What is Post-training? Definition | AI Understanding

Ma'anarsa

Matakan horarwa da aka yi amfani da su bayan horo na farko, kamar kunna koyarwa, inganta fifiko, da daidaita aminci.

Sharuɗɗa masu alaƙa

DPO (Haɓaka fifiko kai tsaye)

Hanyar horarwa wacce ke daidaita ƙira kai tsaye akan nau'ikan zaɓin zaɓi ba tare da buƙatar samfurin lada daban ba.

Matsayin horo na tsaka-tsaki tsakanin horo na farko da bayan horo, galibi ana amfani dashi don iyawa ko daidaita yanki.

Ma'auni-Ingantacciyar Kyawun-Tuning (PEFT)

Hanyoyin da ke daidaita samfura ta hanyar horar da ƙaramin juzu'i na ƙarin sigogi.

Farkon horon ƙirar ƙira mai girma akan faffadan bayanai kafin daidaitawa ta ƙasa.

Saitin kimantawa

Saitin bayanan da aka yi amfani da shi don auna ingancin samfurin bayan horo.

Kyakkyawan-Tuning

Ci gaba da horarwa akan ƙayyadaddun bayanai na yanki don daidaita samfurin da aka riga aka horar zuwa takamaiman aiki.

Ƙara koyo a cikin jagororinmu na kyauta

AI Training Pseudo-Labeling and Self-Training ELECTRA Pretraining RoBERTa Training Recipe

Duba kuma

Self-Play Watermarking RAG-Fusion Citations Multi-Query Retrieval Factuality Parent-Document Retrieval GSM8K

Nemo cikakken AI ƙamus Bincika duk jagororin AI kyauta