^jC`PdZddlmZddlmZddlZddlmZddlmZddl m Z m Z dd l m Z dd lmZdd lmZmZmZdd lmZmZdd lmZmZddlmZmZddlmZddlm Z m!Z!m"Z"m#Z#ddl$m%Z%m&Z&ddl'm(Z(ddl)m*Z*e#jVe,Z-Gddej\Z/dZ0d9dZ1Gddej\Z2Gddej\Z3dejhde5dejhfd Z6 d:d!ej\d"ejhd#ejhd$ejhd%ejhdzd&e7d'e7d(ee fd)Z8Gd*d+ej\Z9Gd,d-eZ:e!Gd.d/eZ;e!Gd0d1e;Z<Gd2d3e;e Z=Gd4d5ee;Z>Gd6d7ee;Z?gd8Z@y);zPyTorch StableLM model.)Callable)OptionalN)nn)ACT2FN)Cache DynamicCache)GenerationMixin)create_causal_mask) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuplelogging)maybe_autocastmerge_with_config_defaults)capture_outputs)StableLmConfigc eZdZUejed<d deffd Ze d dedzde dde dzde d e ffd Z ejed ZxZS)StableLmRotaryEmbeddinginv_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$compute_default_rope_parametersrattention_scalingregister_bufferclone)selfr"device rope_init_fnr! __class__s y/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/stablelm/modeling_stablelm.pyr)z StableLmRotaryEmbedding.__init__;s "("@"@$*$B$B! 44[A!%!E!E >>Y &.t~~>L+7 V+L($( ZeD 0(..2BuUr3z torch.deviceseq_lenreturnz 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_dimNrdtype)r3r@) r-getgetattr hidden_sizenum_attention_headsinttorcharangeint64tofloat) r"r3r8baser<r=dimattention_factorr!s r6r.z7StableLmRotaryEmbedding.compute_default_rope_parametersKs(%%l3 & 6 6 : :;RTW X6:t4h8J8JfNhNh8h(223 U\\!S!5;;?BB&X]XcXcBdgjj k )))r7cN|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) NrrmpscpuF) device_typeenabledr>rLr?)r!rJexpandshaperIr3 isinstancetypestrr transposerFcatcosr/sinr@) r2x position_idsinv_freq_expandedposition_ids_expandedrRfreqsembr\r]s r6forwardzStableLmRotaryEmbedding.forwardlsR!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$N)NNN)__name__ __module__ __qualname__rFTensor__annotations__rr) staticmethodrrEtuplerJr.no_gradrrd __classcell__r5s@r6r r 8sllV~V )-+/"*%*(*t* ~u$ % **>U]]_ <