
     `iV                     N   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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ej-                  Z. G d de          Z/dej0        de1dej0        fdZ2	 d:dej-        dej0        dej0        d ej0        d!eej0                 d"e3d#e3d$e"e$         fd%Z4d& Z5d;d'Z6 G d( d)ej-                  Z7 ed*           G d+ d,ej-                              Z8 G d- d.ej-                  Z9e% G d/ d0e                       Z:e% G d1 d2e:                      Z;e% G d3 d4e:e                      Z< G d5 d6ee:          Z= G d7 d8ee:          Z>g d9Z?dS )<    )CallableOptionalUnionN   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask)FlashAttentionKwargs) 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   )
Glm4Configc                   B     e Zd Z fdZdej        dej        fdZ xZS )Glm4MLPc                 "   t                                                       || _        t          j        |j        d|j        z  d          | _        t          j        |j        |j        d          | _        t          |j
                 | _        d S )N   Fbias)super__init__confignnLinearhidden_sizeintermediate_sizegate_up_proj	down_projr   
hidden_actactivation_fnselfr'   	__class__s     z/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/glm4/modeling_glm4.pyr&   zGlm4MLP.__init__1   sz    If&8!f>V:V]bccc6#;V=OV[\\\#F$56    hidden_statesreturnc                     |                      |          }|                    dd          \  }}||                     |          z  }|                     |          S )Nr"   dim)r,   chunkr/   r-   )r1   r5   	up_statesgates       r3   forwardzGlm4MLP.forward9   sX    %%m44	#//!/44i 2 24 8 88	~~i(((r4   )__name__
__module____qualname__r&   torchFloatTensorr>   __classcell__r2   s   @r3   r    r    0   s`        7 7 7 7 7)U%6 )5;L ) ) ) ) ) ) ) )r4   r    c                   t    e Zd Zdedef fdZ eddd          	 	 	 	 	 	 dd
ej        de	ej                 de	ej
                 de	e         de	e         de	ej
                 de	eej        ej        f                  dee         deej        e	eej        ej        f                  f         fd            Z xZS )Glm4DecoderLayerr'   	layer_idxc                    t                                                       |j        | _        t          ||          | _        t          |          | _        t          |j        |j                  | _	        t          |j        |j                  | _
        t          |j        |j                  | _        t          |j        |j                  | _        d S )N)r'   rH   eps)r%   r&   r*   Glm4Attention	self_attnr    mlpGlm4RMSNormrms_norm_epsinput_layernormpost_attention_layernormpost_self_attn_layernormpost_mlp_layernormr1   r'   rH   r2   s      r3   r&   zGlm4DecoderLayer.__init__C   s    !-&f	JJJ6??*6+=6CVWWW(3F4FFL_(`(`(`%(3F4FFL_(`(`(`%"-f.@fFY"Z"Z"Zr4   past_key_valuepast_key_values4.58new_nameversionNFr5   attention_maskposition_ids	use_cachecache_positionposition_embeddingskwargsr6   c                 $   |}	|                      |          } | j        d|||||||d|\  }}
|                     |          }|	|z   }|}	|                     |          }|                     |          }|                     |          }|	|z   }|S )N)r5   r\   r]   rW   r^   r_   r`    )rQ   rM   rS   rR   rN   rT   )r1   r5   r\   r]   rW   r^   r_   r`   ra   residual_s              r3   r>   zGlm4DecoderLayer.forwardN   s     !,,];;)4> 	
')%+) 3	
 	
 	
 	
q 55mDD =0 55mDD////>> =0r4   )NNNFNN)r?   r@   rA   r   intr&   r   rB   Tensorr   
LongTensorr   booltupler   r   rC   r>   rD   rE   s   @r3   rG   rG   B   sU       	[z 	[c 	[ 	[ 	[ 	[ 	[ 	[ _%0A6RRR 2637+/$)59KO! !|! !.! u/0	!
 "%! D>! !!12! &eEL%,,F&GH! -.! 
u (51BEDU1U+V"WW	X! ! ! SR! ! ! ! !r4   rG   r5   n_repr6   c                     | j         \  }}}}|dk    r| S | dddddddddf                             |||||          } |                     |||z  ||          S )z
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r   N)shapeexpandreshape)r5   rk   batchnum_key_value_headsslenhead_dims         r3   	repeat_kvrt   s   s    
 2?1D.Ehzz!!!!QQQaaa"23::5BUW\^bdlmmM  (;e(CT8TTTr4           modulequerykeyvaluer\   scalingdropoutra   c                 R   t          || j                  }t          || j                  }	t          j        ||                    dd                    |z  }
|$|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 )Nr"   r   r8   )r:   dtype)ptrainingr   )rt   num_key_value_groupsrB   matmul	transposerm   r(   
functionalsoftmaxfloat32tor~   r{   r   
contiguous)rv   rw   rx   ry   r\   rz   r{   ra   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r3   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$$r4   c                     | ddddf         }| ddddf         }t          j        | |fd                              d          S )	z*Rotates half the hidden dims of the input..r   Nr"   r   r8   r9   r}   )rB   stackflatten)xx1x2s      r3   rotate_halfr      sQ    	
319B	
319B;Ryb)))11"555r4   c                 T   |                     |          }|                     |          }|dd|j        d         dz  f                             dd          }|dd|j        d         dz  f                             dd          }|j        d         }| dd|f         | d|df         }}|dd|f         |d|df         }
}	||z  t          |          |z  z   }|	|z  t          |	          |z  z   }t	          j        ||gd          }t	          j        ||
gd          }||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.
    .Nr8   r"   r9   )	unsqueezerm   repeat_interleaver   rB   cat)qkcossinr]   unsqueeze_dim
rotary_dimq_rotq_passk_rotk_passq_embedk_embeds                r3   apply_rotary_pos_embr      s\   ( --
&
&C
--
&
&C c'SYr]a'''
(
:
:1"
:
E
EC
c'SYr]a'''
(
:
:1"
:
E
EC 2Jc;J;&'3
+;)<6Ec;J;&'3
+;)<6E s{{511C78Gs{{511C78G i&)r222Gi&)r222GGr4   c                   "    e Zd ZdZddede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	j
        f         fd            Z xZS )rL   z=Multi-headed attention from 'Attention Is All You Need' paperNr'   rH   c                    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        d          | _        d S )Nrs   g      Tr#   F)r%   r&   r'   rH   getattrr*   num_attention_headsrs   rq   r   rz   attention_dropout	is_causalr(   r)   attention_biasq_projk_projv_projo_projrU   s      r3   r&   zGlm4Attention.__init__   s8   "
F4F&Jd4dee$*$>&B\$\!}d*!'!9i :T] JQWQf
 
 
 i :T] JQWQf
 
 
 i :T] JQWQf
 
 
 i :T] JFL^ejkkkr4   rV   rW   rX   rY   r5   r`   r\   r_   ra   r6   c                 D   |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 )Nr8   r   r"   )r   r   r_   eagerru   )r{   rz   )rm   rs   r   viewr   r   r   r   updaterH   r   r'   _attn_implementationr   r   r   rz   ro   r   r   )r1   r5   r`   r\   rW   r_   ra   input_shapehidden_shapequery_statesr   r   r   r   cache_kwargsattention_interfacer   r   s                     r3   r>   zGlm4Attention.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$2HL	%
 	%
 	%
 	%
!\ *k);;;;;;FFHHkk+..L((r4   N)NN)r?   r@   rA   __doc__r   r   rf   r&   r   rB   rg   rj   r   rh   r   r   r>   rD   rE   s   @r3   rL   rL      s        GGl lz lhsm l l l l l l* _%0A6RRR ,059)) ))|)) #5<#=>)) !.	))
 "%)) !!12)) +,)) 
u|U\)	*)) )) )) SR)) )) )) )) ))r4   rL   RMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )rO   ư>c                     t                                                       t          j        t	          j        |                    | _        || _        dS )z:
        Glm4RMSNorm is equivalent to T5LayerNorm
        N)r%   r&   r(   	ParameterrB   onesweightvariance_epsilon)r1   r*   rK   r2   s      r3   r&   zGlm4RMSNorm.__init__  sD     	l5:k#:#:;; #r4   c                    |j         }|                    t          j                  }|                    d                              dd          }|t          j        || j        z             z  }| j        |                    |          z  S )Nr"   r8   T)keepdim)	r~   r   rB   r   powmeanrsqrtr   r   )r1   r5   input_dtypevariances       r3   r>   zGlm4RMSNorm.forward  s|    #)%((77 $$Q'',,R,>>%Ht?T4T(U(UU{]--k::::r4   c                 H    t          | j        j                   d| j         S )Nz, eps=)rj   r   rm   r   )r1   s    r3   
extra_reprzGlm4RMSNorm.extra_repr   s&    )**II$2GIIIr4   )r   )r?   r@   rA   r&   r>   r   rD   rE   s   @r3   rO   rO     sb        $ $ $ $ $ $; ; ;J J J J J J Jr4   rO   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 )Glm4RotaryEmbeddinginv_freqNr'   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_lenr'   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r1   r'   devicer   r2   s       r3   r&   zGlm4RotaryEmbedding.__init__'  s    6>** 	'z&:Mt/T/T 	'#044[&BUBYBYZ`BaBabbDNN&DN"("@$*$B!/?+/+<+<T[&+Q+Q($(ZeDDD!%r4   c                 X   | j         d d d d f                                                             |j        d         dd                              |j                  }|d d d d d f                                         }t          |j        j        t                    r|j        j        dk    r|j        j        nd}t          j
        |d          5  |                                |                                z                      dd          }t          j        ||fd	          }|                                | j        z  }|                                | j        z  }	d d d            n# 1 swxY w Y   |                    |j        
          |	                    |j        
          fS )Nr   r8   r   mpscpuF)device_typeenabledr"   r9   )r~   )r   floatrn   rm   r   r   r   r   strrB   autocastr   r   r   r   r   r~   )
r1   r   r]   inv_freq_expandedposition_ids_expandedr   freqsembr   r   s
             r3   r>   zGlm4RotaryEmbedding.forward8  s    !M$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/r   )r?   r@   rA   rB   rg   __annotations__r   r&   no_gradr   r>   rD   rE   s   @r3   r   r   $  s         l/ /z / / / / / /" U]__< <  _< < < < <r4   r   c                   L    e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedZdS )Glm4PreTrainedModelr'   modelTrG   rW   )r5   
attentionsN)r?   r@   rA   r   r   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendrG   rL   _can_record_outputsrc   r4   r3   r   r   H  sl         &*#+,#4"5N!"&)# r4   r   c                       e Zd Zdef fdZee	 	 	 	 	 	 	 ddeej	                 deej
                 deej	                 dee         deej                 d	eej	                 d
ee         dee         defd                        Z xZS )	Glm4Modelr'   c                    t                                                     j        | _        j        | _        t          j        j        j        | j                  | _        t          j	        fdt          j                  D                       | _        t          j        j                  | _        t!                    | _        d| _        |                                  d S )Nc                 0    g | ]}t          |          S rc   )rG   ).0rH   r'   s     r3   
<listcomp>z&Glm4Model.__init__.<locals>.<listcomp>d  s$    bbbYfi00bbbr4   rJ   r'   F)r%   r&   pad_token_idpadding_idx
vocab_sizer(   	Embeddingr*   embed_tokens
ModuleListrangenum_hidden_layerslayersrO   rP   normr   
rotary_embgradient_checkpointing	post_initr0   s    `r3   r&   zGlm4Model.__init__]  s       !. +L):F<NPTP`aambbbb%H`BaBabbb
 
   28KLLL	-V<<<&+# 	r4   N	input_idsr\   r]   rW   inputs_embedsr_   r^   ra   r6   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   )r'   input_embedsr\   r_   rW   r]   )r\   r]   rW   r_   r`   )last_hidden_staterW   )
ValueErrorr  r	   r'   get_seq_lengthrB   arangerm   r   r   r   r  r  r  r  r   )r1   r  r\   r]   rW   r  r_   r^   ra   past_seen_tokensr   r5   r`   decoder_layers                 r3   r>   zGlm4Model.forwardm  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*) /-$7   MM 		-00&++
 
 
 	
r4   )NNNNNNN)r?   r@   rA   r   r&   r   r   r   rB   rh   rg   r   rC   ri   r   r   r   r>   rD   rE   s   @r3   r  r  [  s       z         151537+/5959$(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
r4   r  c                   v    e Zd ZdgZddiZddgdgfi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eef         fd                        Z xZS )Glm4ForCausalLMzlm_head.weightlm_headcolwise_repr5   logitsc                     t                                          |           t          |          | _        |j        | _        t          j        |j        |j        d          | _        | 	                                 d S )NFr#   )
r%   r&   r  r   r	  r(   r)   r*   r   r  r0   s     r3   r&   zGlm4ForCausalLM.__init__  sj       v&&
 +y!3V5FUSSS 	r4   Nr   r  r\   r]   rW   r  labelsr^   r_   logits_to_keepra   r6   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 )ah  
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
            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, ..., config.vocab_size]`.

        Example:

        ```python
        >>> from transformers import AutoTokenizer, Glm4ForCausalLM

        >>> model = Glm4ForCausalLM.from_pretrained("THUDM/GLM-4-9B-0414")
        >>> tokenizer = AutoTokenizer.from_pretrained("THUDM/GLM-4-9B-0414")

        >>> 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]   rW   r  r^   r_   N)r"  r$  r	  )lossr"  rW   r5   r   rc   )r   r  r   rf   slicer   loss_functionr'   r	  r   rW   r5   r   )r1   r  r\   r]   rW   r  r$  r^   r_   r%  ra   outputsr5   slice_indicesr"  r'  s                   r3   r>   zGlm4ForCausalLM.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!/)
 
 
 	
r4   )	NNNNNNNNr   )r?   r@   rA   _tied_weights_keys_tp_plan_pp_planr&   r   r   r   rB   rh   rg   r   rC   ri   r   rf   r   r   rj   r   r>   rD   rE   s   @r3   r  r    sl       *+=)H_-z:;H      151537+/59-1$(5934=
 =
E,-=
 !.=
 u/0	=

 "%=
   12=
 )*=
 D>=
 !!12=
 c5</0=
 +,=
 
u,,	-=
 =
 =
 ^ =
 =
 =
 =
 =
r4   r  c                       e Zd ZdS )Glm4ForSequenceClassificationNr?   r@   rA   rc   r4   r3   r0  r0            Dr4   r0  c                       e Zd ZdS )Glm4ForTokenClassificationNr1  rc   r4   r3   r4  r4    r2  r4   r4  )r   r  r  r0  r4  )ru   )Nr   )@typingr   r   r   rB   torch.nnr(   activationsr   cache_utilsr   r	   
generationr
   integrationsr   masking_utilsr   modeling_flash_attention_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.deprecationr   utils.genericr   configuration_glm4r   Moduler    rG   rg   rf   rt   r   r   r   r   rL   rO   r   r   r  r  r0  r4  __all__rc   r4   r3   <module>rH     s  , - , , , , , , , , ,        ! ! ! ! ! ! . . . . . . . . ) ) ) ) ) ) 7 7 7 7 7 7 / / / / / / B B B B B B         
 P 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 / / / / / / * * * * * *) ) ) ) )bi ) ) )$. . . . .1 . . .b	UU\ 	U# 	U%, 	U 	U 	U 	U& % %I%<% 
% <	%
 U\*% % % '(% % % %46 6 6' ' ' 'TB) B) B) B) B)BI B) B) B)J Y''J J J J J") J J ('J(!< !< !< !< !<") !< !< !<H     /   $ K
 K
 K
 K
 K
# K
 K
 K
\ M
 M
 M
 M
 M
)? M
 M
 M
`	 	 	 	 	$DFY 	 	 		 	 	 	 	!>@S 	 	 	  r4   