
    iU                     L   d dl Z 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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 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, G d dejV                        Z- G d dejV                        Z.dej^                  de0dej^                  fdZ1	 d7dejV                  dej^                  dej^                  d ej^                  d!ej^                  dz  d"e2d#e2d$e!e#   fd%Z3d& Z4d8d'Z5 ee5       G d( d)ejV                               Z6 G d* d+e      Z7e$ G d, d-e             Z8e$ G d. d/e8             Z9e$ G d0 d1e8e             Z: G d2 d3ee8      Z; G d4 d5ee8      Z<g d6Z=y)9    N)Callable)Optional   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernelized_func)create_causal_mask) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)check_model_inputsmaybe_autocast   )HeliumConfigc                   ,     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      t/home/obispo/Crisostomo_bridge/mision_env/lib/python3.12/site-packages/transformers/models/helium/modeling_helium.pyr"   zHeliumRMSNorm.__init__0   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       r-   forwardzHeliumRMSNorm.forward5   s    #))%((7 $$Q',,R,>%Ht?T?T4T(UUu}}-=AA+NNr.   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tupler'   shaper(   )r)   s    r-   
extra_reprzHeliumRMSNorm.extra_repr<   s*    ))*+6$2G2G1HIIr.   )gư>)__name__
__module____qualname__r"   r<   r@   __classcell__r,   s   @r-   r   r   /   s    $
OJr.   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 )HeliumRotaryEmbeddinginv_freqNconfigc                    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defaultrH   F)
persistentoriginal_inv_freq)r!   r"   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrI   rope_parametersrK   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r)   rI   devicerope_init_fnrH   r,   s        r-   r"   zHeliumRotaryEmbedding.__init__C   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuUr.   rW   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   r0   r3   )rW   r3   )	rR   getattrr*   num_attention_headsr%   arangeint64r4   float)rI   rW   rY   basedimattention_factorrH   s          r-   rS   z5HeliumRotaryEmbedding.compute_default_rope_parametersS   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r.   c                 N   | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        j	                  |j                   
      	j	                  |j                   
      fS # 1 sw Y   AxY w)Nr   r1   r   mpscpuF)device_typeenabledr0   re   r^   )rH   rc   expandr?   r4   rW   
isinstancetypestrr   	transposer%   catcosrT   sinr3   )
r)   xposition_idsinv_freq_expandedposition_ids_expandedrj   freqsembrs   rt   s
             r-   r<   zHeliumRotaryEmbedding.forwardq   sR    !MM$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)rA   rB   rC   r%   Tensor__annotations__r   r"   staticmethodr   intr>   rc   rS   no_gradr   r<   rD   rE   s   @r-   rG   rG   @   s    llV| V  &*+/"*t#*(* t* 
~u$	%	* *: U]]_<  <r.   rG   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"   rI   r*   intermediate_sizer#   Linearmlp_bias	gate_projup_proj	down_projr   
hidden_actact_fnr)   rI   r,   s     r-   r"   zHeliumMLP.__init__   s    !--!'!9!94#3#3T5K5KRXRaRabyy!1!143I3IPVP_P_`4#9#94;K;KRXRaRabV../r.   c                     | j                  | j                  | j                  |            | j                  |      z        }|S r    )r   r   r   r   )r)   ru   r   s      r-   r<   zHeliumMLP.forward   s6    NN4;;t~~a/@#ADLLQRO#ST	r.   )rA   rB   rC   r"   r<   rD   rE   s   @r-   r   r      s    0r.   r   r9   n_reprZ   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)r?   rm   reshape)r9   r   batchnum_key_value_headsslenr]   s         r-   	repeat_kvr      so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr.   modulequerykeyvalueattention_maskscalingdropoutkwargsc                 T   t        || j                        }t        || j                        }	t        j                  ||j	                  dd            |z  }
|#|d d d d d d d |j
                  d   f   }|
|z   }
t        j                  j                  |
dt        j                        j                  |j                        }
t        j                  j                  |
|| j                        }
t        j                  |
|	      }|j	                  dd      j                         }||
fS )Nr0   r   r1   )re   r3   )ptrainingr   )r   num_key_value_groupsr%   matmulrq   r?   r#   
functionalsoftmaxr5   r4   r3   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r-   eager_attention_forwardr      s    3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#k1==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r.   c                 |    | 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   Nr0   r   r1   rl   r   )r%   stackflatten)ru   x1x2s      r-   rotate_halfr      sJ    	
319B	
319B;;Ryb)11"55r.   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.
        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.
    .Nr1   r0   rl   )	unsqueezer?   repeat_interleaver   )qkrs   rt   unsqueeze_dimq_embedk_embeds          r-   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r.   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z  dej                  dz  d	e
dz  d
ej                  dz  dee   de	ej                  ej                  f   fdZ xZS )HeliumAttentionz=Multi-headed attention from 'Attention Is All You Need' paperNrI   	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   Tr   F)r!   r"   rI   r   r_   r*   r`   r]   r   r   mathsqrtr   attention_dropout	is_causalr#   r   attention_biasq_projk_projv_projo_projr)   rI   r   r,   s      r-   r"   zHeliumAttention.__init__   sC   "
F4F4F&JdJd4de$*$>$>&B\B\$\!499T]]33!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii 2 2F4F4FUSr.   r9   position_embeddingsr   past_key_valuescache_positionr   rZ   c                    |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        j                  | j                  j                  t              } || |	|
||f| j                  sdn| j                   | j"                  d|\  }} |j$                  g |d j'                         }| j)                  |      }||fS )Nr1   r   r0   )rt   rs   r           )r   r   )r?   r]   r   viewrq   r   r   r   updater   r   get_interfacerI   _attn_implementationr   r   r   r   r   r   r   )r)   r9   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   rs   rt   cache_kwargsattention_interfacer   r   s                     r-   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'6'='=j,X\XfXfht'u$J(?(M(MKK,,.E)
 %8	%
  $}}C$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r.   r    )NNNN)rA   rB   rC   __doc__r   r~   r"   r%   r{   r>   r   
LongTensorr   r   r<   rD   rE   s   @r-   r   r      s    GT| Td
 T0 IM.2(,26))||)) #5<<#=>E)) t+	))
 )) ((4/)) +,)) 
u||U\\)	*))r.   r   c                   *    e Zd Zddededz  f fdZ	 	 	 	 	 	 ddej                  dej                  dz  dej                  dz  de	dz  d	e
dz  d
ej                  dz  deej                  ej                  f   dz  dee   dej                  fdZ xZS )HeliumDecoderLayerNrI   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        y )N)rI   r   r+   )r!   r"   r*   r   	self_attnr   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr   s      r-   r"   zHeliumDecoderLayer.__init__#  sl    !--()LV$,V-?-?VEXEXY(5f6H6HfNaNa(b%r.   r9   r   rv   r   	use_cacher   r   r   rZ   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r9   r   rv   r   r   r   r    )r   r   r   r   )r)   r9   r   rv   r   r   r   r   r   residual_s              r-   r<   zHeliumDecoderLayer.forward-  s     !,,];)4>> 	
')%+) 3	
 	
q !=0 !55mD/ =0r.   r    )NNNFNN)rA   rB   rC   r   r~   r"   r%   r{   r   r   boolr>   r   r   r<   rD   rE   s   @r-   r   r   "  s    c| cd
 c /304(,!&26HL|| t+ &&-	
  $; ((4/ #5<<#=>E +, 
r.   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)HeliumPreTrainedModelrI   modelTr   r   )r9   
attentionsN)rA   rB   rC   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-   r   r   O  sQ    &*#-.#4"5N!"&+%r.   r   c                       e Zd Zdef fdZee	 	 	 	 	 	 	 ddej                  dz  dej                  dz  dej                  dz  de
dz  dej                  dz  d	ej                  dz  d
edz  dee   defd              Z xZS )HeliumModelrI   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   rI   F)r!   r"   pad_token_idpadding_idx
vocab_sizer#   	Embeddingr*   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normrG   
rotary_embgradient_checkpointing	post_initr   s      r-   r"   zHeliumModel.__init__d  s     !.. ++LL):):F<N<NPTP`P`ammDI&JbJbDcdy	2d
 "&"4"4&:M:MN	/v>&+# 	 es   DN	input_idsr   rv   r   inputs_embedsr   r   r   rZ   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   )rW   )rI   input_embedsr   r   r   rv   )rv   )r   r   rv   r   r   r   )last_hidden_stater   )
ValueErrorr   r   rI   get_seq_lengthr%   ra   r?   rW   r   r   r  r  r  r  r   )r)   r  r   rv   r   r	  r   r   r   past_seen_tokensr   r9   r   decoder_layers                 r-   r<   zHeliumModel.forwardt  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&++
 	
r.   )NNNNNNN)rA   rB   rC   r   r"   r   r   r%   r   r{   r   FloatTensorr   r   r   r   r<   rD   rE   s   @r-   r   r   b  s    |    .2.204(,2626!%9
##d*9
 t+9
 &&-	9

 9
 ((4/9
 ((4/9
 $;9
 +,9
 
!9
  9
r.   r   c                   b    e Zd ZddiZddiZddgdgfiZ fdZee	 	 	 	 	 	 	 	 	 dd	e	j                  dz  d
e	j                  dz  de	j                  dz  dedz  de	j                  dz  de	j                  dz  dedz  de	j                  dz  dee	j                  z  dee   defd              Z xZS )HeliumForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr9   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y )NFr   )
r!   r"   r   r   r   r#   r   r*   r  r  r   s     r-   r"   zHeliumForCausalLM.__init__  sU      (
 ++yy!3!3V5F5FUS 	r.   Nr  r   rv   r   r	  labelsr   r   logits_to_keepr   rZ   c
                 z    | j                   d|||||||d|
}|j                  }t        |	t              rt	        |	 d      n|	}| j                  |dd|ddf         }d}|* | j                  d||| j                  j                  d|
}t        |||j                  |j                  |j                        S )a  
        Example:

        ```python
        >>> from transformers import AutoTokenizer, 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?"
        ```)r  r   rv   r   r	  r   r   N)r  r  r   )lossr  r   r9   r   r   )r   r  rn   r~   slicer  loss_functionrI   r   r   r   r9   r   )r)   r  r   rv   r   r	  r  r   r   r  r   outputsr9   slice_indicesr  r  s                   r-   r<   zHeliumForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r.   )	NNNNNNNNr   )rA   rB   rC   _tied_weights_keys_tp_plan_pp_planr"   r   r   r%   r   r{   r   r  r   r~   r   r   r   r<   rD   rE   s   @r-   r  r    s/   *,GH23H_-z:;H  .2.204(,26*.!%26-.8
##d*8
 t+8
 &&-	8

 8
 ((4/8
   4'8
 $;8
 ((4/8
 ell*8
 +,8
 
 8
  8
r.   r  c                       e Zd Zy)HeliumForSequenceClassificationNrA   rB   rC   r   r.   r-   r$  r$        r.   r$  c                       e Zd Zy)HeliumForTokenClassificationNr%  r   r.   r-   r(  r(    r&  r.   r(  )r   r   r  r$  r(  )r   )r   )>r   collections.abcr   typingr   r%   torch.nnr#   activationsr   cache_utilsr   r   
generationr	   integrationsr
   masking_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   configuration_heliumr   Moduler   rG   r   r{   r~   r   rc   r   r   r   r   r   r   r   r  r$  r(  __all__r   r.   r-   <module>r;     s  *  $    ! . ) / / 
 P K F & I I ? .JBII J"><BII ><B		  	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%46> )*A)bii A) +A)H*3 *Z O  $ L
' L
 L
^ H
- H
 H
V	&FH] 		#@BW 	r.   