
     `iW                     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$m%Z%m&Z&m'Z' ddl(m)Z) ddl*m+Z+ ddl,m-Z- d Z.d=dZ/dej0        de1dej0        fdZ2	 d>dej3        dej0        dej0        dej0        d eej0                 d!e4d"e4d#e#e%         fd$Z5 G d% d&ej3                  Z6 ed'           G d( d)ej3                              Z7 G d* d+ej3                  Z8 G d, d-e          Z9e& G d. d/e!                      Z: G d0 d1ej3                  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   )SmolLM3Configc                     | 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)shapetorchcat)xx1x2s      /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/smollm3/modeling_smollm3.pyrotate_halfr.   1   s]    	
3"!'"+"""	#B	
3q """	#B9rc2YB''''    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.
    )	unsqueezer.   )qkcossinposition_idsunsqueeze_dimq_embedk_embeds           r-   apply_rotary_pos_embr:   8   sc    ( --
&
&C
--
&
&C3w;q>>C/0G3w;q>>C/0GGr/   hidden_statesn_repreturnc                     | 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)r'   expandreshape)r;   r<   batchnum_key_value_headsslenhead_dims         r-   	repeat_kvrE   S   s    
 2?1D.Ehzz!!!!QQQaaa"23::5BUW\^bdlmmM  (;e(CT8TTTr/           modulequerykeyvalueattention_maskscalingdropoutkwargsc                 R   t          || j                  }t          || j                  }	t          j        ||                    dd                    |z  }
|$|d d d d d d d |j        d         f         }|
|z   }
t          j                            |
dt          j	                  
                    |j                  }
t          j                            |
|| j                  }
t          j        |
|	          }|                    dd                                          }||
fS )Nr$   r   r#   )r&   dtype)ptrainingr    )rE   num_key_value_groupsr(   matmul	transposer'   r   
functionalsoftmaxfloat32torQ   rM   rS   
contiguous)rG   rH   rI   rJ   rK   rL   rM   rN   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r-   eager_attention_forwardra   _   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$$r/   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 )SmolLM3Attentionz=Multi-headed attention from 'Attention Is All You Need' paperconfig	layer_idxc                    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                  | _        |j        |         | _        |j        r|j        |         dk    r|j        nd | _        d S )NrD   g      Tbiassliding_attention)super__init__rd   re   getattrhidden_sizenum_attention_headsrD   rB   rT   rL   attention_dropout	is_causalr   Linearattention_biasq_projk_projv_projo_projno_rope_layersuse_ropeuse_sliding_windowlayer_typessliding_windowselfrd   re   	__class__s      r-   rk   zSmolLM3Attention.__init__|   s   "
F4F&Jd4dee$*$>&B\$\!}d*!'!9i :T] JQWQf
 
 
 i :T] JQWQf
 
 
 i :T] JQWQf
 
 
 i&68JQWQf
 
 
 -i8 (-3-?	-JNa-a-a !! 	r/   past_key_valuepast_key_values4.58new_nameversionNr;   position_embeddingsrK   cache_positionrN   r=   c                 Z   |j         d d         }g |d| j        R }|                     |                              |                              dd          }	|                     |                              |                              dd          }
|                     |                              |                              dd          }| j        r|\  }}t          |	|
||          \  }	}
|$d|i}|	                    |
|| j
        |          \  }
}t          }| j        j        dk    rt          | j        j                 } || |	|
||f| j        sdn| j        | j        | j        d|\  }} |j        g |dR                                  }|                     |          }||fS )Nr#   r    r$   r   eagerrF   )rM   rL   r{   )r'   rD   rs   viewrV   rt   ru   rx   r:   updatere   ra   rd   _attn_implementationr   rS   ro   rL   r{   r@   r[   rv   )r}   r;   r   rK   r   r   rN   input_shapehidden_shapequery_statesr\   r]   r4   r5   cache_kwargsattention_interfacer`   r^   s                     r-   forwardzSmolLM3Attention.forward   s    $)#2#.88b8$-88{{=1166|DDNNqRSTT[[//44\BBLLQPQRR
{{=1166|DDNNqRSTT= 	`*HC';L*VY[^'_'_$L*&,n=L'6'='=j,X\Xfht'u'u$J(?;+w66"9$+:Z"[$7$7
%
  $}HCC$2HL.
%
 
%
 
%
 
%
!\ *k);;;;;;FFHHkk+..L((r/   )NN)__name__
__module____qualname____doc__r!   intrk   r   r(   Tensortupler   r	   
LongTensorr   r   r   __classcell__r~   s   @r-   rc   rc   y   s       GG
} 
 
 
 
 
 
 
< _%0A6RRR ,059*) *)|*) #5<#=>*) !.	*)
 "%*) !!12*) -.*) 
u|Xel33	4*) *) *) SR*) *) *) *) *)r/   rc   RMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )SmolLM3RMSNormư>c                     t                                                       t          j        t	          j        |                    | _        || _        dS )z=
        SmolLM3RMSNorm is equivalent to T5LayerNorm
        N)rj   rk   r   	Parameterr(   onesweightvariance_epsilon)r}   rm   epsr~   s      r-   rk   zSmolLM3RMSNorm.__init__   sD     	l5:k#:#:;; #r/   c                    |j         }|                    t          j                  }|                    d                              dd          }|t          j        || j        z             z  }| j        |                    |          z  S )Nr$   r#   T)keepdim)	rQ   rZ   r(   rY   powmeanrsqrtr   r   )r}   r;   input_dtypevariances       r-   r   zSmolLM3RMSNorm.forward   s|    #)%((77 $$Q'',,R,>>%Ht?T4T(U(UU{]--k::::r/   c                 H    t          | j        j                   d| j         S )Nz, eps=)r   r   r'   r   )r}   s    r-   
extra_reprzSmolLM3RMSNorm.extra_repr   s&    )**II$2GIIIr/   )r   )r   r   r   rk   r   r   r   r   s   @r-   r   r      sb        $ $ $ $ $ $; ; ;J J J J J J Jr/   r   c                   $     e Zd Z fdZd Z xZS )
SmolLM3MLPc                    t                                                       || _        |j        | _        |j        | _        t          j        | j        | j        |j                  | _        t          j        | j        | j        |j                  | _	        t          j        | j        | j        |j                  | _
        t          |j                 | _        d S )Nrg   )rj   rk   rd   rm   intermediate_sizer   rq   mlp_bias	gate_projup_proj	down_projr   
hidden_actact_fnr}   rd   r~   s     r-   rk   zSmolLM3MLP.__init__   s    !-!'!94#3T5KRXRabbby!143IPVP_```4#94;KRXRabbbV./r/   c                     |                      |                     |                     |                    |                     |          z            }|S N)r   r   r   r   )r}   r*   r   s      r-   r   zSmolLM3MLP.forward   sA    NN4;;t~~a/@/@#A#ADLLQROO#STT	r/   )r   r   r   rk   r   r   r   s   @r-   r   r      sG        0 0 0 0 0      r/   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 )SmolLM3DecoderLayerrd   re   c                 X   t                                                       |j        | _        t          ||          | _        t          |          | _        t          |j        |j                  | _	        t          |j        |j                  | _
        |j        |         | _        d S )N)rd   re   r   )rj   rk   rm   rc   	self_attnr   mlpr   rms_norm_epsinput_layernormpost_attention_layernormrz   attention_typer|   s      r-   rk   zSmolLM3DecoderLayer.__init__   s    !-)9MMMf%%-f.@fFYZZZ(6v7IvOb(c(c(c%$0;r/   r   r   r   r   NFr;   rK   r6   	use_cacher   r   rN   r=   c                     |}	|                      |          } | j        d|||||||d|\  }}
|	|z   }|}	|                     |          }|                     |          }|	|z   }|S )N)r;   rK   r6   r   r   r   r    )r   r   r   r   )r}   r;   rK   r6   r   r   r   r   rN   residual_s              r-   r   zSmolLM3DecoderLayer.forward   s     !,,];;)4> 	
')%+) 3	
 	
 	
 	
q !=0 !55mDD// =0r/   )NNNFNN)r   r   r   r!   r   rk   r   r(   r   r   r   r	   boolr   r   r   r   r   r   s   @r-   r   r      s-       	<} 	< 	< 	< 	< 	< 	< 	< _%0A6RRR 2637+/$)59KO | !. u/0	
 "% D> !!12 &eEL%,,F&GH +, 
   SR    r/   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 )SmolLM3PreTrainedModelrd   modelTr   r   )r;   
attentionsN)r   r   r   r!   __annotations__base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   rc   _can_record_outputsr   r/   r-   r   r     sl         &*#./#4"5N!"&,& r/   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 )SmolLM3RotaryEmbeddinginv_freqNrd   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)rj   rk   hasattr
isinstancer   dictgetr   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrd   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r}   rd   devicer   r~   s       r-   rk   zSmolLM3RotaryEmbedding.__init__2  s    6>** 	'z&:Mt/T/T 	'#044[&BUBYBYZ`BaBabbDNN&DN"("@$*$B!/?+/+<+<T[&+Q+Q($(ZeDDD!%r/   c                 X   | j         d d d d f                                                             |j        d         dd                              |j                  }|d d d d d f                                         }t          |j        j        t                    r|j        j        dk    r|j        j        nd}t          j
        |d          5  |                                |                                z                      dd          }t          j        ||fd	          }|                                | j        z  }|                                | j        z  }	d d d            n# 1 swxY w Y   |                    |j        
          |	                    |j        
          fS )Nr   r#   r    mpscpuF)device_typeenabledr$   r%   )rQ   )r   floatr?   r'   rZ   r   r   r   strr(   autocastrV   r)   r4   r   r5   rQ   )
r}   r*   r6   inv_freq_expandedposition_ids_expandedr   freqsembr4   r5   s
             r-   r   zSmolLM3RotaryEmbedding.forwardC  s    !M$4-8>>@@GGHZ[\H]_acdeehhijiqrr ,QQQaaaZ 8 > > @ @'1!(-'E'Ek!(-[`J`J`ahmmfk^UCCC 	5 	5&,,..1F1L1L1N1NNYYZ[]^__E)UEN333C''))d44C''))d44C		5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 vvAGv$$cff17f&;&;;;s   BE++E/2E/r   )r   r   r   r(   r   r   r!   rk   no_gradr   r   r   r   s   @r-   r   r   /  s         l/ /} / / / / / /" U]__< <  _< < < < <r/   r   c                       e Zd Zdef fdZee	 	 	 	 	 	 	 ddeej	                 deej
                 deej	                 dee         deej                 d	ee         d
eej	                 dee         defd                        Z xZS )SmolLM3Modelrd   c                    t                                                     j        | _        j        | _        t          j        j        j        | j                  | _        t          j	        fdt          j                  D                       | _        t          j        j                  | _        t!                    | _        d| _        d| j        j        v | _        |                                  d S )Nc                 0    g | ]}t          |          S r   )r   ).0re   rd   s     r-   
<listcomp>z)SmolLM3Model.__init__.<locals>.<listcomp>\  s$    eee	 33eeer/   r   rd   Fri   )rj   rk   pad_token_idpadding_idx
vocab_sizer   	Embeddingrm   embed_tokens
ModuleListrangenum_hidden_layerslayersr   r   normr   
rotary_embgradient_checkpointingrd   rz   has_sliding_layers	post_initr   s    `r-   rk   zSmolLM3Model.__init__U  s       !. +L):F<NPTP`aameeeeU6KcEdEdeee
 
 #6#56;NOOO	0???&+#"59P"P 	r/   N	input_idsrK   r6   r   inputs_embedsr   r   rN   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   )rd   input_embedsrK   r   r   r6   full_attentionri   )rK   r6   r   r   r   r   )last_hidden_stater   r   )
ValueErrorr  r
   rd   get_seq_lengthr(   aranger'   r   r1   r   r   r   r  r   r  r  r  r   r  r   )r}   r  rK   r6   r   r  r   r   rN   past_seen_tokenscausal_mask_mappingmask_kwargsr;   r   decoder_layers                  r-   r   zSmolLM3Model.forwardf  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) /#-$7	 	 	 	MM 		-00&+/8BOOd
 
 
 	
r/   )NNNNNNN)r   r   r   r!   rk   r   r   r   r(   r   r   r	   FloatTensorr   r   r   r   r   r   r   s   @r-   r   r   S  s*       }      "  151537+/59$(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
r/   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 )SmolLM3ForCausalLMzlm_head.weightlm_headcolwise_repr;   logitsc                     t                                          |           t          |          | _        |j        | _        t          j        |j        |j        d          | _        | 	                                 d S )NFrg   )
rj   rk   r   r   r  r   rq   rm   r"  r  r   s     r-   rk   zSmolLM3ForCausalLM.__init__  sj       !&))
 +y!3V5FUSSS 	r/   Nr   r  rK   r6   r   r  labelsr   r   logits_to_keeprN   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  
        Example:

        ```python
        >>> from transformers import AutoTokenizer, SmolLM3ForCausalLM

        >>> model = SmolLM3ForCausalLM.from_pretrained("meta-smollm3/SmolLM3-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-smollm3/SmolLM3-2-7b-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   r6   r   r  r   r   N)r$  r&  r  )lossr$  r   r;   r   r   )r   r  r   r   slicer"  loss_functionrd   r  r   r   r;   r   )r}   r  rK   r6   r   r  r&  r   r   r'  rN   outputsr;   slice_indicesr$  r)  s                   r-   r   zSmolLM3ForCausalLM.forward  s    @ ,64: 	,
)%+')	,
 	,
 	,
 	,
  18B>SV8W8Wk~ot444]kmAAA}aaa,?@AA%4%pVFt{OeppioppD%#3!/)
 
 
 	
r/   )	NNNNNNNNr   )r   r   r   _tied_weights_keys_tp_plan_pp_planrk   r   r   r   r(   r   r   r	   r  r   r   r   r   r   r   r   r   r   s   @r-   r!  r!    sa       *+=)H_-z:;H      151537+/59-1$(59348
 8
E,-8
 !.8
 u/0	8

 "%8
   128
 )*8
 D>8
 !!128
 c5</08
 +,8
 
 8
 8
 8
 ^ 8
 8
 8
 8
 8
r/   r!  c                       e Zd ZdS ) SmolLM3ForSequenceClassificationNr   r   r   r   r/   r-   r2  r2            Dr/   r2  c                       e Zd ZdS )SmolLM3ForTokenClassificationNr3  r   r/   r-   r6  r6     r4  r/   r6  c                       e Zd ZdZdS )SmolLM3ForQuestionAnsweringtransformerN)r   r   r   r   r   r/   r-   r8  r8    s        %r/   r8  )r   r   r!  r2  r6  r8  )Nr    )rF   )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_smollm3r!   r.   r:   r   r   rE   Moduler   ra   rc   r   r   r   r   r   r   r!  r2  r6  r8  __all__r   r/   r-   <module>rL     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 / / / / / / 0 0 0 0 0 0( ( (   6	UU\ 	U# 	U%, 	U 	U 	U 	U& % %I%<% 
% <	%
 U\*% % % '(% % % %4L) L) L) L) L)ry L) L) L)^ Y''J J J J JRY J J ('J(        , , , , ,4 , , ,^     _   $!< !< !< !< !<RY !< !< !<H Y
 Y
 Y
 Y
 Y
) Y
 Y
 Y
x H
 H
 H
 H
 H
/ H
 H
 H
V	 	 	 	 	'GI_ 	 	 		 	 	 	 	$ACY 	 	 	& & & & &"=?U & & &  r/   