^jeddlZddlmZddlmZddlZddlmZddlmZ ddl m Z ddl m Z mZdd lmZdd lmZmZmZdd lmZdd lmZmZmZmZdd lmZmZddlm Z m!Z!ddl"m#Z#m$Z$ddl%m&Z&ddl'm(Z(m)Z)m*Z*ddl+m,Z,m-Z-ddl.m/Z/ddl0m1Z1GddejdZ3GddejdZ4dZ5edd?dZ6dejnde8dejnfd Z9 d@d!ejdd"ejnd#ejnd$ejnd%ejndzd&e:d'e:d(e&e(fd)Z;d*Z<ee6Gd+d,ejdZ=ed-Gd.d/ejdZ>Gd0d1eZ?e)Gd2d3e$Z@e)Gd4d5e@ZAe)Gd6d7e@eZBGd8d9ee@ZCGd:d;ee@ZDGd<d=ee@ZEgd>ZFy)AN)Callable)Optional)nn)initialization)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)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs)DiffLlamaConfigc$eZdZfdZdZxZS) DiffLlamaMLPct|||_|j|_|j|_t j |j|jd|_t j |j|jd|_t j |j|jd|_ t|j|_ yNFbias) super__init__config hidden_sizeintermediate_sizerLinear gate_projup_proj down_projr hidden_actact_fnselfr+ __class__s {/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/diffllama/modeling_diffllama.pyr*zDiffLlamaMLP.__init__5s  !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV 4#9#94;K;KRWXV../ c|j|j|j||j|z}|SN)r1r3r/r0)r5xr1s r7forwardzDiffLlamaMLP.forward?s6NN4;;t~~a/@#ADLLQRO#ST r8)__name__ __module__ __qualname__r*r< __classcell__r6s@r7r$r$4s 0r8r$c eZdZUejed<d deffd Ze d dedzde dde dzde d e ffd Z ejed ZxZS)DiffLlamaRotaryEmbeddinginv_freqNr+ct||j|_|j|_||_|j j d|_|j}|jdk7rt|j}||j |\}|_ |jd|d|jd|jdy)N rope_typedefaultrDF) persistentoriginal_inv_freq) r)r*max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr+rope_parametersrFcompute_default_rope_parametersrattention_scalingregister_bufferclone)r5r+device rope_init_fnrDr6s r7r*z!DiffLlamaRotaryEmbedding.__init__Gs "("@"@$*$B$B! 44[A!%!E!E >>Y &.t~~>L+7 V+L($( ZeD 0(..2BuUr8rRz 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_dimNg?rdtype)rRr[) rMgetattrr,num_attention_headstorcharangeint64tofloat)r+rRrTbasedimattention_factorrDs r7rNz8DiffLlamaRotaryEmbedding.compute_default_rope_parametersWs&%%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjj k )))r8cN|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) Nrr!mpscpuF) device_typeenabledrYrdrZ)rDrbexpandshaperarR isinstancetypestrr transposer^catcosrOsinr[) r5r; position_idsinv_freq_expandedposition_ids_expandedrjfreqsembrtrus r7r<z DiffLlamaRotaryEmbedding.forwardusR!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$r:)NNN)r=r>r?r^Tensor__annotations__r"r* staticmethodrinttuplerbrNno_gradrr<r@rAs@r7rCrCDsllVV )-+/"*$&*(*t* ~u$ % **:U]]_ <