
    iW                        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	 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- ddl.m/Z/ d Z0 ed      dBd       Z1dejd                  de3dejd                  fdZ4	 dCdejj                  dejd                  dejd                  d ejd                  d!ejd                  dz  d"e6d#e6d$e'e)   fd%Z7d&ejd                  d'e6d(e3dejd                  fd)Z8 ee1       G d* d+ejj                               Z9 G d, d-ejj                        Z: ed.       G d/ d0ejj                               Z; G d1 d2e      Z<e* G d3 d4e%             Z= G d5 d6ejj                        Z>e* G d7 d8e=             Z?e* G d9 d:e=e             Z@ G d; d<ee=      ZA G d= d>ee=      ZB G d? d@ee=      ZCg dAZDy)D    )Callable)OptionalN)nn)check_model_inputs   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernel_func_from_hubuse_kernelized_func)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs)GenericForQuestionAnswering GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocast   )Ministral3Configc                     | dd| j                   d   dz  f   }| d| j                   d   dz  df   }t        j                  | |fd      S )z*Rotates half the hidden dims of the input..N   dim)shapetorchcat)xx1x2s      |/home/obispo/Crisostomo_bridge/mision_env/lib/python3.12/site-packages/transformers/models/ministral3/modeling_ministral3.pyrotate_halfr/   $   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''    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.
    )	unsqueezer/   )qkcossinunsqueeze_dimq_embedk_embeds          r.   apply_rotary_pos_embr;   +   sY    & --
&C
--
&C3w;q>C/0G3w;q>C/0GGr0   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_kvrF   E   so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr0   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$   )r'   dtype)ptrainingr!   )rF   num_key_value_groupsr)   matmul	transposer(   r   
functionalsoftmaxfloat32torQ   rM   rS   
contiguous)rG   rH   rI   rJ   rK   rL   rM   rN   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r.   eager_attention_forwardra   Q   s    3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#k1==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r0   positions_idsbetamax_position_embeddingsc           	          d|t        j                  dt        j                  | |z        z         z  z   }|j                  d      S )Nr!   r$   )r)   logfloorr3   )rb   rc   rd   rL   s       r.   _get_llama_4_attn_scalerh   k   s?    $1u{{=CZ3Z'[#[\\\GR  r0   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 )Ministral3Attentionz=Multi-headed attention from 'Attention Is All You Need' paperconfig	layer_idxc                    t         |           || _        || _        t	        |dd       xs |j
                  |j                  z  | _        |j                  |j                  z  | _	        | j                  dz  | _
        |j                  | _        d| _        t        j                  |j
                  |j                  | j                  z  d      | _        t        j                  |j
                  |j                  | j                  z  d      | _        t        j                  |j
                  |j                  | j                  z  d      | _        t        j                  |j                  | j                  z  |j
                  d      | _        y )NrE   g      TFbias)super__init__rk   rl   getattrhidden_sizenum_attention_headsrE   rC   rT   rL   attention_dropout	is_causalr   Linearq_projk_projv_projo_projselfrk   rl   	__class__s      r.   rq   zMinistral3Attention.__init__t   s2   "
D9mV=O=OSYSmSm=m$*$>$>&B\B\$\!}}d*!'!9!9ii 2 2F4N4NQUQ^Q^4^ejkii 2 2F4N4NQUQ^Q^4^ejkii 2 2F4N4NQUQ^Q^4^ejkii : :T]] JFL^L^ejkr0   Nr<   position_embeddingsrK   past_key_valuescache_positionrN   r>   c           
      "   |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|	t        || j                  j                  j                  d      | j                  j                  j                  d            j                  |	j                        z  }	|'|||d}|j                  |
|| j                  |      \  }
}t!        j"                  | j                  j$                  t&              } || |	|
||f| j(                  sdn| j*                  | j,                  t/        | j                  dd       d	|\  }} |j0                  g |d j3                         }| j5                  |      }||fS )
Nr$   r!   r%   llama_4_scaling_beta original_max_position_embeddings)r7   r6   r           sliding_window)rM   rL   r   )r(   rE   rx   viewrV   ry   rz   r;   rh   rk   rope_parametersgetrZ   rQ   updaterl   r   get_interface_attn_implementationra   rS   ru   rL   rr   rA   r[   r{   )r}   r<   r   rK   r   r   rN   input_shapehidden_shapequery_statesr\   r]   r6   r7   cache_kwargsattention_interfacer`   r^   s                     r.   forwardzMinistral3Attention.forward   s    $))#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&S#7jRUWZ#[ j#&=KK''++,BCKK''++,NO'
 "\
 	! &#&snUL'6'='=j,X\XfXfht'u$J(?(M(MKK,,.E)
 %8
%
  $}}C$2H2HLL"4;;0@$G
%
 
%
!\ *k));;;;FFHkk+.L((r0   )NN)__name__
__module____qualname____doc__r"   intrq   r)   Tensortupler	   
LongTensorr   r   r   __classcell__r~   s   @r.   rj   rj   p   s    Gl/ lC l& )-26/)||/) #5<<#=>/) t+	/)
 /) ((4//) -./) 
u||U\\D00	1/)r0   rj   c                   $     e Zd Z fdZd Z xZS )Ministral3MLPc                    t         |           || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _	        t        |j                     | _        y NFrn   )rp   rq   rk   rs   intermediate_sizer   rw   	gate_projup_proj	down_projr   
hidden_actact_fnr}   rk   r~   s     r.   rq   zMinistral3MLP.__init__   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r0   c                     | j                  | j                  | j                  |            | j                  |      z        }|S N)r   r   r   r   )r}   r+   r   s      r.   r   zMinistral3MLP.forward   s6    NN4;;t~~a/@#ADLLQRO#ST	r0   )r   r   r   rq   r   r   r   s   @r.   r   r      s    0r0   r   RMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )Ministral3RMSNormc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z@
        Ministral3RMSNorm is equivalent to T5LayerNorm
        N)rp   rq   r   	Parameterr)   onesweightvariance_epsilon)r}   rs   epsr~   s      r.   rq   zMinistral3RMSNorm.__init__   s1     	ll5::k#:; #r0   c                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )Nr%   r$   T)keepdim)	rQ   rZ   r)   rY   powmeanrsqrtr   r   )r}   r<   input_dtypevariances       r.   r   zMinistral3RMSNorm.forward   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r0   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)r   r   r(   r   )r}   s    r.   
extra_reprzMinistral3RMSNorm.extra_repr   s*    ))*+6$2G2G1HIIr0   )gư>)r   r   r   rq   r   r   r   r   s   @r.   r   r      s    $;Jr0   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 )Ministral3DecoderLayerrk   rl   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        y )N)rk   rl   r   )rp   rq   rs   rj   	self_attnr   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr|   s      r.   rq   zMinistral3DecoderLayer.__init__   sm    !--,FiP (01C1CI\I\](9&:L:LRXReRe(f%r0   Nr<   rK   position_idsr   	use_cacher   r   rN   r>   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r<   rK   r   r   r   r   r    )r   r   r   r   )r}   r<   rK   r   r   r   r   r   rN   residual_s              r.   r   zMinistral3DecoderLayer.forward   s     !,,];)4>> 	
')%+) 3	
 	
q !=0 !55mD/ =0r0   )NNNFNN)r   r   r   r"   r   rq   r)   r   r   r	   boolr   r   r   r   r   r   s   @r.   r   r      s    g/ gC g /304(,!&26HL|| t+ &&-	
  $; ((4/ #5<<#=>E +, 
r0   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)Ministral3PreTrainedModelrk   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   rj   _can_record_outputsr   r0   r.   r   r     sQ    &*#12#4"5N!"&/)r0   r   c                        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 )Ministral3RotaryEmbeddinginv_freqNrk   c                    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)rp   rq   rd   max_seq_len_cachedoriginal_max_seq_lenrk   r   r   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r}   rk   devicerope_init_fnr   r~   s        r.   rq   z"Ministral3RotaryEmbedding.__init__  s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuUr0   r   ztorch.deviceseq_lenr>   z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_thetarE   Ng      ?r   r%   rQ   )r   rQ   )	r   rr   rs   rt   r)   arangeint64rZ   float)rk   r   r   baser'   attention_factorr   s          r.   r   z9Ministral3RotaryEmbedding.compute_default_rope_parameters*  s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r0   c                 N   | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        j	                  |j                   
      	j	                  |j                   
      fS # 1 sw Y   AxY w)Nr   r$   r!   mpscpuF)device_typeenabledr%   r&   r   )r   r   r@   r(   rZ   r   
isinstancetypestrr    rV   r)   r*   r6   r   r7   rQ   )
r}   r+   r   inv_freq_expandedposition_ids_expandedr   freqsembr6   r7   s
             r.   r   z!Ministral3RotaryEmbedding.forwardH  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$r   )NNN)r   r   r   r)   r   r   r"   rq   staticmethodr   r   r   r   r   no_gradr   r   r   r   s   @r.   r   r     s    llV/ V  *.+/"* 4'*(* t* 
~u$	%	* *: U]]_<  <r0   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 )Ministral3Modelrk   c           	         t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |j                  |j                        | _        t#        |      | _        d| _        | j)                          y c c}w )Nr   rk   F)rp   rq   pad_token_idpadding_idx
vocab_sizer   	Embeddingrs   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normr   
rotary_embgradient_checkpointing	post_initr|   s      r.   rq   zMinistral3Model.__init__Z  s     !.. ++LL):):F<N<NPTP`P`ammHMfNfNfHgh9#FI6h
 &f&8&8f>Q>QR	36B&+# 	 is   DN	input_idsrK   r   r   inputs_embedsr   r   rN   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      }| j                  j                  t        nt        }
 |
| j                  |||||      }|}| j                  ||      }| j                  d | j                  j                   D ]  } ||f||||||d|} | j!                  |      }t#        ||r|	      S d 	      S )
Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r!   )r   )rk   input_embedsrK   r   r   r   )r   )rK   r   r   r   r   r   )last_hidden_stater   )
ValueErrorr
  r
   rk   get_seq_lengthr)   r   r(   r   r3   r   r   r   r  r  r  r  r   )r}   r  rK   r   r   r  r   r   rN   past_seen_tokensmask_functionr_   r<   r   decoder_layers                  r.   r   zMinistral3Model.forwardj  s    -t";<YZZ  --i8M0*$++>O!CRC^==?de"\\ "2]5H5H5K"KTaThThN )33A6L.2kk.H.H.P*Vw#;;&))+%
 &"oom,oW![[)H4;;+H+HI 
	M)	*) /#-$7	 	M
	 		-0&+/8O
 	
>B
 	
r0   )NNNNNNN)r   r   r   r"   rq   r   r   r)   r   r   r	   FloatTensorr   r   r   r   r   r   r   s   @r.   r  r  X  s    /    .2.204(,26!%269
##d*9
 t+9
 &&-	9

 9
 ((4/9
 $;9
 ((4/9
 +,9
 
!9
  9
r0   r  c                   b    e Zd ZddiZddiZddgdgfiZ fdZee	 	 	 	 	 	 	 	 	 dd	e	j                  dz  d
e	j                  dz  de	j                  dz  dedz  de	j                  dz  de	j                  dz  dedz  de	j                  dz  dee	j                  z  dee   defd              Z xZS )Ministral3ForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr<   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y r   )
rp   rq   r  r   r  r   rw   rs   r   r  r   s     r.   rq   zMinistral3ForCausalLM.__init__  sU     $V,
 ++yy!3!3V5F5FUS 	r0   Nr  rK   r   r   r  labelsr   r   logits_to_keeprN   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, Ministral3ForCausalLM

        >>> model = Ministral3ForCausalLM.from_pretrained("meta-ministral3/Ministral3-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-ministral3/Ministral3-2-7b-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  rK   r   r   r  r   r   N)r"  r$  r  )lossr"  r   r<   r   r   )r   r  r   r   slicer   loss_functionrk   r  r   r   r<   r   )r}   r  rK   r   r   r  r$  r   r   r%  rN   outputsr<   slice_indicesr"  r'  s                   r.   r   zMinistral3ForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r0   )	NNNNNNNNr   )r   r   r   _tied_weights_keys_tp_plan_pp_planrq   r   r   r)   r   r   r	   r  r   r   r   r   r   r   r   r   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
 $;8
 ((4/8
 ell*8
 +,8
 
 8
  8
r0   r  c                       e Zd Zy) Ministral3ForTokenClassificationNr   r   r   r   r0   r.   r0  r0        r0   r0  c                       e Zd Zy)#Ministral3ForSequenceClassificationNr1  r   r0   r.   r4  r4    r2  r0   r4  c                       e Zd Zy)Ministral3ForQuestionAnsweringNr1  r   r0   r.   r6  r6    r2  r0   r6  )r  r6  r  r   r4  r0  )r!   )r   )Ecollections.abcr   typingr   r)   r   transformers.utils.genericr   activationsr   cache_utilsr	   r
   
generationr   integrationsr   r   r   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   r   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr    configuration_ministral3r"   r/   r;   r   r   rF   Moduler   ra   rh   rj   r   r   r   r   r   r  r  r0  r4  r6  __all__r   r0   r.   <module>rJ     sJ   %    9 ! . ) f f R B  P K F & I I + 6( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%4!5<< !u !_b !glgsgs !
 )*@)")) @) +@)FBII   Y'J		 J (J((7 (V   $><		 ><B L
/ L
 L
^ H
5 H
 H
V	'DF_ 		*JLe 		%@B[ 	r0   