tjFUDddlmZddlmZddlZddlmZddlmZddl m Z m Z ddl m Z ddlmZdd lmZdd lmZmZmZdd lmZmZdd lmZmZdd lmZmZddlm Z ddl!m"Z"m#Z#m$Z$ddl%m&Z&m'Z'ddl(m)Z)ddl*m+Z+Gddej,Z-Gddej,Z.dej/de0dej/fdZ1 d:dej,dej/dej/d ej/d!ej/dzd"e2d#e2d$e e"fd%Z3d&Z4d;d'Z5Gd(d)ej,Z6ed*Gd+d,ej,Z7Gd-d.eZ8e#Gd/d0eZ9e#Gd1d2e9Z:e#Gd3d4e9e Z;Gd5d6ee9Z<Gd7d8ee9Z=gd9Z>dS)<)Callable)OptionalN)ACT2FN)Cache DynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs) GlmConfigcBeZdZfdZdejdejfdZxZS)GlmMLPc"t||_tj|jd|jzd|_tj|j|jd|_t|j |_ dS)NFbias) super__init__confignnLinear hidden_sizeintermediate_size gate_up_proj down_projr hidden_act activation_fnselfr& __class__s b/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/glm/modeling_glm.pyr%zGlmMLP.__init__0sz  If&8!f>V:V]bccc6#;V=OV[\\\#F$56 hidden_statesreturnc||}|dd\}}|||z}||S)Nr!dim)r+chunkr.r,)r0r4 up_statesgates r2forwardzGlmMLP.forward8sX%%m44 #//!/44i 2 24 8 88 ~~i(((r3)__name__ __module__ __qualname__r%torch FloatTensorr= __classcell__r1s@r2rr/s`77777)U%6)5;L))))))))r3rc eZdZUejed<d deffd Ze d dedzde dde dzde d e ffd Z ejed ZxZS)GlmRotaryEmbeddinginv_freqNr&ct|j|_|j|_||_|jjd|_|j}|jdkrt|j}||j|\}|_ | d|d| d| ddS)N rope_typedefaultrGF) persistentoriginal_inv_freq) r$r%max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr&rope_parametersrIcompute_default_rope_parametersrattention_scalingregister_bufferclone)r0r&device rope_init_fnrGr1s r2r%zGlmRotaryEmbedding.__init__Ds "("@$*$B! 4[A!%!E >Y & &.t~>L+7< V+L+L($( ZeDDD 0(..2B2BuUUUUUr3rUz torch.deviceseq_lenr5z 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_dimNrr!dtype)rUr]) rPgetgetattrr)num_attention_headsintrAarangeint64tofloat) r&rUrWbaserZr[r9attention_factorrGs r2rQz2GlmRotaryEmbedding.compute_default_rope_parametersTs&%l3 & 6 : :;RTW X X6:t44h8JfNh8h(2233 U\!S!5;???BB&X]XcBddgjj k )))r3cN|jddddf|jddd|j}|dddddf}t |jjtr|jjdkr |jjnd}t|d5||z dd}tj ||fd }| |jz}||jz} dddn #1swxYwY||j | |j fS) Nrr7rmpscpuF) device_typeenabledr!r8r\)rGreexpandshaperdrU isinstancetypestrr transposerAcatcosrRsinr]) r0x position_idsinv_freq_expandedposition_ids_expandedrkfreqsembrtrus r2r=zGlmRotaryEmbedding.forwardts!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*NNNN)r>r?r@rATensor__annotations__rr% staticmethodrratuplererQno_gradrr=rCrDs@r2rFrFAslVVyVVVVVV #'+/"**D *(*t* ~u$ % ***\*>U]__ < <_ < < < <