
    hW                     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$m%Z%m&Z&m'Z' ddl(m)Z) ddl*m+Z+ ddl,m-Z- d Z.d<dZ/dej`                  de1dej`                  fdZ2	 d=dejf                  dej`                  dej`                  dej`                  deej`                     d e4d!e4d"e#e%   fd#Z5 G d$ d%ejf                        Z6 ed&       G d' d(ejf                               Z7 G d) d*ejf                        Z8 G d+ d,e      Z9e& G d- d.e!             Z: G d/ d0ejf                        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   )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      j/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/transformers/models/smollm3/modeling_smollm3.pyrotate_halfr.   1   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_embr:   8   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_kvrE   S   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$   r   r#   )r&   dtype)ptrainingr    )rE   num_key_value_groupsr(   matmul	transposer'   r   
functionalsoftmaxfloat32torP   rL   rR   
contiguous)rF   rG   rH   rI   rJ   rK   rL   rM   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r-   eager_attention_forwardr`   _   s    3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!$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                   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 )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 )NrD   g      Tbiassliding_attention)super__init__rc   rd   getattrhidden_sizenum_attention_headsrD   rB   rS   rK   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selfrc   rd   	__class__s      r-   rj   zSmolLM3Attention.__init__|   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 --i8 ((V-?-?	-JNa-a !! 	  	r/   past_key_valuepast_key_values4.58new_nameversionr;   position_embeddingsrJ   cache_positionrM   r=   c                 ^   |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }| j                  r|\  }}t        |	|
||      \  }	}
|%d|i}|j                  |
|| j                  |      \  }
}t        }| j                  j                  dk7  rt        | j                  j                     } || |	|
||f| j                  sdn| j                   | j"                  | j$                  d|\  }} |j&                  g |d j)                         }| j+                  |      }||fS )Nr#   r    r$   r   eager        )rL   rK   rz   )r'   rD   rr   viewrU   rs   rt   rw   r:   updaterd   r`   rc   _attn_implementationr   rR   rn   rK   rz   r@   rZ   ru   )r|   r;   r   rJ   r   r   rM   input_shapehidden_shapequery_statesr[   r\   r4   r5   cache_kwargsattention_interfacer_   r]   s                     r-   forwardzSmolLM3Attention.forward   s    $))#2.88b8$--8{{=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'6'='=j,X\XfXfht'u$J(?;;++w6"9$++:Z:Z"[$7
%
  $}}C$2H2HLL..
%
 
%
!\ *k));;;;FFHkk+.L((r/   )NN)__name__
__module____qualname____doc__r!   intrj   r   r(   Tensortupler   r	   
LongTensorr   r   r   __classcell__r}   s   @r-   rb   rb   y   s    G
} 
 
< %0A6R ,059*)||*) #5<<#=>*) !.	*)
 "%*) !!1!12*) -.*) 
u||Xell33	4*) S*)r/   rb   RMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )SmolLM3RMSNormc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z=
        SmolLM3RMSNorm is equivalent to T5LayerNorm
        N)ri   rj   r   	Parameterr(   onesweightvariance_epsilon)r|   rl   epsr}   s      r-   rj   zSmolLM3RMSNorm.__init__   s1     	ll5::k#:; #r/   c                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )Nr$   r#   T)keepdim)	rP   rY   r(   rX   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$2G2G1HIIr/   )gư>)r   r   r   rj   r   r   r   r   s   @r-   r   r      s    $;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 )Nrf   )ri   rj   rc   rl   intermediate_sizer   rp   mlp_bias	gate_projup_proj	down_projr   
hidden_actact_fnr|   rc   r}   s     r-   rj   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   rj   r   r   r   s   @r-   r   r      s    0r/   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 )SmolLM3DecoderLayerrc   rd   c                 H   t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        |j                  |   | _        y )N)rc   rd   r   )ri   rj   rl   rb   	self_attnr   mlpr   rms_norm_epsinput_layernormpost_attention_layernormry   attention_typer{   s      r-   rj   zSmolLM3DecoderLayer.__init__   s    !--)9Mf%-f.@.@fFYFYZ(6v7I7IvObOb(c%$00;r/   r~   r   r   r   r;   rJ   r6   	use_cacher   r   rM   r=   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r;   rJ   r6   r   r   r   r    )r   r   r   r   )r|   r;   rJ   r6   r   r   r   r   rM   residual_s              r-   r   zSmolLM3DecoderLayer.forward   s     !,,];)4>> 	
')%+) 3	
 	
q !=0 !55mD/ =0r/   )NNNFNN)r   r   r   r!   r   rj   r   r(   r   r   r   r	   boolr   r   r   r   r   r   s   @r-   r   r      s    	<} 	< 	< %0A6R 2637+/$)59KO|| !. u//0	
 "% D> !!1!12 &eELL%,,,F&GH +, 
 S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)SmolLM3PreTrainedModelrc   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   rb   _can_record_outputsr   r/   r-   r   r     sQ    &*#./#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_freqrc   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)ri   rj   hasattr
isinstancer   dictgetr   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrc   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r|   rc   devicer   r}   s       r-   rj   zSmolLM3RotaryEmbedding.__init__2  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$   r%   )rP   )r   floatr?   r'   rY   r   r   r   strr(   autocastrU   r)   r4   r   r5   rP   )
r|   r*   r6   inv_freq_expandedposition_ids_expandedr   freqsembr4   r5   s
             r-   r   zSmolLM3RotaryEmbedding.forwardC  sV    !MM$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(   r   r   r!   rj   no_gradr   r   r   r   s   @r-   r   r   /  s=    ll/} /" 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 )SmolLM3Modelrc   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   rc   Frh   )ri   rj   pad_token_idpadding_idx
vocab_sizer   	Embeddingrl   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normr   
rotary_embgradient_checkpointingrc   ry   has_sliding_layers	post_initr{   s      r-   rj   zSmolLM3Model.__init__U  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_idsrJ   r6   r   inputs_embedsr   r   rM   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   )rc   input_embedsrJ   r   r   r6   full_attentionrh   )rJ   r6   r   r   r   r   )last_hidden_stater   r   )
ValueErrorr  r
   rc   get_seq_lengthr(   aranger'   r   r1   r   r   r   r  r   r
  r  r  r   r	  r   )r|   r  rJ   r6   r   r  r   r   rM   past_seen_tokenscausal_mask_mappingmask_kwargsr;   r   decoder_layers                  r-   r   zSmolLM3Model.forwardf  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) /#-$7	 	M
	 		-0&+/8O
 	
>B
 	
r/   )NNNNNNN)r   r   r   r!   rj   r   r   r   r(   r   r   r	   FloatTensorr   r   r   r   r   r   r   s   @r-   r   r   S  s    } "  151537+/59$(59E
E,,-E
 !.E
 u//0	E

 "%E
   1 12E
 D>E
 !!1!12E
 +,E
 
!E
  E
r/   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 )SmolLM3ForCausalLMzlm_head.weightlm_headcolwise_repr;   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y )NFrf   )
ri   rj   r   r   r  r   rp   rl   r  r  r   s     r-   rj   zSmolLM3ForCausalLM.__init__  sU     !&)
 ++yy!3!3V5F5FUS 	r/   r  rJ   r6   r   r  labelsr   r   logits_to_keeprM   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  rJ   r6   r   r  r   r   N)r   r"  r  )lossr   r   r;   r   r   )r   r  r   r   slicer  loss_functionrc   r  r   r   r;   r   )r|   r  rJ   r6   r   r  r"  r   r   r#  rM   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_planrj   r   r   r   r(   r   r   r	   r  r   r   r   r   r   r   r   r   r   s   @r-   r  r    s0   *+=)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)SmolLM3ForTokenClassificationNr/  r   r/   r-   r2  r2     r0  r/   r2  c                       e Zd ZdZy)SmolLM3ForQuestionAnsweringtransformerN)r   r   r   r   r   r/   r-   r4  r4    s    %r/   r4  )r   r   r  r.  r2  r4  )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_smollm3r!   r.   r:   r   r   rE   Moduler   r`   rb   r   r   r   r   r   r   r  r.  r2  r4  __all__r   r/   r-   <module>rH     s  , - ,   ! . ) 7 R B  P K F & I I 0 / 0(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4L)ryy L)^ Y'JRYY J (J(  ,4 ,^ _  $!<RYY !<H Y
) Y
 Y
x H
/ H
 H
V	'GI_ 		$ACY 	&"=?U &r/   