tjNYddlmZddlmZddlZddlmZddlmZddlm Z m Z ddl m Z dd l mZmZmZdd lmZmZdd lmZdd lmZmZmZmZdd lmZmZddlmZm Z ddl!m"Z"m#Z#ddl$m%Z%ddl&m'Z'm(Z(m)Z)ddl*m+Z+m,Z,ddl-m.Z.ddl/m0Z0Gddej1Z2dZ3edd?dZ4dej5de6dej5fdZ7 d@d ej1d!ej5d"ej5d#ej5d$ej5dzd%e8d&e8d'e%e'fd(Z9ee4Gd)d*ej1Z:ed+Gd,d-ej1Z;Gd.d/ej1Z<Gd0d1eZ=e(Gd2d3e#Z>e(Gd4d5e>Z?e(Gd6d7e>e Z@Gd8d9ee>ZAGd:d;ee>ZBGd<d=ee>ZCgd>ZDdS)A)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|_||_|jjd|_|j}|jdkrt|j}||j|\}|_ | d|d| d| ddS)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 j/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/smollm3/modeling_smollm3.pyr.zSmolLM3RotaryEmbedding.__init__4s "("@$*$B! 4[A!%!E >Y & &.t~>L+7< V+L+L($( ZeDDD 0(..2B2BuUUUUUr8z torch.deviceseq_lenreturnz torch.Tensorc|jd}t|ddp|j|jz}d}d|t jd|dtj|tj|z zz }||fS) a Computes the inverse frequencies according to the original RoPE implementation Args: config ([`~transformers.PreTrainedConfig`]): The model configuration. device (`torch.device`): The device to use for initialization of the inverse frequencies. seq_len (`int`, *optional*): The current sequence length. Unused for this type of RoPE. Returns: Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE). rope_thetahead_dimNg?rdtype)r8rD) r2getattr hidden_sizenum_attention_headstorcharangeint64tofloat)r'r8r=basedimattention_factorr&s r;r3z6SmolLM3RotaryEmbedding.compute_default_rope_parametersDs&%l3fj$//c63EIc3c U\!S!5;???BB&X]XcBddgjj k )))r<cN|jddddf|jddd|j}|dddddf}t |jjtr|jjdkr |jjnd}t|d5||z dd}tj ||fd }| |jz}||jz} dddn #1swxYwY||j | |j fS) Nrr"mpscpuF) device_typeenabledrBrNrC)r&rLexpandshaperKr8 isinstancetypestrr transposerHcatcosr4sinrD) r7x position_idsinv_freq_expandedposition_ids_expandedrTfreqsembr^r_s r;forwardzSmolLM3RotaryEmbedding.forwardbs!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)__name__ __module__ __qualname__rHTensor__annotations__r#r. staticmethodrinttuplerLr3no_gradrrf __classcell__r:s@r;r%r%1slVV}VVVVVV '++/"**$*(*t* ~u$ % ***\*:U]__ < <_ < < < <