
     `iS                     
   d dl mZmZ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 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$m%Z% ddl&m'Z' ddl(m)Z)  ed           G d dej*                              Z+ G d dej*                  Z,d Z-d7dZ.dej/        de0dej/        fdZ1	 d8d!ej*        d"ej/        d#ej/        d$ej/        d%eej/                 d&e2d'e2d(ee!         fd)Z3 G d* d+ej*                  Z4 G d, d-e          Z5 G d. d/ej*                  Z6e" G d0 d1e                      Z7e" G d2 d3e7                      Z8e" G d4 d5e7e                      Z9g d6Z:dS )9    )CallableOptionalUnionN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask)FlashAttentionKwargs)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)deprecate_kwarg)check_model_inputs   )BitNetConfigRMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )BitNetRMSNormư>c                     t                                                       t          j        t	          j        |                    | _        || _        dS )z<
        BitNetRMSNorm is equivalent to T5LayerNorm
        N)super__init__r   	Parametertorchonesweightvariance_epsilon)selfhidden_sizeeps	__class__s      ~/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/bitnet/modeling_bitnet.pyr$   zBitNetRMSNorm.__init__-   sD     	l5:k#:#:;; #    c                    |j         }|                    t          j                  }|                    d                              dd          }|t          j        || j        z             z  }| j        |                    |          z  S )N   T)keepdim)	dtypetor&   float32powmeanrsqrtr)   r(   )r*   hidden_statesinput_dtypevariances       r.   forwardzBitNetRMSNorm.forward5   s|    #)%((77 $$Q'',,R,>>%Ht?T4T(U(UU{]--k::::r/   c                 H    t          | j        j                   d| j         S )Nz, eps=)tupler(   shaper)   )r*   s    r.   
extra_reprzBitNetRMSNorm.extra_repr<   s&    )**II$2GIIIr/   )r!   )__name__
__module____qualname__r$   r=   rA   __classcell__r-   s   @r.   r    r    +   sb        $ $ $ $ $ $; ; ;J J J J J J 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                  | _        d S )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__A   s    !-!'!94#3T5KRWXXXy!143IPUVVV4#94;KRWXXXV./)&*BH[\\\r/   c           	          |                      |                     |                     |                     |                    |                     |          z                      }|S N)rR   rV   rT   rP   rQ   )r*   xrR   s      r.   r=   zBitNetMLP.forwardL   sU    NN4#4#4T[[PQARAR5S5SVZVbVbcdVeVe5e#f#fgg	r/   )rB   rC   rD   r   r$   r=   rE   rF   s   @r.   rH   rH   @   sZ        	]| 	] 	] 	] 	] 	] 	]      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   Q   s]    	
3"!'"+"""	#B	
3q """	#B9rc2YB''''r/   c                     |                     |          }|                     |          }| |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.
        position_ids (`torch.Tensor`, *optional*):
            Deprecated and unused.
        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position_idsunsqueeze_dimq_embedk_embeds           r.   apply_rotary_pos_embrl   X   sc    ( --
&
&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                             |||||          } |                     |||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   s   s    
 2?1D.Ehzz!!!!QQQaaa"23::5BUW\^bdlmmM  (;e(CT8TTTr/           modulequerykeyvalueattention_maskscalingdropoutkwargsc                 R   t          || j                  }t          || j                  }	t          j        ||                    dd                    |z  }
|$|d d d d d d d |j        d         f         }|
|z   }
t          j                            |
dt          j	                  
                    |j                  }
t          j                            |
|| j                  }
t          j        |
|	          }|                    dd                                          }||
fS )Nr1   r   r2   )r]   r4   )ptrainingr   )rv   num_key_value_groupsr&   matmul	transposer@   r   
functionalsoftmaxr6   r5   r4   r~   r   
contiguous)rx   ry   rz   r{   r|   r}   r~   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r.   eager_attention_forwardr      s    3 ;<<JUF$?@@L<z';';Aq'A'ABBWLL!$QQQ111.D
0@0D.D%DE#k1=((2U](SSVVW\WbccL=((6?([[L,|\::K''1--88::K$$r/   c                        e Zd ZdZdedef fdZ eddd          	 	 dd
ej	        de
ej	        ej	        f         deej	                 dee         deej                 dee         de
ej	        eej	                 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                  | _        d S )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__   sa   "
F4F&Jd4dee$*$>&B\$\!}d*!'!9i :T] JQWQf
 
 
 i :T] JQWQf
 
 
 i :T] JQWQf
 
 
 i&68JQWQf
 
 
 +6+=6CVWWWr/   past_key_valuepast_key_values4.58new_nameversionNr:   position_embeddingsr|   cache_positionr   rn   c                 n   |j         d d         }g |d| j        R }|                     |                              |                              dd          }	|                     |                              |                              dd          }
|                     |                              |                              dd          }|\  }}t          |	|
||          \  }	}
|&|||d}|                    |
|| j	        |          \  }
}t          }| j        j        dk    rt          | j        j                 } || |	|
||f| j        sdn| j        | j        d|\  }} |j        g |dR                                  }|                     |          }|                     |          }||fS )Nr2   r   r1   )rg   rf   r   eagerrw   )r~   r}   )r@   ru   r   viewr   r   r   rl   updater   r   rI   _attn_implementationr   r   r   r}   rq   r   r   r   )r*   r:   r   r|   r   r   r   input_shapehidden_shapequery_statesr   r   rf   rg   cache_kwargsattention_interfacer   r   s                     r.   r=   zBitNetAttention.forward   s    $)#2#.88b8$-88{{=1166|DDNNqRSTT[[//44\BBLLQPQRR
{{=1166|DDNNqRSTT&S#7jRUWZ#[#[ j&#&snUUL'6'='=j,X\Xfht'u'u$J(?;+w66"9$+:Z"[$7$7	%
  $}HCC$2HL	%
 	%
 	%
 	%
!\ *k);;;;;;FFHH((55kk+..L((r/   )NN)rB   rC   rD   __doc__r   intr$   r   r&   Tensorr?   r   r	   
LongTensorr   r   r=   rE   rF   s   @r.   r   r      s       GGX| X X X X X X X0 _%0A6RRR ,059+) +)|+) #5<#=>+) !.	+)
 "%+) !!12+) -.+) 
u|Xel33	4+) +) +) SR+) +) +) +) +)r/   r   c                   4    e Zd Zdedef fdZ eddd          	 	 	 	 	 	 dd
ej        de	ej                 de	ej
                 de	e         de	e         de	ej
                 de	eej        ej        f                  dee         dej        fd            Z xZS )BitNetDecoderLayerrI   r   c                 4   t                                                       |j        | _        t          ||          | _        t          |          | _        t          |j        |j                  | _	        t          |j        |j                  | _
        d S )N)rI   r   rM   )r#   r$   r+   r   	self_attnrH   mlpr    rU   input_layernormpost_attention_layernormr   s      r.   r$   zBitNetDecoderLayer.__init__   s    !-()LLLV$$,V-?VEXYYY(5f6HfNa(b(b(b%%%r/   r   r   r   r   NFr:   r|   rh   	use_cacher   r   r   rn   c                     |}	|                      |          } | j        d|||||||d|\  }}
|	|z   }|}	|                     |          }|                     |          }|	|z   }|S )N)r:   r|   rh   r   r   r   r    )r   r   r   r   )r*   r:   r|   rh   r   r   r   r   r   residual_s              r.   r=   zBitNetDecoderLayer.forward   s     !,,];;)4> 	
')%+) 3	
 	
 	
 	
q !=0 !55mDD// =0r/   )NNNFNN)rB   rC   rD   r   r   r$   r   r&   r   r   r   r	   boolr?   r   r   r=   rE   rF   s   @r.   r   r      s5       c| c c c c c c c _%0A6RRR 2637+/$)59KO | !. u/0	
 "% D> !!12 &eEL%,,F&GH +, 
   SR    r/   r   c                   |     e Zd ZU ej        ed<   ddef fdZ ej                    e	d                         Z
 xZS )BitNetRotaryEmbeddinginv_freqNrI   c                    t                                                       t          |d          rSt          |j        t
                    r9|j                            d|j                            d                    | _        nd| _        |j        | _	        |j        | _
        || _        t          | j                 | _        |                     | j        |          \  }| _        |                     d|d           | j        | _        d S )Nrope_scaling	rope_typetypedefaultr   F)
persistent)r#   r$   hasattr
isinstancer   dictgetr   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrI   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r*   rI   devicer   r-   s       r.   r$   zBitNetRotaryEmbedding.__init__  s    6>** 	'z&:Mt/T/T 	'#044[&BUBYBYZ`BaBabbDNN&DN"("@$*$B!/?+/+<+<T[&+Q+Q($(ZeDDD!%r/   c                 X   | j         d d d d f                                                             |j        d         dd                              |j                  }|d d d d d f                                         }t          |j        j        t                    r|j        j        dk    r|j        j        nd}t          j
        |d          5  |                                |                                z                      dd          }t          j        ||fd	          }|                                | j        z  }|                                | j        z  }	d d d            n# 1 swxY w Y   |                    |j        
          |	                    |j        
          fS )Nr   r2   r   mpscpuF)device_typeenabledr1   r\   )r4   )r   floatrp   r@   r5   r   r   r   strr&   autocastr   r^   rf   r   rg   r4   )
r*   rZ   rh   inv_freq_expandedposition_ids_expandedr   freqsembrf   rg   s
             r.   r=   zBitNetRotaryEmbedding.forward%  s    !M$4-8>>@@GGHZ[\H]_acdeehhijiqrr ,QQQaaaZ 8 > > @ @'1!(-'E'Ek!(-[`J`J`ahmmfk^UCCC 	5 	5&,,..1F1L1L1N1NNYYZ[]^__E)UEN333C''))d44C''))d44C		5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 vvAGv$$cff17f&;&;;;s   BE++E/2E/rY   )rB   rC   rD   r&   r   __annotations__r   r$   no_gradr   r=   rE   rF   s   @r.   r   r     s         l/ /| / / / / / /" U]__< <  _< < < < <r/   r   c                   L    e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedZdS )BitNetPreTrainedModelrI   modelTr   r   )r:   
attentionsN)rB   rC   rD   r   r   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsr   r/   r.   r   r   5  sl         &*#-.#4"5N!"&+% r/   r   c                       e Zd Zdef fdZee	 	 	 	 	 	 	 ddeej	                 deej
                 deej	                 dee         deej                 d	eej	                 d
ee         dee         defd                        Z xZS )BitNetModelrI   c                    t                                                     j        | _        j        | _        t          j        j        j        | j                  | _        t          j	        fdt          j                  D                       | _        t          j        j                  | _        t!                    | _        d| _        |                                  d S )Nc                 0    g | ]}t          |          S r   )r   ).0r   rI   s     r.   
<listcomp>z(BitNetModel.__init__.<locals>.<listcomp>Q  s$    dddy	22dddr/   rM   rI   F)r#   r$   pad_token_idpadding_idx
vocab_sizer   	Embeddingr+   embed_tokens
ModuleListrangenum_hidden_layerslayersr    rU   normr   
rotary_embgradient_checkpointing	post_initrW   s    `r.   r$   zBitNetModel.__init__J  s       !. +L):F<NPTP`aamddddE&JbDcDcddd
 
 "&"4&:MNNN	/v>>>&+# 	r/   N	input_idsr|   rh   r   inputs_embedsr   r   r   rn   c           
      N   |d u |d uz  rt          d          ||                     |          }|r|t          | j                  }|B||                                nd}	t          j        |	|	|j        d         z   |j                  }||	                    d          }t          | j        |||||          }
|}|                     ||          }| j        d | j        j                 D ]} ||f|
||||d|}|                     |          }t          ||          S )	Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r   )r   )rI   input_embedsr|   r   r   rh   )r|   rh   r   r   r   )last_hidden_stater   )
ValueErrorr   r
   rI   get_seq_lengthr&   aranger@   r   rc   r   r  r  r  r  r   )r*   r  r|   rh   r   r  r   r   r   past_seen_tokensr   r:   r   decoder_layers                 r.   r=   zBitNetModel.forwardZ  s    -t";< 	[YZZZ *.*;*;I*F*FM 	?0*$+>>>O!CRC^==???de+0< "2]5H5K"KTaTh, , ,N )33A66L(;&))+%
 
 
 &"oom\JJ![)H4;+H)HI 		 		M)M*) /-$7   MM 		-00&++
 
 
 	
r/   )NNNNNNN)rB   rC   rD   r   r$   r   r   r   r&   r   r   r	   FloatTensorr   r   r   r   r=   rE   rF   s   @r.   r   r   H  s       |         151537+/5959$(8
 8
E,-8
 !.8
 u/0	8

 "%8
   128
 !!128
 D>8
 +,8
 
!8
 8
 8
 ^ 8
 8
 8
 8
 8
r/   r   c                   V    e Zd ZdgZdZdZ fdZee	 	 	 	 	 	 	 	 	 dde	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
j                 deee
j        f         dee         defd                        Z xZS )BitNetForCausalLMzlm_head.weightNc                     t                                          |           t          |          | _        |j        | _        t          j        |j        |j        d          | _        | 	                                 d S )NFrK   )
r#   r$   r   r   r   r   rO   r+   lm_headr  rW   s     r.   r$   zBitNetForCausalLM.__init__  sj        ((
 +y!3V5FUSSS 	r/   r   r  r|   rh   r   r  labelsr   r   logits_to_keepr   rn   c
                 R    | j         d|||||||d|
}|j        }t          |	t                    rt	          |	 d          n|	}|                     |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|   rh   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|   rh   r   r  r  r   r   r  r   outputsr:   slice_indicesr  r  s                   r.   r=   zBitNetForCausalLM.forward  s    J ,64: 	,
)%+')	,
 	,
 	,
 	,
  18B>SV8W8Wk~ot444]kmAAA}aaa,?@AA%4%pVFt{OeppioppD%#3!/)
 
 
 	
r/   )	NNNNNNNNr   )rB   rC   rD   _tied_weights_keys_tp_plan_pp_planr$   r   r   r   r&   r   r   r	   r  r   r   r   r   r   r   r=   rE   rF   s   @r.   r  r    sM       *+HH      151537+/59-1$(5934=
 =
E,-=
 !.=
 u/0	=

 "%=
   12=
 )*=
 D>=
 !!12=
 c5</0=
 +,=
 
 =
 =
 =
 ^ =
 =
 =
 =
 =
r/   r  )r  r   r   )Nr   )rw   );typingr   r   r   r&   r   activationsr   cache_utilsr	   r
   
generationr   integrationsr   masking_utilsr   modeling_flash_attention_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.deprecationr   utils.genericr   configuration_bitnetr   Moduler    rH   ra   rl   r   r   rv   r   r   r   r   r   r   r   r  __all__r   r/   r.   <module>r4     s  * - , , , , , , , , ,        ! ! ! ! ! ! . . . . . . . . ) ) ) ) ) ) 7 7 7 7 7 7 / / / / / / B B B B B B 9 9 9 9 9 9 O O O O O O O O K K K K K K K K F F F F F F F F & & & & & & I I I I I I I I I I 0 0 0 0 0 0 / / / / / / . . . . . . Y''J J J J JBI J J ('J(    	   "( ( (   6	UU\ 	U# 	U%, 	U 	U 	U 	U& % %I%<% 
% <	%
 U\*% % % '(% % % %4G) G) G) G) G)bi G) G) G)T+ + + + +3 + + +\!< !< !< !< !<BI !< !< !<H     O   $ K
 K
 K
 K
 K
' K
 K
 K
\ M
 M
 M
 M
 M
- M
 M
 M
` H
G
Gr/   