^jUddlmZddlmZddlZddlmZddlmZddlm Z m Z ddl m Z dd l mZmZmZdd lmZmZdd lmZdd lmZmZmZmZdd lmZmZddlmZm Z ddl!m"Z"m#Z#ddl$m%Z%ddl&m'Z'm(Z(m)Z)ddl*m+Z+m,Z,ddl-m.Z.ddl/m0Z0GddejbZ2GddejbZ3dZ4edd>dZ5dejlde7dejlfd Z8 d?d!ejbd"ejld#ejld$ejld%ejldzd&e9d'e9d(e%e'fd)Z:ee5Gd*d+ejbZ;ed,Gd-d.ejbZ<Gd/d0eZ=e(Gd1d2e#Z>e(Gd3d4e>Z?e(Gd5d6e>e Z@Gd7d8ee>ZAGd9d:ee>ZBGd;dZCgd=ZDy)@)Callable)OptionalN)nn)ACT2FN)Cache DynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernel_func_from_hubuse_kernelized_func)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs)GenericForQuestionAnswering GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs) Qwen2Configc$eZdZfdZdZxZS)Qwen2MLPct|||_|j|_|j|_t j |j|jd|_t j |j|jd|_t j |j|jd|_ t|j|_ yNFbias) super__init__config hidden_sizeintermediate_sizerLinear gate_projup_proj down_projr hidden_actact_fnselfr, __class__s s/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/qwen2/modeling_qwen2.pyr+zQwen2MLP.__init__$s  !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV 4#9#94;K;KRWXV../ c|j|j|j||j|z}|SN)r2r4r0r1)r6xr2s r8forwardzQwen2MLP.forward.s6NN4;;t~~a/@#ADLLQRO#ST r9)__name__ __module__ __qualname__r+r= __classcell__r7s@r8r%r%#s 0r9r%c eZdZUejed<d deffd Ze d dedzde dde dzde d e ffd Z ejed ZxZS)Qwen2RotaryEmbeddinginv_freqNr,ct||j|_|j|_||_|j j d|_|j}|jdk7rt|j}||j |\}|_ |jd|d|jd|jdy)N rope_typedefaultrEF) persistentoriginal_inv_freq) r*r+max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr,rope_parametersrGcompute_default_rope_parametersrattention_scalingregister_bufferclone)r6r,device rope_init_fnrEr7s r8r+zQwen2RotaryEmbedding.__init__6s "("@"@$*$B$B! 44[A!%!E!E >>Y &.t~~>L+7 V+L($( ZeD 0(..2BuUr9rSz torch.deviceseq_lenreturnz torch.Tensorc|jd}t|ddxs|j|jz}d}d|t j d|dtj j|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)rSr\) rNgetattrr-num_attention_headstorcharangeint64tofloat)r,rSrUbasedimattention_factorrEs r8rOz4Qwen2RotaryEmbedding.compute_default_rope_parametersFs&%%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjj k )))r9cN|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) Nrr"mpscpuF) device_typeenabledrZrer[)rErcexpandshaperbrS isinstancetypestrr transposer_catcosrPsinr\) r6r< position_idsinv_freq_expandedposition_ids_expandedrkfreqsembrurvs r8r=zQwen2RotaryEmbedding.forwarddsR!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$r;)NNN)r>r?r@r_Tensor__annotations__r#r+ staticmethodrinttuplercrOno_gradrr=rArBs@r8rDrD3sllV{V %)+/"*d"*(*t* ~u$ % **:U]]_ <