
    rhoS                         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(  G d dejR                        Z*d Z+d5dZ,dejZ                  de.dejZ                  fdZ/	 d6dejR                  dejZ                  dejZ                  dejZ                  deejZ                     d e0d!e0d"e"e$   fd#Z1 G d$ d%ejR                        Z2 G d& d'e      Z3 G d( d)ejR                        Z4e% G d* d+e              Z5e% G d, d-e5             Z6e% G d. d/e5e             Z7 G d0 d1ee5      Z8 G d2 d3ee5      Z9g d4Z:y)7    )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   )Starcoder2Configc                   h     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                 P   t         |           |j                  }t        j                  ||j
                  |j                        | _        t        j                  |j
                  ||j                        | _        t        |j                     | _        |j                  | _        y )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      /var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/starcoder2/modeling_starcoder2.pyr&   zStarcoder2MLP.__init__5   su    &&	IIi)A)AX	ii 8 8)&//Z&++, & 7 7    hidden_statesreturnc                     | j                  |      }| j                  |      }| j                  |      }t        j                  j                  || j                  | j                        }|S )Nptraining)r+   r.   r,   r   
functionaldropoutr/   r:   )r0   r5   s     r3   forwardzStarcoder2MLP.forward=   sZ    		-0/M2--mt?T?T_c_l_l-mr4   )__name__
__module____qualname__r   r&   r   tupletorchFloatTensorr=   __classcell__r2   s   @r3   r    r    4   s9    8/ 8XeE4E4E.F%G EL]L] r4   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)shaperB   cat)xx1x2s      r3   rotate_halfrP   E   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r4   c                     |j                  |      }|j                  |      }| |z  t        |       |z  z   }||z  t        |      |z  z   }||fS )a  Applies Rotary Position Embedding to the query and key tensors.

    Args:
        q (`torch.Tensor`): The query tensor.
        k (`torch.Tensor`): The key tensor.
        cos (`torch.Tensor`): The cosine part of the rotary embedding.
        sin (`torch.Tensor`): The sine part of the rotary embedding.
        position_ids (`torch.Tensor`, *optional*):
            Deprecated and unused.
        unsqueeze_dim (`int`, *optional*, defaults to 1):
            The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
            sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
            that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and
            k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes
            cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have
            the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2.
    Returns:
        `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
    )	unsqueezerP   )qkcossinposition_idsunsqueeze_dimq_embedk_embeds           r3   apply_rotary_pos_embr[   L   sY    ( --
&C
--
&C3w;q>C/0G3w;q>C/0GGr4   r5   n_repr6   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)rK   expandreshape)r5   r\   batchnum_key_value_headsslenhead_dims         r3   	repeat_kvrd   g   so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr4   modulequerykeyvalueattention_maskscalingr<   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 )NrH   r   rG   )rJ   dtyper8   r   )rd   num_key_value_groupsrB   matmul	transposerK   r   r;   softmaxfloat32torn   r<   r:   
contiguous)re   rf   rg   rh   ri   rj   r<   rk   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r3   eager_attention_forwardr{   s   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$$r4   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 )Starcoder2Attentionz=Multi-headed attention from 'Attention Is All You Need' paperr!   	layer_idxc                    t         |           || _        || _        t	        |dd       xs |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(                  | _        y )Nrc   g      Tr#   )r%   r&   r!   r~   getattrr'   num_attention_headsrc   ra   ro   rj   attention_dropout	is_causalr   r(   r*   q_projk_projv_projo_projr/   r0   r!   r~   r2   s      r3   r&   zStarcoder2Attention.__init__   sX   "
D9mV=O=OSYSmSm=m$*$>$>&B\B\$\!}}d*!'!9!9ii 2 2F4N4NQUQ^Q^4^eketetuii 2 2F4N4NQUQ^Q^4^eketetuii 2 2F4N4NQUQ^Q^4^eketetuii : :T]] JFL^L^eketetu & 7 7r4   r5   position_embeddingsri   past_key_valuecache_positionrk   r6   c           
         |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        }| j                  j                  dk7  rt        | j                  j                     } || |	|
||f| j                  sdn| j                  | j                   t#        | j                  dd       d|\  }} |j$                  g |d j'                         }| j)                  |      }t*        j,                  j/                  || j0                  | j                  	      }||fS )
NrG   r   rH   )rV   rU   r   eager        sliding_window)r<   rj   r   r8   )rK   rc   r   viewrq   r   r   r[   updater~   r{   r!   _attn_implementationr   r:   r   rj   r   r_   ru   r   r   r;   r<   r/   )r0   r5   r   ri   r   r   rk   input_shapehidden_shapequery_statesrv   rw   rU   rV   cache_kwargsattention_interfacerz   rx   s                     r3   r=   zStarcoder2Attention.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$J(?;;++w6"9$++:Z:Z"[$7
%
  $}}C$2H2HLL"4;;0@$G
%
 
%
!\ *k));;;;FFHkk+.mm++4004== , 
 L((r4   N)NN)r>   r?   r@   __doc__r   r   intr&   rB   TensorrA   r
   
LongTensorr   r   r=   rD   rE   s   @r3   r}   r}      s    G8/ 8HSM 8( +/59.)||.) #5<<#=>.) !.	.)
 !.) !!1!12.) -..) 
u||Xell3XeELL>Q5RR	S.)r4   r}   c                   (    e Zd Zded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j                     d
eeej                  ej                  f      dee   deej                     fdZ xZS )Starcoder2DecoderLayerr!   r~   c                 H   t         |           |j                  | _        t        ||      | _        t        |      | _        t        j                  |j                  |j                        | _
        t        j                  |j                  |j                        | _        y )N)r!   r~   eps)r%   r&   r'   r}   	self_attnr    mlpr   	LayerNormnorm_epsiloninput_layernormpost_attention_layernormr   s      r3   r&   zStarcoder2DecoderLayer.__init__   st    !--,FiP (!||F,>,>FDWDWX(*V5G5GVM`M`(a%r4   r5   ri   rW   r   	use_cacher   r   rk   r6   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r5   ri   rW   r   r   r   r    )r   r   r   r   )r0   r5   ri   rW   r   r   r   r   rk   residual_s              r3   r=   zStarcoder2DecoderLayer.forward   s     !,,];)4>> 	
')%)) 3	
 	
q !=0 !55mD/ =0r4   )NNNFNN)r>   r?   r@   r   r   r&   rB   r   r   r   r
   boolrA   r   r   r=   rD   rE   s   @r3   r   r      s    b/ bC b 2637*.$)59KO|| !. u//0	
 ! D> !!1!12 &eELL%,,,F&GH +, 
u||	r4   r   c                   ^     e Zd Zddef fdZ ej                         ed               Z xZ	S )Starcoder2RotaryEmbeddingr!   c                    t         |           t        |d      rUt        |j                  t
              r;|j                  j                  d|j                  j                  d            | _        nd| _        |j                  | _	        |j                  | _
        || _        t        | j                     | _        | j                  | j                  |      \  }| _        | j                  d|d       | j                   | _        y )Nrope_scaling	rope_typetypedefaultinv_freqF)
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)r0   r!   devicer   r2   s       r3   r&   z"Starcoder2RotaryEmbedding.__init__   s    6>*z&:M:Mt/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r4   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   rG   r   mpscpuF)device_typeenabledrH   rI   )rn   )r   floatr^   rK   rt   r   r   r   strrB   autocastrq   rL   rU   r   rV   rn   )
r0   rM   rW   inv_freq_expandedposition_ids_expandedr   freqsembrU   rV   s
             r3   r=   z!Starcoder2RotaryEmbedding.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   )
r>   r?   r@   r   r&   rB   no_gradr   r=   rD   rE   s   @r3   r   r      s4    // /" U]]_<  <r4   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)Starcoder2PreTrainedModelr!   modelTr   past_key_values)r5   
attentionsN)r>   r?   r@   r   __annotations__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   r4   r3   r   r     sQ    &*#12#4"5N!"&/)r4   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           	      B   t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        j                  |j                  |j                        | _        t#        |      | _        d| _        |j(                  | _        | j+                          y c c}w )Nr   )r!   F)r%   r&   pad_token_idpadding_idx
vocab_sizer   	Embeddingr'   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normr   
rotary_embgradient_checkpointingembedding_dropout	post_initr   s      r3   r&   zStarcoder2Model.__init__2  s     !.. ++LL):):F<N<NPTP`P`ammHMfNfNfHgh9#FI6h
 LL!3!39L9LM	36B&+#!'!9!9 	 is   D	input_idsri   rW   r   inputs_embedsr   r   rk   r6   c                    |d u |d uz  rt        d      || j                  |      }|r|
t               }|F||j                         nd}	t	        j
                  |	|	|j                  d   z   |j                        }||j                  d      }| j                  j                  t        nt        }
 |
| j                  |||||      }|}t        j                  j                  || j                   | j"                        }| j%                  ||      }| j&                  d | j                  j(                   D ]  } ||f||||||d|} | j+                  |      }t-        ||r|      S d       S )	Nz:You must specify exactly one of input_ids or inputs_embedsr   r   )r   )r!   input_embedsri   r   r   rW   r8   )ri   rW   r   r   r   r   )last_hidden_stater   )
ValueErrorr   r   get_seq_lengthrB   arangerK   r   rR   r!   r   r   r   r   r;   r<   r   r:   r   r   r   r   r   )r0   r   ri   rW   r   r   r   r   rk   past_seen_tokensmask_functionry   r5   r   decoder_layers                  r3   r=   zStarcoder2Model.forwardC  s    -t";<YZZ  --i8M0*nO!CRC^==?de"\\ "2]5H5H5K"KTaThThN )33A6L.2kk.H.H.P*Vw#;;&))+%
 &--T33dmm . 

 #oom\J![[)H4;;+H+HI 
	M)	*).#-$7	 	M
	 		-0&+/8O
 	
>B
 	
r4   )NNNNNNN)r>   r?   r@   r   r&   r   r   rB   r   r   r   r
   listrC   r   r   r   r   r=   rD   rE   s   @r3   r   r   0  s    / "  151537KO59$(59?
E,,-?
 !.?
 u//0	?

 "%tE4E4E/F(F"GH?
   1 12?
 D>?
 !!1!12?
 +,?
 
!?
 ?
r4   r   c                   p    e Zd ZdgZddiZddgdgfiZ 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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_repr5   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y )NFr#   )
r%   r&   r   r   r   r   r(   r'   r   r   )r0   r!   r2   s     r3   r&   zStarcoder2ForCausalLM.__init__  sU     $V,
 ++yy!3!3V5F5FUS 	r4   c                     || _         y r   r   )r0   decoders     r3   set_decoderz!Starcoder2ForCausalLM.set_decoder  s	    
r4   c                     | j                   S r   r  )r0   s    r3   get_decoderz!Starcoder2ForCausalLM.get_decoder  s    zzr4   r   ri   rW   r   r   labelsr   r   logits_to_keeprk   r6   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, 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   ri   rW   r   r   r   r   N)r  r	  r   )lossr  r   r5   r   r   )r   r   r   r   slicer   loss_functionr!   r   r   r   r5   r   )r0   r   ri   rW   r   r   r	  r   r   r
  rk   outputsr5   slice_indicesr  r  s                   r3   r=   zStarcoder2ForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r4   )	NNNNNNNNr   )r>   r?   r@   _tied_weights_keys_tp_plan_pp_planr&   r  r  r   r   r   rB   r   r   r
   rC   r   r   r   r   r   r   r=   rD   rE   s   @r3   r   r     s:   *+=)H_-z:;H  151537+/59-1$(59348
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 ))*8
 D>8
 !!1!128
 c5<</08
 +,8
 
 8
  8
r4   r   c                       e Zd Zy)#Starcoder2ForSequenceClassificationNr>   r?   r@   r   r4   r3   r  r        r4   r  c                       e Zd Zy) Starcoder2ForTokenClassificationNr  r   r4   r3   r  r    r  r4   r  )r   r   r   r  r  )Nr   )r   );typingr   r   r   rB   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   configuration_starcoder2r   Moduler    rP   r[   r   r   rd   r   r{   r}   r   r   r   r   r   r  r  __all__r   r4   r3   <module>r*     s  6 - ,   9 ! . ) R B 
 P K F & I I 6BII "(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4@)")) @)F(7 (V<		 <D   $ R
/ R
 R
j N
5 N
 N
b	*JLe 		'DF_ 	r4   