
    iq[                        d dl mZ d dl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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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$m%Z% ddl&m'Z'm(Z(m)Z) ddl*m+Z+m,Z, ddl-m.Z.  G d dej^                        Z0d Z1 ed      d=d       Z2dejf                  de4dejf                  fdZ5	 d>dej^                  dejf                  d ejf                  d!ejf                  d"ejf                  dz  d#e6d$e6d%e%e'   fd&Z7 ee2       G d' d(ej^                               Z8 ed)       G d* d+ej^                               Z9 G d, d-ej^                        Z: G d. d/e      Z;e( G d0 d1e#             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<      ZAg d<ZBy)?    )Callable)OptionalN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernel_func_from_hubuse_kernelized_func)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maybe_autocast   )SmolLM3Configc                        e Zd ZU ej                  ed<   ddef fdZe	 	 	 ddedz  de	d   de
dz  ded	ef   fd
       Z ej                         ed               Z xZS )SmolLM3RotaryEmbeddinginv_freqNconfigc                    t         |           |j                  | _        |j                  | _        || _        | j
                  j                  d   | _        | j                  }| j                  dk7  rt        | j                     } || j
                  |      \  }| _
        | j                  d|d       | j                  d|j                         d       y )N	rope_typedefaultr%   F)
persistentoriginal_inv_freq)super__init__max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr&   rope_parametersr(   compute_default_rope_parametersr   attention_scalingregister_bufferclone)selfr&   devicerope_init_fnr%   	__class__s        v/home/obispo/Crisostomo_bridge/mision_env/lib/python3.12/site-packages/transformers/models/smollm3/modeling_smollm3.pyr-   zSmolLM3RotaryEmbedding.__init__3   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuU    r7   ztorch.deviceseq_lenreturnztorch.Tensorc                    | j                   d   }t        | dd      xs | j                  | j                  z  }d}d|t	        j
                  d|dt        j                        j                  |t        j                        |z  z  z  }||fS )	a  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
            device (`torch.device`):
                The device to use for initialization of the inverse frequencies.
            seq_len (`int`, *optional*):
                The current sequence length. Unused for this type of RoPE.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        
rope_thetahead_dimNg      ?r      dtype)r7   rC   )	r1   getattrhidden_sizenum_attention_headstorcharangeint64tofloat)r&   r7   r<   basedimattention_factorr%   s          r:   r2   z6SmolLM3RotaryEmbedding.compute_default_rope_parametersC   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r;   c                 N   | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        j	                  |j                   
      	j	                  |j                   
      fS # 1 sw Y   AxY w)Nr   r!   mpscpuF)device_typeenabledrA   rM   rB   )r%   rK   expandshaperJ   r7   
isinstancetypestrr    	transposerG   catcosr3   sinrC   )
r6   xposition_idsinv_freq_expandedposition_ids_expandedrS   freqsembr]   r^   s
             r:   forwardzSmolLM3RotaryEmbedding.forwarda   sR    !MM$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$cff177f&;;;	5 	5s   BFF$N)NNN)__name__
__module____qualname__rG   Tensor__annotations__r"   r-   staticmethodr   inttuplerK   r2   no_gradr   re   __classcell__r9   s   @r:   r$   r$   0   s    llV} V  '++/"*$*(* t* 
~u$	%	* *: U]]_<  <r;   r$   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..NrP   rA   rU   )rW   rG   r\   )r_   x1x2s      r:   rotate_halfru   q   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r;   rotary_pos_embc                     |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.
        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.
    )	unsqueezeru   )qkr]   r^   unsqueeze_dimq_embedk_embeds          r:   apply_rotary_pos_embr~   x   sY    & --
&C
--
&C3w;q>C/0G3w;q>C/0GGr;   hidden_statesn_repr=   c                     | j                   \  }}}}|dk(  r| S | dddddddddf   j                  |||||      } | j                  |||z  ||      S )z
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r!   N)rW   rV   reshape)r   r   batchnum_key_value_headsslenr@   s         r:   	repeat_kvr      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 )NrA   r   rP   )rM   rC   )ptrainingr!   )r   num_key_value_groupsrG   matmulr[   rW   r   
functionalsoftmaxfloat32rJ   rC   r   r   
contiguous)r   r   r   r   r   r   r   r   
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                       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j                  dz  d	e
dz  d
ej                  dz  dee   de	ej                  ej                  dz  f   fdZ xZS )SmolLM3Attentionz=Multi-headed attention from 'Attention Is All You Need' paperr&   	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 )Nr@   g      Tbiassliding_attention)r,   r-   r&   r   rD   rE   rF   r@   r   r   r   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r6   r&   r   r9   s      r:   r-   zSmolLM3Attention.__init__   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 --i8 ((V-?-?	-JNa-a !! 	  	r;   Nr   position_embeddingsr   past_key_valuescache_positionr   r=   c                 B   |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }| j                  r|\  }}t        |	|
||      \  }	}
|%d|i}|j                  |
|| j                  |      \  }
}t        j                  | j                  j                  t              } || |	|
||f| j                   sdn| j"                  | j$                  | j&                  d|\  }} |j(                  g |d j+                         }| j-                  |      }||fS )NrP   r!   rA   r           )r   r   r   )rW   r@   r   viewr[   r   r   r   r~   updater   r   get_interfacer&   _attn_implementationr   r   r   r   r   r   r   r   )r6   r   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   r]   r^   cache_kwargsattention_interfacer   r   s                     r:   re   z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(?(M(MKK,,.E)
 %8
%
  $}}C$2H2HLL..
%
 
%
!\ *k));;;;FFHkk+.L((r;   )NN)rg   rh   ri   __doc__r"   rm   r-   rG   rj   rn   r   
LongTensorr   r   re   rp   rq   s   @r:   r   r      s    G
} 
 
F )-26*)||*) #5<<#=>*) t+	*)
 *) ((4/*) -.*) 
u||U\\D00	1*)r;   r   RMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )SmolLM3RMSNormc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z=
        SmolLM3RMSNorm is equivalent to T5LayerNorm
        N)r,   r-   r   	ParameterrG   onesweightvariance_epsilon)r6   rE   epsr9   s      r:   r-   zSmolLM3RMSNorm.__init__	  s1     	ll5::k#:; #r;   c                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )NrA   rP   T)keepdim)	rC   rJ   rG   r   powmeanrsqrtr   r   )r6   r   input_dtypevariances       r:   re   zSmolLM3RMSNorm.forward  sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r;   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)rn   r   rW   r   )r6   s    r:   
extra_reprzSmolLM3RMSNorm.extra_repr  s*    ))*+6$2G2G1HIIr;   )gư>)rg   rh   ri   r-   re   r   rp   rq   s   @r:   r   r     s    $;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 )Nr   )r,   r-   r&   rE   intermediate_sizer   r   mlp_bias	gate_projup_proj	down_projr   
hidden_actact_fnr6   r&   r9   s     r:   r-   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 rf   )r   r   r   r   )r6   r_   r   s      r:   re   zSmolLM3MLP.forward'  s6    NN4;;t~~a/@#ADLLQRO#ST	r;   )rg   rh   ri   r-   re   rp   rq   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j                  dz  dej                  dz  de	dz  d	e
dz  d
ej                  dz  deej                  ej                  f   dz  dee   dej                  fdZ xZS )SmolLM3DecoderLayerr&   r   c                 H   t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        |j                  |   | _        y )N)r&   r   r   )r,   r-   rE   r   	self_attnr   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr   attention_typer   s      r:   r-   zSmolLM3DecoderLayer.__init__-  s    !--)9Mf%-f.@.@fFYFYZ(6v7I7IvObOb(c%$00;r;   Nr   r   r`   r   	use_cacher   r   r   r=   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r   r   r`   r   r   r   r    )r   r   r   r   )r6   r   r   r`   r   r   r   r   r   residual_s              r:   re   zSmolLM3DecoderLayer.forward8  s     !,,];)4>> 	
')%+) 3	
 	
q !=0 !55mD/ =0r;   )NNNFNN)rg   rh   ri   r"   rm   r-   rG   rj   r   r   boolrn   r   r   re   rp   rq   s   @r:   r   r   ,  s    	<} 	< 	< /304(,!&26HL|| t+ &&-	
  $; ((4/ #5<<#=>E +, 
r;   r   c                   J    e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedZy)SmolLM3PreTrainedModelr&   modelTr   r   )r   
attentionsN)rg   rh   ri   r"   rk   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsr   r;   r:   r   r   Z  sQ    &*#./#4"5N!"&,&r;   r   c                       e Zd Zdef fdZee	 	 	 	 	 	 	 ddej                  dz  dej                  dz  dej                  dz  de
dz  dej                  dz  d	edz  d
ej                  dz  dee   defd              Z xZS )SmolLM3Modelr&   c           	      F   t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |j                  |j                        | _        t#        |      | _        d| _        d| j(                  j*                  v | _        | j/                          y c c}w )Nr   r&   Fr   )r,   r-   pad_token_idpadding_idx
vocab_sizer   	EmbeddingrE   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normr$   
rotary_embgradient_checkpointingr&   r   has_sliding_layers	post_initr   s      r:   r-   zSmolLM3Model.__init__o  s     !.. ++LL):):F<N<NPTP`P`ammEJ6KcKcEde	 3e
 #6#5#56;N;NO	0?&+#"59P9P"P 	 fs   DN	input_idsr   r`   r   inputs_embedsr   r   r   r=   c                    |d u |d uz  rt        d      || j                  |      }|r|t        | j                        }|F||j	                         nd}	t        j                  |	|	|j                  d   z   |j                        }||j                  d      }t        |x}
t              s:| j                  |||||d}dt        di |i}
| j                  rt        di ||
d<   |}| j                  ||      }| j                   d | j                  j"                   D ]  } ||f|
|j$                     |||||d	|}! | j'                  |      }t)        ||r|
      S d 
      S )Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r!   )r7   )r&   input_embedsr   r   r   r`   full_attentionr   )r   r   r`   r   r   r   )last_hidden_stater   r   )
ValueErrorr  r	   r&   get_seq_lengthrG   rH   rW   r7   rx   rX   dictr   r  r   r  r  r  r   r  r   )r6   r  r   r`   r   r  r   r   r   past_seen_tokenscausal_mask_mappingmask_kwargsr   r   decoder_layers                  r:   re   zSmolLM3Model.forward  s    -t";<YZZ  --i8M0*$++>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)rg   rh   ri   r"   r-   r   r   rG   r   rj   r   FloatTensorr   r   r   r   re   rp   rq   s   @r:   r  r  m  s    } "  .2.204(,26!%26C
##d*C
 t+C
 &&-	C

 C
 ((4/C
 $;C
 ((4/C
 +,C
 
!C
  C
r;   r  c                   b    e Zd ZddiZddiZddgdgfiZ fdZee	 	 	 	 	 	 	 	 	 dd	e	j                  dz  d
e	j                  dz  de	j                  dz  dedz  de	j                  dz  de	j                  dz  dedz  de	j                  dz  dee	j                  z  dee   defd              Z xZS )SmolLM3ForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y )NFr   )
r,   r-   r  r   r  r   r   rE   r"  r  r   s     r:   r-   zSmolLM3ForCausalLM.__init__  sU     !&)
 ++yy!3!3V5F5FUS 	r;   Nr  r   r`   r   r  labelsr   r   logits_to_keepr   r=   c
                 z    | j                   d|||||||d|
}|j                  }t        |	t              rt	        |	 d      n|	}| j                  |dd|ddf         }d}|* | j                  d||| j                  j                  d|
}t        |||j                  |j                  |j                        S )a  
        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  r   r`   r   r  r   r   N)r$  r&  r  )lossr$  r   r   r   r   )r   r  rX   rm   slicer"  loss_functionr&   r  r   r   r   r   )r6   r  r   r`   r   r  r&  r   r   r'  r   outputsr   slice_indicesr$  r)  s                   r:   re   zSmolLM3ForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r;   )	NNNNNNNNr   )rg   rh   ri   _tied_weights_keys_tp_plan_pp_planr-   r   r   rG   r   rj   r   r  r   rm   r   r   r   re   rp   rq   s   @r:   r!  r!    s/   *,GH23H_-z:;H  .2.204(,26*.!%26-.8
##d*8
 t+8
 &&-	8

 8
 ((4/8
   4'8
 $;8
 ((4/8
 ell*8
 +,8
 
 8
  8
r;   r!  c                       e Zd Zy) SmolLM3ForSequenceClassificationNrg   rh   ri   r   r;   r:   r2  r2        r;   r2  c                       e Zd Zy)SmolLM3ForTokenClassificationNr3  r   r;   r:   r6  r6    r4  r;   r6  c                       e Zd ZdZy)SmolLM3ForQuestionAnsweringtransformerN)rg   rh   ri   r   r   r;   r:   r8  r8    s    %r;   r8  )r   r  r!  r2  r6  r8  )r!   )r   )Ccollections.abcr   typingr   rG   r   activationsr   cache_utilsr   r	   
generationr
   integrationsr   r   r   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   r   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r    configuration_smollm3r"   Moduler$   ru   r~   rj   rm   r   rK   r   r   r   r   r   r   r  r!  r2  r6  r8  __all__r   r;   r:   <module>rL     s  * %    ! . ) f f R B  P K F & I I ? 0><RYY ><B( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%4 )*K)ryy K) +K)\ Y'JRYY J (J(  +4 +\ _  $ W
) W
 W
t H
/ H
 H
V	'GI_ 		$ACY 	&"=?U &r;   