^jT\`ddlmZddlmZddlZddlmZddlmZddlm 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\Z0dZ1dejdde3dejdfdZ4 d;dej\d ejdd!ejdd"ejdd#ejddzd$e5d%e5d&e"e$fd'Z6dGd8d9ee;Z?gd:Z@y)=)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) Phi3ConfigcVeZdZfdZdej dej fdZxZS)Phi3MLPc*t|||_tj|j d|j zd|_tj|j |j d|_t|j|_ y)NFbias) super__init__configrLinear hidden_sizeintermediate_size gate_up_proj down_projr hidden_act activation_fnselfr) __class__s q/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/phi3/modeling_phi3.pyr(zPhi3MLP.__init__2sp  IIf&8&8!f>V>V:V]bc6#;#;V=O=OV[\#F$5$56 hidden_statesreturnc|j|}|jdd\}}||j|z}|j|S)Nr$dim)r-chunkr0r.)r2r6 up_statesgates r4forwardzPhi3MLP.forward:sL%%m4 #//!/4i 2 24 88 ~~i((r5)__name__ __module__ __qualname__r(torch FloatTensorr? __classcell__r3s@r4r"r"1s'7)U%6%6)5;L;L)r5r"c eZdZUejed<d deffd Ze d dedzde dde dzde d e ffd Z ejed ZxZS)Phi3RotaryEmbeddinginv_freqNr)ct||j|_|j|_||_|j j d|_|j}|jdk7rt|j}||j |\}|_ |jd|d|jd|jdy)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$B! 44[A!%!E!E >>Y &.t~~>L+7 V+L($( ZeD 0(..2BuUr5rWz torch.deviceseq_lenr7z torch.Tensorcn|jd}|jjdd}t|ddxs|j|jz}t ||z}d}d|t jd|dt jj|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$dtype)rWr_) rRgetgetattrr+num_attention_headsintrCarangeint64tofloat) r)rWrYbaser\r]r;attention_factorrIs r4rSz3Phi3RotaryEmbedding.compute_default_rope_parametersVs&%%l3 & 6 6 : :;RTW X6:t4h8J8JfNhNh8h(223 U\\!S!5;;?BB&X]XcXcBdgjj k )))r5cN|jddddfjj|jdddj |j }|dddddfj}t |j jtr/|j jdk7r|j jnd}t|d5|j|jzjdd}tj||fd }|j|jz}|j|jz} dddj |j  j |j fS#1swYAxYw) Nrr9rmpscpuF) device_typeenabledr$r:r^)rIrgexpandshaperfrW isinstancetypestrr transposerCcatcosrTsinr_) r2x position_idsinv_freq_expandedposition_ids_expandedrmfreqsembrvrws r4r?zPhi3RotaryEmbedding.forwardvsR!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$N)NNN)r@rArBrCTensor__annotations__r r( staticmethodrrctuplergrSno_gradrr?rErFs@r4rHrHCsllVzV $(+/"*T!*(*t* ~u$ % **>U]]_ <