Incamake
Ibyifuzo bya Optimisation itaziguye (DPO) nuburyo bwo guhuza imiterere yururimi nibyifuzo byabantu utabanje guhugura ibihembo bitandukanye cyangwa gukora imyitozo yo gushimangira. Isenyuka umuyoboro utoroshye wibyiciro byinshi mumahugurwa amwe, ahamye.
Ibyifuzo Byibanze Byiza ni igice cyururimi-AI ikoreshwa mugusoma, kubyara, gutondekanya, no guhindura inyandiko nimvugo murwego.
Kwibira cyane
DPO, yatangijwe na Rafailov na bagenzi be i Stanford mu 2023, irongera itekereza uburyo twigisha icyitegererezo ibyo abantu bakunda. Uburyo gakondo (RLHF) butoza icyitegererezo cyigihembo kubigereranya ryabantu, hanyuma bigakoresha kwiga gushimangira kugirango ibihembo byinshi. Ubushishozi bwibanze bwa DPO ni imibare: politiki nziza iyobowe nintego ya RLHF ifitanye isano ifunze nigihembo, urashobora rero gutondekanya ibigereranyo hanyuma ugahindura imiterere yururimi muburyo bubiri. Uratanga igisubizo, igisubizo 'cyatoranijwe' (gikunzwe), hamwe nigisubizo 'cyanze', hamwe nuburyo bworoshye bwo gutondekanya-uburyo bwo gutakaza icyerekezo cyerekana igisubizo cyatoranijwe bishoboka. Nta bihembo byigihembo, nta sample loop, nta bihembo bya hacking. Nibyoroshye cyane kandi bihamye gukora.
Ubushishozi
DPO ikoresha binary cross-entropy igihombo kuruta guhitamo byombi. Yongera igipimo-gishoboka cyo kugereranya igisubizo cyatoranijwe ugereranije nicyo cyanze, buriwese yapimwe nicyitegererezo cyakonjeshejwe (mubisanzwe bigenzurwa-neza-neza neza aho byatangiriye). Ubushyuhe bwa beta bugenzura intera politiki ishobora kuva kuri iyo nyandiko, igashyira mu bikorwa mu buryo butaziguye imbogamizi ya KL RLHF ikoresha mu buryo bweruye. Igihembo nticyigera kibaho; biragaragara muri politiki yonyine log-probabilite.
Kumenya neza Ibyifuzo Byiza
Ibyifuzo bya Optimisation itaziguye (DPO) nuburyo bwo guhuza imiterere yururimi nibyifuzo byabantu utabanje guhugura ibihembo bitandukanye cyangwa gukora imyitozo yo gushimangira. Isenyuka umuyoboro utoroshye wibyiciro byinshi murwego rwo gutakaza imyitozo ihamye. Ibyifuzo Byibanze Byiza ni igice cyururimi-AI ikoreshwa mugusoma, kubyara, gutondekanya, no guhindura inyandiko nimvugo murwego. Kugirango wubake byimbitse, fata Optimisation itaziguye nkicyitegererezo gikora, ntabwo ari ikintu kimwe: gusobanura ibyagezweho, gusobanura ibitekerezo, no gutandukanya ibyo sisitemu ishobora gukora byizewe nibisaba guca imanza zinzobere.
Mu myitozo, amakipe akomeye akoresha Direct Preference Optimization igishushanyo mbonera, kugarura, no gusubiramo imirongo nka sisitemu imwe y'itumanaho ihuriweho. Bandika ibipimo ngenderwaho byerekana intsinzi, bagerageza kurwanya amakuru afatika hamwe nakazi keza, kandi bagasubiramo bashingiye kubikorwa byagaragaye ko batsinzwe aho gutsinda inshuro imwe. Aha niho imyumvire yubumenyi ihinduka mubushobozi burambye kubicuruzwa, politiki, nibikorwa.
Ururimi rwakazi rushobora kugenda byihuse nta gutamba guhuzagurika. Mugihe kimwe, ibintu bya Hallucinated birashobora kwinjiza bucece raporo, gushyigikira imigendekere, cyangwa ibisubizo byubushakashatsi. Uburyo bukomeye cyane ni uguhuza umuvuduko wikigereranyo hamwe na disipuline yimiyoborere: kuyobora abaderevu, gufata ibimenyetso, gutangaza ibyemezo byicyemezo, no gukomeza kuvugurura uburyo bwo kwirinda nkimyitwarire yicyitegererezo, ibyo abakoresha bategereje, nibisabwa n'amategeko bigenda bihinduka.
Ingaruka z'Ingamba
Ururimi rwakazi rushobora kugenda byihuse nta gutamba guhuzagurika.
Ururimi rwakazi rushobora kugenda byihuse nta gutamba guhuzagurika. Mubikorwa byujuje ubuziranenge, ibi bihindurwa mumategeko agenga imikorere, imipaka nyirubwite, hamwe n'imihango yo gusubiramo kenshi kugirango amakipe ashobore kwigirira ikizere aho gupima ibidasobanutse.
Yagura uburyo bwindimi nuburyo bwo gutumanaho.
Yagura uburyo bwindimi nuburyo bwo gutumanaho. Mubikorwa byujuje ubuziranenge, ibi bihindurwa mumategeko agenga imikorere, imipaka nyirubwite, hamwe n'imihango yo gusubiramo kenshi kugirango amakipe ashobore kwigirira ikizere aho gupima ibidasobanutse.
Amakipe arashobora kumara umwanya munini murubanza mugihe automatike ikora gusubiramo.
Amakipe arashobora kumara umwanya munini murubanza mugihe automatike ikora gusubiramo. Mubikorwa byujuje ubuziranenge, ibi bihindurwa mumategeko agenga imikorere, imipaka nyirubwite, hamwe n'imihango yo gusubiramo kenshi kugirango amakipe ashobore kwigirira ikizere aho gupima ibidasobanutse.
Gushyira mu bikorwa Isi
Kuringaniza neza uburyo bwo kuganira buremereye nka Zephyr hamwe nibikomoka kuri Llama na Mistral byinshi, byahujwe na DPO kumibare yamakuru.
Kugabanya ibisubizo byangiza cyangwa bidafasha ukoresheje bibiri aho igisubizo cyizewe, gifasha 'cyatoranijwe' hejuru yikibazo
Kwigisha umufasha wa code guhitamo guhitamo neza, byanditse neza ibisubizo kurenza amakosa ukoresheje igereranya ryakozwe nabaterankunga
Guhuza incamake yuburyo rero icyitegererezo gikunda incamake, kwizerwa kurenza verose cyangwa salusiyo
Uburyo bwo Gushyira mu bikorwa
Ibyifuzo Byibanze Byiza mubikorwa
Kuringaniza neza gufungura-uburemere bwibiganiro nka Zephyr hamwe nibikomoka kuri Llama na Mistral byinshi, byahujwe na DPO kumibare yamakuru.
Kuringaniza neza uburyo bwo kuganira buremereye nka Zephyr hamwe nibikomoka kuri Llama na Mistral byinshi, byahujwe na DPO kuri datasets zikunzwe Amakipe ubusanzwe abona ibisubizo byiza iyo asobanuye ibipimo ngenderwaho byimbere, agakomeza inzira yo kuzamura abantu kubibazo byimbitse, kandi akurikirana inyungu zibyara umusaruro hamwe nibiciro byamakosa mugihe runaka.
Ibyifuzo Byibanze Byiza mubikorwa
Kugabanya ibisubizo byangiza cyangwa bidafasha ukoresheje bibiri aho igisubizo cyizewe, gifasha 'cyatoranijwe' hejuru yikibazo.
Kugabanya ibisubizo byangiza cyangwa bidafasha ukoresheje byombi aho igisubizo cyizewe, cyingirakamaro 'cyatoranijwe' hejuru yikibazo kimwe Amakipe akunze kubona ibisubizo byiza iyo asobanuye ibipimo ngenderwaho byimbere, agakomeza inzira yo kuzamuka kwabantu kubibazo byimbitse, kandi akurikirana inyungu zibyara umusaruro nibiciro byamakosa mugihe runaka.
Ibyifuzo Byibanze Byiza mubikorwa
Kwigisha umufasha wa code guhitamo guhitamo neza, byanditse neza ibisubizo kurenza amakosa ukoresheje igereranya ryakozwe nabaterankunga.
Kwigisha umufasha wa coding guhitamo ibisubizo nyabyo, byanditse neza kurenza amakosa ya buggy ukoresheje igereranya ryakozwe nabaterankunga Amakipe ubusanzwe abona ibisubizo byiza iyo asobanuye ibipimo ngenderwaho byimbere, agakomeza inzira yo kuzamuka kwabantu kubibazo byimbitse, kandi agakurikirana inyungu zibyara umusaruro nibiciro byamakosa mugihe runaka.
Ibyifuzo Byibanze Byiza mubikorwa
Guhuza incamake yuburyo rero icyitegererezo gikunda incamake, kwizerwa kurenza verose cyangwa salusiyo.
Guhuza incamake yuburyo rero icyitegererezo gikunda incamake, incamake yizerwa kurenza inshinga cyangwa za salusine Amakipe ubusanzwe abona ibisubizo byiza iyo asobanuye ibipimo byujuje ubuziranenge imbere, agakomeza inzira yo kuzamuka kwabantu kubibazo, kandi akurikirana inyungu zibyara umusaruro hamwe nibiciro byamakosa mugihe runaka.
Ingaruka & Kurinda
Ibintu bifatika bishobora kwinjiza bucece raporo, gushyigikira imigendekere, cyangwa ibisubizo byubushakashatsi.
Kwihuta byihuse birashobora gukora ibisubizo bidahuye mubisabwa bisa.
Ibyanditswe byumvikana birashobora kugaragara niba kugenzura kugenzura ari ntege.
Igishushanyo mbonera
Sobanura imiterere isohoka, amajwi, hamwe nubuziranenge mbere yo gutangira.
Sobanura imiterere isohoka, amajwi, hamwe nubuziranenge mbere yo gutangira. Fata buri ntambwe nk irembo ryibimenyetso: niba ibipimo bitujujwe, hagarika kuzenguruka, funga icyuho, hanyuma noneho wagure imikoreshereze.
Ibisubizo byibanze hamwe nisoko yizewe igihe cyose ukuri kwingirakamaro.
Ibisubizo byibanze hamwe nisoko yizewe igihe cyose ukuri kwingirakamaro. Fata buri ntambwe nk irembo ryibimenyetso: niba ibipimo bitujujwe, hagarika kuzenguruka, funga icyuho, hanyuma noneho wagure imikoreshereze.
Komeza kugenzura abantu kugenzura ibisubizo byinshi.
Komeza kugenzura abantu kugenzura ibisubizo byinshi. Fata buri ntambwe nk irembo ryibimenyetso: niba ibipimo bitujujwe, hagarika kuzenguruka, funga icyuho, hanyuma noneho wagure imikoreshereze.
Kurikirana uburyo bwo kunanirwa no kongera imyitozo cyangwa akazi gahoraho.
Kurikirana uburyo bwo kunanirwa no kongera imyitozo cyangwa akazi gahoraho. Fata buri ntambwe nk irembo ryibimenyetso: niba ibipimo bitujujwe, hagarika kuzenguruka, funga icyuho, hanyuma noneho wagure imikoreshereze.