
    rhHW                     h   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$m%Z%m&Z&m'Z' ddl(m)Z) ddl*m+Z+ d Z,d;dZ-dej\                  de/dej\                  fdZ0	 d<dejb                  dej\                  dej\                  dej\                  deej\                     de2d e2d!e#e%   fd"Z3 G d# d$ejb                        Z4 ed%       G d& d'ejb                               Z5 G d( d)ejb                        Z6 G d* d+e      Z7e& G d, d-e!             Z8 G d. d/ejb                        Z9e& G d0 d1e8             Z:e& G d2 d3e8e             Z; G d4 d5ee8      Z< G d6 d7ee8      Z= G d8 d9ee8      Z>g d:Z?y)=    )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)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      /var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/smollm3/modeling_smollm3.pyrotate_halfr-   0   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''    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.
    )	unsqueezer-   )qkcossinposition_idsunsqueeze_dimq_embedk_embeds           r,   apply_rotary_pos_embr9   7   sY    ( --
&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   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)r&   expandreshape)r:   r;   batchnum_key_value_headsslenhead_dims         r,   	repeat_kvrD   R   so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr.   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 )Nr#   r   r"   )r%   dtype)ptrainingr   )rD   num_key_value_groupsr'   matmul	transposer&   r   
functionalsoftmaxfloat32torO   rK   rQ   
contiguous)rE   rF   rG   rH   rI   rJ   rK   rL   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r,   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$$r.   c                   6    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
ej                     de
e   d	e
ej                     d
ee   de	ej                  e
ej                     e
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|j0                  | _        y d | _        y )NrC   g      Tbiassliding_attention)super__init__rb   rc   getattrhidden_sizenum_attention_headsrC   rA   rR   rJ   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selfrb   rc   	__class__s      r,   ri   zSmolLM3Attention.__init__{   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 --i8 ((V-?-?	-JNa-a !! 	  	r.   r:   position_embeddingsrI   past_key_valuecache_positionrL   r<   c                 ^   |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }| j                  r|\  }}t        |	|
||      \  }	}
|%d|i}|j                  |
|| j                  |      \  }
}t        }| j                  j                  dk7  rt        | j                  j                     } || |	|
||f| j                  sdn| j                   | j"                  | j$                  d|\  }} |j&                  g |d j)                         }| j+                  |      }||fS )Nr"   r   r#   r   eager        )rK   rJ   ry   )r&   rC   rq   viewrT   rr   rs   rv   r9   updaterc   r_   rb   _attn_implementationr   rQ   rm   rJ   ry   r?   rY   rt   )r{   r:   r}   rI   r~   r   rL   input_shapehidden_shapequery_statesrZ   r[   r3   r4   cache_kwargsattention_interfacer^   r\   s                     r,   forwardzSmolLM3Attention.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==*HC';L*VY[^'_$L*%,n=L'5'<'<ZW[WeWegs't$J(?;;++w6"9$++:Z:Z"[$7
%
  $}}C$2H2HLL..
%
 
%
!\ *k));;;;FFHkk+.L((r.   )NN)__name__
__module____qualname____doc__r    intri   r'   Tensortupler   r	   
LongTensorr   r   r   __classcell__r|   s   @r,   ra   ra   x   s    G
} 
 
F +/59*)||*) #5<<#=>*) !.	*)
 !*) !!1!12*) -.*) 
u||Xell3XeELL>Q5RR	S*)r.   ra   RMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )SmolLM3RMSNormc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z=
        SmolLM3RMSNorm is equivalent to T5LayerNorm
        N)rh   ri   r   	Parameterr'   onesweightvariance_epsilon)r{   rk   epsr|   s      r,   ri   zSmolLM3RMSNorm.__init__   s1     	ll5::k#:; #r.   c                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )Nr#   r"   T)keepdim)	rO   rX   r'   rW   powmeanrsqrtr   r   )r{   r:   input_dtypevariances       r,   r   zSmolLM3RMSNorm.forward   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r.   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)r   r   r&   r   r{   s    r,   
extra_reprzSmolLM3RMSNorm.extra_repr   s*    ))*+6$2G2G1HIIr.   )gư>)r   r   r   ri   r   r   r   r   s   @r,   r   r      s    $;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                     | _        y )Nre   )rh   ri   rb   rk   intermediate_sizer   ro   mlp_bias	gate_projup_proj	down_projr   
hidden_actact_fnr{   rb   r|   s     r,   ri   zSmolLM3MLP.__init__   s    !--!'!9!94#3#3T5K5KRXRaRabyy!1!143I3IPVP_P_`4#9#94;K;KRXRaRabV../r.   c                     | j                  | j                  | j                  |            | j                  |      z        }|S N)r   r   r   r   )r{   r)   r   s      r,   r   zSmolLM3MLP.forward   s6    NN4;;t~~a/@#ADLLQRO#ST	r.   )r   r   r   ri   r   r   r   s   @r,   r   r      s    0r.   r   c                   (    e Zd Zdedef fdZ	 	 	 	 	 	 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ej                     fdZ xZS )SmolLM3DecoderLayerrb   rc   c                 H   t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        |j                  |   | _        y )N)rb   rc   r   )rh   ri   rk   ra   	self_attnr   mlpr   rms_norm_epsinput_layernormpost_attention_layernormrx   attention_typerz   s      r,   ri   zSmolLM3DecoderLayer.__init__   s    !--)9Mf%-f.@.@fFYFYZ(6v7I7IvObOb(c%$00;r.   r:   rI   r5   r~   	use_cacher   r}   rL   r<   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r:   rI   r5   r~   r   r   r}    )r   r   r   r   )r{   r:   rI   r5   r~   r   r   r}   rL   residual_s              r,   r   zSmolLM3DecoderLayer.forward   s     !,,];)4>> 	
')%)) 3	
 	
q !=0 !55mD/ =0r.   )NNNFNN)r   r   r   r    r   ri   r'   r   r   r   r	   boolr   r   r   r   r   r   s   @r,   r   r      s    	<} 	< 	< 2637*.$)59KO|| !. u//0	
 ! D> !!1!12 &eELL%,,,F&GH +, 
u||	r.   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)SmolLM3PreTrainedModelrb   modelTr   past_key_values)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   ra   _can_record_outputsr   r.   r,   r   r     sQ    &*#./#4"5N!"&,&r.   r   c                   ^     e Zd Zddef fdZ ej                         ed               Z xZ	S )SmolLM3RotaryEmbeddingrb   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defaultinv_freqF)
persistent)rh   ri   hasattr
isinstancer   dictgetr   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrb   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r{   rb   devicer   r|   s       r,   ri   zSmolLM3RotaryEmbedding.__init__-  s    6>*z&:M:Mt/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r.   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   r"   r   mpscpuF)device_typeenabledr#   r$   )rO   )r   floatr>   r&   rX   r   r   r   strr'   autocastrT   r(   r3   r   r4   rO   )
r{   r)   r5   inv_freq_expandedposition_ids_expandedr   freqsembr3   r4   s
             r,   r   zSmolLM3RotaryEmbedding.forward>  sV    !MM$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   )
r   r   r   r    ri   r'   no_gradr   r   r   r   s   @r,   r   r   ,  s3    /} /" 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 )SmolLM3Modelrb   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   )rb   Frg   )rh   ri   pad_token_idpadding_idx
vocab_sizer   	Embeddingrk   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normr   
rotary_embgradient_checkpointingrb   rx   has_sliding_layers	post_initrz   s      r,   ri   zSmolLM3Model.__init__P  s     !.. ++LL):):F<N<NPTP`P`ammEJ6KcKcEde	 3e
 #6#5#56;N;NO	0?&+#"59P9P"P 	 fs   D	input_idsrI   r5   r   inputs_embedsr   r   rL   r<   c                    |d u |d uz  rt        d      || j                  |      }|r|
t               }|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   )rb   input_embedsrI   r   r   r5   full_attentionrg   )rI   r5   r~   r   r   r}   )last_hidden_stater   r   )
ValueErrorr   r
   get_seq_lengthr'   aranger&   r   r0   r   r   rb   r   r  r   r  r  r  r   r  r   )r{   r	  rI   r5   r   r
  r   r   rL   past_seen_tokenscausal_mask_mappingmask_kwargsr:   r}   decoder_layers                  r,   r   zSmolLM3Model.forwarda  s    -t";<YZZ  --i8M0*nO!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).#-$7	 	M
	 		-0&+/8O
 	
>B
 	
r.   )NNNNNNN)r   r   r   r    ri   r   r   r   r'   r   r   r	   FloatTensorr   r   r   r   r   r   r   s   @r,   r   r   N  s    } "  151537+/59$(59E
E,,-E
 !.E
 u//0	E

 "%E
   1 12E
 D>E
 !!1!12E
 +,E
 
!E
  E
r.   r   c                   p    e Zd ZdgZddiZddgdgfiZ fdZd Z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      | _        | j                          y )NFre   )
rh   ri   r   r   r   r   ro   rk   r  r  r   s     r,   ri   zSmolLM3ForCausalLM.__init__  sU     !&)
 ++yy!3!3V5F5FUS 	r.   c                     || _         y r   r   )r{   decoders     r,   set_decoderzSmolLM3ForCausalLM.set_decoder  s	    
r.   c                     | j                   S r   r  r   s    r,   get_decoderzSmolLM3ForCausalLM.get_decoder  s    zzr.   r	  rI   r5   r   r
  labelsr   r   logits_to_keeprL   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  
        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	  rI   r5   r   r
  r   r   N)r  r#  r   )lossr  r   r:   r   r   )r   r  r   r   slicer  loss_functionrb   r   r   r   r:   r   )r{   r	  rI   r5   r   r
  r#  r   r   r$  rL   outputsr:   slice_indicesr  r&  s                   r,   r   zSmolLM3ForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r.   )	NNNNNNNNr   )r   r   r   _tied_weights_keys_tp_plan_pp_planri   r   r"  r   r   r   r'   r   r   r	   r  r   r   r   r   r   r   r   r   r   s   @r,   r  r    s:   *+=)H_-z:;H  151537+/59-1$(59348
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 ))*8
 D>8
 !!1!128
 c5<</08
 +,8
 
 8
  8
r.   r  c                       e Zd Zy) SmolLM3ForSequenceClassificationNr   r   r   r   r.   r,   r/  r/        r.   r/  c                       e Zd Zy)SmolLM3ForTokenClassificationNr0  r   r.   r,   r3  r3    r1  r.   r3  c                       e Zd ZdZy)SmolLM3ForQuestionAnsweringtransformerN)r   r   r   r   r   r.   r,   r5  r5    s    %r.   r5  )r   r   r  r/  r3  r5  )Nr   )r   )@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.genericr   configuration_smollm3r    r-   r9   r   r   rD   Moduler   r_   ra   r   r   r   r   r   r   r  r/  r3  r5  __all__r   r.   r,   <module>rH     s  , - ,   ! . ) 7 R B  P K F & I I / 0(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4K)ryy K)\ Y'JRYY J (J(  +4 +\ _  $<RYY <D Y
) Y
 Y
x N
/ N
 N
b	'GI_ 		$ACY 	&"=?U &r.   