tjiddlmZddlmZddlmZddlmZddlm Z ddl m Z ddl m Z dd lmZmZmZmZdd lmZmZdd lmZmZdd lmZdd lmZmZmZmZddl m!Z!m"Z"m#Z#ddl$m%Z%ddl&m'Z'ddl(m)Z)m*Z*er ddl+Z+ddl+m,Z,Gdde,j-Z.dZ/de+j0de1de+j0fdZ2 d@de,j-de+j0d e+j0d!e+j0d"e+j0dzd#e3d$e3d%eefd&Z4dAd'Z5Gd(d)e,j-Z6Gd*d+e,j-Z7Gd,d-e Z8eGd.d/eZ9Gd0d1e9Z:Gd2d3e,j-Z;eGd4d5eZ<ed67Gd8d9e9Z=ed:7eGd;ded67Gd=d>e9e Z?gd?Z@dS)B)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|_||_|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 h/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/glmasr/modeling_glmasr.pyr,zGlmAsrRotaryEmbedding.__init__5s "("@$*$B! 4[A!%!E >Y & &.t~>L+7< V+L+L($( ZeDDD 0(..2B2BuUUUUUr6z torch.deviceseq_lenreturnz torch.TensorcV|jd}|jdd}t|ddp|j|jz}t ||z}d}d|t jd|dt j |t j |z zz }||fS) a Computes the inverse frequencies according to the original RoPE implementation Args: config ([`~transformers.PreTrainedConfig`]): The model configuration. device (`torch.device`): The device to use for initialization of the inverse frequencies. seq_len (`int`, *optional*): The current sequence length. Unused for this type of RoPE. Returns: Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE). rope_thetapartial_rotary_factorg?head_dimNrrdtype)r6rB) r0getgetattr hidden_sizenum_attention_headsinttorcharangeint64tofloat) r%r6r;baser?r@dimattention_factorr$s r9r1z5GlmAsrRotaryEmbedding.compute_default_rope_parametersEs&%l3 & 6 : :;RTW X X6:t44h8JfNh8h(2233 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) NrrmpscpuF) device_typeenabledrrNrA)r$rLexpandshaperKr6 isinstancetypestrr transposerHcatcosr2sinrB) r5x position_idsinv_freq_expandedposition_ids_expandedrTfreqsembr^r_s r9forwardzGlmAsrRotaryEmbedding.forwardes!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__rr, staticmethodrrGtuplerLr1no_gradrrf __classcell__r8s@r9r#r#2slVV|VVVVVV &*+/"**t#*(*t* ~u$ % ***\*>U]__ < <_ < < < <