
     `iQ                        d dl Z 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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$m%Z% ddl&m'Z' ddl(m)Z)  G d dej*                  Z+ G d dej*                  Z, G d dej*                  Z-dej.        de/dej.        fdZ0	 d7dej*        dej.        dej.        d ej.        d!eej.                 d"e1d#e1d$ee!         fd%Z2d& Z3d8d'Z4 G d( d)ej*                  Z5 G d* d+e          Z6e" G d, d-e                      Z7e" G d. d/e7                      Z8e" G d0 d1e7e                      Z9 G d2 d3ee7          Z: G d4 d5ee7          Z;g d6Z<dS )9    N)CallableOptionalUnion   )ACT2FN)CacheDynamicCache)GenerationMixin)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)deprecate_kwarg)check_model_inputs   )HeliumConfigc                   ,     e Zd Zd fd	Zd Zd Z xZS )HeliumRMSNormư>c                     t                                                       t          j        t	          j        |                    | _        || _        d S N)super__init__nn	Parametertorchonesweightvariance_epsilon)selfhidden_sizeeps	__class__s      ~/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/helium/modeling_helium.pyr#   zHeliumRMSNorm.__init__0   sB    l5:k#:#:;; #    c                 T   |j         }|                    t          j                  }|                    d                              dd          }|t          j        || j        z             z  }| j                            t          j                  |z                      |          S )N   T)keepdim)	dtypetor&   float32powmeanrsqrtr)   r(   )r*   hidden_statesinput_dtypevariances       r.   forwardzHeliumRMSNorm.forward5   s    #)%((77 $$Q'',,R,>>%Ht?T4T(U(UUu}--=AA+NNNr/   c                 H    t          | j        j                   d| j         S )Nz, eps=)tupler(   shaper)   )r*   s    r.   
extra_reprzHeliumRMSNorm.extra_repr<   s&    )**II$2GIIIr/   )r   )__name__
__module____qualname__r#   r=   rA   __classcell__r-   s   @r.   r   r   /   se        $ $ $ $ $ $
O O OJ J J J J J Jr/   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 )HeliumRotaryEmbeddinginv_freqNconfigc                    t                                                       t          |d          rSt          |j        t
                    r9|j                            d|j                            d                    | _        nd| _        |j        | _	        |j        | _
        || _        t          | j                 | _        |                     | j        |          \  }| _        |                     d|d           | j        | _        d S )Nrope_scaling	rope_typetypedefaultrI   F)
persistent)r"   r#   hasattr
isinstancerL   dictgetrM   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrJ   r   rope_init_fnattention_scalingregister_bufferrI   original_inv_freq)r*   rJ   devicerI   r-   s       r.   r#   zHeliumRotaryEmbedding.__init__C   s    6>** 	'z&:Mt/T/T 	'#044[&BUBYBYZ`BaBabbDNN&DN"("@$*$B!/?+/+<+<T[&+Q+Q($(ZeDDD!%r/   c                 X   | j         d d d d f                                                             |j        d         dd                              |j                  }|d d d d d f                                         }t          |j        j        t                    r|j        j        dk    r|j        j        nd}t          j
        |d          5  |                                |                                z                      dd          }t          j        ||fd	          }|                                | j        z  }|                                | j        z  }	d d d            n# 1 swxY w Y   |                    |j        
          |	                    |j        
          fS )Nr   r2   r   mpscpuF)device_typeenabledr1   dim)r4   )rI   floatexpandr@   r5   r\   rR   rN   strr&   autocast	transposecatcosrY   sinr4   )
r*   xposition_idsinv_freq_expandedposition_ids_expandedr`   freqsembrj   rk   s
             r.   r=   zHeliumRotaryEmbedding.forwardT   s    !M$4-8>>@@GGHZ[\H]_acdeehhijiqrr ,QQQaaaZ 8 > > @ @'1!(-'E'Ek!(-[`J`J`ahmmfk^UCCC 	5 	5&,,..1F1L1L1N1NNYYZ[]^__E)UEN333C''))d44C''))d44C		5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 vvAGv$$cff17f&;&;;;s   BE++E/2E/r!   )rB   rC   rD   r&   Tensor__annotations__r   r#   no_gradr   r=   rE   rF   s   @r.   rH   rH   @   s         l/ /| / / / / / /" U]__< <  _< < < < <r/   rH   c                   $     e Zd Z fdZd Z xZS )	HeliumMLPc                    t                                                       || _        |j        | _        |j        | _        t          j        | j        | j        |j                  | _        t          j        | j        | j        |j                  | _	        t          j        | j        | j        |j                  | _
        t          |j                 | _        d S )Nbias)r"   r#   rJ   r+   intermediate_sizer$   Linearmlp_bias	gate_projup_proj	down_projr   
hidden_actact_fnr*   rJ   r-   s     r.   r#   zHeliumMLP.__init__e   s    !-!'!94#3T5KRXRabbby!143IPVP_```4#94;KRXRabbbV./r/   c                     |                      |                     |                     |                    |                     |          z            }|S r!   )r   r   r}   r~   )r*   rl   r   s      r.   r=   zHeliumMLP.forwardo   sA    NN4;;t~~a/@/@#A#ADLLQROO#STT	r/   )rB   rC   rD   r#   r=   rE   rF   s   @r.   rv   rv   d   sG        0 0 0 0 0      r/   rv   r:   n_repreturnc                     | j         \  }}}}|dk    r| S | dddddddddf                             |||||          } |                     |||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@   re   reshape)r:   r   batchnum_key_value_headsslenhead_dims         r.   	repeat_kvr   t   s    
 2?1D.Ehzz!!!!QQQaaa"23::5BUW\^bdlmmM  (;e(CT8TTTr/           modulequerykeyvalueattention_maskscalingdropoutkwargsc                 R   t          || j                  }t          || j                  }	t          j        ||                    dd                    |z  }
|$|d d d d d d d |j        d         f         }|
|z   }
t          j                            |
dt          j	                  
                    |j                  }
t          j                            |
|| j                  }
t          j        |
|	          }|                    dd                                          }||
fS )Nr1   r   r2   )rc   r4   )ptrainingr   )r   num_key_value_groupsr&   matmulrh   r@   r$   
functionalsoftmaxr6   r5   r4   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$?@@L<z';';Aq'A'ABBWLL!$QQQ111.D
0@0D.D%DE#k1=((2U](SSVVW\WbccL=((6?([[L,|\::K''1--88::K$$r/   c                     | ddddf         }| ddddf         }t          j        | |fd                              d          S )	z*Rotates half the hidden dims of the input..r   Nr1   r   r2   rb   r   )r&   stackflatten)rl   x1x2s      r.   rotate_halfr      sQ    	
319B	
319B;Ryb)))11"555r/   c                 z   |                     |          }|                     |          }|dd|j        d         dz  f                             dd          }|dd|j        d         dz  f                             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.
    .Nr2   r1   rb   )	unsqueezer@   repeat_interleaver   )qkrj   rk   rm   unsqueeze_dimq_embedk_embeds           r.   apply_rotary_pos_embr      s    ( --
&
&C
--
&
&C c'SYr]a'''
(
:
:1"
:
E
EC
c'SYr]a'''
(
:
:1"
:
E
EC3w;q>>C/0G3w;q>>C/0GGr/   c                   "    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 )HeliumAttentionz=Multi-headed attention from 'Attention Is All You Need' paperNrJ   	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          | _        d S )Nr   r   Trx   F)r"   r#   rJ   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*   rJ   r   r-   s      r.   r#   zHeliumAttention.__init__   s:   "
F4F&Jd4dee$*$>&B\$\!49T]333!'!9i :T] JQWQf
 
 
 i :T] JQWQf
 
 
 i :T] JQWQf
 
 
 i 2F4FUSSSr/   past_key_valuepast_key_values4.58new_nameversionr:   position_embeddingsr   cache_positionr   r   c                 D   |j         d d         }g |d| j        R }|                     |                              |                              dd          }	|                     |                              |                              dd          }
|                     |                              |                              dd          }|\  }}t          |	|
||          \  }	}
|&|||d}|                    |
|| j	        |          \  }
}t          }| j        j        dk    rt          | j        j                 } || |	|
||f| j        sdn| j        | j        d|\  }} |j        g |dR                                  }|                     |          }||fS )Nr2   r   r1   )rk   rj   r   eagerr   )r   r   )r@   r   r   viewrh   r   r   r   updater   r   rJ   _attn_implementationr   r   r   r   r   r   r   )r*   r:   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   rj   rk   cache_kwargsattention_interfacer   r   s                     r.   r=   zHeliumAttention.forward   s    $)#2#.88b8$-88{{=1166|DDNNqRSTT[[//44\BBLLQPQRR
{{=1166|DDNNqRSTT&S#7jRUWZ#[#[ j&#&snUUL'6'='=j,X\Xfht'u'u$J(?;+w66"9$+:Z"[$7$7	%
  $}HCC$2HL	%
 	%
 	%
 	%
!\ *k);;;;;;FFHHkk+..L((r/   r!   )NN)rB   rC   rD   __doc__r   r   intr#   r   r&   rr   r?   r   
LongTensorr   r   r=   rE   rF   s   @r.   r   r      s        GGT T| T T T T T T T* _%0A6RRR ,059)) ))|)) #5<#=>)) !.	))
 "%)) !!12)) +,)) 
u|U\)	*)) )) )) SR)) )) )) )) ))r/   r   c                   B    e Zd Zddedee         f fdZ eddd          	 	 	 	 	 	 dd
ej	        deej	                 deej
                 dee         dee         deej
                 deeej	        ej	        f                  dee         dej	        fd            Z xZS )HeliumDecoderLayerNrJ   r   c                 4   t                                                       |j        | _        t          ||          | _        t          |          | _        t          |j        |j                  | _	        t          |j        |j                  | _
        d S )N)rJ   r   r,   )r"   r#   r+   r   	self_attnrv   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr   s      r.   r#   zHeliumDecoderLayer.__init__  s    !-()LLLV$$,V-?VEXYYY(5f6HfNa(b(b(b%%%r/   r   r   r   r   Fr:   r   rm   	use_cacher   r   r   r   c                     |}	|                      |          } | j        d|||||||d|\  }}
|	|z   }|}	|                     |          }|                     |          }|	|z   }|S )N)r:   r   rm   r   r   r   r    )r   r   r   r   )r*   r:   r   rm   r   r   r   r   r   residual_s              r.   r=   zHeliumDecoderLayer.forward  s     !,,];;)4> 	
')%+) 3	
 	
 	
 	
q !=0 !55mDD// =0r/   r!   )NNNFNN)rB   rC   rD   r   r   r   r#   r   r&   rr   r   r   boolr?   r   r   r=   rE   rF   s   @r.   r   r     s?       c c| c c c c c c c _%0A6RRR 2637+/$)59KO | !. u/0	
 "% D> !!12 &eEL%,,F&GH +, 
   SR    r/   r   c                   L    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dS )HeliumPreTrainedModelrJ   modelTr   r   )r:   
attentionsN)rB   rC   rD   r   rs   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   5  sl         &*#-.#4"5N!"&+% r/   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 )HeliumModelrJ   c                    t                                                     j        | _        j        | _        t          j        j        j        | j                  | _        t          j	        fdt          j                  D                       | _        t          j        j                  | _        t!                    | _        d| _        |                                  d S )Nc                 0    g | ]}t          |          S r   )r   ).0r   rJ   s     r.   
<listcomp>z(HeliumModel.__init__.<locals>.<listcomp>Q  s$    dddy	22dddr/   r   F)r"   r#   pad_token_idpadding_idx
vocab_sizer$   	Embeddingr+   embed_tokens
ModuleListrangenum_hidden_layerslayersr   r   normrH   
rotary_embgradient_checkpointing	post_initr   s    `r.   r#   zHeliumModel.__init__J  s       !. +L):F<NPTP`aamddddE&JbDcDcddd
 
 "&"4&:MNNN	/77&+# 	r/   N	input_idsr   rm   r   inputs_embedsr   r   r   r   c           
      N   |d u |d uz  rt          d          ||                     |          }|r|t          | j                  }|B||                                nd}	t          j        |	|	|j        d         z   |j                  }||	                    d          }t          | j        |||||          }
|}|                     ||          }| j        d | j        j                 D ]} ||f|
||||d|}|                     |          }t          ||          S )	Nz:You must specify exactly one of input_ids or inputs_embeds)rJ   r   r   )r\   )rJ   input_embedsr   r   r   rm   )r   rm   r   r   r   )last_hidden_stater   )
ValueErrorr   r	   rJ   get_seq_lengthr&   aranger@   r\   r   r   r  r  r  r  r   )r*   r	  r   rm   r   r
  r   r   r   past_seen_tokensr   r:   r   decoder_layers                 r.   r=   zHeliumModel.forwardZ  s    -t";< 	[YZZZ *.*;*;I*F*FM 	?0*$+>>>O!CRC^==???de+0< "2]5H5K"KTaTh, , ,N )33A66L(;&))+%
 
 
 &"oom\JJ![)H4;+H)HI 		 		M)M*) /-$7   MM 		-00&++
 
 
 	
r/   )NNNNNNN)rB   rC   rD   r   r#   r   r   r   r&   r   rr   r   FloatTensorr   r   r   r   r=   rE   rF   s   @r.   r   r   H  s       |         151537+/5959$(8
 8
E,-8
 !.8
 u/0	8

 "%8
   128
 !!128
 D>8
 +,8
 
!8
 8
 8
 ^ 8
 8
 8
 8
 8
r/   r   c                   f    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 )HeliumForCausalLMzlm_head.weightlm_headcolwise_repr:   logitsc                     t                                          |           t          |          | _        |j        | _        t          j        |j        |j        d          | _        | 	                                 d S )NFrx   )
r"   r#   r   r   r   r$   r{   r+   r  r  r   s     r.   r#   zHeliumForCausalLM.__init__  sj        ((
 +y!3V5FUSSS 	r/   Nr   r	  r   rm   r   r
  labelsr   r   logits_to_keepr   r   c
                 R    | j         d|||||||d|
}|j        }t          |	t                    rt	          |	 d          n|	}|                     |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   rm   r   r
  r   r   N)r  r  r   )lossr  r   r:   r   r   )r   r  rR   r   slicer  loss_functionrJ   r   r   r   r:   r   )r*   r	  r   rm   r   r
  r  r   r   r  r   outputsr:   slice_indicesr  r  s                   r.   r=   zHeliumForCausalLM.forward  s    @ ,64: 	,
)%+')	,
 	,
 	,
 	,
  18B>SV8W8Wk~ot444]kmAAA}aaa,?@AA%4%pVFt{OeppioppD%#3!/)
 
 
 	
r/   )	NNNNNNNNr   )rB   rC   rD   _tied_weights_keys_tp_plan_pp_planr#   r   r   r   r&   r   rr   r   r  r   r   r   r   r   r   r=   rE   rF   s   @r.   r  r    sa       *+=)H_-z:;H      151537+/59-1$(59348
 8
E,-8
 !.8
 u/0	8

 "%8
   128
 )*8
 D>8
 !!128
 c5</08
 +,8
 
 8
 8
 8
 ^ 8
 8
 8
 8
 8
r/   r  c                       e Zd ZdS )HeliumForSequenceClassificationNrB   rC   rD   r   r/   r.   r&  r&            Dr/   r&  c                       e Zd ZdS )HeliumForTokenClassificationNr'  r   r/   r.   r*  r*    r(  r/   r*  )r   r   r  r&  r*  )r   )Nr   )=r   typingr   r   r   r&   torch.nnr$   activationsr   cache_utilsr   r	   
generationr
   masking_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.deprecationr   utils.genericr   configuration_heliumr   Moduler   rH   rv   rr   r   r   rd   r   r   r   r   r   r   r   r  r&  r*  __all__r   r/   r.   <module>r<     sh  ,  , , , , , , , , , ,        ! ! ! ! ! ! . . . . . . . . ) ) ) ) ) ) / / / / / /         
 P O O O O O O O K K K K K K K K F F F F F F F F & & & & & & I I I I I I I I I I 0 0 0 0 0 0 / / / / / / . . . . . .J J J J JBI J J J"!< !< !< !< !<BI !< !< !<H    	    	UU\ 	U# 	U%, 	U 	U 	U 	U& % %I%<% 
% <	%
 U\*% % % '(% % % %46 6 6   BB) B) B) B) B)bi B) B) B)J+ + + + +3 + + +\     O   $ K
 K
 K
 K
 K
' K
 K
 K
\ H
 H
 H
 H
 H
- H
 H
 H
V	 	 	 	 	&FH] 	 	 		 	 	 	 	#@BW 	 	 	  r/   