
    <h?                        S SK JrJr  S SKrSSKJr  SSKJrJr  SSK	J
r
  SSKJr  SSKJr  SS	KJr  SS
KJr  SSKJrJrJrJrJrJrJrJrJr  SSKJr  \R>                  " \ 5      r! " S S\5      r" " S S\5      r# " S S\5      r$ " S S\5      r% " S S\5      r& " S S\5      r' " S S\5      r( " S S\5      r) " S S\5      r*/ S Qr+g)!    )CallableOptionalN   )Cache)PretrainedConfiglayer_type_validation)FlashAttentionKwargs)rope_config_validation)ALL_ATTENTION_FUNCTIONS)Unpack)logging   )	LlamaAttentionLlamaDecoderLayerLlamaForCausalLMLlamaForQuestionAnsweringLlamaForSequenceClassificationLlamaForTokenClassificationLlamaPreTrainedModelapply_rotary_pos_embeager_attention_forward)
Qwen2Modelc                      ^  \ rS rSrSrSrS/rSSSSSSSS.rS/S	/4S
S/S
/4S
/S
/4S.r                        SU 4S jjr	Sr
U =r$ )SmolLM3Config,   aB  
This is the configuration class to store the configuration of a [`SmolLM3Model`]. It is used to instantiate a
SmolLM3 model according to the specified arguments, defining the model architecture. Instantiating a configuration
with the defaults will yield a similar configuration to that of the SmolLM3 3B.
e.g. [HuggingFaceTB/SmolLM3-3B](https://huggingface.co/HuggingFaceTB/SmolLM3-3B)

Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
documentation from [`PretrainedConfig`] for more information.

Args:
    vocab_size (`int`, *optional*, defaults to 128256):
        Vocabulary size of the SmolLM3 model. Defines the number of different tokens that can be represented by the
        `inputs_ids` passed when calling [`SmolLM3Model`]
    hidden_size (`int`, *optional*, defaults to 2048):
        Dimension of the hidden representations.
    intermediate_size (`int`, *optional*, defaults to 11008):
        Dimension of the MLP representations.
    num_hidden_layers (`int`, *optional*, defaults to 36):
        Number of hidden layers in the Transformer encoder.
    num_attention_heads (`int`, *optional*, defaults to 16):
        Number of attention heads for each attention layer in the Transformer encoder.
    num_key_value_heads (`int`, *optional*, defaults to 4):
        This is the number of key_value heads that should be used to implement Grouped Query Attention. If
        `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
        `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
        converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
        by meanpooling all the original heads within that group. For more details checkout [this
        paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `16`.
    hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
        The non-linear activation function (function or string) in the decoder.
    max_position_embeddings (`int`, *optional*, defaults to 32768):
        The maximum sequence length that this model might ever be used with.
    initializer_range (`float`, *optional*, defaults to 0.02):
        The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
    rms_norm_eps (`float`, *optional*, defaults to 1e-06):
        The epsilon used by the rms normalization layers.
    use_cache (`bool`, *optional*, defaults to `True`):
        Whether or not the model should return the last key/values attentions (not used by all models). Only
        relevant if `config.is_decoder=True`.
    pad_token_id (`int`, *optional*, defaults to 128004):
        The id of the padding token.
    bos_token_id (`int`, *optional*, defaults to 128000):
        The id of the beginning of sentence token.
    eos_token_id (`int`, *optional*, defaults to 128001):
        The id of the end of sentence token.
    rope_theta (`float`, *optional*, defaults to 2000000.0):
        The base period of the RoPE embeddings.
    rope_scaling (`Dict`, *optional*):
        Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type
        and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
        accordingly.
        Expected contents:
            `rope_type` (`str`):
                The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
                'llama3'], with 'default' being the original RoPE implementation.
            `factor` (`float`, *optional*):
                Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
                most scaling types, a `factor` of x will enable the model to handle sequences of length x *
                original maximum pre-trained length.
            `original_max_position_embeddings` (`int`, *optional*):
                Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
                pretraining.
            `attention_factor` (`float`, *optional*):
                Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
                computation. If unspecified, it defaults to value recommended by the implementation, using the
                `factor` field to infer the suggested value.
            `beta_fast` (`float`, *optional*):
                Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
                ramp function. If unspecified, it defaults to 32.
            `beta_slow` (`float`, *optional*):
                Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
                ramp function. If unspecified, it defaults to 1.
            `short_factor` (`List[float]`, *optional*):
                Only used with 'longrope'. The scaling factor to be applied to short contexts (<
                `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
                size divided by the number of attention heads divided by 2
            `long_factor` (`List[float]`, *optional*):
                Only used with 'longrope'. The scaling factor to be applied to long contexts (<
                `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
                size divided by the number of attention heads divided by 2
            `low_freq_factor` (`float`, *optional*):
                Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
            `high_freq_factor` (`float`, *optional*):
                Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
    use_sliding_window (`bool`, *optional*, defaults to `False`):
        Whether to use sliding window attention.
    sliding_window (`int`, *optional*):
        Sliding window attention (SWA) window size. If not specified, will default to `None`.
    no_rope_layers (`List[int]`, *optional*):
        List with at least the same length as the number of layers in the model.
        A `1` at an index position indicates that the corresponding layer will use RoPE,
        while a `0` indicates that it's a NoPE layer.
    no_rope_layer_interval (`int`, *optional*, defaults to 4):
        If `no_rope_layers` is `None`, it will be created using a NoPE layer every
        `no_rope_layer_interval` layers.
    layer_types (`list`, *optional*):
        Attention pattern for each layer. Automatically computed based on sliding window and NoPE settings.
    attention_bias (`bool`, *optional*, defaults to `False`):
        Whether to use a bias in the query, key, value and output projection layers during self-attention.
    attention_dropout (`float`, *optional*, defaults to 0.0):
        The dropout ratio for the attention probabilities.

```python
>>> from transformers import SmolLM3Model, SmolLM3Config

>>> # Initializing a SmolLM3 style configuration
>>> configuration = SmolLM3Config()

>>> # Initializing a model from the SmolLM3 style configuration
>>> model = SmolLM3Model(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```smollm3past_key_valuescolwiserowwise)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_proj	input_idsinputs_embedshidden_statesattention_mask)embed_tokenslayersnormc                 $  > [         TU ]  " SUUUS.UD6  Xl        Xl        UU l        X l        X0l        X@l        XPl        UU l	        UU l
        Uc  UnX`l        Xpl        Xl        Xl        Xl        Xl        UU l        UU l        UU l        Uc3  [)        U5       Vs/ sH  n[+        US-   U-  S:g  5      PM     snU l        OUU l        UU l        UcX  / n[)        U5       HG  nU R,                  U   nU(       a  Ub  U(       d  UR1                  S5        M6  UR1                  S5        MI     UU l        [5        U R2                  5        U R"                  b,  SU R"                  ;   a  U R"                  S   U R"                  S'   [7        U 5        g s  snf )	N)pad_token_idbos_token_ideos_token_id   r   sliding_attentionfull_attentiontype	rope_type )super__init__
vocab_sizemax_position_embeddingsmlp_biashidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsuse_sliding_windowsliding_windownum_key_value_heads
hidden_actinitializer_rangerms_norm_eps	use_cache
rope_thetarope_scalingattention_biasattention_dropoutrangeintno_rope_layersno_rope_layer_intervalappendlayer_typesr   r
   )selfr3   r6   r7   r8   r9   r<   r=   r4   r>   r?   r@   r(   r)   r*   rA   rB   r:   r;   rG   rH   rJ   rC   rD   r5   kwargs	layer_idxhas_rope	__class__s                               c/var/www/html/shao/venv/lib/python3.13/site-packages/transformers/models/smollm3/modular_smollm3.pyr2   SmolLM3Config.__init__   s   8 	 	
%%%	
 		
 %'>$ &!2!2#6 "4, &"5#6 $!2("$(,!2!TYZkTl#TlyY]&<<ABTl#D #1D&<# K"#45	..y9%.*DX&&':;&&'78 6 'd../ (Vt7H7H-H-1->->v-FDk*t$3#s   F)rC   rD   r=   r6   r>   r7   rJ   r4   r5   rH   rG   r9   r8   r<   r?   rB   rA   r;   r@   r:   r3   )i  i   i +  $         silui   g{Gz?gư>Ti i  i g    >ANFNNrT   NF        F)__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planr2   __static_attributes____classcell__rO   s   @rP   r   r   ,   s    qf J#4"5 &/%.%.%."+ )"+ &(9:#%568IJ!"_$56  %  3T% T%    r   c                   B  ^  \ rS rSrS\S\4U 4S jjr  SS\R                  S\	\R                  \R                  4   S\
\R                     S\
\   S	\
\R                     S
\\   S\	\R                  \
\R                     \
\	\R                        4   4S jjrSrU =r$ )SmolLM3Attentioni	  configrM   c                    > [         TU ]  X5        UR                  U   U l        UR                  (       a%  UR
                  U   S:X  a  UR                  U l        g S U l        g )Nr,   )r1   r2   rG   use_roper:   rJ   r;   rK   rf   rM   rO   s      rP   r2   SmolLM3Attention.__init__
  s`    +--i8 ((V-?-?	-JNa-a !! 	  	rc   r"   position_embeddingsr#   past_key_valuecache_positionrL   returnc                 j   UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
U R                  U5      R                  U5      R	                  SS5      nU R                  (       a  Uu  p[        XX5      u  pUb#  SU0nUR                  XU R                  U5      u  p[        nU R                  R                  S:w  a  [        U R                  R                     nU" U U	U
UU4U R                  (       d  SOU R                   U R"                  U R$                  S.UD6u  nnUR&                  " / UQSP76 R)                  5       nU R+                  U5      nUU4$ )Nr+   r   rm   eagerrV   )dropoutscalingr;   )shapehead_dimq_projview	transposek_projv_projrh   r   updaterM   r   rf   _attn_implementationr   trainingrD   rs   r;   reshape
contiguouso_proj)rK   r"   rk   r#   rl   rm   rL   input_shapehidden_shapequery_states
key_statesvalue_statescossincache_kwargsattention_interfaceattn_outputattn_weightss                     rP   forward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';LVY'_$L%,n=L'5'<'<ZW[WeWegs't$J(?;;++w6"9$++:Z:Z"[$7
%
  $}}C$2H2HLL..
%
 
%
!\ "));;;;FFHkk+.L((rc   )r;   rh   )NN)rW   rX   rY   rZ   r   rF   r2   torchTensortupler   r   
LongTensorr   r	   r   r`   ra   rb   s   @rP   re   re   	  s    
} 
 
 +/59*)||*) #5<<#=>*) !.	*)
 !*) !!1!12*) -.*) 
u||Xell3XeELL>Q5RR	S*) *)rc   re   c                   4   ^  \ rS rSrS\S\4U 4S jjrSrU =r$ )SmolLM3DecoderLayeriA  rf   rM   c                 L   > [         TU ]  X5        UR                  U   U l        g )N)r1   r2   rJ   attention_typeri   s      rP   r2   SmolLM3DecoderLayer.__init__B  s#    +$00;rc   )r   )	rW   rX   rY   rZ   r   rF   r2   r`   ra   rb   s   @rP   r   r   A  s    <} < < <rc   r   c                       \ rS rSrSrg)SmolLM3PreTrainedModeliG  r0   NrW   rX   rY   rZ   r`   r0   rc   rP   r   r   G      rc   r   c                       \ rS rSrSrg)SmolLM3ModeliK  r0   Nr   r0   rc   rP   r   r   K  r   rc   r   c                       \ rS rSrSrg)SmolLM3ForCausalLMiO  r0   Nr   r0   rc   rP   r   r   O  r   rc   r   c                       \ rS rSrSrg) SmolLM3ForSequenceClassificationiS  r0   Nr   r0   rc   rP   r   r   S  r   rc   r   c                       \ rS rSrSrg)SmolLM3ForTokenClassificationiW  r0   Nr   r0   rc   rP   r   r   W  r   rc   r   c                       \ rS rSrSrg)SmolLM3ForQuestionAnsweringi[  r0   Nr   r0   rc   rP   r   r   [  r   rc   r   )r   r   r   r   r   r   r   ),typingr   r   r   cache_utilsr   configuration_utilsr   r   modeling_flash_attention_utilsr	   modeling_rope_utilsr
   modeling_utilsr   processing_utilsr   utilsr   llama.modeling_llamar   r   r   r   r   r   r   r   r   qwen2.modeling_qwen2r   
get_loggerrW   loggerr   re   r   r   r   r   r   r   r   __all__r0   rc   rP   <module>r      s     &    J B 9 5 & 
 
 
 . 
		H	%Z%$ Z%z5)~ 5)p<+ <	1 		: 		) 		'E 		$? 		"; 	rc   