Zj0TzSSKJr SSKJr SSKrSSKJr SSKJr SSKJ r J r SSK J r SS K JrJrJr SS KJrJr SS KJr SS KJr SS KJrJr SSKJrJr SSKJrJ r SSK!J"r" SSK#J$r$J%r%J&r& SSK'J(r(J)r) SSK*J+r+ SSK,J-r- "SS\R\5r/Sr0\"S5S:Sj5r1S\RdS\3S\Rd4Sjr4S;S\R\S \RdS!\RdS"\RdS#\RdS-S$\5S%\5S&\"\$4S'jjr6\"\15"S(S)\R\55r7\"S*5"S+S,\R\55r8"S-S.\R\5r9"S/S0\5r:\%"S1S2\ 55r;"S3S4\5r<\%"S5S6\;55r=\%"S7S8\;\ 55r>/S9Qr?g)<)Callable)OptionalN)nn)ACT2FN)Cache DynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernel_func_from_hubuse_kernelized_func)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs) CwmConfigc ^\rSrSr%\R \S'SS\4U4Sjjjr\ SS\S-S\ SS\ S-S \ S \ 44S jj5r\R"5\S 55rS rU=r$)CwmRotaryEmbedding-inv_freqNconfigc>[TU]5 URUlURUlXlUR R SUlURnURS:wa[URnU"UR U5uo@l URSUSS9 URSUR5SS9 g)N rope_typedefaultr$F) persistentoriginal_inv_freq) super__init__max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr%rope_parametersr'compute_default_rope_parametersrattention_scalingregister_bufferclone)selfr%device rope_init_fnr$ __class__s u/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/cwm/modeling_cwm.pyr,CwmRotaryEmbedding.__init__0s "("@"@$*$B$B! 44[A!%!E!E >>Y &.t~~>L+7 V+L(( ZeD 0(..2BuUr6z torch.deviceseq_lenreturnz torch.Tensorc URSn[USS5=(d URUR-nSnSU[R "SUS[R S9RU[RS9U- -- nXe4$) 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_thetahead_dimNg?rdtype)r6rC) r0getattr hidden_sizenum_attention_headstorcharangeint64tofloat)r%r6r<basedimattention_factorr$s r9r12CwmRotaryEmbedding.compute_default_rope_parameters@s&%%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjj k ))r;cLURSSS2S4R5RURSSS5R 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$!,(df  N@=f) NrrmpscpuF) device_typeenabledrArMrB)r$rKexpandshaperJr6 isinstancetypestrr transposerGcatcosr2sinrC) r5x position_idsinv_freq_expandedposition_ids_expandedrTfreqsembr^r_s r9forwardCwmRotaryEmbedding.forward^sN!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#)r2r%r.r/r'N)NNN)__name__ __module__ __qualname____firstlineno__rGTensor__annotations__r r, staticmethodrinttuplerKr1no_gradrrf__static_attributes__ __classcell__r8s@r9r"r"-sllVyVV #'+/"*D *(*t* ~u$ % **: ]]_ <