tjeddlZddlmZddlmZddlZddlmZddlmZ 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/ddl0m1Z1Gddej2Z3Gddej2Z4dZ5edd@dZ6dej7de8dej7fd Z9 dAd"ej2d#ej7d$ej7d%ej7d&ej7dzd'e:d(e:d)e&e(fd*Z;d+Z<ee6Gd,d-ej2Z=ed.Gd/d0ej2Z>Gd1d2eZ?e)Gd3d4e$Z@e)Gd5d6e@ZAe)Gd7d8e@eZBGd9d:ee@ZCGd;dee@ZEgd?ZFdS)BN)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$eZdZfdZdZxZS) DiffLlamaMLPct||_|j|_|j|_t j|j|jd|_t j|j|jd|_t j|j|jd|_ t|j |_ dSNFbias) super__init__config hidden_sizeintermediate_sizerLinear gate_projup_proj down_projr hidden_actact_fnselfr+ __class__s n/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/diffllama/modeling_diffllama.pyr*zDiffLlamaMLP.__init__5s  !-!'!94#3T5KRWXXXy!143IPUVVV 4#94;KRWXXXV./ c||||||z}|SN)r1r3r/r0)r5xr1s r7forwardzDiffLlamaMLP.forward?sANN4;;t~~a/@/@#A#ADLLQROO#STT r8)__name__ __module__ __qualname__r*r< __classcell__r6s@r7r$r$4sG00000r8r$c eZdZUejed<d deffd Ze d dedzde dde dzde d e ffd Z ejed ZxZS)DiffLlamaRotaryEmbeddinginv_freqNr+ct|j|_|j|_||_|jjd|_|j}|jdkrt|j}||j|\}|_ | d|d| d| ddS)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! 4[A!%!E >Y & &.t~>L+7< V+L+L($( ZeDDD 0(..2B2BuUUUUUr8rRz torch.deviceseq_lenreturnz torch.Tensorc|jd}t|ddp|j|jz}d}d|t jd|dtj|tj|z zz }||fS) a Computes the inverse frequencies according to the original RoPE implementation Args: config ([`~transformers.PreTrainedConfig`]): The model configuration. device (`torch.device`): The device to use for initialization of the inverse frequencies. seq_len (`int`, *optional*): The current sequence length. Unused for this type of RoPE. Returns: Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE). rope_thetahead_dimNg?rdtype)rRr[) rMgetattrr,num_attention_headstorcharangeint64tofloat)r+rRrTbasedimattention_factorrDs r7rNz8DiffLlamaRotaryEmbedding.compute_default_rope_parametersWs&%l3fj$//c63EIc3c U\!S!5;???BB&X]XcBddgjj k )))r8cN|jddddf|jddd|j}|dddddf}t |jjtr|jjdkr |jjnd}t|d5||z dd}tj ||fd }| |jz}||jz} dddn #1swxYwY||j | |j fS) Nrr!mpscpuF) device_typeenabledrYrdrZ)rDrbexpandshaperarR isinstancetypestrr transposer^catcosrOsinr[) r5r; position_idsinv_freq_expandedposition_ids_expandedrjfreqsembrtrus r7r<z DiffLlamaRotaryEmbedding.forwardus!M$4-8>>@@GG HZ[\H]_acdeehhijiqrr ,QQQaaaZ 8 > > @ @'1!(-'E'Ek!(-[`J`J`ahmmfk  U C C C 5 5&,,..1F1L1L1N1NNYYZ[]^__E)UEN333C''))d44C''))d44C  5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 vvAGv$$cff17f&;&;;;s BE&&E*-E*r:)NNN)r=r>r?r^Tensor__annotations__r"r* staticmethodrinttuplerbrNno_gradrr<r@rAs@r7rCrCDslVVVVVVVV )-+/"**$&*(*t* ~u$ % ***\*:U]__ < <_ < < < <