^jFUPddlmZddlmZddlZddlmZddlmZddl 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+GddejXZ-GddejXZ.dej^de0dej^fdZ1 d9dejXdej^dej^dej^d ej^dzd!e2d"e2d#e e"fd$Z3d%Z4d:d&Z5Gd'd(ejXZ6ed)Gd*d+ejXZ7Gd,d-eZ8e#Gd.d/eZ9e#Gd0d1e9Z:e#Gd2d3e9e Z;Gd4d5ee9Z<Gd6d7ee9Z=gd8Z>y);)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) GlmConfigcVeZdZfdZdej dej fdZxZS)GlmMLPc*t|||_tj|j d|j zd|_tj|j |j d|_t|j|_ y)NFbias) super__init__confignnLinear hidden_sizeintermediate_size gate_up_proj down_projr hidden_act activation_fnselfr& __class__s o/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/glm/modeling_glm.pyr%zGlmMLP.__init__0sp  IIf&8&8!f>V>V:V]bc6#;#;V=O=OV[\#F$5$56 hidden_statesreturnc|j|}|jdd\}}||j|z}|j|S)Nr!dim)r+chunkr.r,)r0r4 up_statesgates r2forwardzGlmMLP.forward8sL%%m4 #//!/4i 2 24 88 ~~i((r3)__name__ __module__ __qualname__r%torch FloatTensorr= __classcell__r1s@r2rr/s'7)U%6%6)5;L;L)r3rc eZdZUejed<d deffd Ze d dedzde dde dzde d e ffd Z ejed ZxZS)GlmRotaryEmbeddinginv_freqNr&ct||j|_|j|_||_|j j d|_|j}|jdk7rt|j}||j |\}|_ |jd|d|jd|jdy)N rope_typedefaultrGF) persistentoriginal_inv_freq) r$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$B! 44[A!%!E!E >>Y &.t~~>L+7 V+L($( ZeD 0(..2BuUr3rUz torch.deviceseq_lenr5z 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_dimNrr!dtype)rUr]) rPgetgetattrr)num_attention_headsintrAarangeint64tofloat) r&rUrWbaserZr[r9attention_factorrGs r2rQz2GlmRotaryEmbedding.compute_default_rope_parametersTs&%%l3 & 6 6 : :;RTW X6:t4h8J8JfNhNh8h(223 U\\!S!5;;?BB&X]XcXcBdgjj k )))r3cN|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) Nrr7rmpscpuF) device_typeenabledr!r8r\)rGreexpandshaperdrU isinstancetypestrr transposerAcatcosrRsinr]) r0x position_idsinv_freq_expandedposition_ids_expandedrkfreqsembrtrus r2r=zGlmRotaryEmbedding.forwardtsR!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$NNNN)r>r?r@rATensor__annotations__rr% staticmethodrratuplererQno_gradrr=rCrDs@r2rFrFAsllVyV #'+/"*D *(*t* ~u$ % **>U]]_ <