ZjUSSKJr SSKJr SSKrSSKJr SSKJr SSKJ r J r SSK J r SS K JrJrJr SS KJrJr SS KJr SS KJrJrJrJr SS KJrJr SSKJrJ r SSK!J"r"J#r# SSK$J%r% SSK&J'r'J(r(J)r) SSK*J+r+J,r, SSK-J.r. SSK/J0r0 "SS\Rb5r2"SS\Rb5r3Sr4\"S5S>Sj5r5S\RlS\7S\Rl4S jr8S?S!\RbS"\RlS#\RlS$\RlS%\RlS-S&\9S'\9S(\%\'4S)jjr:\"\55"S*S+\Rb55r;\"S,5"S-S.\Rb55r<"S/S0\5r=\("S1S2\#55r>\("S3S4\>55r?\("S5S6\>\ 55r@"S7S8\\>5rA"S9S:\\>5rB"S;S<\\>5rC/S=QrDg)@)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)GenericForQuestionAnswering GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs) Qwen2Configc.^\rSrSrU4SjrSrSrU=r$)Qwen2MLP#c>[TU]5 XlURUlURUl[ R "URURSS9Ul[ R "URURSS9Ul[ R "URURSS9Ul [URUl gNFbias) super__init__config hidden_sizeintermediate_sizerLinear gate_projup_proj down_projr hidden_actact_fnselfr- __class__s y/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/qwen2/modeling_qwen2.pyr,Qwen2MLP.__init__$s  !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV 4#9#94;K;KRWXV../ cURURURU55URU5-5nU$N)r3r5r1r2)r7xr3s r9forwardQwen2MLP.forward.s6NN4;;t~~a/@#ADLLQRO#ST r;)r5r-r3r1r.r/r2)__name__ __module__ __qualname____firstlineno__r,r?__static_attributes__ __classcell__r8s@r9r%r%#s0r;r%c ^\rSrSr%\R \S'SS\4U4Sjjjr\ SS\S-S\ SS\ S-S \ S \ 44S jj5r\R"5\S 55rS rU=r$)Qwen2RotaryEmbedding3inv_freqNr-c>[TU]5 URUlURUlXlUR R SUlURnURS:wa[URnU"UR U5uo@l URSUSS9 URSUR5SS9 g)N rope_typedefaultrKF) persistentoriginal_inv_freq) r+r,max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr-rope_parametersrMcompute_default_rope_parametersrattention_scalingregister_bufferclone)r7r-device rope_init_fnrKr8s r9r,Qwen2RotaryEmbedding.__init__6s "("@"@$*$B$B! 44[A!%!E!E >>Y &.t~~>L+7 V+L(( ZeD 0(..2BuUr;rYz torch.deviceseq_lenreturnz torch.Tensorc URSn[USS5=(d URUR-nSnSU[R "SUS[R S9RU[RS9U- -- nXe4$) 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)rYrc) rTgetattrr.num_attention_headstorcharangeint64tofloat)r-rYr\basedimattention_factorrKs r9rU4Qwen2RotaryEmbedding.compute_default_rope_parametersFs&%%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) Nrr"mpscpuF) device_typeenabledrarlrb)rKrjexpandshaperirY isinstancetypestrr transposerfcatcosrVsinrc) r7r> position_idsinv_freq_expandedposition_ids_expandedrsfreqsembr}r~s r9r?Qwen2RotaryEmbedding.forwarddsN!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#)rVr-rRrSrMr=)NNN)rArBrCrDrfTensor__annotations__r#r, staticmethodrinttuplerjrUno_gradrr?rErFrGs@r9rIrI3sllV{VV %)+/"*d"*(*t* ~u$ % **: ]]_ <