o
    iS                     @   s
  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$m%Z% ddl&m'Z' ddl(m)Z) edG dd dej*Z+G dd dej*Z,dd Z-d;ddZ.dej/de0d ej/fd!d"Z1	#d<d$ej*d%ej/d&ej/d'ej/d(eej/ d)e2d*e2d+ee! fd,d-Z3G d.d/ d/ej*Z4G d0d1 d1eZ5G d2d3 d3ej*Z6e"G d4d5 d5eZ7e"G d6d7 d7e7Z8e"G d8d9 d9e7eZ9g d:Z:dS )=    )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                       s.   e Zd Zd fdd	Zdd Zdd Z  ZS )	BitNetRMSNormư>c                    s&   t    tt|| _|| _dS )z<
        BitNetRMSNorm is equivalent to T5LayerNorm
        N)super__init__r   	Parametertorchonesweightvariance_epsilon)selfhidden_sizeeps	__class__ g/home/ubuntu/veenaModal/venv/lib/python3.10/site-packages/transformers/models/bitnet/modeling_bitnet.pyr!   -   s   

zBitNetRMSNorm.__init__c                 C   sJ   |j }|tj}|djddd}|t|| j  }| j|| S )N   T)keepdim)	dtypetor#   float32powmeanrsqrtr&   r%   )r'   hidden_statesinput_dtypevariancer,   r,   r-   forward5   s
   zBitNetRMSNorm.forwardc                 C   s   t | jj d| j S )Nz, eps=)tupler%   shaper&   )r'   r,   r,   r-   
extra_repr<   s   zBitNetRMSNorm.extra_repr)r   )__name__
__module____qualname__r!   r:   r=   __classcell__r,   r,   r*   r-   r   +   s    r   c                       s*   e Zd Zdef fddZdd Z  ZS )	BitNetMLPconfigc                    s   t    || _|j| _|j| _tj| j| jdd| _tj| j| jdd| _tj| j| jdd| _	t
|j | _t|j|jd| _d S )NFbiasr)   )r    r!   rC   r(   intermediate_sizer   Linear	gate_projup_proj	down_projr   
hidden_actact_fnr   rms_norm_epsffn_sub_normr'   rC   r*   r,   r-   r!   A   s   
zBitNetMLP.__init__c              	   C   s*   |  | | | || | }|S N)rK   rO   rM   rI   rJ   )r'   xrK   r,   r,   r-   r:   L   s   &zBitNetMLP.forward)r>   r?   r@   r   r!   r:   rA   r,   r,   r*   r-   rB   @   s    rB   c                 C   sH   | dd| j d d f }| d| j d d df }tj| |fddS )z*Rotates half the hidden dims of the input..Nr/   r.   dim)r<   r#   cat)rR   x1x2r,   r,   r-   rotate_halfQ   s   rX   c                 C   sD   | |}| |}| | t| |  }|| t||  }||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.
    )	unsqueezerX   )qkcossinposition_idsunsqueeze_dimq_embedk_embedr,   r,   r-   apply_rotary_pos_embX   s
   

rb   r7   n_repreturnc                 C   s^   | j \}}}}|dkr| S | dddddddddf |||||} | ||| ||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)r7   rc   batchnum_key_value_headsslenhead_dimr,   r,   r-   	repeat_kvs   s
   0rk           modulequerykeyvalueattention_maskscalingdropoutkwargsc                 K   s   t || j}t || j}	t||dd| }
|d ur3|d d d d d d d |jd f }|
| }
tjj|
dtj	d
|j}
tjj|
|| jd}
t|
|	}|dd }||
fS )Nr.   r   r/   )rT   r1   )ptrainingr   )rk   num_key_value_groupsr#   matmul	transposer<   r   
functionalsoftmaxr3   r2   r1   rs   rw   
contiguous)rm   rn   ro   rp   rq   rr   rs   rt   
key_statesvalue_statesattn_weightscausal_maskattn_outputr,   r,   r-   eager_attention_forward   s   
&r   c                       s   e Zd ZdZdedef fddZed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dZ  ZS )BitNetAttentionz=Multi-headed attention from 'Attention Is All You Need' paperrC   	layer_idxc                    s   t    || _|| _t|d|j|j | _|j|j | _	| jd | _
|j| _d| _tj|j|j| j |jd| _tj|j|j| j |jd| _tj|j|j| j |jd| _tj|j| j |j|jd| _t|j|jd| _d S )Nrj   g      TrD   rF   )r    r!   rC   r   getattrr(   num_attention_headsrj   rh   rx   rr   attention_dropout	is_causalr   rH   attention_biasq_projk_projv_projo_projr   rN   attn_sub_normr'   rC   r   r*   r,   r-   r!      s*   
zBitNetAttention.__init__past_key_valuepast_key_values4.58new_nameversionNr7   position_embeddingsrq   cache_positionrt   rd   c                 K   s.  |j d d }g |d| jR }| ||dd}	| ||dd}
| ||dd}|\}}t|	|
||\}	}
|d urW|||d}||
|| j	|\}
}t
}| jjdkret| jj }|| |	|
||f| jsqdn| j| jd|\}}|jg |dR   }| |}| |}||fS )Nr/   r   r.   )r]   r\   r   eagerrl   )rs   rr   )r<   rj   r   viewrz   r   r   rb   updater   r   rC   _attn_implementationr   rw   r   rr   rf   r}   r   r   )r'   r7   r   rq   r   r   rt   input_shapehidden_shapequery_statesr~   r   r\   r]   cache_kwargsattention_interfacer   r   r,   r,   r-   r:      s:   



zBitNetAttention.forward)NN)r>   r?   r@   __doc__r   intr!   r   r#   Tensorr;   r   r   
LongTensorr   r   r:   rA   r,   r,   r*   r-   r      s*    r   c                       s   e Zd Zdedef fddZed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dZ  ZS )BitNetDecoderLayerrC   r   c                    sR   t    |j| _t||d| _t|| _t|j|jd| _	t|j|jd| _
d S )N)rC   r   rF   )r    r!   r(   r   	self_attnrB   mlpr   rN   input_layernormpost_attention_layernormr   r*   r,   r-   r!      s   

zBitNetDecoderLayer.__init__r   r   r   r   NFr7   rq   r^   	use_cacher   r   rt   rd   c              
   K   s^   |}	|  |}| jd|||||||d|\}}
|	| }|}	| |}| |}|	| }|S )N)r7   rq   r^   r   r   r   r   r,   )r   r   r   r   )r'   r7   rq   r^   r   r   r   r   rt   residual_r,   r,   r-   r:      s&   




zBitNetDecoderLayer.forward)NNNFNN)r>   r?   r@   r   r   r!   r   r#   r   r   r   r   boolr;   r   r   r:   rA   r,   r,   r*   r-   r      s8    
	
r   c                       sD   e Zd ZU ejed< ddef fddZe e	dd Z
  ZS )	BitNetRotaryEmbeddinginv_freqNrC   c                    s   t    t|drt|jtr|jd|jd| _nd| _|j| _	|j| _
|| _t| j | _| | j|\}| _| jd|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_lenrC   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r'   rC   devicer   r*   r,   r-   r!     s   
zBitNetRotaryEmbedding.__init__c           
      C   s   | j d d d d f  |jd dd|j}|d d d d d f  }t|jjtr6|jjdkr6|jjnd}t	j
|dd+ | |  dd}t	j||fdd	}| | j }| | j }	W d    n1 smw   Y  |j|jd
|	j|jd
fS )Nr   r/   r   mpscpuF)device_typeenabledr.   rS   )r1   )r   floatre   r<   r2   r   r   r   strr#   autocastrz   rU   r\   r   r]   r1   )
r'   rR   r^   inv_freq_expandedposition_ids_expandedr   freqsembr\   r]   r,   r,   r-   r:   %  s   0&zBitNetRotaryEmbedding.forwardrQ   )r>   r?   r@   r#   r   __annotations__r   r!   no_gradr   r:   rA   r,   r,   r*   r-   r     s   
 
r   c                   @   sH   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 )BitNetPreTrainedModelrC   modelTr   r   )r7   
attentionsN)r>   r?   r@   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  s   
 
r   c                       s   e Zd Zdef fd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dZ  ZS )BitNetModelrC   c                    s   t     j| _ j| _t j j| j| _t	 fddt
 jD | _t j jd| _t d| _d| _|   d S )Nc                    s   g | ]}t  |qS r,   )r   ).0r   rC   r,   r-   
<listcomp>Q  s    z(BitNetModel.__init__.<locals>.<listcomp>rF   r   F)r    r!   pad_token_idpadding_idx
vocab_sizer   	Embeddingr(   embed_tokens
ModuleListrangenum_hidden_layerslayersr   rN   normr   
rotary_embgradient_checkpointing	post_initrP   r*   r   r-   r!   J  s   zBitNetModel.__init__N	input_idsrq   r^   r   inputs_embedsr   r   rt   rd   c              	   K   s   |d u |d uA rt d|d u r| |}|r!|d u r!t| jd}|d u r=|d ur-| nd}	tj|	|	|jd  |jd}|d u rF|	d}t
| j|||||d}
|}| ||}| jd | jj D ]}||f|
||||d|}qb| |}t||dS )	Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r   )r   )rC   input_embedsrq   r   r   r^   )rq   r^   r   r   r   )last_hidden_stater   )
ValueErrorr   r	   rC   get_seq_lengthr#   aranger<   r   rY   r   r   r   r   r   r   )r'   r   rq   r^   r   r   r   r   rt   past_seen_tokensr   r7   r   decoder_layerr,   r,   r-   r:   Z  sP   

	

zBitNetModel.forward)NNNNNNN)r>   r?   r@   r   r!   r   r   r   r#   r   r   r   FloatTensorr   r   r   r   r:   rA   r,   r,   r*   r-   r   H  s<    	
r   c                       s   e Zd ZdgZdZdZ fd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dZ  ZS )BitNetForCausalLMzlm_head.weightNc                    s@   t  | t|| _|j| _tj|j|jdd| _| 	  d S )NFrD   )
r    r!   r   r   r   r   rH   r(   lm_headr   rP   r*   r,   r-   r!     s
   
zBitNetForCausalLM.__init__r   r   rq   r^   r   r   labelsr   r   logits_to_keeprt   rd   c
              
   K   s   | j d|||||||d|
}|j}t|	trt|	 dn|	}| |dd|ddf }d}|durB| jd||| jjd|
}t	|||j
|j|jd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   rq   r^   r   r   r   r   N)logitsr   r   )lossr   r   r7   r   r,   )r   r   r   r   slicer   loss_functionrC   r   r   r   r7   r   )r'   r   rq   r^   r   r   r   r   r   r   rt   outputsr7   slice_indicesr   r   r,   r,   r-   r:     s0   %zBitNetForCausalLM.forward)	NNNNNNNNr   )r>   r?   r@   _tied_weights_keys_tp_plan_pp_planr!   r   r   r   r#   r   r   r   r   r   r   r   r   r   r   r:   rA   r,   r,   r*   r-   r     sN    		
r   )r   r   r   )Nr   )rl   );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   rB   rX   rb   r   r   rk   r   r   r   r   r   r   r   r   __all__r,   r,   r,   r-   <module>   sh   

J.$NP