^j]UlddlmZddlmZddlZddlmZddlmZmZddl m Z m Z ddl m Z dd lmZmZmZdd lmZdd lmZmZdd lmZmZdd lmZmZddlmZmZddl m!Z!ddl"m#Z#m$Z$m%Z%ddl&m'Z'm(Z(ddl)m*Z*ddl+m,Z,GddejZZ.edGddejZZ/GddejZZ0dZ1edd9dZ2dejfd e4d!ejffd"Z5 d:d#ejZd$ejfd%ejfd&ejfd'ejfdzd(e6d)e6d*e!e#fd+Z7ee2Gd,d-ejZZ8Gd.d/eZ9e$Gd0d1eZ:e$Gd2d3e:Z;e$Gd4d5e:e Z<Gd6d7ee:Z=gd8Z>y);)Callable)OptionalN)nn)ACT2CLSACT2FN)Cache DynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernel_func_from_hubuse_kernelized_func)create_causal_mask)GenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs) ApertusConfigc$eZdZfdZdZxZS) ApertusMLPct|||_|j|_|j|_t j |j|jd|_t j |j|jd|_t|j|_ |jdk(rtd|j|_ yy)NFbiasxieludtype)super__init__config hidden_sizeintermediate_sizerLinearup_proj down_projr hidden_actact_fnrr(selfr+ __class__s w/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/apertus/modeling_apertus.pyr*zApertusMLP.__init__,s  !--!'!9!9yy!1!143I3IPUV 4#9#94;K;KRWXV../    '!'*>DK (c`|j|j|j|SN)r0r2r/)r4xs r6forwardzApertusMLP.forward7s"~~dkk$,,q/:;;r7)__name__ __module__ __qualname__r*r; __classcell__r5s@r6r"r"+s  ?% Ht?T?T4T(UU {{]--k:::r7c^t|jjd|jS)Nz, eps=)tuplerJshaperK)r4s r6 extra_reprzApertusRMSNorm.extra_reprLs* ))*+6$2G2G1HIIr7)gư>) r<r=r>floatr*rHTensorr;r[r?r@s@r6rCrC;s7$$$$;U\\;ell;Jr7rCc eZdZUejed<d deffd Ze d dedzde dde dzde d e ffd Z ejed ZxZS)ApertusRotaryEmbeddinginv_freqNr+ct||j|_|j|_||_|j j d|_|j}|jdk7rt|j}||j |\}|_ |jd|d|jd|jdy)N rope_typedefaultr`F) persistentoriginal_inv_freq) r)r*max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr+rope_parametersrbcompute_default_rope_parametersrattention_scalingregister_bufferclone)r4r+device rope_init_fnr`r5s r6r*zApertusRotaryEmbedding.__init__Ss "("@"@$*$B$B! 44[A!%!E!E >>Y &.t~~>L+7 V+L($( ZeD 0(..2BuUr7rnz torch.deviceseq_lenrEz torch.Tensorc|jd}t|ddxs|j|jz}d}d|t j d|dtj j|tj|z zz }||fS) a 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?rrNr')rnr() rigetattrr,num_attention_headsrHarangeint64rQr\)r+rnrpbasedimattention_factorr`s r6rjz6ApertusRotaryEmbedding.compute_default_rope_parameterscs&%%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjj k )))r7cN|jddddfjj|jdddj |j }|dddddfj}t |j jtr/|j jdk7r|j jnd}t|d5|j|jzjdd}tj||fd }|j|jz}|j|jz} dddj |j  j |j fS#1swYAxYw) NrrOrmpscpuF) device_typeenabledrNryr')r`r\expandrZrQrn isinstancetypestrr transposerHcatcosrksinr() r4r: position_idsinv_freq_expandedposition_ids_expandedr~freqsembrrs r6r;zApertusRotaryEmbedding.forwardsR!MM$4-8>>@GG HZHZ[\H]_acdehhijiqiqr ,QaZ 8 > > @'1!((--'E!((--[`J`ahhmmfk  U C 5&,,.1F1L1L1NNYYZ[]^_E))UEN3C'')d444C'')d444C  5 vvAGGv$cff177f&;;;  5 5s BFF$r9)NNN)r<r=r>rHr]__annotations__r r* staticmethodrintrYr\rjno_gradrr;r?r@s@r6r_r_PsllV}V '++/"*$*(*t* ~u$ % **:U]]_ <