
    cCiS                     P   S SK JrJrJr  S SKrS SKJr  SSKJr  SSK	J
r
Jr  SSKJr  SSKJr  SSKJr  SS	KJrJrJr  SS
KJrJr  SSKJrJr  SSKJrJr  SSKJ r   SSK!J"r"J#r#J$r$  SSK%J&r&  SSK'J(r(  SSK)J*r*   " S S\RV                  5      r,S\RZ                  S\.S\RZ                  4S jr/ S8S\RV                  S\RZ                  S\RZ                  S\RZ                  S\\RZ                     S\0S\0S \ \"   4S! jjr1S" r2S9S# jr3 " S$ S%\RV                  5      r4\" S&5       " S' S(\RV                  5      5       r5 " S) S*\RV                  5      r6 " S+ S,\5      r7\# " S- S.\5      5       r8\# " S/ S0\85      5       r9\# " S1 S2\8\5      5       r: " S3 S4\\85      r; " S5 S6\\85      r</ S7Qr=g):    )CallableOptionalUnionN   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)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   )	GlmConfigc                   b   ^  \ rS rSrU 4S jrS\R                  S\R                  4S jrSrU =r	$ )GlmMLP/   c                    > [         TU ]  5         Xl        [        R                  " UR
                  SUR                  -  SS9U l        [        R                  " UR                  UR
                  SS9U l        [        UR                     U l        g )N   Fbias)super__init__confignnLinearhidden_sizeintermediate_sizegate_up_proj	down_projr   
hidden_actactivation_fnselfr'   	__class__s     ^/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/glm/modeling_glm.pyr&   GlmMLP.__init__0   sn    IIf&8&8!f>V>V:V]bc6#;#;V=O=OV[\#F$5$56    hidden_statesreturnc                     U R                  U5      nUR                  SSS9u  p2X R                  U5      -  nU R                  U5      $ )Nr"   dim)r,   chunkr/   r-   )r1   r6   	up_statesgates       r3   forwardGlmMLP.forward8   sH    %%m4	#//!/4 2 24 88	~~i((r5   )r/   r'   r-   r,   )
__name__
__module____qualname____firstlineno__r&   torchFloatTensorr?   __static_attributes____classcell__r2   s   @r3   r   r   /   s,    7)U%6%6 )5;L;L ) )r5   r   r6   n_repr7   c                     U R                   u  p#pEUS:X  a  U $ U SS2SS2SSS2SS24   R                  X#XU5      n U R                  X#U-  XE5      $ )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)r6   rJ   batchnum_key_value_headsslenhead_dims         r3   	repeat_kvrS   A   s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr5   modulequerykeyvalueattention_maskscalingdropoutkwargsc                 @   [        X R                  5      n[        X0R                  5      n	[        R                  " XR	                  SS5      5      U-  n
Ub"  US S 2S S 2S S 2S UR
                  S   24   nX-   n
[        R                  R                  U
S[        R                  S9R                  UR                  5      n
[        R                  R                  XU R                  S9n
[        R                  " X5      nUR	                  SS5      R                  5       nX4$ )Nr"   r   r9   )r;   dtype)ptrainingr   )rS   num_key_value_groupsrE   matmul	transposerL   r(   
functionalsoftmaxfloat32tor^   rZ   r`   
contiguous)rT   rU   rV   rW   rX   rY   rZ   r[   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r3   eager_attention_forwardrn   M   s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#1==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r5   c                 x    U SSSS24   nU SSSS24   n[         R                  " U* U4SS9R                  S5      $ )	z*Rotates half the hidden dims of the input..r   Nr"   r   r9   r:   r]   )rE   stackflatten)xx1x2s      r3   rotate_halfru   g   sJ    	
319B	
319B;;Ryb)11"55r5   c                    UR                  U5      nUR                  U5      nUSSUR                  S   S-  24   R                  SSS9nUSSUR                  S   S-  24   R                  SSS9nUR                  S   nU SSU24   U SUS24   pUSSU24   USUS24   pXr-  [        U5      U-  -   nX-  [        U	5      U-  -   n[        R
                  " X/SS9n[        R
                  " X/SS9nX4$ )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.
.Nr9   r"   r:   )	unsqueezerL   repeat_interleaveru   rE   cat)qkcossinposition_idsunsqueeze_dim
rotary_dimq_rotq_passk_rotk_passq_embedk_embeds                r3   apply_rotary_pos_embr   n   s6   ( --
&C
--
&C c'SYYr]a'''
(
:
:1"
:
EC
c'SYYr]a'''
(
:
:1"
:
EC 2Jc;J;&'3
+;)<6c;J;&'3
+;)<6 {{51C78G{{51C78G ii)r2Gii)r2Gr5   c                   >  ^  \ rS rSrSrSS\S\\   4U 4S jjjr\	" SSSS	9  SS
\
R                  S\\
R                  \
R                  4   S\\
R                     S\\   S\\
R                     S\\   S\\
R                  \
R                  4   4S jj5       rSrU =r$ )GlmAttention   z=Multi-headed attention from 'Attention Is All You Need' paperr'   	layer_idxc                 <  > [         TU ]  5         Xl        X l        [	        USUR
                  UR                  -  5      U l        UR                  UR                  -  U l	        U R                  S-  U l
        UR                  U l        SU l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR                  U R                  -  UR
                  SS9U l        g )NrR   g      Tr#   F)r%   r&   r'   r   getattrr*   num_attention_headsrR   rP   ra   rY   attention_dropout	is_causalr(   r)   attention_biasq_projk_projv_projo_projr1   r'   r   r2   s      r3   r&   GlmAttention.__init__   s@   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JFL^L^ejkr5   past_key_valuepast_key_values4.58new_nameversionr6   position_embeddingsrX   cache_positionr[   r7   c                 4   UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
U R                  U5      R                  U5      R	                  SS5      nUu  p[        XX5      u  pUb$  XUS.nUR                  XU R                  U5      u  p[        nU R                  R                  S:w  a  [        U R                  R                     nU" U U	U
UU4U R                  (       d  SOU R                  U R                   S.UD6u  nnUR"                  " / UQSP76 R%                  5       nU R'                  U5      nUU4$ )Nr9   r   r"   )r}   r|   r   eager        )rZ   rY   )rL   rR   r   viewrc   r   r   r   updater   rn   r'   _attn_implementationr   r`   r   rY   rN   rh   r   )r1   r6   r   rX   r   r   r[   input_shapehidden_shapequery_statesri   rj   r|   r}   cache_kwargsattention_interfacerm   rk   s                     r3   r?   GlmAttention.forward   s    $))#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&#7RU#[ &#&nUL'6'='=jX\XfXfht'u$J(?;;++w6"9$++:Z:Z"[$7	%
  $}}C$2H2HLL	%
 	%
!\ "));;;;FFHkk+.L((r5   )r   r'   rR   r   r   r   ra   r   r   rY   r   N)NN)rA   rB   rC   rD   __doc__r   r   intr&   r   rE   Tensortupler   
LongTensorr   r   r?   rG   rH   rI   s   @r3   r   r      s    Gly lXc] l l* %0A6R ,059))||)) #5<<#=>)) !.	))
 "%)) !!1!12)) +,)) 
u||U\\)	*)) S))r5   r   RMSNormc                   8   ^  \ rS rSrSU 4S jjrS rS rSrU =r$ )
GlmRMSNorm   c                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)z)
GlmRMSNorm is equivalent to T5LayerNorm
N)r%   r&   r(   	ParameterrE   onesweightvariance_epsilon)r1   r*   epsr2   s      r3   r&   GlmRMSNorm.__init__   s/     	ll5::k#:; #r5   c                    UR                   nUR                  [        R                  5      nUR	                  S5      R                  SSS9nU[        R                  " X0R                  -   5      -  nU R                  UR                  U5      -  $ )Nr"   r9   T)keepdim)	r^   rg   rE   rf   powmeanrsqrtr   r   )r1   r6   input_dtypevariances       r3   r?   GlmRMSNorm.forward   sw    #))%((7 $$Q',,R,>%H?T?T4T(UU{{]--k:::r5   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)r   r   rL   r   )r1   s    r3   
extra_reprGlmRMSNorm.extra_repr   s*    ))*+6$2G2G1HIIr5   )r   r   )gư>)	rA   rB   rC   rD   r&   r?   r   rG   rH   rI   s   @r3   r   r      s    $;J Jr5   r   c                      ^  \ rS rSr% \R
                  \S'   SS\4U 4S jjjr\R                  " 5       \
S 5       5       rSrU =r$ )GlmRotaryEmbedding   inv_freqr'   c                   > [         TU ]  5         [        US5      (       aZ  [        UR                  [
        5      (       a;  UR                  R                  SUR                  R                  S5      5      U l        OSU l        UR                  U l	        UR                  U l
        Xl        [        U R                     U l        U R                  U R                  U5      u  o0l        U R                  SUSS9  U R                   U l        g )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&   GlmRotaryEmbedding.__init__   s    6>**z&:M:Mt/T/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q((ZeD!%r5   c                 b   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        R                  " USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r9   r   mpscpuF)device_typeenabledr"   r:   )r^   )r   floatrM   rL   rg   r   r   r   strrE   autocastrc   ry   r|   r   r}   r^   )
r1   rr   r~   inv_freq_expandedposition_ids_expandedr   freqsembr|   r}   s
             r3   r?   GlmRotaryEmbedding.forward  sR    !MM$4-8>>@GGHZHZ[\H]_acdehhijiqiqr ,QaZ 8 > > @'1!((--'E'E!((--[`J`ahhmmfk^^UC&,,.1F1L1L1NNYYZ[]^_E))UN3C'')d444C'')d444C	 D vvAGGv$cff177f&;;; DCs   $BF  
F.)r   r'   r   r   r   r   r   r   )rA   rB   rC   rD   rE   r   __annotations__r   r&   no_gradr   r?   rG   rH   rI   s   @r3   r   r      s@    ll/y / /" ]]_<  <r5   r   c                   H  ^  \ rS rSrS\S\4U 4S jjr\" SSSS9      SS	\R                  S
\
\R                     S\
\R                     S\
\   S\
\   S\
\R                     S\
\\R                  \R                  4      S\\   S\R                  4S jj5       rSrU =r$ )GlmDecoderLayeri  r'   r   c                   > [         TU ]  5         UR                  U l        [        XS9U l        [        U5      U l        [        UR                  UR                  S9U l	        [        UR                  UR                  S9U l
        g )N)r'   r   r   )r%   r&   r*   r   	self_attnr   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr   s      r3   r&   GlmDecoderLayer.__init__  si    !--%VI&>)&*<*<&BUBUV(263E3E6K^K^(_%r5   r   r   r   r   r6   rX   r~   	use_cacher   r   r[   r7   c                     Un	U R                  U5      nU R                  " SUUUUUUUS.UD6u  pX-   nUn	U R                  U5      nU R                  U5      nX-   nU$ )N)r6   rX   r~   r   r   r   r    )r   r   r   r   )r1   r6   rX   r~   r   r   r   r   r[   residual_s              r3   r?   GlmDecoderLayer.forward!  s     !,,];>> 	
')%+) 3	
 	
 !0 !55mD/ 0r5   )r*   r   r   r   r   )NNNFNN)rA   rB   rC   rD   r   r   r&   r   rE   r   r   r   r   boolr   r   r   r?   rG   rH   rI   s   @r3   r   r     s    `y `S ` %0A6R 2637+/$)59KO|| !. u//0	
 "% D> !!1!12 &eELL%,,,F&GH +, 
 Sr5   r   c                   R    \ rS rSr% \\S'   SrSrS/rS/r	Sr
SrSrSrSr\\S.rSrg	)
GlmPreTrainedModeliD  r'   modelTr   r   )r6   
attentionsr   N)rA   rB   rC   rD   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_outputsrG   r   r5   r3   r   r   D  sQ    &*#*+#4"5N!"&("r5   r   c                   "  ^  \ rS rSrS\4U 4S jjr\" 5       \       SS\\	R                     S\\	R                     S\\	R                     S\\   S\\	R                     S	\\	R                     S
\\   S\\   S\4S jj5       5       rSrU =r$ )GlmModeliW  r'   c           	        > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [        UR                  UR                  S9U l        [#        US9U l        SU l        U R)                  5         g s  snf )Nr   r'   F)r%   r&   pad_token_idpadding_idx
vocab_sizer(   	Embeddingr*   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normr   
rotary_embgradient_checkpointing	post_initr   s      r3   r&   GlmModel.__init__Y  s     !.. ++LL):):F<N<NPTP`P`ammAFvG_G_A`aA`I_V/A`a
 v11v7J7JK	,F;&+# 	 bs   C?	input_idsrX   r~   r   inputs_embedsr   r   r[   r7   c           
      J   US L US L-  (       a  [        S5      eUc  U R                  U5      nU(       a  Uc  [        U R                  S9nUcD  Ub  UR	                  5       OSn	[
        R                  " XUR                  S   -   UR                  S9nUc  UR                  S5      n[        U R                  UUUUUS9n
UnU R                  X5      nU R                  S U R                  R                    H  nU" U4U
UUUUS.UD6nM     U R                  U5      n[        UUS9$ )	Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r   )r   )r'   input_embedsrX   r   r   r~   )rX   r~   r   r   r   )last_hidden_stater   )
ValueErrorr  r	   r'   get_seq_lengthrE   arangerL   r   rw   r   r  r  r  r  r   )r1   r  rX   r~   r   r   r   r   r[   past_seen_tokensrl   r6   r   decoder_layers                 r3   r?   GlmModel.forwardi  sR    -t";<YZZ *.*;*;I*FM0*$++>O!CRC^==?de+0<< ]5H5H5K"KTaThTh,N )33A6L(;;&))+%
 &"oomJ![[)H4;;+H+HIM)*) /-$7 M J 		-0&++
 	
r5   )r  r  r  r  r  r  r  )NNNNNNN)rA   rB   rC   rD   r   r&   r   r   r   rE   r   r   r   rF   r   r   r   r   r?   rG   rH   rI   s   @r3   r  r  W  s    y    151537+/5959$(8
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 !!1!128
 D>8
 +,8
 
!8
  8
r5   r  c                   r  ^  \ rS rSrS/rSS0rSS/S/40rU 4S jr\\	         SS\
\R                     S	\
\R                     S
\
\R                     S\
\   S\
\R                     S\
\R                     S\
\   S\
\R                     S\\\R                  4   S\\   S\4S jj5       5       rSrU =r$ )GlmForCausalLMi  zlm_head.weightlm_headcolwise_repr6   logitsc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g )NFr#   )
r%   r&   r  r  r  r(   r)   r*   r,  r  r0   s     r3   r&   GlmForCausalLM.__init__  sU     f%
 ++yy!3!3V5F5FUS 	r5   r  rX   r~   r   r   labelsr   r   logits_to_keepr[   r7   c
                 ~   U R                   " SUUUUUUUS.U
D6nUR                  n[        U	[        5      (       a  [	        U	* S5      OU	nU R                  USS2USS24   5      nSnUb)  U R                  " SXU R                  R                  S.U
D6n[        UUUR                  UR                  UR                  S9$ )ac  
Example:

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

>>> model = GlmForCausalLM.from_pretrained("meta-glm/Glm-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-glm/Glm-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  rX   r~   r   r   r   r   N)r.  r1  r  )lossr.  r   r6   r  r   )r  r#  r   r   slicer,  loss_functionr'   r  r   r   r6   r  )r1   r  rX   r~   r   r   r1  r   r   r2  r[   outputsr6   slice_indicesr.  r4  s                   r3   r?   GlmForCausalLM.forward  s    @ ,0:: 	,
)%+')	,
 	,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r5   )r,  r  r  )	NNNNNNNNr   )rA   rB   rC   rD   _tied_weights_keys_tp_plan_pp_planr&   r   r   r   rE   r   r   r   rF   r   r   r   r   r   r   r?   rG   rH   rI   s   @r3   r+  r+    s0   *+=)H_-z:;H  151537+/59-1$(59348
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 ))*8
 D>8
 !!1!128
 c5<</08
 +,8
 
 8
  8
r5   r+  c                       \ rS rSrSrg)GlmForSequenceClassificationi  r   NrA   rB   rC   rD   rG   r   r5   r3   r>  r>        r5   r>  c                       \ rS rSrSrg)GlmForTokenClassificationi  r   Nr?  r   r5   r3   rB  rB    r@  r5   rB  )r   r  r+  r>  rB  )r   )Nr   )>typingr   r   r   rE   torch.nnr(   activationsr   cache_utilsr   r	   
generationr
   integrationsr   masking_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_glmr   Moduler   r   r   rS   r   rn   ru   r   r   r   r   r   r   r  r+  r>  rB  __all__r   r5   r3   <module>rU     s  , - ,   ! . ) 7 / 
 P K F & I I 0 / ()RYY )$	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%46'TB)299 B)J Y'J J (J(!< !<H+0 +\   $ K
! K
 K
\ H
' H
 H
V	#CEW 		 =?Q 	r5   