
    rhO8                        d dl mZmZ d dlZd dlmZ ddlmZ ddlmZ ddl	m
Z
 ddlmZ dd	lmZ d
dlmZmZmZmZmZmZ d
dlmZ ddlmZ  ej4                  e      Z G d de      Z G d dej<                        Z G d dej<                        Z  G d de      Z! G d de      Z" G d de      Z# G d de      Z$ G d de      Z%g dZ&y)     )OptionalUnionN)nn   )ACT2FN)Cache)FlashAttentionKwargs)Unpack)logging   )LlavaCausalLMOutputWithPastLlavaForConditionalGeneration
LlavaModelLlavaModelOutputWithPastLlavaPreTrainedModelTransformersKwargs)MistralRMSNorm   )Mistral3Configc                       e Zd Zy)Mistral3RMSNormN__name__
__module____qualname__     /var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/mistral3/modular_mistral3.pyr   r   )       r   r   c                   x     e Zd ZdZdef fdZdej                  dej                  dej                  fdZ xZ	S )Mistral3PatchMergerz<
    Learned merging of spatial_merge_size ** 2 patches
    configc                 "   t         |           || _        |j                  j                  }|j
                  | _        | j                  j                  j                  | _        t        j                  || j
                  dz  z  |d      | _	        y )Nr   Fbias)
super__init__r"   vision_confighidden_sizespatial_merge_size
patch_sizer   Linearmerging_layer)selfr"   r)   	__class__s      r   r'   zMistral3PatchMerger.__init__2   sr    **66"(";";++33>>YY{T5L5La5O'OQ\chir   image_featuresimage_sizesreturnc                    |D cg c]&  }|d   | j                   z  |d   | j                   z  f( }}|D cg c]
  \  }}||z   }}}|j                  d   }g }t        |j                  |            D ]  \  }	}
||	   \  }}|
j	                  |||      j                  ddd      j                  d      }t        j                  j                  j                  || j                  | j                        }|j	                  || j                  dz  z  d      j                         }|j                  |        t        j                  |d      }| j                  |      }|S c c}w c c}}w )Nr   r   r   )kernel_sizestridedim)r+   shape	enumeratesplitviewpermute	unsqueezetorchr   
functionalunfoldr*   tappendcatr-   )r.   r0   r1   
image_sizehwtokens_per_imagedpermuted_tensorimage_indeximage_tokens
image_gridgrids                r   forwardzMistral3PatchMerger.forward;   sl   cn
U_Z]doo-z!}/OP
 
 /::daAE::  $)2>3G3GHX3Y)Z 	)%K{+DAq%**1a3;;Aq!DNNqQJ88&&--(?(?H_H_ . D 99Q!8!8!!;;R@BBDD""4(	) ?:++N;)
 ;s
   +E"E')
r   r   r   __doc__r   r'   r?   TensorrO   __classcell__r/   s   @r   r!   r!   -   s?    j~ jell  RWR^R^ r   r!   c                   \     e Zd Zdef fdZdej                  dej                  fdZ xZS )Mistral3MultiModalProjectorr"   c                    t         |           t        |j                  j                  |j
                  j                        | _        t        |      | _	        t        |j                  t              rdnt        |j                        }t        j                  |j                  j                  |z  |j
                  j                  |j                         | _        t$        |j&                     | _        t        j                  |j
                  j                  |j
                  j                  |j                         | _        y )N)epsr   r$   )r&   r'   r   r(   r)   text_configrms_norm_epsnormr!   patch_merger
isinstancevision_feature_layerintlenr   r,   multimodal_projector_biaslinear_1r   projector_hidden_actactlinear_2)r.   r"   num_feature_layersr/   s      r   r'   z$Mistral3MultiModalProjector.__init__T   s    #F$8$8$D$D&J\J\JiJij	/7",V-H-H#"NQTWX^XsXsTt		  ,,/AA**11

 &556		**F,>,>,J,JQWQqQq
r   r0   r1   c                     | j                  |      }| j                  ||      }| j                  |      }| j                  |      }| j	                  |      }|S N)rZ   r[   ra   rc   rd   )r.   r0   r1   hidden_statess       r   rO   z#Mistral3MultiModalProjector.forwardd   sR    >2**>;Gn5/m4r   )	r   r   r   r   r'   r?   rQ   rO   rR   rS   s   @r   rU   rU   S   s*    
~ 
 ell  r   rU   c                       e Zd Zy)Mistral3CausalLMOutputWithPastNr   r   r   r   rj   rj   m   r   r   rj   c                       e Zd Zy)Mistral3ModelOutputWithPastNr   r   r   r   rl   rl   q   r   r   rl   c                       e Zd Zy)Mistral3PreTrainedModelNr   r   r   r   rn   rn   u   r   r   rn   c            !          e Zd Z	 ddej                  dej
                  deeee	e   f      fdZ
	 	 	 	 	 	 	 	 	 	 	 	 	 ddej                  dej                  deej
                     deej                     d	ee   d
eej                     deeee	e   f      dee   dee   dee   dee   deej                     dej
                  dee   deeef   fdZy)Mistral3ModelNpixel_valuesr1   r]   c                    ||n| j                   j                  }|j                         D ci c]  \  }}|	|| }}} | j                  |f|dd|}t	        |t
              r|j                  |   }n3|D 	cg c]  }	|j                  |	    }
}	t        j                  |
d      }| j                  |j                  d      |      }| j                  j                  | j                   j                  z  }|D cg c]  \  }}||z  ||z  z   }}}t        j                  |j                  d      |      }|S c c}}w c c}	w c c}}w )aU  
        Obtains image last hidden states from the vision tower and apply multimodal projection.

        Args:
            pixel_values (`torch.FloatTensor]` of shape `(batch_size, channels, height, width)`):
               The tensors corresponding to the input images.
            vision_feature_layer (`Union[int, list[int]]`, *optional*):
                The index of the layer to select the vision feature. If multiple indices are provided,
                the vision feature of the corresponding indices will be concatenated to form the
                vision features.
            image_sizes (`torch.Tensor`, *optional*):
                Tensor containing the image sizes as returned by the processor.
        Returns:
            image_features (`torch.Tensor`): Image feature tensor of shape `(num_images, image_length, embed_dim)`).
        T)r1   output_hidden_statesr4   r7   r   )r"   r]   itemsvision_towerr\   r^   rh   r?   rD   multi_modal_projectorsqueezer+   r*   r;   )r.   rq   r1   r]   kwargskvimage_outputsselected_image_feature	layer_idxhs_poolr0   downsample_ratioheightwidthsplit_sizess                   r   get_image_featuresz Mistral3Model.get_image_featuresz   sR   . %9$D $++JjJj 	 $*<<>C41aQ]!Q$CC))),uKfjuntu *C0%2%@%@AU%V"Ocd)}229=dGd%*YYwB%?"334J4R4RST4UWbc,,77$++:X:XXgrsVcV\^c"22u@P7PQss^%;%;A%>L D e
 ts   
D<D<;E=E	input_idsattention_maskposition_idspast_key_valuesinputs_embeds	use_cacheoutput_attentionsrs   return_dictcache_positionrx   r2   c                    |	|	n| j                   j                  }	|
|
n| j                   j                  }
||n| j                   j                  }||n| j                   j                  }|d u |d uz  rt        d      | | j                         |      }|u| j                  |||      }t        j                  |d      j                  |j                  |j                        }| j                  |||      }|j                  ||      } | j                  d	||||||	|
d|d	|}t!        |j"                  |j$                  |j&                  |j(                  |      S d       S )
Nz:You must specify exactly one of input_ids or inputs_embeds)rq   r]   r1   r   r7   )r   r0   T)	r   r   r   r   r   r   rs   r   r   )last_hidden_stater   rh   
attentionsimage_hidden_statesr   )r"   r   rs   use_return_dictr]   
ValueErrorget_input_embeddingsr   r?   rD   todevicedtypeget_placeholder_maskmasked_scatterlanguage_modelrl   r   r   rh   r   )r.   r   rq   r   r   r   r   r]   r   r   rs   r   r   r1   rx   r0   special_image_maskoutputss                     r   rO   zMistral3Model.forward   s   " 2C1N-TXT_T_TqTq$8$D $++JjJj 	 &1%<k$++B]B]$8$D $++JjJj 	 -t";<YZZ 7D557	BM#!44)%9' 5 N
 #YY~1=@@AUAUWdWjWjkN!%!:!:~ "; " *889K^\M%$%% 
)%+'/!5)
 
 +%77#33!//))2>2J
 	

 QU
 	
r   rg   )NNNNNNNNNNNNN)r   r   r   r?   FloatTensorrQ   r   r   r^   listr   
LongTensorr   boolr
   r	   tuplerl   rO   r   r   r   rp   rp   y   sz   
 AE	)'') \\) 'uS$s)^'<=	)Z '+*.1537+/59@D$(,0/3&*59$(?
##?
 ''?
 !.	?

 u//0?
 "%?
   1 12?
 'uS$s)^'<=?
 D>?
 $D>?
 'tn?
 d^?
 !!1!12?
 \\?
 -.?
  
u11	2!?
r   rp   c            #          e Zd Z	 ddej                  dej
                  deeee	e   f      fdZ
	 	 	 	 	 	 	 	 	 	 	 	 	 	 ddej                  d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   dee   dee   deej                     deeej
                  f   deej
                     dee   deeef   f dZy) Mistral3ForConditionalGenerationNrq   r1   r]   c                 B     | j                   j                  d|||d|S )N)rq   r1   r]   r   )modelr   )r.   rq   r1   r]   rx   s        r   r   z3Mistral3ForConditionalGeneration.get_image_features   s5     -tzz,, 
%#!5
 	
 	
r   r   r   r   r   r   labelsr   r   rs   r   r   logits_to_keeprx   r2   c                 <   |	|	n| j                   j                  }	|
|
n| j                   j                  }
||n| j                   j                  } | j                  d||||||||	|
d||d|}|d   }t        |t              rt        | d      n|}| j                  |dd|ddf         }d}|4 | j                  d||| j                   j                  j                  d|}t        |||j                  |j                  |j                  |j                         S )a  
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
            config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
            (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

        Example:

        ```python
        >>> from PIL import Image
        >>> import requests
        >>> from transformers import AutoProcessor, Mistral3ForConditionalGeneration

        >>> model = Mistral3ForConditionalGeneration.from_pretrained("mistralai/Mistral-Small-3.1-24B-Instruct-2503")
        >>> processor = AutoProcessor.from_pretrained("mistralai/Mistral-Small-3.1-24B-Instruct-2503")

        >>> prompt = "<s>[INST][IMG]What is the image?[/INST]"
        >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
        >>> image = Image.open(requests.get(url, stream=True).raw)

        >>> inputs = processor(images=image, text=prompt, return_tensors="pt")

        >>> # Generate
        >>> generate_ids = model.generate(**inputs, max_new_tokens=15)
        >>> processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
        "What is the image?The image depicts two cats lying on a pink blanket."
        ```NT)r   rq   r   r   r   r   r   r   rs   r   r   r1   r   )logitsr   
vocab_size)lossr   r   rh   r   r   r   )r"   r   rs   r   r   r\   r^   slicelm_headloss_functionrX   r   rj   r   rh   r   r   )r.   r   rq   r   r   r   r   r   r   r   rs   r   r   r   r1   rx   r   rh   slice_indicesr   r   s                        r   rO   z(Mistral3ForConditionalGeneration.forward   sP   Z 2C1N-TXT_T_TqTq$8$D $++JjJj 	 &1%<k$++B]B]$** 
%)%+'/!5)#
 
   
8B>SV8W~ot4]kmA}a,?@A%4%% f9P9P9[9[_eD .#33!//)) ' ; ;
 	
r   rg   )NNNNNNNNNNNNr   N)r   r   r   r?   r   rQ   r   r   r^   r   r   r   r   r   r
   r   r   rj   rO   r   r   r   r   r      s   
 AE	
''
 \\
 'uS$s)^'<=	
  '+*.1537+/59-1$(,0/3&*5934.2U
##U
 ''U
 !.	U

 u//0U
 "%U
   1 12U
 ))*U
 D>U
 $D>U
 'tnU
 d^U
 !!1!12U
 c5<</0U
 ell+U
  +,!U
" 
u44	5#U
r   r   )rp   rn   r   )'typingr   r   r?   r   activationsr   cache_utilsr   modeling_flash_attention_utilsr	   processing_utilsr
   utilsr   llava.modeling_llavar   r   r   r   r   r   mistral.modeling_mistralr   configuration_mistral3r   
get_loggerr   loggerr   Moduler!   rU   rj   rl   rn   rp   r   __all__r   r   r   <module>r      s     #   !   B &   6 2 
		H	%	n 	#")) #L")) 4	%@ 		": 		2 	k
J k
\d
'D d
Nr   