o
    eiP                     @   s   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 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$m%Z%m&Z& ddl'm(Z( ddl)m*Z* G dd dej+Z,dd Z-edd8ddZ.dej/de0dej/fddZ1	 d9d!ej+d"ej/d#ej/d$ej/d%ej/dB d&e2d'e2d(ee! fd)d*Z3ee.G d+d, d,ej+Z4G d-d. d.eZ5e"G d/d0 d0eZ6G d1d2 d2ej+Z7e"G d3d4 d4e6Z8e"G d5d6 d6e6eZ9g d7Z:dS ):    )Callable)OptionalN   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_func_from_hubuse_kernelized_func)create_causal_mask)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs   )Jais2Configc                       s$   e Zd Z fddZdd Z  ZS )Jais2MLPc                    s`   t    || _|j| _|j| _tj| j| j|jd| _tj| j| j|jd| _	t
|j | _d S )Nbias)super__init__confighidden_sizeintermediate_sizennLinearmlp_biasup_proj	down_projr   
hidden_actact_fnselfr!   	__class__ f/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/jais2/modeling_jais2.pyr    -   s   
zJais2MLP.__init__c                 C   s   |  | | |S N)r(   r*   r'   )r,   xr/   r/   r0   forward6   s   zJais2MLP.forward)__name__
__module____qualname__r    r3   __classcell__r/   r/   r-   r0   r   ,   s    	r   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..N   dim)shapetorchcat)r2   x1x2r/   r/   r0   rotate_half:   s   rA   rotary_pos_embc                 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.
        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_embedr/   r/   r0   apply_rotary_pos_embA   s
   

rK   hidden_states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)rL   rM   batchnum_key_value_headsslenhead_dimr/   r/   r0   	repeat_kv[   s
   0rU           modulequerykeyvalueattention_maskscalingdropoutkwargsc                 K   s   t || j}t || j}	t||dd| }
|d ur |
| }
tjj|
dtjd	|j
}
tjj|
|| jd}
t|
|	}|dd }||
fS )Nr9   r   r8   )r;   dtype)ptrainingr   )rU   num_key_value_groupsr=   matmul	transposer$   
functionalsoftmaxfloat32tor_   r]   ra   
contiguous)rW   rX   rY   rZ   r[   r\   r]   r^   
key_statesvalue_statesattn_weightsattn_outputr/   r/   r0   eager_attention_forwardg   s   
rn   c                       s   e Zd ZdZdedef fddZ				ddejde	ejejf dB d	ejdB d
e
dB dejdB dee de	ejejf fddZ  ZS )Jais2Attentionz=Multi-headed attention from 'Attention Is All You Need' paperr!   	layer_idxc                    s   t    || _|| _t|d|j|j | _|j|j | _	| jd | _
|j| _d| _tj|j|j| j |jd| _tj|j|j| j |jd| _tj|j|j| j |jd| _tj|j| j |j|jd| _d S )NrT   g      Tr   )r   r    r!   rp   getattrr"   num_attention_headsrT   rR   rb   r\   attention_dropout	is_causalr$   r%   attention_biasq_projk_projv_projo_projr,   r!   rp   r-   r/   r0   r       s(   
zJais2Attention.__init__NrL   position_embeddingsr[   past_key_valuescache_positionr^   rN   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t}|| |	|
||f| jskdn| j| jd|\}}|jg |dR   }| |}||fS )Nr8   r   r9   )rG   rF   r}   rV   )r]   r\   )r<   rT   rv   viewrd   rw   rx   rK   updaterp   r   get_interfacer!   _attn_implementationrn   ra   rs   r\   rP   ri   ry   )r,   rL   r{   r[   r|   r}   r^   input_shapehidden_shapequery_statesrj   rk   rF   rG   cache_kwargsattention_interfacerm   rl   r/   r/   r0   r3      s8   	

zJais2Attention.forward)NNNN)r4   r5   r6   __doc__r   intr    r=   Tensortupler   
LongTensorr   r   r3   r7   r/   r/   r-   r0   ro      s,    ro   c                       s   e Zd Zdedef fddZ						ddejdejdB d	ejdB d
e	dB de
dB dejdB deejejf dB dee dejfddZ  ZS )Jais2DecoderLayerr!   rp   c                    sV   t    |j| _t||d| _t|| _tj|j|j	d| _
tj|j|j	d| _d S )N)r!   rp   eps)r   r    r"   ro   	self_attnr   mlpr$   	LayerNormlayer_norm_epsinput_layernormpost_attention_layernormrz   r-   r/   r0   r       s   

zJais2DecoderLayer.__init__NFrL   r[   position_idsr|   	use_cacher}   r{   r^   rN   c              
   K   s^   |}	|  |}| jd|||||||d|\}}
|	| }|}	| |}| |}|	| }|S )N)rL   r[   r   r|   r   r}   r{   r/   )r   r   r   r   )r,   rL   r[   r   r|   r   r}   r{   r^   residual_r/   r/   r0   r3      s&   




zJais2DecoderLayer.forward)NNNFNN)r4   r5   r6   r   r   r    r=   r   r   r   boolr   r   r   r3   r7   r/   r/   r-   r0   r      s6    	
r   c                   @   sH   e Zd ZU eed< dZdZdgZdgZdZ	dZ
dZdZdZeedZdS )Jais2PreTrainedModelr!   modelTr   r|   )rL   
attentionsN)r4   r5   r6   r   __annotations__base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   ro   _can_record_outputsr/   r/   r/   r0   r      s   
 
r   c                       s~   e Zd ZU ejed< ddef fddZe			ddedB de	d de
dB d	ed
ef fddZe edd Z  ZS )Jais2RotaryEmbeddinginv_freqNr!   c                    s   t    |j| _|j| _|| _| jjd | _| j}| jdkr$t	| j }|| j|\}| _
| jd|dd | jd| dd d S )N	rope_typedefaultr   F)
persistentoriginal_inv_freq)r   r    max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr!   rope_parametersr   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r,   r!   devicerope_init_fnr   r-   r/   r0   r    
  s   


zJais2RotaryEmbedding.__init__r   ztorch.deviceseq_lenrN   ztorch.Tensorc                 C   sZ   | j d }t| ddp| j| j }d}d|tjd|dtjdj|tjd|   }||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_thetarT   Ng      ?r   r9   r_   )r   r_   )	r   rq   r"   rr   r=   arangeint64rh   float)r!   r   r   baser;   attention_factorr   r/   r/   r0   r     s   
&z4Jais2RotaryEmbedding.compute_default_rope_parametersc           
      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	|dd+ | |  
dd}tj||fdd	}| | j }| | j }	W d    n1 slw   Y  |j|jd
|	j|jd
fS )Nr   r8   r   mpscpuF)device_typeenabledr9   r:   r   )r   r   rO   r<   rh   r   
isinstancetypestrr   rd   r=   r>   rF   r   rG   r_   )
r,   r2   r   inv_freq_expandedposition_ids_expandedr   freqsembrF   rG   r/   r/   r0   r3   8  s   0&zJais2RotaryEmbedding.forwardr1   )NNN)r4   r5   r6   r=   r   r   r   r    staticmethodr   r   r   r   r   no_gradr   r3   r7   r/   r/   r-   r0   r     s&   
 

r   c                       s   e Zd Zdef fddZeee							ddej	dB dej
dB dej	dB dedB d	ejdB d
ej	dB dedB dee defddZ  ZS )
Jais2Modelr!   c                    s   t     j| _ j| _t j j| j| _t	 fddt
 jD | _tj j jd| _t d| _d| _|   d S )Nc                    s   g | ]}t  |qS r/   )r   ).0rp   r!   r/   r0   
<listcomp>Q  s    z'Jais2Model.__init__.<locals>.<listcomp>r   r   F)r   r    pad_token_idpadding_idx
vocab_sizer$   	Embeddingr"   embed_tokens
ModuleListrangenum_hidden_layerslayersr   r   normr   
rotary_embgradient_checkpointing	post_initr+   r-   r   r0   r    J  s   zJais2Model.__init__N	input_idsr[   r   r|   inputs_embedsr}   r   r^   rN   c              
   K   s   |d u |d uA rt d|d u r| |}|r!|d u r!t| jd}|d u r<|d ur-| nd}	tj|jd |jd|	 }|d u rE|	d}t
| j|||||d}
|}| j||d}| jd | jj D ]}||f|
|||||d|}qb| |}t||d	S )
Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r   )r   )r!   r   r[   r}   r|   r   )r   )r[   r{   r   r|   r   r}   )last_hidden_stater|   )
ValueErrorr   r   r!   get_seq_lengthr=   r   r<   r   rC   r   r   r   r   r   r   )r,   r   r[   r   r|   r   r}   r   r^   past_seen_tokenscausal_maskrL   r{   decoder_layerr/   r/   r0   r3   Z  sP   

	
zJais2Model.forward)NNNNNNN)r4   r5   r6   r   r    r   r   r   r=   r   r   r   FloatTensorr   r   r   r   r3   r7   r/   r/   r-   r0   r   H  s>    	
r   c                       s   e Zd ZddiZddiZddgdgfiZ fddZee																	
dde	j
d	B de	jd	B de	j
d	B ded	B de	jd	B de	j
d	B ded	B de	j
d	B dee	jB dee defddZ  ZS )Jais2ForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputrL   logitsc                    s@   t  | t|| _|j| _tj|j|jdd| _| 	  d S )NFr   )
r   r    r   r   r   r$   r%   r"   r   r   r+   r-   r/   r0   r      s
   
zJais2ForCausalLM.__init__Nr   r   r[   r   r|   r   labelsr   r}   logits_to_keepr^   rN   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  
        Example:

        ```python
        >>> from transformers import AutoTokenizer, Jais2ForCausalLM

        >>> model = Jais2ForCausalLM.from_pretrained("inceptionai/Jais-2-8B-Chat")
        >>> tokenizer = AutoTokenizer.from_pretrained("inceptionai/Jais-2-8B-Chat")

        >>> 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   r[   r   r|   r   r   r}   N)r   r   r   )lossr   r|   rL   r   r/   )r   r   r   r   slicer   loss_functionr!   r   r   r|   rL   r   )r,   r   r[   r   r|   r   r   r   r}   r   r^   outputsrL   slice_indicesr   r   r/   r/   r0   r3     s0    zJais2ForCausalLM.forward)	NNNNNNNNr   )r4   r5   r6   _tied_weights_keys_tp_plan_pp_planr    r   r   r=   r   r   r   r   r   r   r   r   r   r3   r7   r/   r/   r-   r0   r     sN    		
r   )r   r   r   )r   )rV   );collections.abcr   typingr   r=   torch.nnr$   activationsr   cache_utilsr   r   
generationr   integrationsr	   r
   masking_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   utils.output_capturingr   configuration_jais2r   Moduler   rA   rK   r   r   rU   r   rn   ro   r   r   r   r   r   __all__r/   r/   r/   r0   <module>   sh   
F-APK