
    iW                     L   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	 ddl
mZmZ dd	l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m Z  ddl!m"Z"m#Z# ddl$m%Z% ddl&m'Z'm(Z(m)Z) ddl*m+Z+ ddl,m-Z-  G d dej\                        Z/d Z0 ed      d9d       Z1dejd                  de3dejd                  fdZ4	 d:dej\                  d ejd                  d!ejd                  d"ejd                  d#ejd                  dz  d$e5d%e5d&e%e'   fd'Z6 ee1       G d( d)ej\                               Z7 G d* d+e      Z8e( G d, d-e#             Z9 G d. d/ej\                        Z:e( G d0 d1e9             Z;e( G d2 d3e9e             Z< G d4 d5ee9      Z= G d6 d7ee9      Z>g d8Z?y);    )Callable)OptionalN)nn)check_model_inputs   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_func_from_hubuse_kernelized_func)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)maybe_autocast   )Starcoder2Configc                   h     e Zd Zdef fdZdeej                     dz  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      |/home/obispo/Crisostomo_bridge/mision_env/lib/python3.12/site-packages/transformers/models/starcoder2/modeling_starcoder2.pyr(   zStarcoder2MLP.__init__7   su    &&	IIi)A)AX	ii 8 8)&//Z&++, & 7 7    hidden_statesNreturnc                     | j                  |      }| j                  |      }| j                  |      }t        j                  j                  || j                  | j                        }|S )Nptraining)r-   r0   r.   r   
functionaldropoutr1   r<   )r2   r7   s     r5   forwardzStarcoder2MLP.forward?   sZ    		-0/M2--mt?T?T_c_l_l-mr6   )
__name__
__module____qualname__r    r(   tupletorchFloatTensorr?   __classcell__r4   s   @r5   r"   r"   6   s9    8/ 8U5+<+<%=%D IZIZ r6   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)shaperD   cat)xx1x2s      r5   rotate_halfrR   G   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r6   rotary_pos_embc                     |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.
        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.
    )	unsqueezerR   )qkcossinunsqueeze_dimq_embedk_embeds          r5   apply_rotary_pos_embr]   N   sY    & --
&C
--
&C3w;q>C/0G3w;q>C/0GGr6   r7   n_repr8   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)rM   expandreshape)r7   r^   batchnum_key_value_headsslenhead_dims         r5   	repeat_kvrf   h   so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr6   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 )NrJ   r   rI   )rL   dtyper:   r   )rf   num_key_value_groupsrD   matmul	transposerM   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                r5   eager_attention_forwardr}   t   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$$r6   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ej                  dz  d	e
dz  d
ej                  dz  dee   de	ej                  ej                  dz  e	ej                     dz  f   fdZ xZS )Starcoder2Attentionz=Multi-headed attention from 'Attention Is All You Need' paperNr#   	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 )Nre   g      Tr%   )r'   r(   r#   r   getattrr)   num_attention_headsre   rc   rq   rl   attention_dropout	is_causalr   r*   r,   q_projk_projv_projo_projr1   r2   r#   r   r4   s      r5   r(   zStarcoder2Attention.__init__   sX   "
D9mV=O=OSYSmSm=m$*$>$>&B\B\$\!}}d*!'!9!9ii 2 2F4N4NQUQ^Q^4^eketetuii 2 2F4N4NQUQ^Q^4^eketetuii 2 2F4N4NQUQ^Q^4^eketetuii : :T]] JFL^L^eketetu & 7 7r6   r7   position_embeddingsrk   past_key_valuescache_positionrm   r8   c           
         |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        j                  | j                  j                  t              } || |	|
||f| j                  sdn| j                   | j"                  t%        | j                  dd       d|\  }} |j&                  g |d j)                         }| j+                  |      }t,        j.                  j1                  || j2                  | j                        }||fS )	NrI   r   rJ   )rY   rX   r           sliding_window)r>   rl   r   r:   )rM   re   r   viewrs   r   r   r]   updater   r   get_interfacer#   _attn_implementationr}   r<   r   rl   r   ra   rw   r   r   r=   r>   r1   )r2   r7   r   rk   r   r   rm   input_shapehidden_shapequery_statesrx   ry   rX   rY   cache_kwargsattention_interfacer|   rz   s                     r5   r?   zStarcoder2Attention.forward   s    $))#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'6'='=j,X\XfXfht'u$J(?(M(MKK,,.E)
 %8
%
  $}}C$2H2HLL"4;;0@$G
%
 
%
!\ *k));;;;FFHkk+.mm++4004== , 
 L((r6   N)NN)r@   rA   rB   __doc__r    intr(   rD   TensorrC   r	   
LongTensorr   r   r?   rF   rG   s   @r5   r   r      s    G8/ 8C$J 8( )-26.)||.) #5<<#=>.) t+	.)
 .) ((4/.) -..) 
u||U\\D0%2E2LL	M.)r6   r   c                   "    e Zd Zdedef fdZ	 	 	 	 	 	 ddej                  dej                  dz  dej                  dz  de	dz  d	e
dz  d
ej                  dz  deej                  ej                  f   dz  dee   dej                  fdZ xZS )Starcoder2DecoderLayerr#   r   c                 H   t         |           |j                  | _        t        ||      | _        t        |      | _        t        j                  |j                  |j                        | _
        t        j                  |j                  |j                        | _        y )N)r#   r   eps)r'   r(   r)   r   	self_attnr"   mlpr   	LayerNormnorm_epsiloninput_layernormpost_attention_layernormr   s      r5   r(   zStarcoder2DecoderLayer.__init__   st    !--,FiP (!||F,>,>FDWDWX(*V5G5GVM`M`(a%r6   Nr7   rk   position_idsr   	use_cacher   r   rm   r8   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r7   rk   r   r   r   r   r    )r   r   r   r   )r2   r7   rk   r   r   r   r   r   rm   residual_s              r5   r?   zStarcoder2DecoderLayer.forward   s     !,,];)4>> 	
')%+) 3	
 	
q !=0 !55mD/ =0r6   )NNNFNN)r@   rA   rB   r    r   r(   rD   r   r   r	   boolrC   r   r   r?   rF   rG   s   @r5   r   r      s    b/ bC b /304(,!&26HL|| t+ &&-	
  $; ((4/ #5<<#=>E +, 
r6   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   r   )r7   
attentionsN)r@   rA   rB   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   r6   r5   r   r      sQ    &*#12#4"5N!"&/)r6   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 )Starcoder2RotaryEmbeddinginv_freqNr#   c                    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defaultr   F)
persistentoriginal_inv_freq)r'   r(   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr#   rope_parametersr   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r2   r#   devicerope_init_fnr   r4   s        r5   r(   z"Starcoder2RotaryEmbedding.__init__  s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuUr6   r   ztorch.deviceseq_lenr8   z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_thetare   Ng      ?r   rJ   rp   )r   rp   )	r   r   r)   r   rD   arangeint64rv   float)r#   r   r   baserL   attention_factorr   s          r5   r   z9Starcoder2RotaryEmbedding.compute_default_rope_parameters#  s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r6   c                 N   | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        j	                  |j                   
      	j	                  |j                   
      fS # 1 sw Y   AxY w)Nr   rI   r   mpscpuF)device_typeenabledrJ   rK   r   )r   r   r`   rM   rv   r   
isinstancetypestrr   rs   rD   rN   rX   r   rY   rp   )
r2   rO   r   inv_freq_expandedposition_ids_expandedr   freqsembrX   rY   s
             r5   r?   z!Starcoder2RotaryEmbedding.forwardA  sR    !MM$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)r@   rA   rB   rD   r   r   r    r(   staticmethodr   r   rC   r   r   no_gradr   r?   rF   rG   s   @r5   r   r     s    llV/ V  *.+/"* 4'*(* t* 
~u$	%	* *: U]]_<  <r6   r   c                       e Zd Zdef fdZ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dz  d
ej                  dz  dee   deez  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      r5   r(   zStarcoder2Model.__init__S  s     !.. ++LL):):F<N<NPTP`P`ammHMfNfNfHgh9#FI6h
 LL!3!39L9LM	36B&+#!'!9!9 	 is   DN	input_idsrk   r   r   inputs_embedsr   r   rm   r8   c                    |d u |d uz  rt        d      || j                  |      }|r|t        | j                        }|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   )r#   input_embedsrk   r   r   r   r:   )r   )rk   r   r   r   r   r   )last_hidden_stater   )
ValueErrorr   r
   r#   get_seq_lengthrD   r   rM   r   rU   r   r   r   r   r=   r>   r   r<   r   r   r   r   r   )r2   r   rk   r   r   r   r   r   rm   past_seen_tokensmask_functionr{   r7   r   decoder_layers                  r5   r?   zStarcoder2Model.forwardd  s    -t";<YZZ  --i8M0*$++>O!CRC^==?de"\\ "2]5H5H5K"KTaThThN )33A6L.2kk.H.H.P*Vw#;;&))+%
 &--T33dmm . 
 #oom,oW![[)H4;;+H+HI 
	M)	*) /#-$7	 	M
	 		-0&+/8O
 	
>B
 	
r6   )NNNNNNN)r@   rA   rB   r    r(   r   rD   r   r   r	   rE   r   r   r   rC   r   r?   rF   rG   s   @r5   r   r   Q  s    / "  .2.204(,26!%26>
##d*>
 t+>
 &&-	>

 >
 ((4/>
 $;>
 ((4/>
 +,>
 
(	(>
 >
r6   r   c                   b    e Zd ZddiZddiZddgdgfiZ fdZee	 	 	 	 	 	 	 	 	 dd	e	j                  dz  d
e	j                  dz  de	j                  dz  dedz  de	j                  dz  de	j                  dz  dedz  de	j                  dz  dee	j                  z  dee   defd              Z xZS )Starcoder2ForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr7   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y )NFr%   )
r'   r(   r   r   r   r   r*   r)   r  r   )r2   r#   r4   s     r5   r(   zStarcoder2ForCausalLM.__init__  sU     $V,
 ++yy!3!3V5F5FUS 	r6   Nr   rk   r   r   r   labelsr   r   logits_to_keeprm   r8   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   rk   r   r   r   r   r   N)r	  r  r   )lossr	  r   r7   r   r   )r   r   r   r   slicer  loss_functionr#   r   r   r   r7   r   )r2   r   rk   r   r   r   r  r   r   r  rm   outputsr7   slice_indicesr	  r  s                   r5   r?   zStarcoder2ForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r6   )	NNNNNNNNr   )r@   rA   rB   _tied_weights_keys_tp_plan_pp_planr(   r   r   rD   r   r   r	   rE   r   r   r   r   r   r?   rF   rG   s   @r5   r  r    s/   *,GH23H_-z:;H  .2.204(,26*.!%26-.8
##d*8
 t+8
 &&-	8

 8
 ((4/8
   4'8
 $;8
 ((4/8
 ell*8
 +,8
 
 8
  8
r6   r  c                       e Zd Zy)#Starcoder2ForSequenceClassificationNr@   rA   rB   r   r6   r5   r  r        r6   r  c                       e Zd Zy) Starcoder2ForTokenClassificationNr  r   r6   r5   r  r    r  r6   r  )r  r   r   r  r  )r   )r   )@collections.abcr   typingr   rD   r   transformers.utils.genericr   activationsr   cache_utilsr	   r
   
generationr   integrationsr   r   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   configuration_starcoder2r    Moduler"   rR   r]   r   r   rf   r   r}   r   r   r   r   r   r  r  r  __all__r   r6   r5   <module>r/     s  4 %    9 ! . ) I R B 
 P K F & I I + 6BII "( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%4 )*@)")) @) +@)F(7 (V   $><		 ><B Q
/ Q
 Q
h H
5 H
 H
V	*JLe 		'DF_ 	r6   