
     `i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$m%Z%m&Z&m'Z' ddl(m)Z) ddl*m+Z+ ddl,m-Z-  ed           G d dej.                              Z/ G d dej.                  Z0d Z1d=dZ2dej3        de4dej3        fdZ5	 d>d!ej.        d"ej3        d#ej3        d$ej3        d%eej3                 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 d0 d1ej.                  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:          Z@g d<ZAdS )?    )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                   T     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 )
Qwen3RMSNormư>epsreturnNc                     t                                                       t          j        t	          j        |                    | _        || _        dS )z;
        Qwen3RMSNorm is equivalent to T5LayerNorm
        N)super__init__r   	Parametertorchonesweightvariance_epsilon)selfhidden_sizer&   	__class__s      |/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/qwen3/modeling_qwen3.pyr*   zQwen3RMSNorm.__init__3   sD     	l5:k#:#:;; #    hidden_statesc                    |j         }|                    t          j                  }|                    d                              dd          }|t          j        || j        z             z  }| j        |                    |          z  S )N   T)keepdim)	dtypetor,   float32powmeanrsqrtr/   r.   )r0   r5   input_dtypevariances       r3   forwardzQwen3RMSNorm.forward;   s|    #)%((77 $$Q'',,R,>>%Ht?T4T(U(UU{]--k::::r4   c                 H    t          | j        j                   d| j         S )Nz, eps=)tupler.   shaper/   )r0   s    r3   
extra_reprzQwen3RMSNorm.extra_reprB   s&    )**II$2GIIIr4   )r%   )
__name__
__module____qualname__floatr*   r,   TensorrB   rF   __classcell__r2   s   @r3   r$   r$   1   s        $ $ $$ $ $ $ $ $ $;U\ ;el ; ; ; ;J J J J J J Jr4   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                 | _        d S NFbias)r)   r*   configr1   intermediate_sizer   Linear	gate_projup_proj	down_projr   
hidden_actact_fnr0   rT   r2   s     r3   r*   zQwen3MLP.__init__G   s    !-!'!94#3T5KRWXXXy!143IPUVVV4#94;KRWXXXV./r4   c                     |                      |                     |                     |                    |                     |          z            }|S N)rY   r[   rW   rX   )r0   xrY   s      r3   rB   zQwen3MLP.forwardQ   sA    NN4;;t~~a/@/@#A#ADLLQROO#STT	r4   )rG   rH   rI   r*   rB   rL   rM   s   @r3   rO   rO   F   sG        0 0 0 0 0      r4   rO   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..Nr8   r7   dim)rE   r,   cat)r_   x1x2s      r3   rotate_halfrf   V   s]    	
3"!'"+"""	#B	
3q """	#B9rc2YB''''r4   c                     |                     |          }|                     |          }| |z  t          |           |z  z   }||z  t          |          |z  z   }||fS )a  Applies Rotary Position Embedding to the query and key tensors.

    Args:
        q (`torch.Tensor`): The query tensor.
        k (`torch.Tensor`): The key tensor.
        cos (`torch.Tensor`): The cosine part of the rotary embedding.
        sin (`torch.Tensor`): The sine part of the rotary embedding.
        position_ids (`torch.Tensor`, *optional*):
            Deprecated and unused.
        unsqueeze_dim (`int`, *optional*, defaults to 1):
            The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
            sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
            that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and
            k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes
            cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have
            the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2.
    Returns:
        `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
    )	unsqueezerf   )qkcossinposition_idsunsqueeze_dimq_embedk_embeds           r3   apply_rotary_pos_embrq   ]   sc    ( --
&
&C
--
&
&C3w;q>>C/0G3w;q>>C/0GGr4   r5   n_repr'   c                     | j         \  }}}}|dk    r| S | dddddddddf                             |||||          } |                     |||z  ||          S )z
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r    N)rE   expandreshape)r5   rr   batchnum_key_value_headsslenhead_dims         r3   	repeat_kvrz   x   s    
 2?1D.Ehzz!!!!QQQaaa"23::5BUW\^bdlmmM  (;e(CT8TTTr4           modulequerykeyvalueattention_maskscalingdropoutkwargsc                 R   t          || j                  }t          || j                  }	t          j        ||                    dd                    |z  }
|$|d d d d d d d |j        d         f         }|
|z   }
t          j                            |
dt          j	                  
                    |j                  }
t          j                            |
|| j                  }
t          j        |
|	          }|                    dd                                          }||
fS )Nr7   r   r8   )rb   r:   )ptrainingr    )rz   num_key_value_groupsr,   matmul	transposerE   r   
functionalsoftmaxr<   r;   r:   r   r   
contiguous)r|   r}   r~   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r3   eager_attention_forwardr      s    3 ;<<JUF$?@@L<z';';Aq'A'ABBWLL!$QQQ111.D
0@0D.D%DE#k1=((2U](SSVVW\WbccL=((6?([[L,|\::K''1--88::K$$r4   c                        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' paperrT   	layer_idxc                 l   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                  | _        |j        |         dk    r|j        nd | _        d S )Nry   g      TrR   r&   sliding_attention)r)   r*   rT   r   getattrr1   num_attention_headsry   rw   r   r   attention_dropout	is_causalr   rV   attention_biasq_projk_projv_projo_projr$   rms_norm_epsq_normk_normlayer_typessliding_windowr0   rT   r   r2   s      r3   r*   zQwen3Attention.__init__   s   "
F4F&Jd4dee$*$>&B\$\!}d*!'!9i :T] JQWQf
 
 
 i :T] JQWQf
 
 
 i :T] JQWQf
 
 
 i&68JQWQf
 
 
 #4=f6IJJJ"4=f6IJJJ7=7I)7TXk7k7kf33qur4   past_key_valuepast_key_values4.58new_nameversionNr5   position_embeddingsr   cache_positionr   r'   c                    |j         d d         }g |d| j        R }|                     |                     |                              |                                        dd          }	|                     |                     |                              |                                        dd          }
|                     |                              |                              dd          }|\  }}t          |	|
||          \  }	}
|&|||d}|
                    |
|| j        |          \  }
}t          }| j        j        dk    rt          | j        j                 } || |	|
||f| j        sdn| j        | j        | j        d|\  }} |j        g |dR                                  }|                     |          }||fS )Nr8   r    r7   )rl   rk   r   eagerr{   )r   r   r   )rE   ry   r   r   viewr   r   r   r   rq   updater   r   rT   _attn_implementationr   r   r   r   r   ru   r   r   )r0   r5   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   rk   rl   cache_kwargsattention_interfacer   r   s                     r3   rB   zQwen3Attention.forward   s    $)#2#.88b8$-88{{4;;}#=#=#B#B<#P#PQQ[[\]_`aa[[]!;!;!@!@!N!NOOYYZ[]^__
{{=1166|DDNNqRSTT&S#7jRUWZ#[#[ j&#&snUUL'6'='=j,X\Xfht'u'u$J(?;+w66"9$+:Z"[$7$7
%
  $}HCC$2HL.
%
 
%
 
%
 
%
!\ *k);;;;;;FFHHkk+..L((r4   )NN)rG   rH   rI   __doc__r!   intr*   r   r,   rK   rD   r   r	   
LongTensorr   r   rB   rL   rM   s   @r3   r   r      s       GGv{ vs v v v v v v4 _%0A6RRR ,059*) *)|*) #5<#=>*) !.	*)
 "%*) !!12*) -.*) 
u|Xel33	4*) *) *) SR*) *) *) *) *)r4   r   c                   4    e Zd Zdedef fdZ eddd          	 	 	 	 	 	 dd
ej        de	ej                 de	ej
                 de	e         de	e         de	ej
                 de	eej        ej        f                  dee         dej        fd            Z xZS )Qwen3DecoderLayerrT   r   c                 X   t                                                       |j        | _        t          ||          | _        t          |          | _        t          |j        |j                  | _	        t          |j        |j                  | _
        |j        |         | _        d S )N)rT   r   r   )r)   r*   r1   r   	self_attnrO   mlpr$   r   input_layernormpost_attention_layernormr   attention_typer   s      r3   r*   zQwen3DecoderLayer.__init__   s    !-'vKKKF##+F,>FDWXXX(4V5GVM`(a(a(a%$0;r4   r   r   r   r   NFr5   r   rm   	use_cacher   r   r   r'   c                     |}	|                      |          } | j        d|||||||d|\  }}
|	|z   }|}	|                     |          }|                     |          }|	|z   }|S )N)r5   r   rm   r   r   r   r    )r   r   r   r   )r0   r5   r   rm   r   r   r   r   r   residual_s              r3   rB   zQwen3DecoderLayer.forward   s     !,,];;)4> 	
')%+) 3	
 	
 	
 	
q !=0 !55mDD// =0r4   )NNNFNN)rG   rH   rI   r!   r   r*   r   r,   rK   r   r   r	   boolrD   r   r   rB   rL   rM   s   @r3   r   r      s-       	<{ 	<s 	< 	< 	< 	< 	< 	< _%0A6RRR 2637+/$)59KO | !. u/0	
 "% D> !!12 &eEL%,,F&GH +, 
   SR    r4   r   c                   L    e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedZdS )Qwen3PreTrainedModelrT   modelTr   r   )r5   
attentionsN)rG   rH   rI   r!   __annotations__base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsr   r4   r3   r   r     sl         &*#,-#4"5N!"&*$ r4   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_freqNrT   c                    t                                                       t          |d          rSt          |j        t
                    r9|j                            d|j                            d                    | _        nd| _        |j        | _	        |j        | _
        || _        t          | j                 | _        |                     | j        |          \  }| _        |                     d|d           | j        | _        d S )Nrope_scaling	rope_typetypedefaultr   F)
persistent)r)   r*   hasattr
isinstancer   dictgetr   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrT   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r0   rT   devicer   r2   s       r3   r*   zQwen3RotaryEmbedding.__init__.  s    6>** 	'z&:Mt/T/T 	'#044[&BUBYBYZ`BaBabbDNN&DN"("@$*$B!/?+/+<+<T[&+Q+Q($(ZeDDD!%r4   c                 X   | j         d d d d f                                                             |j        d         dd                              |j                  }|d d d d d f                                         }t          |j        j        t                    r|j        j        dk    r|j        j        nd}t          j
        |d          5  |                                |                                z                      dd          }t          j        ||fd	          }|                                | j        z  }|                                | j        z  }	d d d            n# 1 swxY w Y   |                    |j        
          |	                    |j        
          fS )Nr   r8   r    mpscpuF)device_typeenabledr7   ra   )r:   )r   rJ   rt   rE   r;   r   r   r   strr,   autocastr   rc   rk   r   rl   r:   )
r0   r_   rm   inv_freq_expandedposition_ids_expandedr   freqsembrk   rl   s
             r3   rB   zQwen3RotaryEmbedding.forward?  s    !M$4-8>>@@GGHZ[\H]_acdeehhijiqrr ,QQQaaaZ 8 > > @ @'1!(-'E'Ek!(-[`J`J`ahmmfk^UCCC 	5 	5&,,..1F1L1L1N1NNYYZ[]^__E)UEN333C''))d44C''))d44C		5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 vvAGv$$cff17f&;&;;;s   BE++E/2E/r^   )rG   rH   rI   r,   rK   r   r!   r*   no_gradr   rB   rL   rM   s   @r3   r   r   +  s         l/ /{ / / / / / /" U]__< <  _< < < < <r4   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 )
Qwen3ModelrT   c                    t                                                     j        | _        j        | _        t          j        j        j        | j                  | _        t          j	        fdt          j                  D                       | _        t          j        j                  | _        t!                    | _        d| _        d| j        j        v | _        |                                  d S )Nc                 0    g | ]}t          |          S r   )r   ).0r   rT   s     r3   
<listcomp>z'Qwen3Model.__init__.<locals>.<listcomp>X  s$    cccivy11cccr4   r   rT   Fr   )r)   r*   pad_token_idpadding_idx
vocab_sizer   	Embeddingr1   embed_tokens
ModuleListrangenum_hidden_layerslayersr$   r   normr   
rotary_embgradient_checkpointingrT   r   has_sliding_layers	post_initr\   s    `r3   r*   zQwen3Model.__init__Q  s       !. +L):F<NPTP`aamcccc5IaCbCbccc
 
 !!39LMMM	.f===&+#"59P"P 	r4   N	input_idsr   rm   r   inputs_embedsr   r   r   r'   c                    |d u |d uz  rt          d          ||                     |          }|r|t          | j                  }|B||                                nd}	t          j        |	|	|j        d         z   |j                  }||	                    d          }t          |x}
t                    s2| j        |||||d}dt          di |i}
| j        rt          di ||
d<   |}|                     ||          }| j        d | j        j                 D ]} ||f|
|j                 |||||d	|}|                     |          }t)          ||r|nd 
          S )Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r    )r   )rT   input_embedsr   r   r   rm   full_attentionr   )r   rm   r   r   r   r   )last_hidden_stater   r   )
ValueErrorr  r
   rT   get_seq_lengthr,   arangerE   r   rh   r   r   r   r  r   r  r  r
  r   r  r   )r0   r  r   rm   r   r  r   r   r   past_seen_tokenscausal_mask_mappingmask_kwargsr5   r   decoder_layers                  r3   rB   zQwen3Model.forwardb  s    -t";< 	[YZZZ  --i88M 	?0*$+>>>O!CRC^==???de"\ "2]5H5K"KTaTh  N )33A66L ?-FF 	l + -"0"0#2 , K !"4"C"C{"C"C# & l;\;k;k_j;k;k#$78% #oom\JJ![)H4;+H)HI 
	 
	M)M	2=3OP) /#-$7	 	 	 	MM 		-00&+/8BOOd
 
 
 	
r4   )NNNNNNN)rG   rH   rI   r!   r*   r   r   r   r,   r   rK   r	   FloatTensorr   r   r   r   rB   rL   rM   s   @r3   r   r   O  s*       {      "  151537+/59$(59E
 E
E,-E
 !.E
 u/0	E

 "%E
   12E
 D>E
 !!12E
 +,E
 
!E
 E
 E
 ^ E
 E
 E
 E
 E
r4   r   c                   f    e Zd ZdgZddiZddgdgfiZ fdZee	 	 	 	 	 	 	 	 	 dd	e	e
j                 d
e	e
j                 de	e
j                 de	e         de	e
j                 de	e
j                 de	e         de	e
j                 deee
j        f         dee         defd                        Z xZS )Qwen3ForCausalLMzlm_head.weightlm_headcolwise_repr5   logitsc                     t                                          |           t          |          | _        |j        | _        t          j        |j        |j        d          | _        | 	                                 d S rQ   )
r)   r*   r   r   r  r   rV   r1   r!  r  r\   s     r3   r*   zQwen3ForCausalLM.__init__  sj       ''
 +y!3V5FUSSS 	r4   Nr   r  r   rm   r   r  labelsr   r   logits_to_keepr   r'   c
                 R    | j         d|||||||d|
}|j        }t          |	t                    rt	          |	 d          n|	}|                     |dd|ddf                   }d}| | j        d||| j        j        d|
}t          |||j
        |j        |j                  S )a^  
        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   rm   r   r  r   r   N)r#  r%  r  )lossr#  r   r5   r   r   )r   r  r   r   slicer!  loss_functionrT   r  r   r   r5   r   )r0   r  r   rm   r   r  r%  r   r   r&  r   outputsr5   slice_indicesr#  r(  s                   r3   rB   zQwen3ForCausalLM.forward  s    J ,64: 	,
)%+')	,
 	,
 	,
 	,
  18B>SV8W8Wk~ot444]kmAAA}aaa,?@AA%4%pVFt{OeppioppD%#3!/)
 
 
 	
r4   )	NNNNNNNNr   )rG   rH   rI   _tied_weights_keys_tp_plan_pp_planr*   r   r   r   r,   r   rK   r	   r  r   r   r   r   r   r   rB   rL   rM   s   @r3   r   r     sa       *+=)H_-z:;H      151537+/59-1$(5934=
 =
E,-=
 !.=
 u/0	=

 "%=
   12=
 )*=
 D>=
 !!12=
 c5</0=
 +,=
 
 =
 =
 =
 ^ =
 =
 =
 =
 =
r4   r   c                       e Zd ZdS )Qwen3ForSequenceClassificationNrG   rH   rI   r   r4   r3   r1  r1            Dr4   r1  c                       e Zd ZdS )Qwen3ForTokenClassificationNr2  r   r4   r3   r5  r5    r3  r4   r5  c                       e Zd ZdZdS )Qwen3ForQuestionAnsweringtransformerN)rG   rH   rI   r   r   r4   r3   r7  r7    s        %r4   r7  )r   r7  r   r   r1  r5  )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$   rO   rf   rq   rK   r   rz   rJ   r   r   r   r   r   r   r   r1  r5  r7  __all__r   r4   r3   <module>rK     s  , - , , , , , , , , ,        ! ! ! ! ! ! . . . . . . . . ) ) ) ) ) ) 7 7 7 7 7 7 R R R R R R R R B B B B B B            P O O O O O O O K K K K K K K K F F F F F F F F & & & & & & I I I I I I I I I I 0 0 0 0 0 0 / / / / / / , , , , , , Y''J J J J J29 J J ('J(    ry    ( ( (   6	UU\ 	U# 	U%, 	U 	U 	U 	U& % %I%<% 
% <	%
 U\*% % % '(% % % %4H) H) H) H) H)RY H) H) H)V, , , , ,2 , , ,^     ?   $!< !< !< !< !<29 !< !< !<H Y
 Y
 Y
 Y
 Y
% Y
 Y
 Y
x M
 M
 M
 M
 M
+_ M
 M
 M
`	 	 	 	 	%EG[ 	 	 		 	 	 	 	"?AU 	 	 	& & & & & ;=Q & & &  r4   