^jNYddlmZddlmZddlZddlmZddlmZddlm Z m Z ddl m Z dd l mZmZmZdd lmZmZdd lmZdd lmZmZmZmZdd lmZmZddlmZm Z ddl!m"Z"m#Z#ddl$m%Z%ddl&m'Z'm(Z(m)Z)ddl*m+Z+m,Z,ddl-m.Z.ddl/m0Z0GddejbZ2dZ3edd>dZ4dejjde6dejjfdZ7 d?dejbd ejjd!ejjd"ejjd#ejjdzd$e8d%e8d&e%e'fd'Z9ee4Gd(d)ejbZ:ed*Gd+d,ejbZ;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) SmolLM3Configc eZdZUejed<d deffd Ze d dedzde dde dzde d e ffd Z ejed ZxZS)SmolLM3RotaryEmbeddinginv_freqNconfigct||j|_|j|_||_|j j d|_|j}|jdk7rt|j}||j |\}|_ |jd|d|jd|jdy)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 w/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/smollm3/modeling_smollm3.pyr.zSmolLM3RotaryEmbedding.__init__4s "("@"@$*$B$B! 44[A!%!E!E >>Y &.t~~>L+7 V+L($( ZeD 0(..2BuUr8z 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)r8rD) r2getattr hidden_sizenum_attention_headstorcharangeint64tofloat)r'r8r=basedimattention_factorr&s r;r3z6SmolLM3RotaryEmbedding.compute_default_rope_parametersDs&%%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjj k )))r<cN|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_typeenabledrBrNrC)r&rLexpandshaperKr8 isinstancetypestrr transposerHcatcosr4sinrD) r7x position_idsinv_freq_expandedposition_ids_expandedrTfreqsembr^r_s r;forwardzSmolLM3RotaryEmbedding.forwardbsR!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$N)NNN)__name__ __module__ __qualname__rHTensor__annotations__r#r. staticmethodrinttuplerLr3no_gradrrf __classcell__r:s@r;r%r%1sllV}V '++/"*$*(*t* ~u$ % **:U]]_ <