^jiddlmZddlmZddlmZddlmZddlm Z ddl m Z ddl m Z dd lmZmZmZmZdd lmZmZdd lmZmZdd lmZdd lmZmZmZmZddl m!Z!m"Z"m#Z#ddl$m%Z%ddl&m'Z'ddl(m)Z)m*Z*er ddl+Z+ddl+m,Z,Gdde,jZZ.dZ/de+j`de1de+j`fdZ2 d?de,jZde+j`de+j`d e+j`d!e+j`dzd"e3d#e3d$eefd%Z4d@d&Z5Gd'd(e,jZZ6Gd)d*e,jZZ7Gd+d,e Z8eGd-d.eZ9Gd/d0e9Z:Gd1d2e,jZZ;eGd3d4eZ<ed56Gd7d8e9Z=ed96eGd:d;eZ>ed56Gd<d=e9e Z?gd>Z@y)A)Callable) dataclass)Optional)ACT2FN)Cache)GenerationMixin)GradientCheckpointingLayer)BaseModelOutputWithPastBaseModelOutputWithPoolingCausalLMOutputWithPast ModelOutput)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringis_torch_availabletorch_compilable_check)can_return_tuplemaybe_autocastmerge_with_config_defaults)capture_outputs) AutoModel) GlmAsrConfigGlmAsrEncoderConfigN)nnc eZdZUejed<d deffd Ze d dedzde dde dzde d e ffd Z ejed ZxZS)GlmAsrRotaryEmbeddinginv_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 u/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/glmasr/modeling_glmasr.pyr,zGlmAsrRotaryEmbedding.__init__5s "("@"@$*$B$B! 44[A!%!E!E >>Y &.t~~>L+7 V+L($( ZeD 0(..2BuUr6z 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_dimNrrdtype)r6rB) r0getgetattr hidden_sizenum_attention_headsinttorcharangeint64tofloat) r%r6r;baser?r@dimattention_factorr$s r9r1z5GlmAsrRotaryEmbedding.compute_default_rope_parametersEs&%%l3 & 6 6 : :;RTW X6:t4h8J8JfNhNh8h(223 U\\!S!5;;?BB&X]XcXcBdgjj k )))r:cN|jddddfjj|jdddj |j }|dddddfj}t |j jtr/|j jdk7r|j jnd}t|d5|j|jzjdd}tj||fd }|j|jz}|j|jz} dddj |j  j |j fS#1swYAxYw) NrrmpscpuF) device_typeenabledrrNrA)r$rLexpandshaperKr6 isinstancetypestrr transposerHcatcosr2sinrB) r5x position_idsinv_freq_expandedposition_ids_expandedrTfreqsembr^r_s r9forwardzGlmAsrRotaryEmbedding.forwardesR!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$N)NNN)__name__ __module__ __qualname__rHTensor__annotations__rr, staticmethodrrGtuplerLr1no_gradrrf __classcell__r8s@r9r#r#2sllV|V &*+/"*t#*(*t* ~u$ % **>U]]_ <