j                  }| j                  |      }| j                  |      }d}|| j	                  ||| j
                        }t        |||
j                  |
j                        S )rz  r{  N)rj  rR  r=   r   )	r   r  r   rv  rl  rM   r   r=   r   )r-   r  r   rp   r   r  rf  r   r   r  r   sequence_outputrR  rj  s                 r1   r@   z$HeliumForTokenClassification.forwardF  s    * ,0::)%+'/!5 ,6 	,
 "33,,7O,%%ffdkkBD$!//))	
 	
r2   rJ  )rF   rG   rH   r   r&   r  r  r   r   r   r)   r   r   r	   r   r   r   r@   rI   rJ   s   @r1   r  r  .  s    |  '(  151537+/59-1$(,0/3*
E,,-*
 !.*
 u//0	*

 "%*
   1 12*
 ))**
 D>*
 $D>*
 'tn*
 
*
  *
r2   r  )r   r  rO  rs  r  )r   )Nr   )Fr   typingr   r   r   r   r)   torch.nnr'   activationsr   cache_utilsr	   r
   
generationr   modeling_attn_mask_utilsr   modeling_flash_attention_utilsr   modeling_layersr   modeling_outputsr   r   r   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   r   configuration_heliumr   !torch.nn.attention.flex_attentionr   integrations.flex_attentionr    
get_loggerrF   r   Moduler"   rL   rw   r   r   r   rf   r   r   r   r   r   r   r  rM  rO  rs  r  __all__r   r2   r1   <module>r     s  ,  3 3   ! . ) > B 9  L F & h h .  !;J 
		H	%JBII J"<BII <D		  	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % %46BH)bii H)V23 2j *O * *8 p' p pf ?,j > i
- i
 i
X S
&; S
S
l C
#8 C
 C
Lr2   