tjy}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,Gddej-Z.dZ/eddBdZ0dej1de2dej1fdZ3 dCd ej-d!ej1d"ej1d#ej1d$ej1dzd%e4d&e4d'e!e#fd(Z5Gd)d*ej-Z6Gd+d,ej-Z7Gd-d.ej-Z8Gd/d0ej-Z9Gd1d2ej-Z:Gd3d4ej-Z;Gd5d6eZ<Gd7d8eZ=e$Gd9d:e=Z> dDdZ@Gd?d@e=eZAgdAZBdS)E)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|_||_|jjd|_|j}|jdkrt|j}||j|\}|_ | d|d| d| ddS)N rope_typedefaultr!F) persistentoriginal_inv_freq) super__init__max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr"rope_parametersr$compute_default_rope_parametersrattention_scalingregister_bufferclone)selfr"device rope_init_fnr! __class__s d/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/dbrx/modeling_dbrx.pyr)zDbrxRotaryEmbedding.__init__/s "("@$*$B! 4[A!%!E >Y & &.t~>L+7< V+L+L($( ZeDDD 0(..2B2BuUUUUUr3z 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_dimN?rdtype)r3r@) r-getattr hidden_sizenum_attention_headstorcharangeint64tofloat)r"r3r8basedimattention_factorr!s r6r.z3DbrxRotaryEmbedding.compute_default_rope_parameters?s&%l3fj$//c63EIc3c U\!S!5;???BB&X]XcBddgjj k )))r7cN|jddddf|jddd|j}|dddddf}t |jjtr|jjdkr |jjnd}t|d5||z dd}tj ||fd }| |jz}||jz} dddn #1swxYwY||j | |j fS) NrrmpscpuF) device_typeenabledr>rJr?)r!rHexpandshaperGr3 isinstancetypestrr transposerDcatcosr/sinr@) r2x position_idsinv_freq_expandedposition_ids_expandedrPfreqsembrZr[s r6forwardzDbrxRotaryEmbedding.forward]s!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*NNNN)__name__ __module__ __qualname__rDTensor__annotations__rr) staticmethodrinttuplerHr.no_gradrrb __classcell__r5s@r6r r ,slVVzVVVVVV $(+/"**T!*(*t* ~u$ % ***\*:U]__ < <_ < < < <