What is Parameter-Efficient Fine-Tuning (PEFT)? Definition | AI Understanding

Qeexid

Hababka la qabsada moodooyinka iyadoo la tababarayo qayb yar oo xaddidaadyo lagu daray.

Shuruudaha la xiriira

Sii wadida tababarka xogta gaarka ah ee domain-ka si loo waafajiyo qaabka horay loo tababaray ee hawl gaar ah.

LoRA (Laqabsiga Darajada Hoose)

Habka hagaajinta wanaagsan ee wax-ku-oolka ah ee ku daraya mitirada adabtarada ee darajada hoose.

Tababarka kadib

Tallaabooyinka tababbarka ayaa la dabaqay tababbarka hore ka dib, sida hagaajinta tilmaamaha, hagaajinta doorbidka, iyo hagaajinta badbaadada.

Dajinta Tilmaamaha

Hagaajinta qaab ku saabsan lammaanaha jawaab-celinta-tilmaan-bixinta si loo horumariyo hawsha soo socota.

Heerka Barashada

Xakamaynta hyperparameter-ka tabobarka ee xakamaynaya inta cabbiradu bedelayaan tallaabo kasta oo cusub.

DPO (Doorashada Tooska ah)

Habka tababarka oo si toos ah u hagaajinaya moodooyinka lammaanaha doorbida iyada oo aan loo baahnayn nooc abaalmarin gaar ah.

Wax badan ka baro hagayaashayada bilaashka ah

Fine-Tuning Hard Parameter Sharing in Multi-Task Networks Gumbel-Softmax and Reparameterization Rejection Sampling Fine-Tuning

Eeg sidoo kale

Parameter Perplexity Overfitting Pipeline Open-Source Model Precision OCR (Optical Character Recognition)Pretraining

Ka baadh Qaamuuska AI oo buuxa Baadh dhammaan hagayaasha AI ee bilaashka ah