ZjT\hSSKJr SSKJr SSKrSSKJr SSKJr SSKJ r J r SSK J r SS K Jr SS KJrJr SS KJr SS KJrJrJr 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/"SS\R\5r0Sr1S\RdS\3S\Rd4Sjr4S;S\R\S \RdS!\RdS"\RdS#\RdS-S$\5S%\5S&\"\$4S'jjr6S"S8S9\\;5r?/S:Qr@g)=)Callable)OptionalN)nn)ACT2FN)Cache DynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs) Phi3Configcb^\rSrSrU4SjrS\R S\R 4SjrSrU=r $)Phi3MLP1c >[TU]5 Xl[R"UR SUR -SS9Ul[R"UR UR SS9Ul[URUl g)NFbias) super__init__configrLinear hidden_sizeintermediate_size gate_up_proj down_projr hidden_act activation_fnselfr* __class__s w/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/phi3/modeling_phi3.pyr)Phi3MLP.__init__2sn  IIf&8&8!f>V>V:V]bc6#;#;V=O=OV[\#F$5$56 hidden_statesreturncURU5nURSSS9up2X RU5-nURU5$)Nr%dim)r.chunkr1r/)r3r8 up_statesgates r5forwardPhi3MLP.forward:sH%%m4 #//!/4 2 24 88 ~~i((r7)r1r*r/r.) __name__ __module__ __qualname____firstlineno__r)torch FloatTensorrA__static_attributes__ __classcell__r4s@r5r"r"1s,7)U%6%6)5;L;L))r7r"c ^\rSrSr%\R \S'SS\4U4Sjjjr\ SS\S-S\ SS\ S-S \ S \ 44S jj5r\R"5\S 55rS rU=r$)Phi3RotaryEmbeddingCinv_freqNr*c>[TU]5 URUlURUlXlUR R SUlURnURS:wa[URnU"UR U5uo@l URSUSS9 URSUR5SS9 g)N rope_typedefaultrOF) persistentoriginal_inv_freq) r(r)max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr*rope_parametersrQcompute_default_rope_parametersrattention_scalingregister_bufferclone)r3r*device rope_init_fnrOr4s r5r)Phi3RotaryEmbedding.__init__Fs "("@"@$*$B$B! 44[A!%!E!E >>Y &.t~~>L+7 V+L(( ZeD 0(..2BuUr7r]z torch.deviceseq_lenr9z torch.Tensorc jURSnURRSS5n[USS5=(d URUR-n[ XT-5nSnSU[ R"SUS[ RS9RU[ RS 9U- -- nX4$) aH Computes the inverse frequencies according to the original RoPE implementation Args: config ([`~transformers.PreTrainedConfig`]): The model configuration. device (`torch.device`): The device to use for initialization of the inverse frequencies. seq_len (`int`, *optional*): The current sequence length. Unused for this type of RoPE. Returns: Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE). rope_thetapartial_rotary_factorg?head_dimNrr%dtype)r]rf) rXgetgetattrr,num_attention_headsintrGarangeint64tofloat) r*r]r`basercrdr=attention_factorrOs r5rY3Phi3RotaryEmbedding.compute_default_rope_parametersVs&%%l3 & 6 6 : :;RTW X6:t4h8J8JfNhNh8h(23 U\\!S!5;;?BB&X]XcXcBdgjj k ))r7cLURSSS2S4R5RURSSS5R UR 5nUSS2SSS24R5n[ UR R[5(a0UR RS:waUR ROSn[USS9 UR5UR5-RSS5n[R"Xf4SS 9nUR5UR-nUR5UR-n SSS5 WR UR S 9W R UR S 94$!,(df  N@=f) Nrr;rmpscpuF) device_typeenabledr%r<re)rOrnexpandshapermr] isinstancetypestrr transposerGcatcosrZsinrf) r3x position_idsinv_freq_expandedposition_ids_expandedrufreqsembr~rs r5rAPhi3RotaryEmbedding.forwardvsN!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#)rZr*rVrWrQN)NNN)rCrDrErFrGTensor__annotations__r r) staticmethodrrjtuplernrYno_gradrrArIrJrKs@r5rMrMCsllVzVV $(+/"*T!*(*t* ~u$ % **> ]]_ <