HejuruUbuyobozi bukurikira
Umwanya Interpolation yo Kwagura Imirongo
Ururimi AI
Ubuyobozi bwa tekiniki
YaRN (Nyamara ubundi RoPE extensioN) nubuhanga bukora neza bwo kurambura imiterere yimiterere yimiterere yimiterere irenze kure ibyo yatojwe.
Umva iki gitaboAI-byavuzwe · ~2 min
It cleverly rescales rotary position embeddings so a model trained on, say, 4K tokens can handle 32K or more with minimal fine-tuning.
Ibyinshi muri LLM bigezweho byerekana ibimenyetso hamwe na RoPE (Rotary Position Embeddings), izenguruka ikibazo hamwe nurufunguzo rwibanze kumpande zifatanije numwanya. Iyo ugaburira urutonde rurerure kuruta uburebure bwamahugurwa, ibyo bizunguruka byinjira mubitagaragara kandi icyitegererezo kiracika. YaRN, yatangijwe mu 2023 na Bowen Peng nabafatanyabikorwa, ikosora ibi hamwe na NTK-izi interpolation ikoreshwa kuri frequence: isiga ibipimo byinshyi nyinshi (bifata umubano waho, intera ngufi) ahanini idakorwa mugihe ihuza interuro ntoya (ikurikirana umwanya muremure). YaRN kandi yongeraho ubushyuhe bwo guhindura kugirango yitondere guhangana na entropiya ihinduka kuva murwego rurerure. Igisubizo ni imbaraga ndende-mikorere nyuma yo guhuza neza agace gato kamakuru hamwe nintambwe uburyo bworoshye busaba.
Kwagura moderi ifunguye ya 4K kuri 32K cyangwa 128K kubibazo byinyandiko ndende isubiza hamwe neza-neza
Gushoboza kugarura-kongera sisitemu yo kwinjiza ibice byinshi bihujwe nta guca
Imbaraga za kode zifasha zikeneye dosiye nini yububiko cyangwa dosiye nyinshi mugihe kimwe
Guhuza icyitegererezo cyibanze kubiganiro byinshi birebire bikusanya amateka manini yo kuganira
Kwagura imvugo ni imyitozo isanzwe: gufungura imiterere isanzwe yohereza YaRN-yaguwe ihinduka igera kuri 128K ibimenyetso cyangwa birenze. Ubushakashatsi bugenda bwerekeza kuburyo bwaguka imiterere hamwe na zeru cyangwa hafi ya zeru neza-guhuza, guhuza RoPE ikuraho amayeri-yerekana amayeri, kandi igakomeza ubuziranenge hejuru yidirishya ryuzuye aho kuba impera gusa. Tegereza guhuza ubu buhanga muburyo bwo kwerekana imiterere ndende ni kavukire aho guhindurwa.
Ibaruwa y'amakuru y'ubuntu
Inkuru eshatu zizewe za AI buri gitondo cy'iminsi y'akazi, zanditse mu rurimi rworoshye. Ubuntu iteka ryose, nta kwamamaza.
Imeri imwe buri munsi y'akazi. Kwiyimura mu buryo bumwe. Ntitwigera tugurisha cyangwa ngo dusangire aderesi yawe.
Isuzume
Ibisubizo ako kanya kuri buri kibazo, n'icyemezo gishobora gusangirwa gifite ID yagenzurwa umaze gutsinda isomo.
Fasha uburezi bwa AI bw'ubuntu. AI Understanding ni umuryango utegamiye kuri leta wa 501(c)(3) — nta kwamamaza, nta kwishyura, iteka ryose. Tanga impano
YaRN (Nyamara ubundi RoPE extensioN) nubuhanga bukora neza bwo kurambura imiterere yimiterere yimiterere yimiterere irenze kure ibyo yatojwe. Ihinduranya ubushishozi ikizunguruka cyumwanya kugirango moderi yatojwe, tuvuge, ibimenyetso 4K bishobora gukora 32K cyangwa birenga hamwe na tuning nziza.
YaRN, izina ryayo risobanura Ubundi RoPE extensioN, ikuraho imyanya izenguruka ikoreshwa muri LLM nyinshi zigezweho.
Imyanya irenze imyitozo itanga inguni yo kuzenguruka icyitegererezo kitigeze kibona, bityo imyitwarire yo kwitondera igabanuka cyane.
YaRN ikoresha NTK-by-ibice byambukiranya interpolate intera ndende-yumurambararo muto kandi igasiga intera ngufi-nini cyane cyane idahwitse.
YaRN yongeramo ubushyuhe bwo gupima ibitekerezo kugirango uhangane na entropie ihinduka ibaho uko imiterere ikura.
YaRN igera ku ntera ndende-ndende nyuma yo guhuza neza agace gato k'amakuru yuburyo bworoshye busaba.
Komeza wige
Abandi bayobozi batoranijwe kuriyi ngingo
HejuruUbuyobozi bukurikira
Umwanya Interpolation yo Kwagura Imirongo
Ururimi AI