
    inX                        d dl mZ d dlmZ d dlZd dlmZ ddlmZ ddlm	Z	m
Z
 ddlmZ dd	lmZ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mZ ddlmZmZ ddlmZm Z  ddl!m"Z"m#Z# ddl$m%Z% ddl&m'Z'm(Z(m)Z) ddl*m+Z+m,Z, ddl-m.Z.  G d dej^                        Z0 G d dej^                        Z1d Z2 ed      d=d       Z3dejh                  de5dejh                  fdZ6	 d>d ej^                  d!ejh                  d"ejh                  d#ejh                  d$ejh                  dz  d%e7d&e7d'e%e'   fd(Z8 ee3       G d) d*ej^                               Z9 ed+       G d, d-ej^                               Z: G d. d/e      Z;e( G d0 d1e#             Z<e( G d2 d3e<             Z=e( G d4 d5e<e             Z> G d6 d7ee<      Z? G d8 d9ee<      Z@ G d: d;ee<      ZAg d<ZBy)?    )Callable)OptionalN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernel_func_from_hubuse_kernelized_func)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs)GenericForQuestionAnswering GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)check_model_inputsmaybe_autocast   )Qwen2Configc                   $     e Zd Z fdZd Z xZS )Qwen2MLPc                    t         |           || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _	        t        |j                     | _        y NFbias)super__init__confighidden_sizeintermediate_sizer   Linear	gate_projup_proj	down_projr   
hidden_actact_fnselfr+   	__class__s     r/home/obispo/Crisostomo_bridge/mision_env/lib/python3.12/site-packages/transformers/models/qwen2/modeling_qwen2.pyr*   zQwen2MLP.__init__#   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../    c                     | j                  | j                  | j                  |            | j                  |      z        }|S N)r1   r3   r/   r0   )r5   xr1   s      r7   forwardzQwen2MLP.forward-   s6    NN4;;t~~a/@#ADLLQRO#ST	r8   )__name__
__module____qualname__r*   r<   __classcell__r6   s   @r7   r$   r$   "   s    0r8   r$   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 )Qwen2RotaryEmbedding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defaultrD   F)
persistentoriginal_inv_freq)r)   r*   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr+   rope_parametersrF   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r5   r+   devicerope_init_fnrD   r6   s        r7   r*   zQwen2RotaryEmbedding.__init__5   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuUr8   rR   ztorch.deviceseq_lenreturnztorch.Tensorc                    | j                   d   }t        | dd      xs | j                  | j                  z  }d}d|t	        j
                  d|dt        j                        j                  |t        j                        |z  z  z  }||fS )	a  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
            device (`torch.device`):
                The device to use for initialization of the inverse frequencies.
            seq_len (`int`, *optional*):
                The current sequence length. Unused for this type of RoPE.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        
rope_thetahead_dimNg      ?r      dtype)rR   r[   )	rM   getattrr,   num_attention_headstorcharangeint64tofloat)r+   rR   rT   basedimattention_factorrD   s          r7   rN   z4Qwen2RotaryEmbedding.compute_default_rope_parametersE   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r8   c                 N   | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        j	                  |j                   
      	j	                  |j                   
      fS # 1 sw Y   AxY w)Nr   r!   mpscpuF)device_typeenabledrY   rd   rZ   )rD   rb   expandshapera   rR   
isinstancetypestrr    	transposer^   catcosrO   sinr[   )
r5   r;   position_idsinv_freq_expandedposition_ids_expandedrj   freqsembrt   ru   s
             r7   r<   zQwen2RotaryEmbedding.forwardc   sR    !MM$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=   r>   r?   r^   Tensor__annotations__r"   r*   staticmethodr   inttuplerb   rN   no_gradr   r<   r@   rA   s   @r7   rC   rC   2   s    llV{ V  %)+/"*d"*(* t* 
~u$	%	* *: U]]_<  <r8   rC   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..Nrg   rY   rl   )rn   r^   rs   )r;   x1x2s      r7   rotate_halfr   s   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r8   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.
    )	unsqueezer   )qkrt   ru   unsqueeze_dimq_embedk_embeds          r7   apply_rotary_pos_embr   z   sY    & --
&C
--
&C3w;q>C/0G3w;q>C/0GGr8   hidden_statesn_reprU   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)rn   rm   reshape)r   r   batchnum_key_value_headsslenrX   s         r7   	repeat_kvr      so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr8   modulequerykeyvalueattention_maskscalingdropoutkwargsc                 T   t        || j                        }t        || j                        }	t        j                  ||j	                  dd            |z  }
|#|d d d d d d d |j
                  d   f   }|
|z   }
t        j                  j                  |
dt        j                        j                  |j                        }
t        j                  j                  |
|| j                        }
t        j                  |
|	      }|j	                  dd      j                         }||
fS )NrY   r   rg   )rd   r[   )ptrainingr!   )r   num_key_value_groupsr^   matmulrr   rn   r   
functionalsoftmaxfloat32ra   r[   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r7   eager_attention_forwardr      s    3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#k1==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r8   c                       e Zd ZdZdede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  f   fdZ xZS )Qwen2Attentionz=Multi-headed attention from 'Attention Is All You Need' paperr+   	layer_idxc                    t         |           t        |d      r|j                  |   nd | _        || _        || _        t        |d|j                  |j                  z        | _
        |j                  |j                  z  | _        | j                  dz  | _        |j                  | _        d| _        t!        j"                  |j                  |j                  | j                  z  d      | _        t!        j"                  |j                  |j                  | j                  z  d      | _        t!        j"                  |j                  |j                  | j                  z  d      | _        t!        j"                  |j                  | j                  z  |j                  d      | _        | j                  dk(  r|j,                  | _        y d | _        y )Nlayer_typesrX   g      Tr'   Fsliding_attention)r)   r*   hasattrr   
layer_typer+   r   r\   r,   r]   rX   r   r   r   attention_dropout	is_causalr   r.   q_projk_projv_projo_projsliding_windowr5   r+   r   r6   s      r7   r*   zQwen2Attention.__init__   sl   ;B6=;Y&,,Y7_c"
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii 2 2F4N4NQUQ^Q^4^eijii 2 2F4N4NQUQ^Q^4^eijii 2 2F4N4NQUQ^Q^4^eijii : :T]] JFL^L^ejk7;J]7]f33cgr8   Nr   position_embeddingsr   past_key_valuescache_positionr   rU   c                 .   |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        j                  | j                  j                  t              } || |	|
||f| j                  sdn| j                   | j"                  | j$                  d|\  }} |j&                  g |d j)                         }| j+                  |      }||fS )Nrg   r!   rY   )ru   rt   r           )r   r   r   )rn   rX   r   viewrr   r   r   r   updater   r   get_interfacer+   _attn_implementationr   r   r   r   r   r   r   r   )r5   r   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   rt   ru   cache_kwargsattention_interfacer   r   s                     r7   r<   zQwen2Attention.forward   s    $))#2.88b8$--8{{=166|DNNqRST[[/44\BLLQPQR
{{=166|DNNqRST&S#7jRUWZ#[ j&#&snUL'6'='=j,X\XfXfht'u$J(?(M(MKK,,.E)
 %8
%
  $}}C$2H2HLL..
%
 
%
!\ *k));;;;FFHkk+.L((r8   )NN)r=   r>   r?   __doc__r"   r~   r*   r^   r{   r   r   
LongTensorr   r   r<   r@   rA   s   @r7   r   r      s    Gh{ hs h* )-26*)||*) #5<<#=>*) t+	*)
 *) ((4/*) -.*) 
u||U\\D00	1*)r8   r   RMSNormc                   h     e Zd Zddeddf fdZdej                  dej                  fdZd Z xZ	S )	Qwen2RMSNormepsrU   Nc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z;
        Qwen2RMSNorm is equivalent to T5LayerNorm
        N)r)   r*   r   	Parameterr^   onesweightvariance_epsilon)r5   r,   r   r6   s      r7   r*   zQwen2RMSNorm.__init__   s1     	ll5::k#:; #r8   r   c                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )NrY   rg   T)keepdim)	r[   ra   r^   r   powmeanrsqrtr   r   )r5   r   input_dtypevariances       r7   r<   zQwen2RMSNorm.forward  sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r8   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)r   r   rn   r   )r5   s    r7   
extra_reprzQwen2RMSNorm.extra_repr  s*    ))*+6$2G2G1HIIr8   )gư>)
r=   r>   r?   rb   r*   r^   r{   r<   r   r@   rA   s   @r7   r   r      s7    $ $$ $;U\\ ;ell ;Jr8   r   c                   "    e Zd Zdedef fdZ	 	 	 	 	 	 ddej                  dej                  dz  dej                  dz  de	dz  d	e
dz  d
ej                  dz  deej                  ej                  f   dz  dee   dej                  fdZ xZS )Qwen2DecoderLayerr+   r   c                 H   t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        |j                  |   | _        y )N)r+   r   r   )r)   r*   r,   r   	self_attnr$   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr   attention_typer   s      r7   r*   zQwen2DecoderLayer.__init__  s    !--'vKF#+F,>,>FDWDWX(4V5G5GVM`M`(a%$00;r8   Nr   r   rv   r   	use_cacher   r   r   rU   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r   r   rv   r   r   r   r    )r   r   r   r   )r5   r   r   rv   r   r   r   r   r   residual_s              r7   r<   zQwen2DecoderLayer.forward  s     !,,];)4>> 	
')%+) 3	
 	
q !=0 !55mD/ =0r8   )NNNFNN)r=   r>   r?   r"   r~   r*   r^   r{   r   r   boolr   r   r   r<   r@   rA   s   @r7   r   r     s    	<{ 	<s 	< /304(,!&26HL|| t+ &&-	
  $; ((4/ #5<<#=>E +, 
r8   r   c                   J    e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedZy)Qwen2PreTrainedModelr+   modelTr   r   )r   
attentionsN)r=   r>   r?   r"   r|   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsr   r8   r7   r   r   >  sQ    &*#,-#4"5N!"&*$r8   r   c                       e Zd Zdef fdZee	 	 	 	 	 	 	 ddej                  dz  dej                  dz  dej                  dz  de
dz  dej                  dz  d	edz  d
ej                  dz  dee   defd              Z xZS )
Qwen2Modelr+   c           	      F   t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |j                  |j                        | _        t#        |      | _        d| _        d| j(                  j*                  v | _        | j/                          y c c}w )Nr   r+   Fr   )r)   r*   pad_token_idpadding_idx
vocab_sizer   	Embeddingr,   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normrC   
rotary_embgradient_checkpointingr+   r   has_sliding_layers	post_initr   s      r7   r*   zQwen2Model.__init__S  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcivy1c
 !!3!39L9LM	.f=&+#"59P9P"P 	 ds   DN	input_idsr   rv   r   inputs_embedsr   r   r   rU   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      }t        |x}
t              s:| j                  |||||d}dt        di |i}
| j                  rt        di ||
d<   |}| j                  ||      }| j                   d | j                  j"                   D ]  } ||f|
|j$                     |||||d	|}! | j'                  |      }t)        ||r|
      S d 
      S )Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r!   )rR   )r+   input_embedsr   r   r   rv   full_attentionr   )r   r   rv   r   r   r   )last_hidden_stater   r   )
ValueErrorr  r	   r+   get_seq_lengthr^   r_   rn   rR   r   ro   dictr   r  r   r  r
  r	  r   r  r   )r5   r  r   rv   r   r  r   r   r   past_seen_tokenscausal_mask_mappingmask_kwargsr   r   decoder_layers                  r7   r<   zQwen2Model.forwardd  s    -t";<YZZ  --i8M0*$++>O!CRC^==?de"\\ "2]5H5H5K"KTaThThN )33A6L ?-F ++ -"0"0#2 ,K !"4"C{"C# &&;\;k_j;k#$78%"oom\J![[)H4;;+H+HI 
	M)	2=3O3OP$7) /#-	 	M
	 		-0&+/8O
 	
>B
 	
r8   )NNNNNNN)r=   r>   r?   r"   r*   r   r   r^   r   r{   r   FloatTensorr   r   r   r   r<   r@   rA   s   @r7   r   r   Q  s    { "  .2.204(,26!%26C
##d*C
 t+C
 &&-	C

 C
 ((4/C
 $;C
 ((4/C
 +,C
 
!C
  C
r8   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 )Qwen2ForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y r&   )
r)   r*   r   r   r  r   r.   r,   r   r  r4   s     r7   r*   zQwen2ForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r8   Nr  r   rv   r   r  labelsr   r   logits_to_keepr   rU   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, Qwen2ForCausalLM

        >>> model = Qwen2ForCausalLM.from_pretrained("meta-qwen2/Qwen2-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-qwen2/Qwen2-2-7b-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  r   rv   r   r  r   r   N)r"  r$  r  )lossr"  r   r   r   r   )r   r  ro   r~   slicer   loss_functionr+   r  r   r   r   r   )r5   r  r   rv   r   r  r$  r   r   r%  r   outputsr   slice_indicesr"  r'  s                   r7   r<   zQwen2ForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r8   )	NNNNNNNNr   )r=   r>   r?   _tied_weights_keys_tp_plan_pp_planr*   r   r   r^   r   r{   r   r  r   r~   r   r   r   r<   r@   rA   s   @r7   r  r    s/   *,GH23H_-z:;H  .2.204(,26*.!%26-.8
##d*8
 t+8
 &&-	8

 8
 ((4/8
   4'8
 $;8
 ((4/8
 ell*8
 +,8
 
 8
  8
r8   r  c                       e Zd Zy)Qwen2ForSequenceClassificationNr=   r>   r?   r   r8   r7   r0  r0        r8   r0  c                       e Zd Zy)Qwen2ForTokenClassificationNr1  r   r8   r7   r4  r4    r2  r8   r4  c                       e Zd ZdZy)Qwen2ForQuestionAnsweringtransformerN)r=   r>   r?   r   r   r8   r7   r6  r6     s    %r8   r6  )r   r   r  r   r0  r4  r6  )r!   )r   )Ccollections.abcr   typingr   r^   r   activationsr   cache_utilsr   r	   
generationr
   integrationsr   r   r   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   r   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r    configuration_qwen2r"   Moduler$   rC   r   r   r{   r~   r   rb   r   r   r   r   r   r   r  r0  r4  r6  __all__r   r8   r7   <module>rJ     s   %    ! . ) f f R B  P K F & I I ? ,ryy  ><299 ><B( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%4 )*=)RYY =) +=)@ Y'J299 J (J(+2 +\ ?  $ W
% W
 W
t H
+_ H
 H
V	%EG[ 		"?AU 	& ;=Q &r8   