a
    hQ                  
   @   s
  d dl Z 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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$m%Z% ddl&m'Z' ddl(m)Z) G dd dej*Z+G dd dej*Z,G dd dej*Z-ej.e/ej.dddZ0d2ej*ej.ej.ej.eej. e1e1ee! dddZ2dd  Z3d3d!d"Z4G d#d$ d$ej*Z5G d%d& d&eZ6e"G d'd( d(eZ7e"G d)d* d*e7Z8e"G d+d, d,e7eZ9G d-d. d.ee7Z:G d/d0 d0ee7Z;g d1Z<dS )4    N)CallableOptionalUnion   )ACT2FN)CacheDynamicCache)GenerationMixin)create_causal_mask) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)deprecate_kwarg)check_model_inputs   )HeliumConfigc                       s.   e Zd Zd fdd	Zdd Zdd Z  ZS )	HeliumRMSNormư>c                    s&   t    tt|| _|| _d S N)super__init__nn	ParametertorchZonesweightvariance_epsilon)selfhidden_sizeeps	__class__ f/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/models/helium/modeling_helium.pyr    0   s    
zHeliumRMSNorm.__init__c                 C   sR   |j }|tj}|djddd}|t|| j  }| jtj| |S )N   T)Zkeepdim)	dtypetor#   float32powmeanZrsqrtr%   r$   )r&   hidden_statesZinput_dtypeZvariancer+   r+   r,   forward5   s
    zHeliumRMSNorm.forwardc                 C   s   t | jj d| j S )Nz, eps=)tupler$   shaper%   )r&   r+   r+   r,   
extra_repr<   s    zHeliumRMSNorm.extra_repr)r   )__name__
__module____qualname__r    r5   r8   __classcell__r+   r+   r)   r,   r   /   s   r   c                       sD   e Zd ZU ejed< ded fddZe e	dd Z
  ZS )	HeliumRotaryEmbeddinginv_freqNconfigc                    s   t    t|dr:t|jtr:|jd|jd| _nd| _|j| _	|j| _
|| _t| j | _| | j|\}| _| jd|dd | j| _d S )Nrope_scaling	rope_typetypedefaultr>   F)
persistent)r   r    hasattr
isinstancerA   dictgetrB   Zmax_position_embeddingsZmax_seq_len_cachedZoriginal_max_seq_lenr@   r   Zrope_init_fnattention_scalingZregister_bufferr>   Zoriginal_inv_freq)r&   r@   devicer>   r)   r+   r,   r    C   s    
zHeliumRotaryEmbedding.__init__c           
      C   s   | j d d d d f  |jd dd|j}|d d d d d f  }t|jjtrl|jjdkrl|jjnd}t	j
|ddV | |  dd}t	j||fdd	}| | j }| | j }	W d    n1 s0    Y  |j|jd
|	j|jd
fS )Nr   r.   r   ZmpscpuF)device_typeZenabledr-   dim)r/   )r>   floatexpandr7   r0   rK   rG   rC   strr#   Zautocast	transposecatcosrJ   sinr/   )
r&   xposition_idsZinv_freq_expandedZposition_ids_expandedrM   ZfreqsZembrU   rV   r+   r+   r,   r5   T   s    0&,zHeliumRotaryEmbedding.forward)N)r9   r:   r;   r#   Tensor__annotations__r   r    Zno_gradr   r5   r<   r+   r+   r)   r,   r=   @   s
   

r=   c                       s$   e Zd Z fddZdd Z  ZS )	HeliumMLPc                    sx   t    || _|j| _|j| _tj| j| j|jd| _tj| j| j|jd| _	tj| j| j|jd| _
t|j | _d S )NZbias)r   r    r@   r'   Zintermediate_sizer!   LinearZmlp_bias	gate_projup_proj	down_projr   Z
hidden_actact_fnr&   r@   r)   r+   r,   r    e   s    
zHeliumMLP.__init__c                 C   s$   |  | | || | }|S r   )r`   ra   r^   r_   )r&   rW   r`   r+   r+   r,   r5   o   s     zHeliumMLP.forward)r9   r:   r;   r    r5   r<   r+   r+   r)   r,   r[   d   s   
r[   )r4   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)r7   rQ   reshape)r4   rc   batchnum_key_value_headsslenhead_dimr+   r+   r,   	repeat_kvt   s
    0rj           )modulequerykeyvalueattention_maskscalingdropoutkwargsc                 K   s   t || j}t || j}	t||dd| }
|d urf|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.   )rO   r/   )ptrainingr   )rj   num_key_value_groupsr#   matmulrS   r7   r!   Z
functionalZsoftmaxr1   r0   r/   rr   rv   
contiguous)rl   rm   rn   ro   rp   rq   rr   rs   
key_statesvalue_statesattn_weightscausal_maskattn_outputr+   r+   r,   eager_attention_forward   s    
&r   c                 C   s>   | ddddf }| ddddf }t j| |fdddS )	z*Rotates half the hidden dims of the input..r   Nr-   r   r.   rN   rt   )r#   stackflatten)rW   x1Zx2r+   r+   r,   rotate_half   s    r   c                 C   s   | |}| |}|dd|jd d f jddd}|dd|jd d f jddd}| | 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.
    .Nr.   r-   rN   )	unsqueezer7   Zrepeat_interleaver   )qkrU   rV   rX   Zunsqueeze_dimZq_embedZk_embedr+   r+   r,   apply_rotary_pos_emb   s    

$$r   c                       s   e Zd ZdZdeee d fddZedddd	de	j
ee	j
e	j
f ee	j
 ee ee	j ee ee	j
e	j
f d
ddZ  ZS )HeliumAttentionz=Multi-headed attention from 'Attention Is All You Need' paperNr@   	layer_idxc                    s   t    || _|| _t|d|j|j | _|j|j | _	dt
| 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|jdd| _d S )Nri   r   Tr\   F)r   r    r@   r   getattrr'   Znum_attention_headsri   rg   rw   mathsqrtrq   attention_dropoutZ	is_causalr!   r]   Zattention_biasq_projk_projv_projo_projr&   r@   r   r)   r+   r,   r       s$    
zHeliumAttention.__init__past_key_valuepast_key_values4.58new_nameversion)r4   position_embeddingsrp   r   cache_positionrs   rd   c                 K   s$  |j d d }g |d| jR }| ||dd}	| ||dd}
| ||dd}|\}}t|	|
||\}	}
|d ur|||d}||
|| j	|\}
}t
}| jjdkrt| jj }|| |	|
||f| jsdn| j| jd|\}}|jg |dR   }| |}||fS )Nr.   r   r-   )rV   rU   r   eagerrk   )rr   rq   )r7   ri   r   viewrS   r   r   r   updater   r   r@   Z_attn_implementationr   rv   r   rq   re   ry   r   )r&   r4   r   rp   r   r   rs   Zinput_shapeZhidden_shapeZquery_statesrz   r{   rU   rV   Zcache_kwargsZattention_interfacer~   r|   r+   r+   r,   r5      s8    


zHeliumAttention.forward)N)NN)r9   r:   r;   __doc__r   r   intr    r   r#   rY   r6   r   
LongTensorr   r   r5   r<   r+   r+   r)   r,   r      s     r   c                       s   e Zd Zdeee d fddZedddddej	eej	 eej
 ee ee eej
 eeej	ej	f  ee ej	d
	ddZ  ZS )HeliumDecoderLayerNr   c                    sR   t    |j| _t||d| _t|| _t|j|jd| _	t|j|jd| _
d S )Nr   r(   )r   r    r'   r   	self_attnr[   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr   r)   r+   r,   r      s    

zHeliumDecoderLayer.__init__r   r   r   r   F)	r4   rp   rX   r   	use_cacher   r   rs   rd   c              
   K   s^   |}	|  |}| jf |||||||d|\}}
|	| }|}	| |}| |}|	| }|S )N)r4   rp   rX   r   r   r   r   )r   r   r   r   )r&   r4   rp   rX   r   r   r   r   rs   Zresidual_r+   r+   r,   r5     s&    




zHeliumDecoderLayer.forward)N)NNNFNN)r9   r:   r;   r   r   r   r    r   r#   rY   r   r   boolr6   r   r   r5   r<   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 )HeliumPreTrainedModelr@   modelTr   r   )r4   
attentionsN)r9   r:   r;   r   rZ   Zbase_model_prefixZsupports_gradient_checkpointingZ_no_split_modulesZ_skip_keys_device_placementZ_supports_flash_attnZ_supports_sdpaZ_supports_flex_attnZ_can_compile_fullgraphZ_supports_attention_backendr   r   Z_can_record_outputsr+   r+   r+   r,   r   5  s   
r   c                       st   e Zd Zed fddZeedeej	 eej
 eej	 ee eej eej	 ee ee ed	ddZ  ZS )	HeliumModelr?   c                    s   t     j| _ j| _t j j| j| _t	 fddt
 jD | _t j jd| _t | _d| _|   d S )Nc                    s   g | ]}t  |qS r+   )r   ).0r   r?   r+   r,   
<listcomp>Q      z(HeliumModel.__init__.<locals>.<listcomp>r   F)r   r    Zpad_token_idZpadding_idx
vocab_sizer!   Z	Embeddingr'   embed_tokensZ
ModuleListrangenum_hidden_layerslayersr   r   normr=   
rotary_embZgradient_checkpointing	post_initrb   r)   r?   r,   r    J  s    
zHeliumModel.__init__N)		input_idsrp   rX   r   inputs_embedsr   r   rs   rd   c              	   K   s   |d u |d uA rt d|d u r*| |}|rB|d u rBt| jd}|d u rz|d urZ| nd}	tj|	|	|jd  |jd}|d u r|	d}t
| j|||||d}
|}| ||}| jd | jj D ] }||f|
||||d|}q| |}t||dS )	Nz:You must specify exactly one of input_ids or inputs_embedsr?   r   r   )rK   )r@   Zinput_embedsrp   r   r   rX   )rp   rX   r   r   r   )last_hidden_stater   )
ValueErrorr   r   r@   Zget_seq_lengthr#   Zaranger7   rK   r   r
   r   r   r   r   r   )r&   r   rp   rX   r   r   r   r   rs   Zpast_seen_tokensr}   r4   r   Zdecoder_layerr+   r+   r,   r5   Z  sP    

	

zHeliumModel.forward)NNNNNNN)r9   r:   r;   r   r    r   r   r   r#   r   rY   r   FloatTensorr   r   r   r   r5   r<   r+   r+   r)   r,   r   H  s*          r   c                       s   e Zd ZdgZddiZddgdgfiZ fddZeede	e
j e	e
j e	e
j e	e e	e
j e	e
j e	e e	e
j eee
jf ee ed
ddZ  ZS )HeliumForCausalLMzlm_head.weightlm_headZcolwise_repr4   logitsc                    s@   t  | t|| _|j| _tj|j|jdd| _| 	  d S )NFr\   )
r   r    r   r   r   r!   r]   r'   r   r   rb   r)   r+   r,   r      s
    
zHeliumForCausalLM.__init__Nr   )r   rp   rX   r   r   labelsr   r   logits_to_keeprs   rd   c
              
   K   s   | j f |||||||d|
}|j}t|	tr<t|	 dn|	}| |dd|ddf }d}|dur| jf ||| jjd|
}t	|||j
|j|jdS )a  
        Example:

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

        >>> model = HeliumForCausalLM.from_pretrained("google/helium-7b")
        >>> tokenizer = AutoTokenizer.from_pretrained("google/helium-7b")

        >>> prompt = "What is your favorite condiment?"
        >>> 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]
        "What is your favorite condiment?"
        ```)r   rp   rX   r   r   r   r   N)r   r   r   )lossr   r   r4   r   )r   r   rG   r   slicer   Zloss_functionr@   r   r   r   r4   r   )r&   r   rp   rX   r   r   r   r   r   r   rs   outputsr4   Zslice_indicesr   r   r+   r+   r,   r5     s0     zHeliumForCausalLM.forward)	NNNNNNNNr   )r9   r:   r;   Z_tied_weights_keysZ_tp_planZ_pp_planr    r   r   r   r#   r   rY   r   r   r   r   r   r   r   r   r5   r<   r+   r+   r)   r,   r     s8   	         r   c                   @   s   e Zd ZdS )HeliumForSequenceClassificationNr9   r:   r;   r+   r+   r+   r,   r     s   r   c                   @   s   e Zd ZdS )HeliumForTokenClassificationNr   r+   r+   r+   r,   r     s   r   )r   r   r   r   r   )rk   )Nr   )=r   typingr   r   r   r#   Ztorch.nnr!   Zactivationsr   Zcache_utilsr   r   Z
generationr	   Zmasking_utilsr
   Zmodeling_layersr   r   r   Zmodeling_outputsr   r   Zmodeling_rope_utilsr   r   Zmodeling_utilsr   r   Zprocessing_utilsr   utilsr   r   r   Zutils.deprecationr   Zutils.genericr   Zconfiguration_heliumr   Moduler   r=   r[   rY   r   rj   rP   r   r   r   r   r   r   r   r   r   r   __all__r+   r+   r+   r,   <module>   sX   $ 
!E.NK