
     `i!T                        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	 ddl
mZmZ ddl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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*  G d dej+                  Z,d Z-d7dZ.dej/        de0dej/        fdZ1	 d8dej+        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j+                  Z4 G d( d)e          Z5 G d* d+ej+                  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    )CallableOptionalUnionN)nn)check_model_inputs   )ACT2FN)CacheDynamicCache)GenerationMixin)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)deprecate_kwarg   )Starcoder2Configc                   `     e Zd Zdef fdZdeeej                          dej        fdZ	 xZ
S )Starcoder2MLPconfigc                 4   t                                                       |j        }t          j        ||j        |j                  | _        t          j        |j        ||j                  | _        t          |j
                 | _        |j        | _        d S )Nbias)super__init__hidden_sizer   Linearintermediate_sizeuse_biasc_fcc_projr	   
hidden_actactresidual_dropout)selfr"   	embed_dim	__class__s      /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/starcoder2/modeling_starcoder2.pyr'   zStarcoder2MLP.__init__6   s{    &	Ii)AXXX	i 8)&/ZZZ&+, & 7    hidden_statesreturnc                     |                      |          }|                     |          }|                     |          }t          j                            || j        | j                  }|S )Nptraining)r,   r/   r-   r   
functionaldropoutr0   r;   )r1   r6   s     r4   forwardzStarcoder2MLP.forward>   s^    		-00//M22--mt?T_c_l-mmr5   )__name__
__module____qualname__r   r'   r   tupletorchFloatTensorr>   __classcell__r3   s   @r4   r!   r!   5   sw        8/ 8 8 8 8 8 8XeE4E.F%G EL]        r5   r!   c                     | dd| j         d         dz  f         }| d| j         d         dz  df         }t          j        | |fd          S )z*Rotates half the hidden dims of the input..N   dim)shaperC   cat)xx1x2s      r4   rotate_halfrQ   F   s]    	
3"!'"+"""	#B	
3q """	#B9rc2YB''''r5   c                     |                     |          }|                     |          }| |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.
    )	unsqueezerQ   )qkcossinposition_idsunsqueeze_dimq_embedk_embeds           r4   apply_rotary_pos_embr\   M   sc    ( --
&
&C
--
&
&C3w;q>>C/0G3w;q>>C/0GGr5   r6   n_repr7   c                     | 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)rL   expandreshape)r6   r]   batchnum_key_value_headsslenhead_dims         r4   	repeat_kvre   h   s    
 2?1D.Ehzz!!!!QQQaaa"23::5BUW\^bdlmmM  (;e(CT8TTTr5           modulequerykeyvalueattention_maskscalingr=   kwargsc                 R   t          || j                  }t          || j                  }	t          j        ||                    dd                    |z  }
|$|d d d d d d d |j        d         f         }|
|z   }
t          j                            |
dt          j	                  
                    |j                  }
t          j                            |
|| j                  }
t          j        |
|	          }|                    dd                                          }||
fS )NrI   r   rH   )rK   dtyper9   r   )re   num_key_value_groupsrC   matmul	transposerL   r   r<   softmaxfloat32torp   r=   r;   
contiguous)rg   rh   ri   rj   rk   rl   r=   rm   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r4   eager_attention_forwardr}   t   s    3 ;<<JUF$?@@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$$r5   c                   R    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e	j
                 eee	j
                          f         fd            Z xZS )Starcoder2Attentionz=Multi-headed attention from 'Attention Is All You Need' paperNr"   	layer_idxc                    t                                                       || _        || _        t	          |dd           p|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                  | _        |j        | _        d S )Nrd   g      Tr$   )r&   r'   r"   r   getattrr(   num_attention_headsrd   rb   rq   rl   attention_dropout	is_causalr   r)   r+   q_projk_projv_projo_projr0   r1   r"   r   r3   s      r4   r'   zStarcoder2Attention.__init__   s9   "
D99mV=OSYSm=m$*$>&B\$\!}d*!'!9i 2F4NQUQ^4^eketuuui 2F4NQUQ^4^eketuuui 2F4NQUQ^4^eketuuui :T] JFL^eketuuu & 7r5   past_key_valuepast_key_values4.58new_nameversionr6   position_embeddingsrk   cache_positionrm   r7   c           
         |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        t#          | j        dd           d|\  }} |j        g |dR                                  }|                     |          }t*          j                            || j        | j        	          }||fS )
NrH   r   rI   )rW   rV   r   eagerrf   sliding_window)r=   rl   r   r9   )rL   rd   r   viewrs   r   r   r\   updater   r}   r"   _attn_implementationr   r;   r   rl   r   r`   rw   r   r   r<   r=   r0   )r1   r6   r   rk   r   r   rm   input_shapehidden_shapequery_statesrx   ry   rV   rW   cache_kwargsattention_interfacer|   rz   s                     r4   r>   zStarcoder2Attention.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$2HL"4;0@$GG
%
 
%
 
%
 
%
!\ *k);;;;;;FFHHkk+..m++404= , 
 
 L((r5   N)NN)r?   r@   rA   __doc__r   r   intr'   r   rC   TensorrB   r
   
LongTensorr   r   r>   rE   rF   s   @r4   r   r      s+       GG8 8/ 8HSM 8 8 8 8 8 8 _%0A6RRR ,059.) .)|.) #5<#=>.) !.	.)
 "%.) !!12.) -..) 
u|Xel3XeEL>Q5RR	S.) .) .) SR.) .) .) .) .)r5   r   c                   4    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j        fd            Z xZS )Starcoder2DecoderLayerr"   r   c                 H   t                                                       |j        | _        t          ||          | _        t          |          | _        t          j        |j        |j	                  | _
        t          j        |j        |j	                  | _        d S )N)r"   r   eps)r&   r'   r(   r   	self_attnr!   mlpr   	LayerNormnorm_epsiloninput_layernormpost_attention_layernormr   s      r4   r'   zStarcoder2DecoderLayer.__init__   s    !-,FiPPP ((!|F,>FDWXXX(*V5GVM`(a(a(a%%%r5   r   r   r   r   NFr6   rk   rX   	use_cacher   r   rm   r7   c                     |}	|                      |          } | j        d|||||||d|\  }}
|	|z   }|}	|                     |          }|                     |          }|	|z   }|S )N)r6   rk   rX   r   r   r   r    )r   r   r   r   )r1   r6   rk   rX   r   r   r   r   rm   residual_s              r4   r>   zStarcoder2DecoderLayer.forward   s     !,,];;)4> 	
')%+) 3	
 	
 	
 	
q !=0 !55mDD// =0r5   )NNNFNN)r?   r@   rA   r   r   r'   r   rC   r   r   r   r
   boolrB   r   r   r>   rE   rF   s   @r4   r   r      s6       b/ bC b b b b b b _%0A6RRR 2637+/$)59KO | !. u/0	
 "% D> !!12 &eEL%,,F&GH +, 
   SR    r5   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 )Starcoder2RotaryEmbeddinginv_freqNr"   c                    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defaultr   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_bufferr   original_inv_freq)r1   r"   devicer   r3   s       r4   r'   z"Starcoder2RotaryEmbedding.__init__  s    6>** 	'z&:Mt/T/T 	'#044[&BUBYBYZ`BaBabbDNN&DN"("@$*$B!/?+/+<+<T[&+Q+Q($(ZeDDD!%r5   c                 X   | j         d d d d f                                                             |j        d         dd                              |j                  }|d d d d d f                                         }t          |j        j        t                    r|j        j        dk    r|j        j        nd}t          j
        |d          5  |                                |                                z                      dd          }t          j        ||fd	          }|                                | j        z  }|                                | j        z  }	d d d            n# 1 swxY w Y   |                    |j        
          |	                    |j        
          fS )Nr   rH   r   mpscpuF)device_typeenabledrI   rJ   )rp   )r   floatr_   rL   rv   r   r   r   strrC   autocastrs   rM   rV   r   rW   rp   )
r1   rN   rX   inv_freq_expandedposition_ids_expandedr   freqsembrV   rW   s
             r4   r>   z!Starcoder2RotaryEmbedding.forward  s    !M$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   )r?   r@   rA   rC   r   __annotations__r   r'   no_gradr   r>   rE   rF   s   @r4   r   r      s         l/ // / / / / / /" U]__< <  _< < < < <r5   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 )Starcoder2PreTrainedModelr"   modelTr   r   )r6   
attentionsN)r?   r@   rA   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   r5   r4   r   r   "  sl         &*#12#4"5N!"&/) r5   r   c                   (    e Zd Zdef fdZe	 	 	 	 	 	 	 ddeej                 deej	                 deej                 dee
eeej                 f                  deej                 d	ee         d
eej                 dee         defd            Z xZS )Starcoder2Modelr"   c                     t                                                     j        | _        j        | _        t          j        j        j        | j                  | _        t          j	        fdt          j                  D                       | _        t          j        j        j                  | _        t!                    | _        d| _        j        | _        |                                  d S )Nc                 0    g | ]}t          |          S r   )r   ).0r   r"   s     r4   
<listcomp>z,Starcoder2Model.__init__.<locals>.<listcomp>>  s$    hhh9#FI66hhhr5   r   r"   F)r&   r'   pad_token_idpadding_idx
vocab_sizer   	Embeddingr(   embed_tokens
ModuleListrangenum_hidden_layerslayersr   r   normr   
rotary_embgradient_checkpointingembedding_dropout	post_initr1   r"   r3   s    `r4   r'   zStarcoder2Model.__init__7  s       !. +L):F<NPTP`aamhhhhfNfHgHghhh
 
 L!39LMMM	36BBB&+#!'!9 	r5   N	input_idsrk   rX   r   inputs_embedsr   r   rm   r7   c                    |d u |d uz  rt          d          ||                     |          }|r|t          | j                  }|B||                                nd}	t          j        |	|	|j        d         z   |j                  }||	                    d          }| j        j
        t          nt          }
 |
| j        |||||          }|}t          j                            || j        | j                  }|                     ||          }| j        d | j        j                 D ]} ||f||||||d|}|                     |          }t-          ||r|nd 	          S )
Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r   )r   )r"   input_embedsrk   r   r   rX   r9   )rk   rX   r   r   r   r   )last_hidden_stater   )
ValueErrorr   r   r"   get_seq_lengthrC   arangerL   r   rS   r   r   r   r   r<   r=   r   r;   r   r   r   r   r   )r1   r   rk   rX   r   r   r   r   rm   past_seen_tokensmask_functionr{   r6   r   decoder_layers                  r4   r>   zStarcoder2Model.forwardH  s    -t";< 	[YZZZ  --i88M 	?0*$+>>>O!CRC^==???de"\ "2]5H5K"KTaTh  N )33A66L.2k.H.P**Vw#m;&))+%
 
 
 &--T3dm . 
 

 #oom\JJ![)H4;+H)HI 
	 
	M)M	*) /#-$7	 	 	 	MM 		-00&+/8BOOd
 
 
 	
r5   )NNNNNNN)r?   r@   rA   r   r'   r   r   rC   r   r   r   r
   listrD   r   r   r   r   r>   rE   rF   s   @r4   r   r   5  s"       /      "  151537KO59$(59?
 ?
E,-?
 !.?
 u/0	?

 "%tE4E/F(F"GH?
   12?
 D>?
 !!12?
 +,?
 
!?
 ?
 ?
 ?
 ?
 ?
 ?
 ?
r5   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 )Starcoder2ForCausalLMzlm_head.weightlm_headcolwise_repr6   logitsc                     t                                          |           t          |          | _        |j        | _        t          j        |j        |j        d          | _        | 	                                 d S )NFr$   )
r&   r'   r   r   r   r   r)   r(   r	  r   r   s     r4   r'   zStarcoder2ForCausalLM.__init__  sj       $V,,
 +y!3V5FUSSS 	r5   Nr   r   rk   rX   r   r   labelsr   r   logits_to_keeprm   r7   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, Starcoder2ForCausalLM

        >>> model = Starcoder2ForCausalLM.from_pretrained("meta-starcoder2/Starcoder2-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-starcoder2/Starcoder2-2-7b-hf")

        >>> 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   rk   rX   r   r   r   r   N)r  r  r   )lossr  r   r6   r   r   )r   r   r   r   slicer	  loss_functionr"   r   r   r   r6   r   )r1   r   rk   rX   r   r   r  r   r   r  rm   outputsr6   slice_indicesr  r  s                   r4   r>   zStarcoder2ForCausalLM.forward  s    @ ,64: 	,
)%+')	,
 	,
 	,
 	,
  18B>SV8W8Wk~ot444]kmAAA}aaa,?@AA%4%pVFt{OeppioppD%#3!/)
 
 
 	
r5   )	NNNNNNNNr   )r?   r@   rA   _tied_weights_keys_tp_plan_pp_planr'   r   r   r   rC   r   r   r
   rD   r   r   r   r   r   r   r>   rE   rF   s   @r4   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
r5   r  c                       e Zd ZdS )#Starcoder2ForSequenceClassificationNr?   r@   rA   r   r5   r4   r  r            Dr5   r  c                       e Zd ZdS ) Starcoder2ForTokenClassificationNr  r   r5   r4   r  r    r  r5   r  )r  r   r   r  r  )Nr   )rf   )=typingr   r   r   rC   r   transformers.utils.genericr   activationsr	   cache_utilsr
   r   
generationr   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.deprecationr   configuration_starcoder2r   Moduler!   rQ   r\   r   r   re   r   r}   r   r   r   r   r   r  r  r  __all__r   r5   r4   <module>r/     sB  6 - , , , , , , , , ,        9 9 9 9 9 9 ! ! ! ! ! ! . . . . . . . . ) ) ) ) ) ) R R R R R R R R B B B B B B         
 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 6 6 6 6 6 6    BI   "( ( (   6	UU\ 	U# 	U%, 	U 	U 	U 	U& % %I%<% 
% <	%
 U\*% % % '(% % % %4A) A) A) A) A)") A) A) A)H) ) ) ) )7 ) ) )X!< !< !< !< !<	 !< !< !<H        $ R
 R
 R
 R
 R
/ R
 R
 R
j H
 H
 H
 H
 H
5 H
 H
 H
V	 	 	 	 	*JLe 	 	 		 	 	 	 	'DF_ 	 	 	  r5   