^jy}&ddlmZddlmZmZddlZddlmZddlmZ ddl m Z ddl m Z mZdd lmZdd lmZdd lmZdd lmZdd lmZmZddlmZmZddlmZmZddl m!Z!ddl"m#Z#m$Z$m%Z%ddl&m'Z'm(Z(ddl)m*Z*ddl+m,Z,GddejZZ.dZ/edd@dZ0dejbde2dejbfdZ3 dAdejZd ejbd!ejbd"ejbd#ejbdzd$e4d%e4d&e!e#fd'Z5Gd(d)ejZZ6Gd*d+ejZZ7Gd,d-ejZZ8Gd.d/ejZZ9Gd0d1ejZZ:Gd2d3ejZZ;Gd4d5eZ<Gd6d7eZ=e$Gd8d9e=Z> dBd:ejbe?ejbzdzd;e2dzd#ejbdzdejbe2zfd<Z@Gd=d>e=eZAgd?ZBy)C)Callable)AnyOptionalN)nn)initialization)ACT2FN)Cache DynamicCache)GenerationMixin)use_kernel_func_from_hub)create_causal_mask)GradientCheckpointingLayer)MoeCausalLMOutputWithPastMoeModelOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs) DbrxConfigc eZdZUejed<d deffd Ze d dedzde dde dzde d e ffd Z ejed ZxZS)DbrxRotaryEmbeddinginv_freqNconfigct||j|_|j|_||_|j j d|_|j}|jdk7rt|j}||j |\}|_ |jd|d|jd|jdy)N rope_typedefaultr!F) persistentoriginal_inv_freq) super__init__max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr"rope_parametersr$compute_default_rope_parametersrattention_scalingregister_bufferclone)selfr"device rope_init_fnr! __class__s q/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/dbrx/modeling_dbrx.pyr)zDbrxRotaryEmbedding.__init__/s "("@"@$*$B$B! 44[A!%!E!E >>Y &.t~~>L+7 V+L($( ZeD 0(..2BuUr3z torch.deviceseq_lenreturnz torch.Tensorc|jd}t|ddxs|j|jz}d}d|t j d|dtj j|tj|z zz }||fS) a Computes the inverse frequencies according to the original RoPE implementation Args: config ([`~transformers.PreTrainedConfig`]): The model configuration. device (`torch.device`): The device to use for initialization of the inverse frequencies. seq_len (`int`, *optional*): The current sequence length. Unused for this type of RoPE. Returns: Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE). rope_thetahead_dimN?rdtype)r3r@) r-getattr hidden_sizenum_attention_headstorcharangeint64tofloat)r"r3r8basedimattention_factorr!s r6r.z3DbrxRotaryEmbedding.compute_default_rope_parameters?s&%%l3fj$/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) NrrmpscpuF) device_typeenabledr>rJr?)r!rHexpandshaperGr3 isinstancetypestrr transposerDcatcosr/sinr@) r2x position_idsinv_freq_expandedposition_ids_expandedrPfreqsembrZr[s r6forwardzDbrxRotaryEmbedding.forward]sR!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$NNNN)__name__ __module__ __qualname__rDTensor__annotations__rr) staticmethodrinttuplerHr.no_gradrrb __classcell__r5s@r6r r ,sllVzV $(+/"*T!*(*t* ~u$ % **:U]]_ <