
    iW                     L   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 ddlmZ ddl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*  ed       G d dejV                               Z, G d dejV                        Z-d Z. ed      d7d       Z/dej`                  de1dej`                  fd Z2	 d8d!ejV                  d"ej`                  d#ej`                  d$ej`                  d%ej`                  dz  d&e3d'e3d(e!e#   fd)Z4 ee/       G d* d+ejV                               Z5 G d, d-e      Z6 G d. d/ejV                        Z7e$ G d0 d1e             Z8e$ G d2 d3e8             Z9e$ G d4 d5e8e             Z:g d6Z;y)9    )Callable)OptionalN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernel_func_from_hubuse_kernelized_func)create_causal_mask)FlashAttentionKwargs)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   )BitNetConfigRMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )BitNetRMSNormc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z<
        BitNetRMSNorm is equivalent to T5LayerNorm
        N)super__init__r   	Parametertorchonesweightvariance_epsilon)selfhidden_sizeeps	__class__s      t/home/obispo/Crisostomo_bridge/mision_env/lib/python3.12/site-packages/transformers/models/bitnet/modeling_bitnet.pyr$   zBitNetRMSNorm.__init__,   s1     	ll5::k#:; #    c                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )N   T)keepdim)	dtypetor&   float32powmeanrsqrtr)   r(   )r*   hidden_statesinput_dtypevariances       r.   forwardzBitNetRMSNorm.forward4   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r/   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tupler(   shaper)   )r*   s    r.   
extra_reprzBitNetRMSNorm.extra_repr;   s*    ))*+6$2G2G1HIIr/   )gư>)__name__
__module____qualname__r$   r=   rA   __classcell__r-   s   @r.   r!   r!   *   s    $;Jr/   r!   c                   *     e Zd Zdef fdZd Z xZS )	BitNetMLPconfigc                    t         |           || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _	        t        |j                     | _        t        |j                  |j                        | _        y )NFbiasr,   )r#   r$   rI   r+   intermediate_sizer   Linear	gate_projup_proj	down_projr   
hidden_actact_fnr!   rms_norm_epsffn_sub_normr*   rI   r-   s     r.   r$   zBitNetMLP.__init__@   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../)&*B*BH[H[\r/   c           	          | j                  | j                  | j                  | j                  |            | j	                  |      z              }|S N)rR   rV   rT   rP   rQ   )r*   xrR   s      r.   r=   zBitNetMLP.forwardK   sF    NN4#4#4T[[PQAR5SVZVbVbcdVe5e#fg	r/   )rB   rC   rD   r   r$   r=   rE   rF   s   @r.   rH   rH   ?   s    	]| 	]r/   rH   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..Nr2   r1   dim)r@   r&   cat)rZ   x1x2s      r.   rotate_halfra   P   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.
    )	unsqueezera   )qkcossinunsqueeze_dimq_embedk_embeds          r.   apply_rotary_pos_embrl   W   sY    & --
&C
--
&C3w;q>C/0G3w;q>C/0GGr/   r:   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:   rm   batchnum_key_value_headsslenhead_dims         r.   	repeat_kvrv   q   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 )Nr1   r   r2   )r]   r4   )ptrainingr   )rv   num_key_value_groupsr&   matmul	transposer@   r   
functionalsoftmaxr6   r5   r4   r}   r   
contiguous)rw   rx   ry   rz   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 )BitNetAttentionz=Multi-headed attention from 'Attention Is All You Need' paperrI   	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                        | _        t)        |j
                  |j*                        | _        y )Nru   g      TrK   rM   )r#   r$   rI   r   getattrr+   num_attention_headsru   rs   r   r|   attention_dropout	is_causalr   rO   attention_biasq_projk_projv_projo_projr!   rU   attn_sub_normr*   rI   r   r-   s      r.   r$   zBitNetAttention.__init__   sj   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 +6+=+=6CVCVWr/   Nr:   position_embeddingsr{   past_key_valuescache_positionr~   rn   c                 :   |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        j                  | j                  j                  t              } || |	|
||f| j                  sdn| j                   | j"                  d|\  }} |j$                  g |d j'                         }| j)                  |      }| j+                  |      }||fS )Nr2   r   r1   )rh   rg   r           )r}   r|   )r@   ru   r   viewr   r   r   rl   updater   r   get_interfacerI   _attn_implementationr   r   r   r|   rq   r   r   r   )r*   r:   r   r{   r   r   r~   input_shapehidden_shapequery_statesr   r   rg   rh   cache_kwargsattention_interfacer   r   s                     r.   r=   zBitNetAttention.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&#&snUL'6'='=j,X\XfXfht'u$J(?(M(MKK,,.E)
 %8	%
  $}}C$2H2HLL	%
 	%
!\ *k));;;;FFH((5kk+.L((r/   )NN)rB   rC   rD   __doc__r   intr$   r&   Tensorr?   r   
LongTensorr   r   r=   rE   rF   s   @r.   r   r      s    GX| X X: )-26*)||*) #5<<#=>*) t+	*)
 *) ((4/*) -.*) 
u||U\\D00	1*)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 )BitNetDecoderLayerrI   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        y )N)rI   r   rM   )r#   r$   r+   r   	self_attnrH   mlpr!   rU   input_layernormpost_attention_layernormr   s      r.   r$   zBitNetDecoderLayer.__init__   sl    !--()LV$,V-?-?VEXEXY(5f6H6HfNaNa(b%r/   Nr:   r{   position_idsr   	use_cacher   r   r~   rn   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r:   r{   r   r   r   r   r    )r   r   r   r   )r*   r:   r{   r   r   r   r   r   r~   residual_s              r.   r=   zBitNetDecoderLayer.forward   s     !,,];)4>> 	
')%+) 3	
 	
q !=0 !55mD/ =0r/   )NNNFNN)rB   rC   rD   r   r   r$   r&   r   r   r   boolr?   r   r   r=   rE   rF   s   @r.   r   r      s    c| c c /304(,!&26HL|| t+ &&-	
  $; ((4/ #5<<#=>E +, 
r/   r   c                        e Zd ZU ej                  ed<   ddef fdZe	 	 	 ddedz  de	d   de
dz  ded	ef   fd
       Z ej                         ed               Z xZS )BitNetRotaryEmbeddinginv_freqNrI   c                    t         |           |j                  | _        |j                  | _        || _        | j
                  j                  d   | _        | j                  }| j                  dk7  rt        | j                     } || j
                  |      \  }| _
        | j                  d|d       | j                  d|j                         d       y )N	rope_typedefaultr   F)
persistentoriginal_inv_freq)r#   r$   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrI   rope_parametersr   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r*   rI   devicerope_init_fnr   r-   s        r.   r$   zBitNetRotaryEmbedding.__init__  s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuUr/   r   ztorch.deviceseq_lenrn   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_thetaru   Ng      ?r   r1   r4   )r   r4   )	r   r   r+   r   r&   arangeint64r5   float)rI   r   r   baser]   attention_factorr   s          r.   r   z5BitNetRotaryEmbedding.compute_default_rope_parameters   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r/   c                 N   | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        j	                  |j                   
      	j	                  |j                   
      fS # 1 sw Y   AxY w)Nr   r2   r   mpscpuF)device_typeenabledr1   r\   r   )r   r   rp   r@   r5   r   
isinstancetypestrr   r   r&   r^   rg   r   rh   r4   )
r*   rZ   r   inv_freq_expandedposition_ids_expandedr   freqsembrg   rh   s
             r.   r=   zBitNetRotaryEmbedding.forward>  sR    !MM$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$cff177f&;;;	5 	5s   BFF$rY   )NNN)rB   rC   rD   r&   r   __annotations__r   r$   staticmethodr   r   r?   r   r   no_gradr   r=   rE   rF   s   @r.   r   r     s    llV| V  &*+/"*t#*(* t* 
~u$	%	* *: U]]_<  <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)BitNetPreTrainedModelrI   modelTr   r   )r:   
attentionsN)rB   rC   rD   r   r   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   N  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j                  dz  d
edz  dee   defd              Z xZS )BitNetModelrI   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 )NrM   rI   F)r#   r$   pad_token_idpadding_idx
vocab_sizer   	Embeddingr+   embed_tokens
ModuleListrangenum_hidden_layersr   layersr!   rU   normr   
rotary_embgradient_checkpointing	post_initr   s      r.   r$   zBitNetModel.__init__c  s     !.. ++LL):):F<N<NPTP`P`ammDI&JbJbDcdy	2d
 "&"4"4&:M:MN	/v>&+# 	 es   DN	input_idsr{   r   r   inputs_embedsr   r   r~   rn   c                 D   |d u |d uz  rt        d      || j                  |      }|r|t        | j                        }|E||j	                         nd}	t        j                  |j                  d   |j                        |	z   }||j                  d      }t        | j                  |||||      }
|}| j                  ||      }| j                  d | j                  j                   D ]  } ||f|
|||||d|} | j                  |      }t        ||	      S )
Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r   )r   )rI   input_embedsr{   r   r   r   )r   )r{   r   r   r   r   r   )last_hidden_stater   )
ValueErrorr   r	   rI   get_seq_lengthr&   r   r@   r   rd   r   r  r  r  r  r   )r*   r  r{   r   r   r  r   r   r~   past_seen_tokensr   r:   r   decoder_layers                 r.   r=   zBitNetModel.forwards  s]    -t";<YZZ *.*;*;I*FM0*$++>O!CRC^==?de]003M<P<PQTdd  )33A6L(;;&))+%
 &"oom,oW![[)H4;;+H+HI 
	M)	*$7) /#-	 	M
	 		-0&++
 	
r/   )NNNNNNN)rB   rC   rD   r   r$   r   r   r&   r   r   r   FloatTensorr   r   r   r   r=   rE   rF   s   @r.   r   r   a  s    |    .2.204(,2626!%9
##d*9
 t+9
 &&-	9

 9
 ((4/9
 ((4/9
 $;9
 +,9
 
!9
  9
r/   r   c                   R    e Zd ZddiZdZdZ fdZee	 	 	 	 	 	 	 	 	 dde	j                  dz  de	j                  dz  de	j                  dz  dedz  d	e	j                  dz  d
e	j                  dz  dedz  de	j                  dz  dee	j                  z  dee   defd              Z xZS )BitNetForCausalLMzlm_head.weightzmodel.embed_tokens.weightNc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y )NFrK   )
r#   r$   r   r   r   r   rO   r+   lm_headr  rW   s     r.   r$   zBitNetForCausalLM.__init__  sU      (
 ++yy!3!3V5F5FUS 	r/   r  r{   r   r   r  labelsr   r   logits_to_keepr~   rn   c
                 z    | j                   d|||||||d|
}|j                  }t        |	t              rt	        |	 d      n|	}| j                  |dd|ddf         }d}|* | j                  d||| j                  j                  d|
}t        |||j                  |j                  |j                        S )a$  
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the masked language modeling loss. Indices should either be in `[0, transformers.,
            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, transformers., config.vocab_size]`.

        Example:

        ```python
        >>> from transformers import AutoTokenizer, BitNetForCausalLM

        >>> model = BitNetForCausalLM.from_pretrained("microsoft/bitnet-b1.58-2B-4T")
        >>> tokenizer = AutoTokenizer.from_pretrained("microsoft/bitnet-b1.58-2B-4T")

        >>> prompt = f'<|begin_of_text|>User: Hey, are you conscious? Can you talk to me?<|eot_id|>Assistant: '
        >>> inputs = tokenizer(prompt, return_tensors="pt")

        >>> # Generate
        >>> generate_ids = model.generate(inputs.input_ids, max_length=100)
        >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
        "User: Hey, are you conscious? Can you talk to me?Assistant: No, I'm not conscious. I'm an artificial intelligence designed to assist with information and tasks. How can I help you today?"
        ```)r  r{   r   r   r  r   r   N)logitsr  r   )lossr  r   r:   r   r   )r   r  r   r   slicer  loss_functionrI   r   r   r   r:   r   )r*   r  r{   r   r   r  r  r   r   r  r~   outputsr:   slice_indicesr  r  s                   r.   r=   zBitNetForCausalLM.forward  s    J ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r/   )	NNNNNNNNr   )rB   rC   rD   _tied_weights_keys_tp_plan_pp_planr$   r   r   r&   r   r   r   r  r   r   r   r   r   r=   rE   rF   s   @r.   r  r    s   *,GHHH  .2.204(,26*.!%26-.=
##d*=
 t+=
 &&-	=

 =
 ((4/=
   4'=
 $;=
 ((4/=
 ell*=
 +,=
 
 =
  =
r/   r  )r  r   r   )r   )r   )<collections.abcr   typingr   r&   r   activationsr   cache_utilsr   r	   
generationr
   integrationsr   r   r   masking_utilsr   modeling_flash_attention_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   configuration_bitnetr   Moduler!   rH   ra   rl   r   r   rv   r   r   r   r   r   r   r   r  __all__r   r/   r.   <module>r3     s  ( %    ! . ) f f / B 9 O K F & I I ? . Y'JBII J (J(		 "( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%4 )*E)bii E) +E)P*3 *Z><BII ><B O  $ L
' L
 L
^ M
- M
 M
` Hr/   