
    hZ                     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	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mZmZ ddlmZmZ ddlmZmZ ddlm Z m!Z! ddl"m#Z# ddl$m%Z%m&Z&m'Z' ddl(m)Z) ddl*m+Z+ ddl,m-Z-  ed       G d dej\                               Z/ G d dej\                        Z0d Z1d<dZ2dejf                  de4dejf                  fdZ5	 d=d ej\                  d!ejf                  d"ejf                  d#ejf                  d$eejf                     d%e6d&e6d'e#e%   fd(Z7 G d) d*ej\                        Z8 G d+ d,e      Z9e& G d- d.e!             Z: G d/ d0ej\                        Z;e& G d1 d2e:             Z<e& G d3 d4e:e             Z= G d5 d6ee:      Z> G d7 d8ee:      Z? G d9 d:ee:      Z@g d;ZAy)>    )CallableOptionalUnionN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)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)deprecate_kwarg)check_model_inputs   )Qwen3Config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 )	Qwen3RMSNormepsreturnNc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z;
        Qwen3RMSNorm is equivalent to T5LayerNorm
        N)super__init__r   	Parametertorchonesweightvariance_epsilon)selfhidden_sizer%   	__class__s      f/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/transformers/models/qwen3/modeling_qwen3.pyr)   zQwen3RMSNorm.__init__3   s1     	ll5::k#:; #    hidden_statesc                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )N   T)keepdim)	dtypetor+   float32powmeanrsqrtr.   r-   )r/   r4   input_dtypevariances       r2   forwardzQwen3RMSNorm.forward;   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r3   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tupler-   shaper.   )r/   s    r2   
extra_reprzQwen3RMSNorm.extra_reprB   s*    ))*+6$2G2G1HIIr3   )gư>)
__name__
__module____qualname__floatr)   r+   TensorrA   rE   __classcell__r1   s   @r2   r$   r$   1   s7    $ $$ $;U\\ ;ell ;Jr3   r$   c                   $     e Zd Z fdZd Z xZS )Qwen3MLPc                    t         |           || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _	        t        |j                     | _        y NFbias)r(   r)   configr0   intermediate_sizer   Linear	gate_projup_proj	down_projr   
hidden_actact_fnr/   rS   r1   s     r2   r)   zQwen3MLP.__init__G   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r3   c                     | j                  | j                  | j                  |            | j                  |      z        }|S N)rX   rZ   rV   rW   )r/   xrX   s      r2   rA   zQwen3MLP.forwardQ   s6    NN4;;t~~a/@#ADLLQRO#ST	r3   )rF   rG   rH   r)   rA   rK   rL   s   @r2   rN   rN   F   s    0r3   rN   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..Nr7   r6   dim)rD   r+   cat)r^   x1x2s      r2   rotate_halfre   V   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r3   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.
    )	unsqueezere   )qkcossinposition_idsunsqueeze_dimq_embedk_embeds           r2   apply_rotary_pos_embrp   ]   sY    ( --
&C
--
&C3w;q>C/0G3w;q>C/0GGr3   r4   n_repr&   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)rD   expandreshape)r4   rq   batchnum_key_value_headsslenhead_dims         r2   	repeat_kvry   x   so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr3   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 )Nr6   r   r7   )ra   r9   )ptrainingr    )ry   num_key_value_groupsr+   matmul	transposerD   r   
functionalsoftmaxr;   r:   r9   r   r   
contiguous)rz   r{   r|   r}   r~   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r2   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$$r3   c                   0    e Zd ZdZded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                     f   fd       Z xZS )Qwen3Attentionz=Multi-headed attention from 'Attention Is All You Need' paperrS   	layer_idxc                 R   t         |           || _        || _        t	        |d|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                        | _        t)        | j                  |j*                        | _        t)        | j                  |j*                        | _        |j0                  |   dk(  r|j2                  | _        y d | _        y )Nrx   g      TrQ   r%   sliding_attention)r(   r)   rS   r   getattrr0   num_attention_headsrx   rv   r   r   attention_dropout	is_causalr   rU   attention_biasq_projk_projv_projo_projr$   rms_norm_epsq_normk_normlayer_typessliding_windowr/   rS   r   r1   s      r2   r)   zQwen3Attention.__init__   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 #4==f6I6IJ"4==f6I6IJ7=7I7I)7TXk7kf33qur3   past_key_valuepast_key_values4.58new_nameversionr4   position_embeddingsr~   cache_positionr   r&   c                    |j                   d d }g |d| j                  }| j                  | j                  |      j	                  |            j                  dd      }	| j                  | j                  |      j	                  |            j                  dd      }
| j                  |      j	                  |      j                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        }| j                  j                  dk7  rt        | j                  j                     } || |	|
||f| j                   sdn| j"                  | j$                  | j&                  d|\  }} |j(                  g |d j+                         }| j-                  |      }||fS )Nr7   r    r6   )rk   rj   r   eager        )r   r   r   )rD   rx   r   r   viewr   r   r   r   rp   updater   r   rS   _attn_implementationr   r   r   r   r   rt   r   r   )r/   r4   r   r~   r   r   r   input_shapehidden_shapequery_statesr   r   rj   rk   cache_kwargsattention_interfacer   r   s                     r2   rA   zQwen3Attention.forward   s    $))#2.88b8$--8{{4;;}#=#B#B<#PQ[[\]_`a[[]!;!@!@!NOYYZ[]^_
{{=166|DNNqRST&S#7jRUWZ#[ j&#&snUL'6'='=j,X\XfXfht'u$J(?;;++w6"9$++:Z:Z"[$7
%
  $}}C$2H2HLL..
%
 
%
!\ *k));;;;FFHkk+.L((r3   )NN)rF   rG   rH   __doc__r!   intr)   r   r+   rJ   rC   r   r	   
LongTensorr   r   rA   rK   rL   s   @r2   r   r      s    Gv{ vs v4 %0A6R ,059*)||*) #5<<#=>*) !.	*)
 "%*) !!1!12*) -.*) 
u||Xell33	4*) S*)r3   r   c                   >    e Zd Zdedef fdZ eddd      	 	 	 	 	 	 ddej                  d	e	ej                     d
e	ej                     de	e   de	e   de	ej                     de	eej                  ej                  f      dee   dej                  fd       Z xZS )Qwen3DecoderLayerrS   r   c                 H   t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        |j                  |   | _        y )N)rS   r   r   )r(   r)   r0   r   	self_attnrN   mlpr$   r   input_layernormpost_attention_layernormr   attention_typer   s      r2   r)   zQwen3DecoderLayer.__init__   s    !--'vKF#+F,>,>FDWDWX(4V5G5GVM`M`(a%$00;r3   r   r   r   r   r4   r~   rl   	use_cacher   r   r   r&   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r4   r~   rl   r   r   r   r    )r   r   r   r   )r/   r4   r~   rl   r   r   r   r   r   residual_s              r2   rA   zQwen3DecoderLayer.forward   s     !,,];)4>> 	
')%+) 3	
 	
q !=0 !55mD/ =0r3   )NNNFNN)rF   rG   rH   r!   r   r)   r   r+   rJ   r   r   r	   boolrC   r   r   rA   rK   rL   s   @r2   r   r      s    	<{ 	<s 	< %0A6R 2637+/$)59KO|| !. u//0	
 "% D> !!1!12 &eELL%,,,F&GH +, 
 Sr3   r   c                   J    e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedZy)Qwen3PreTrainedModelrS   modelTr   r   )r4   
attentionsN)rF   rG   rH   r!   __annotations__base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsr   r3   r2   r   r     sQ    &*#,-#4"5N!"&*$r3   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 )Qwen3RotaryEmbeddinginv_freqrS   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defaultr   F)
persistent)r(   r)   hasattr
isinstancer   dictgetr   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrS   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r/   rS   devicer   r1   s       r2   r)   zQwen3RotaryEmbedding.__init__.  s    6>*z&:M:Mt/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r3   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   r7   r    mpscpuF)device_typeenabledr6   r`   )r9   )r   rI   rs   rD   r:   r   r   r   strr+   autocastr   rb   rj   r   rk   r9   )
r/   r^   rl   inv_freq_expandedposition_ids_expandedr   freqsembrj   rk   s
             r2   rA   zQwen3RotaryEmbedding.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]   )rF   rG   rH   r+   rJ   r   r!   r)   no_gradr   rA   rK   rL   s   @r2   r   r   +  s=    ll/{ /" U]]_<  <r3   r   c                       e Zd Zdef fdZee	 	 	 	 	 	 	 ddeej                     deej                     deej                     dee   deej                     dee   d	eej                     d
ee   defd              Z xZS )
Qwen3ModelrS   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   rS   Fr   )r(   r)   pad_token_idpadding_idx
vocab_sizer   	Embeddingr0   embed_tokens
ModuleListrangenum_hidden_layersr   layersr$   r   normr   
rotary_embgradient_checkpointingrS   r   has_sliding_layers	post_initr   s      r2   r)   zQwen3Model.__init__Q  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcivy1c
 !!3!39L9LM	.f=&+#"59P9P"P 	 ds   D	input_idsr~   rl   r   inputs_embedsr   r   r   r&   c                    |d u |d uz  rt        d      || j                  |      }|r|t        | j                        }|F||j	                         nd}	t        j                  |	|	|j                  d   z   |j                        }||j                  d      }t        |x}
t              s:| j                  |||||d}dt        di |i}
| j                  rt        di ||
d<   |}| j                  ||      }| j                   d | j                  j"                   D ]  } ||f|
|j$                     |||||d	|}! | j'                  |      }t)        ||r|
      S d 
      S )Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r    )r   )rS   input_embedsr~   r   r   rl   full_attentionr   )r~   rl   r   r   r   r   )last_hidden_stater   r   )
ValueErrorr  r
   rS   get_seq_lengthr+   arangerD   r   rg   r   r   r   r  r   r	  r  r  r   r  r   )r/   r  r~   rl   r   r  r   r   r   past_seen_tokenscausal_mask_mappingmask_kwargsr4   r   decoder_layers                  r2   rA   zQwen3Model.forwardb  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) /#-$7	 	M
	 		-0&+/8O
 	
>B
 	
r3   )NNNNNNN)rF   rG   rH   r!   r)   r   r   r   r+   r   rJ   r	   FloatTensorr   r   r   r   rA   rK   rL   s   @r2   r   r   O  s    { "  151537+/59$(59E
E,,-E
 !.E
 u//0	E

 "%E
   1 12E
 D>E
 !!1!12E
 +,E
 
!E
  E
r3   r   c                   d    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 )Qwen3ForCausalLMzlm_head.weightlm_headcolwise_repr4   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y rP   )
r(   r)   r   r   r  r   rU   r0   r  r  r[   s     r2   r)   zQwen3ForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r3   r  r~   rl   r   r  labelsr   r   logits_to_keepr   r&   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^  
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
            config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
            (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

        Example:

        ```python
        >>> from transformers import AutoTokenizer, Qwen3ForCausalLM

        >>> model = Qwen3ForCausalLM.from_pretrained("Qwen/Qwen3-8B")
        >>> tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B")

        >>> 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~   rl   r   r  r   r   N)r  r!  r  )lossr  r   r4   r   r   )r   r  r   r   slicer  loss_functionrS   r  r   r   r4   r   )r/   r  r~   rl   r   r  r!  r   r   r"  r   outputsr4   slice_indicesr  r$  s                   r2   rA   zQwen3ForCausalLM.forward  s    J ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r3   )	NNNNNNNNr   )rF   rG   rH   _tied_weights_keys_tp_plan_pp_planr)   r   r   r   r+   r   rJ   r	   r  r   r   r   r   r   r   rA   rK   rL   s   @r2   r  r    s0   *+=)H_-z:;H  151537+/59-1$(5934=
E,,-=
 !.=
 u//0	=

 "%=
   1 12=
 ))*=
 D>=
 !!1!12=
 c5<</0=
 +,=
 
 =
  =
r3   r  c                       e Zd Zy)Qwen3ForSequenceClassificationNrF   rG   rH   r   r3   r2   r-  r-        r3   r-  c                       e Zd Zy)Qwen3ForTokenClassificationNr.  r   r3   r2   r1  r1    r/  r3   r1  c                       e Zd ZdZy)Qwen3ForQuestionAnsweringtransformerN)rF   rG   rH   r   r   r3   r2   r3  r3    s    %r3   r3  )r  r3  r   r   r-  r1  )Nr    )r   )Btypingr   r   r   r+   r   activationsr   cache_utilsr	   r
   
generationr   integrationsr   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.deprecationr   utils.genericr   configuration_qwen3r!   Moduler$   rN   re   rp   rJ   r   ry   rI   r   r   r   r   r   r   r  r-  r1  r3  __all__r   r3   r2   <module>rG     s  , - ,   ! . ) 7 R B  P K F & I I 0 / , Y'J299 J (J(ryy  (6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4H)RYY H)V,2 ,^ ?  $!<299 !<H Y
% Y
 Y
x M
+_ M
 M
`	%EG[ 		"?AU 	& ;=Q &r3   