tjT\TddlmZddlmZddlZddlmZddlmZddlm Z m Z ddl m Z dd l mZdd lmZmZdd lmZdd lmZmZmZdd lmZmZddlmZmZddlmZm Z ddl!m"Z"ddl#m$Z$m%Z%m&Z&ddl'm(Z(m)Z)ddl*m+Z+ddl,m-Z-Gddej.Z/Gddej.Z0dZ1dej2de3dej2fdZ4 dGd9d:ee;Z?gd;Z@dS)>)Callable)OptionalN)nn)ACT2FN)Cache DynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs) Phi3ConfigcBeZdZfdZdejdejfdZxZS)Phi3MLPc"t||_tj|jd|jzd|_tj|j|jd|_t|j |_ dS)NFbias) super__init__configrLinear hidden_sizeintermediate_size gate_up_proj down_projr hidden_act activation_fnselfr) __class__s d/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/phi3/modeling_phi3.pyr(zPhi3MLP.__init__2sz  If&8!f>V:V]bccc6#;V=OV[\\\#F$56 hidden_statesreturnc||}|dd\}}|||z}||S)Nr$dim)r-chunkr0r.)r2r6 up_statesgates r4forwardzPhi3MLP.forward:sX%%m44 #//!/44i 2 24 8 88 ~~i(((r5)__name__ __module__ __qualname__r(torch FloatTensorr? __classcell__r3s@r4r"r"1s`77777)U%6)5;L))))))))r5r"c eZdZUejed<d deffd Ze d dedzde dde dzde d e ffd Z ejed ZxZS)Phi3RotaryEmbeddinginv_freqNr)ct|j|_|j|_||_|jjd|_|j}|jdkrt|j}||j|\}|_ | d|d| d| ddS)N rope_typedefaultrIF) persistentoriginal_inv_freq) r'r(max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr)rope_parametersrKcompute_default_rope_parametersrattention_scalingregister_bufferclone)r2r)device rope_init_fnrIr3s r4r(zPhi3RotaryEmbedding.__init__Fs "("@$*$B! 4[A!%!E >Y & &.t~>L+7< V+L+L($( ZeDDD 0(..2B2BuUUUUUr5rWz torch.deviceseq_lenr7z torch.TensorcV|jd}|jdd}t|ddp|j|jz}t ||z}d}d|t jd|dt j |t j |z zz }||fS) a Computes the inverse frequencies according to the original RoPE implementation Args: config ([`~transformers.PreTrainedConfig`]): The model configuration. device (`torch.device`): The device to use for initialization of the inverse frequencies. seq_len (`int`, *optional*): The current sequence length. Unused for this type of RoPE. Returns: Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE). rope_thetapartial_rotary_factorg?head_dimNrr$dtype)rWr_) rRgetgetattrr+num_attention_headsintrCarangeint64tofloat) r)rWrYbaser\r]r;attention_factorrIs r4rSz3Phi3RotaryEmbedding.compute_default_rope_parametersVs&%l3 & 6 : :;RTW X X6:t44h8JfNh8h(2233 U\!S!5;???BB&X]XcBddgjj k )))r5cN|jddddf|jddd|j}|dddddf}t |jjtr|jjdkr |jjnd}t|d5||z dd}tj ||fd }| |jz}||jz} dddn #1swxYwY||j | |j fS) Nrr9rmpscpuF) device_typeenabledr$r:r^)rIrgexpandshaperfrW isinstancetypestrr transposerCcatcosrTsinr_) r2x position_idsinv_freq_expandedposition_ids_expandedrmfreqsembrvrws r4r?zPhi3RotaryEmbedding.forwardvs!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)r@rArBrCTensor__annotations__r r( staticmethodrrctuplergrSno_gradrr?rErFs@r4rHrHCslVVzVVVVVV $(+/"**T!*(*t* ~u$ % ***\*>U]__ < <_ < < < <