^jTddlmZddlmZddlZddlmZddlmZddlm Z ddl m Z m Z dd l mZdd lmZmZmZdd lmZdd lmZmZmZmZdd lmZmZddlmZmZddl m!Z!m"Z"ddl#m$Z$ddl%m&Z&m'Z'ddl(m)Z)m*Z*ddl+m,Z,ddl-m.Z.Gddej^Z0edGddej^Z1Gddej^Z2dZ3edd@dZ4d ejjd!e6d"ejjfd#Z7 dAd$ej^d%ejjd&ejjd'ejjd(ejjdzd)e8d*e8d+e$e&fd,Z9ee4Gd-d.ej^Z:Gd/d0eZ;eGd1d2e"Zed56Gd9d:ee<Z?ed56Gd;dee<ZAgd?ZBy)B)Callable)OptionalN)nn)auto_docstring)ACT2FN)Cache DynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernel_func_from_hubuse_kernelized_func)create_causal_mask)GenericForQuestionAnswering GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargscan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs) ArceeConfigc$eZdZfdZdZxZS)ArceeMLPct|||_|j|_|j|_t j |j|j|j|_t j |j|j|j|_ t|j|_ y)Nbias) super__init__config hidden_sizeintermediate_sizerLinearmlp_biasup_proj down_projr hidden_actact_fnselfr) __class__s s/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/arcee/modeling_arcee.pyr(zArceeMLP.__init__3s  !--!'!9!9yy!1!143I3IPVP_P_` 4#9#94;K;KRXRaRabV../ c`|j|j|j|SN)r/r1r.)r3xs r5forwardzArceeMLP.forward<s"~~dkk$,,q/:;;r6)__name__ __module__ __qualname__r(r: __classcell__r4s@r5r#r#2s 0% Ht?T?T4T(UU {{]--k:::r6c^t|jjd|jS)Nz, eps=)tuplerIshaperJ)r3s r5 extra_reprzArceeRMSNorm.extra_reprQs* ))*+6$2G2G1HIIr6)gư>) r;r<r=floatr(rGTensorr:r[r>r?s@r5rBrB@s7$$$$;U\\;ell;Jr6rBc eZdZUejed<d deffd Ze d dedzde dde dzde d e ffd Z ejed ZxZS)ArceeRotaryEmbeddinginv_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)r3r)device rope_init_fnr`r4s r5r(zArceeRotaryEmbedding.__init__Xs "("@"@$*$B$B! 44[A!%!E!E >>Y &.t~~>L+7 V+L($( ZeD 0(..2BuUr6rnz torch.deviceseq_lenrDz 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?rrMrP)rnrP) rigetattrr*num_attention_headsrGarangeint64rQr\)r)rnrpbasedimattention_factorr`s r5rjz4ArceeRotaryEmbedding.compute_default_rope_parametershs&%%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjj k )))r6cN|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) NrrNr mpscpuF) device_typeenabledrMrzrt)r`r\expandrZrQrn isinstancetypestrr transposerGcatcosrksinrP) r3r9 position_idsinv_freq_expandedposition_ids_expandedrfreqsembrrs r5r:zArceeRotaryEmbedding.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$r8NNN)r;r<r=rGr]__annotations__r!r( staticmethodrintrYr\rjno_gradrr:r>r?s@r5r_r_UsllV{V %)+/"*d"*(*t* ~u$ % **:U]]_ <