tjqQDddlmZddlmZddlZddlmZddlmZddl m Z m Z ddl m Z ddlmZmZdd lmZdd lmZmZmZdd lmZmZdd lmZmZdd lmZmZddl m!Z!ddl"m#Z#m$Z$ddl%m&Z&m'Z'm(Z(ddl)m*Z*ddl+m,Z,Gddej-Z.dZ/edd8dZ0dej1de2dej1fdZ3 d9dej-dej1d ej1d!ej1d"ej1dzd#e4d$e4d%e!e#fd&Z5ee0Gd'd(ej-Z6Gd)d*ej-Z7Gd+d,eZ8e$Gd-d.eZ9e$Gd/d0e9Z:e$Gd1d2e9e Z;Gd3d4ee9Z<Gd5d6ee9Z=gd7Z>dS):)Callable)OptionalN)ACT2FN)Cache DynamicCache)GenerationMixin)use_kernel_func_from_hubuse_kernelized_func)create_causal_mask) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstring)can_return_tuplemaybe_autocastmerge_with_config_defaults)capture_outputs) PhiConfigc eZdZUejed<d deffd Ze d dedzde dde dzde d e ffd Z ejed ZxZS)PhiRotaryEmbeddinginv_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$compute_default_rope_parametersrattention_scalingregister_bufferclone)selfr"device rope_init_fnr! __class__s b/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/phi/modeling_phi.pyr)zPhiRotaryEmbedding.__init__$s "("@$*$B! 4[A!%!E >Y & &.t~>L+7< V+L+L($( ZeDDD 0(..2B2BuUUUUUr3z torch.deviceseq_lenreturnz torch.TensorcV|jd}|jdd}t|ddp|j|jz}t ||z}d}d|t jd|dt j |t j |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_thetapartial_rotary_factorg?head_dimNrdtype)r3r@) r-getgetattr hidden_sizenum_attention_headsinttorcharangeint64tofloat) r"r3r8baser<r=dimattention_factorr!s r6r.z2PhiRotaryEmbedding.compute_default_rope_parameters4s&%l3 & 6 : :;RTW X X6:t44h8JfNh8h(2233 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>rLr?)r!rJexpandshaperIr3 isinstancetypestrr transposerFcatcosr/sinr@) r2x position_idsinv_freq_expandedposition_ids_expandedrRfreqsembr\r]s r6forwardzPhiRotaryEmbedding.forwardTs!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*N)NNN)__name__ __module__ __qualname__rFTensor__annotations__rr) staticmethodrrEtuplerJr.no_gradrrd __classcell__r5s@r6r r !slVVyVVVVVV #'+/"**D *(*t* ~u$ % ***\*>U]__ < <_ < < < <