
    iW                     r   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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ej\                        Z/d Z0 ed      d:d       Z1dejd                  de3dejd                  fdZ4	 d;dej\                  d ejd                  d!ejd                  d"ejd                  d#ejd                  dz  d$e5d%e5d&e"e$   fd'Z6 ee1       G d( d)ej\                               Z7 ed*       G d+ d,ej\                               Z8 G d- d.ej\                        Z9 G d/ d0e      Z:e% G d1 d2e              Z; G d3 d4e      Z<e% G d5 d6e;             Z=e% G d7 d8e;e             Z>g d9Z?y)<    )Callable)OptionalN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernel_func_from_hubuse_kernelized_func)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs)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   )	CwmConfigc                        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 )CwmRotaryEmbeddinginv_freqNconfigc                    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)super__init__max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr$   rope_parametersr&   compute_default_rope_parametersr   attention_scalingregister_bufferclone)selfr$   devicerope_init_fnr#   	__class__s        `/mnt/e/genesis-system/.venv/lib/python3.12/site-packages/transformers/models/cwm/modeling_cwm.pyr+   zCwmRotaryEmbedding.__init__0   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuU    r5   ztorch.deviceseq_lenreturnz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_thetahead_dimNg      ?r      dtype)r5   rA   )	r/   getattrhidden_sizenum_attention_headstorcharangeint64tofloat)r$   r5   r:   basedimattention_factorr#   s          r8   r0   z2CwmRotaryEmbedding.compute_default_rope_parameters@   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r9   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   r   mpscpuF)device_typeenabledr?   rK   r@   )r#   rI   expandshaperH   r5   
isinstancetypestrr   	transposerE   catcosr1   sinrA   )
r4   xposition_idsinv_freq_expandedposition_ids_expandedrQ   freqsembr[   r\   s
             r8   forwardzCwmRotaryEmbedding.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$N)NNN)__name__
__module____qualname__rE   Tensor__annotations__r    r+   staticmethodr   inttuplerI   r0   no_gradr   rc   __classcell__r7   s   @r8   r"   r"   -   s    llVy V  #'+/"*D *(* t* 
~u$	%	* *: U]]_<  <r9   r"   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..NrN   r?   rS   )rU   rE   rZ   )r]   x1x2s      r8   rotate_halfrs   n   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r9   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.
    )	unsqueezers   )qkr[   r\   unsqueeze_dimq_embedk_embeds          r8   apply_rotary_pos_embr|   u   sY    & --
&C
--
&C3w;q>C/0G3w;q>C/0GGr9   hidden_statesn_repr;   c                     | 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)rU   rT   reshape)r}   r~   batchnum_key_value_headsslenr>   s         r8   	repeat_kvr      so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr9   modulequerykeyvalueattention_maskscalingdropoutkwargsc                    t        || j                        }t        || j                        }	t        j                  ||j	                  dd            |z  }
||
|z   }
t
        j                  j                  |
dt        j                        j                  |j                        }
t
        j                  j                  |
|| j                        }
t        j                  |
|	      }|j	                  dd      j                         }||
fS )Nr?   r   rN   )rK   rA   )ptrainingr   )r   num_key_value_groupsrE   matmulrY   r   
functionalsoftmaxfloat32rH   rA   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightsattn_outputs               r8   eager_attention_forwardr      s     3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!#n4==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r9   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 )CwmAttentionz=Multi-headed attention from 'Attention Is All You Need' paperr$   	layer_idxc                    t         |           t        |d      r|j                  |   nd | _        || _        || _        t        |d|j                  |j                  z        | _
        |j                  |j                  z  | _        | j                  dz  | _        |j                  | _        d| _        t         j"                  j%                  |j                  |j                  | j                  z  d      | _        t         j"                  j%                  |j                  |j                  | j                  z  d      | _        t         j"                  j%                  |j                  |j                  | j                  z  d      | _        t#        j$                  |j                  | j                  z  |j                  d      | _        | j                  dk(  r|j.                  | _        y d | _        y )Nlayer_typesr>   g      TFbiassliding_attention)r*   r+   hasattrr   
layer_typer$   r   rB   rC   rD   r>   r   r   r   attention_dropout	is_causalrE   r   Linearq_projk_projv_projo_projsliding_windowr4   r$   r   r7   s      r8   r+   zCwmAttention.__init__   s~   ;B6=;Y&,,Y7_c"
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9hhoof&8&8&:T:TW[WdWd:dkpoqhhoof&8&8&:T:TW[WdWd:dkpoqhhoof&8&8&:T:TW[WdWd:dkpoqii : :T]] JFL^L^ejk7;J]7]f33cgr9   Nr}   position_embeddingsr   past_key_valuescache_positionr   r;   c                 .   |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        j                  | j                  j                  t              } || |	|
||f| j                  sdn| j                   | j"                  | j$                  d|\  }} |j&                  g |d j)                         }| j+                  |      }||fS )NrN   r   r?   )r\   r[   r           )r   r   r   )rU   r>   r   viewrY   r   r   r|   updater   r   get_interfacer$   _attn_implementationr   r   r   r   r   r   r   r   )r4   r}   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   r[   r\   cache_kwargsattention_interfacer   r   s                     r8   rc   zCwmAttention.forward   s    $))#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$2H2HLL..
%
 
%
!\ *k));;;;FFHkk+.L((r9   )NN)re   rf   rg   __doc__r    rk   r+   rE   rh   rl   r   
LongTensorr   r   rc   rn   ro   s   @r8   r   r      s    Ghy hS h* )-26*)||*) #5<<#=>*) t+	*)
 *) ((4/*) -.*) 
u||U\\D00	1*)r9   r   RMSNormc                   h     e Zd Zddeddf fdZdej                  dej                  fdZd Z xZ	S )	
CwmRMSNormepsr;   Nc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z9
        CwmRMSNorm is equivalent to T5LayerNorm
        N)r*   r+   r   	ParameterrE   onesweightvariance_epsilon)r4   rC   r   r7   s      r8   r+   zCwmRMSNorm.__init__   s1     	ll5::k#:; #r9   r}   c                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )Nr?   rN   T)keepdim)	rA   rH   rE   r   powmeanrsqrtr   r   )r4   r}   input_dtypevariances       r8   rc   zCwmRMSNorm.forward   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r9   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)rl   r   rU   r   )r4   s    r8   
extra_reprzCwmRMSNorm.extra_repr  s*    ))*+6$2G2G1HIIr9   )gư>)
re   rf   rg   rI   r+   rE   rh   rc   r   rn   ro   s   @r8   r   r      s7    $ $$ $;U\\ ;ell ;Jr9   r   c                   $     e Zd Z fdZd Z xZS )CwmMLPc                    t         |           || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  |j                        | _        t        j                  | j                  | j                  |j                        | _	        t        j                  | j                  | j                  |j                        | _
        t        |j                     | _        y )Nr   )r*   r+   r$   rC   intermediate_sizer   r   mlp_bias	gate_projup_proj	down_projr   
hidden_actact_fnr4   r$   r7   s     r8   r+   zCwmMLP.__init__  s    !--!'!9!94#3#3T5K5KRXRaRabyy!1!143I3IPVP_P_`4#9#94;K;KRXRaRabV../r9   c                     | j                  | j                  | j                  |            | j                  |      z        }|S rd   )r   r   r   r   )r4   r]   r   s      r8   rc   zCwmMLP.forward  s6    NN4;;t~~a/@#ADLLQRO#ST	r9   )re   rf   rg   r+   rc   rn   ro   s   @r8   r   r   
  s    0r9   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 )CwmDecoderLayerr$   r   c                 H   t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        |j                  |   | _        y )N)r$   r   r   )r*   r+   rC   r   	self_attnr   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr   attention_typer   s      r8   r+   zCwmDecoderLayer.__init__  s~    !--%VyI&>)&*<*<&BUBUV(263E3E6K^K^(_%$00;r9   Nr}   r   r^   r   	use_cacher   r   r   r;   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r}   r   r^   r   r   r   r    )r   r   r   r   )r4   r}   r   r^   r   r   r   r   r   residual_s              r8   rc   zCwmDecoderLayer.forward%  s     !,,];)4>> 	
')%+) 3	
 	
q !=0 !55mD/ =0r9   )NNNFNN)re   rf   rg   r    rk   r+   rE   rh   r   r   boolrl   r   r   rc   rn   ro   s   @r8   r   r     s    <y <S < /304(,!&26HL|| t+ &&-	
  $; ((4/ #5<<#=>E +, 
r9   r   c                   J    e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedZy)CwmPreTrainedModelr$   modelTr   r   )r}   
attentionsN)re   rf   rg   r    ri   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   r9   r8   r   r   G  sQ    &*#*+#4"5N!"&("r9   r   c                       e Zd Zy)CwmModelOutputWithPastN)re   rf   rg   r   r9   r8   r   r   Z  s    r9   r   c                       e Zd ZeZdef fdZe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 )CwmModelr$   c           	          t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j
                  j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |j                  |j                         | _        t%        |      | _        d| _        | j+                          y c c}w )Nr   r$   F)r*   r+   pad_token_idpadding_idx
vocab_sizer   	EmbeddingrC   embed_tokensrE   
ModuleListrangenum_hidden_layersr   layersr   r   normr"   
rotary_embgradient_checkpointing	post_initr   s      r8   r+   zCwmModel.__init__b  s     !.. ++LL):):F<N<NPTP`P`ahh))AFvG_G_A`aI_VY/a
 v11v7J7JK	,F;&+# 	 bs   DN	input_idsr   r^   r   inputs_embedsr   r   r   r;   c           
         |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        |x}
t              s:| j                  |||||d}|j                         }t        d
i |t        d
i |d}
|}| j                  ||      }| j                   d | j                  j"                   D ]  } ||f|
|j$                     ||||d|}  | j'                  |      }t)        ||	      S )Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r   )r5   )r$   r  r   r   r   r^   )full_attentionr   )r   r^   r   r   r   )last_hidden_stater   r   )
ValueErrorr  r	   r$   get_seq_lengthrE   rF   rU   r5   rv   rV   dictcopyr   r   r
  r  r  r   r	  r   )r4   r  r   r^   r   r  r   r   r   past_seen_tokenscausal_mask_mappingmask_kwargssliding_mask_kwargsr}   r   decoder_layers                   r8   rc   zCwmModel.forwardr  s    -t";<YZZ *.*;*;I*FM0*$++>O!CRC^==?de]003M<P<PQTdd  )33A6L?-F++!."0"0#2 ,K #."2"2"4 #5"C{"C%F%]I\%]#
 &"oom\J![[)H4;;+H+HI 		M)2=3O3OP) /-$7 M		 		-0%++
 	
r9   )NNNNNNN)re   rf   rg   r    config_classr+   r   r   r   rE   r   rh   r   FloatTensorr   r   r   r   rc   rn   ro   s   @r8   r   r   ^  s    Ly     .2.204(,2626!%?
##d*?
 t+?
 &&-	?

 ?
 ((4/?
 ((4/?
 $;?
 +,?
 
 ?
    ?
r9   r   c                   b    e Zd ZddiZddiZddgdgfi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 )CwmForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr}   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y )NFr   )
r*   r+   r   r   r  r   r   rC   r  r  r   s     r8   r+   zCwmForCausalLM.__init__  sU     f%
 ++yy!3!3V5F5FUS 	r9   Nr  r   r^   r   r  labelsr   r   logits_to_keepr   r;   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  
        Example:

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

        >>> model = CwmForCausalLM.from_pretrained("meta-cwm/Cwm-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-cwm/Cwm-2-7b-hf")

        >>> 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   r}   r   r   )r   r  rV   rk   slicer  loss_functionr$   r  r   r   r}   r   )r4   r  r   r^   r   r  r#  r   r   r$  r   outputsr}   slice_indicesr!  r&  s                   r8   rc   zCwmForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r9   )	NNNNNNNNr   )re   rf   rg   _tied_weights_keys_tp_plan_pp_planr+   r   r   rE   r   rh   r   r  r   rk   r   r   r   rc   rn   ro   s   @r8   r  r    s/   *,GH23H_-z:;H  .2.204(,26*.!%26-.8
##d*8
 t+8
 &&-	8

 8
 ((4/8
   4'8
 $;8
 ((4/8
 ell*8
 +,8
 
 8
  8
r9   r  )r   r   r  )r   )r   )@collections.abcr   typingr   rE   r   activationsr   cache_utilsr   r	   
generationr
   integrationsr   r   r   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   utils.output_capturingr   configuration_cwmr    Moduler"   rs   r|   rh   rk   r   rI   r   r   r   r   r   r   r   r   r  __all__r   r9   r8   <module>rA     s  , %    ! . ) f f R B 9 O K F & I I G 5 (>< ><B( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%2 )*=)299 =) +=)@ Y'J J (J(RYY  *0 *Z   $	4 	 U
! U
 U
p H
' H
 H
V ?r9   