ZjUrSSKJr SSKJr SSKrSSKJr SSKJr SSK J r J r SSK J r SSKJrJr SS KJr SS KJrJrJr SS KJrJr SS KJrJr SS KJrJr SSK J!r! SSK"J#r#J$r$J%r% SSK&J'r'J(r( SSK)J*r* SSK+J,r, "SS\RZ5r."SS\RZ5r/S\R`S\1S\R`4Sjr2S9S\RZS\R`S\R`S\R`S \R`S-S!\3S"\3S#\!\#4S$jjr4S%r5S:S&jr6\"\65"S'S(\RZ55r7\"S)5"S*S+\RZ55r8"S,S-\5r9\$"S.S/\55r:\$"S0S1\:55r;\$"S2S3\:\ 55r<"S4S5\\:5r="S6S7\\:5r>/S8Qr?g);)Callable)OptionalN)ACT2FN)Cache DynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernelized_func)create_causal_mask) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs) GlmConfigcb^\rSrSrU4SjrS\R S\R 4SjrSrU=r $)GlmMLP/c >[TU]5 Xl[R"UR SUR -SS9Ul[R"UR UR SS9Ul[URUl g)NFbias) super__init__confignnLinear hidden_sizeintermediate_size gate_up_proj down_projr hidden_act activation_fnselfr( __class__s u/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/glm/modeling_glm.pyr'GlmMLP.__init__0sn  IIf&8&8!f>V>V:V]bc6#;#;V=O=OV[\#F$5$56 hidden_statesreturncURU5nURSSS9up2X RU5-nURU5$)Nr#dim)r-chunkr0r.)r2r7 up_statesgates r4forwardGlmMLP.forward8sH%%m4 #//!/4 2 24 88 ~~i((r6)r0r(r.r-) __name__ __module__ __qualname____firstlineno__r'torch FloatTensorr@__static_attributes__ __classcell__r3s@r4r r /s,7)U%6%6)5;L;L))r6r c ^\rSrSr%\R \S'SS\4U4Sjjjr\ SS\S-S\ SS\ S-S \ S \ 44S jj5r\R"5\S 55rS rU=r$)GlmRotaryEmbeddingAinv_freqNr(c>[TU]5 URUlURUlXlUR R SUlURnURS:wa[URnU"UR U5uo@l URSUSS9 URSUR5SS9 g)N rope_typedefaultrNF) persistentoriginal_inv_freq) r&r'max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr(rope_parametersrPcompute_default_rope_parametersrattention_scalingregister_bufferclone)r2r(device rope_init_fnrNr3s r4r'GlmRotaryEmbedding.__init__Ds "("@"@$*$B$B! 44[A!%!E!E >>Y &.t~~>L+7 V+L(( ZeD 0(..2BuUr6r\z torch.deviceseq_lenr8z torch.Tensorc jURSnURRSS5n[USS5=(d URUR-n[ XT-5nSnSU[ R"SUS[ RS9RU[ RS 9U- -- nX4$) aH Computes the inverse frequencies according to the original RoPE implementation Args: config ([`~transformers.PreTrainedConfig`]): The model configuration. device (`torch.device`): The device to use for initialization of the inverse frequencies. seq_len (`int`, *optional*): The current sequence length. Unused for this type of RoPE. Returns: Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE). rope_thetapartial_rotary_factorg?head_dimNrr#dtype)r\re) rWgetgetattrr+num_attention_headsintrFarangeint64tofloat) r(r\r_baserbrcr<attention_factorrNs r4rX2GlmRotaryEmbedding.compute_default_rope_parametersTs&%%l3 & 6 6 : :;RTW X6:t4h8J8JfNhNh8h(23 U\\!S!5;;?BB&X]XcXcBdgjj k ))r6cLURSSS2S4R5RURSSS5R UR 5nUSS2SSS24R5n[ UR R[5(a0UR RS:waUR ROSn[USS9 UR5UR5-RSS5n[R"Xf4SS 9nUR5UR-nUR5UR-n SSS5 WR UR S 9W R UR S 94$!,(df  N@=f) Nrr:rmpscpuF) device_typeenabledr#r;rd)rNrmexpandshaperlr\ isinstancetypestrr transposerFcatcosrYsinre) r2x position_idsinv_freq_expandedposition_ids_expandedrtfreqsembr}r~s r4r@GlmRotaryEmbedding.forwardtsN!MM$4-8>>@GG HZHZ[\H]_acdehhijiqiqr ,QaZ 8 > > @'1!((--'E'E!((--[`J`ahhmmfk  U C&,,.1F1L1L1NNYYZ[]^_E))UN3C'')d444C'')d444C D vvAGGv$cff177f&;;; D Cs BF F#)rYr(rUrVrPNNNN)rBrCrDrErFTensor__annotations__rr' staticmethodrrituplermrXno_gradrr@rHrIrJs@r4rLrLAsllVyVV #'+/"*D *(*t* ~u$ % **> ]]_ <