InoteveraGaidhi rinotevera
Position Interpolation yeContext Extension
Mutauro AI
Nhungamiro yehunyanzvi
Positional Interpolation (PI) inzira yakapfava, ine pesvedzero inotambanudza hwindo reTransformer remukati nekudzvanya ma indices ezvinzvimbo muhuwandu iyo modhi inotoziva.
Teerera kugwaro iriAI-yakarondedzerwa · ~2 min
Instead of extrapolating to unseen positions, it interpolates within trained ones, requiring only brief fine-tuning.
Yakaunzwa ne Meta vaongorori (Chen et al.) muna 2023, Positional Interpolation inobata chokwadi chekuti mamodheru ane RoPE anokundikana zvakanyanya kana achiwedzera kune zvinzvimbo kupfuura kudzidziswa. Muono wacho unopokana: pane kukumbira modhi kuti ibate mahombe ezvinzvimbo zvayasati yamboona, PI inokamura maindisi enzvimbo anouya nechikero kuitira kureba kwe, toti, 8K mepu kudzoka muyekutanga 2K renji. Nekuti iyo modhi yakadzidziswa pane iyo siyana, iyo inotenderera inogara mu-kugovera. Mushure mekungoita chiuru-yekugadzirisa matanho, modhi yeLLaMA yakawedzera nzira iyi yakabatwa kusvika kumakumi matatu nemaviri mamiriro. Iro bepa rakaratidza kuwedzeredza kunogona kukwidza kutarisisa zvibodzwa kune hukuru hukuru, nepo kududzira kuchiita kuti irambe yakasungwa uye yakagadzikana, ndosaka kududzira kunoshanda zvakanyanya zvirinani pane kuwedzera.
Kuwedzera 2K-context LLaMA modhi yekubata 8K-32K tokens ine angangoita chiuru-yekugadzirisa matanho.
Kugadzirisa iyo iripo yekukurukura modhi yekupfupisa-refu-gwara pasina kudzidziswa kubva pakutanga
Kushanda seyambiro yekutanga iyo NTK-inoziva kuyera uye YaRN inovandudza pairi
Kugonesa kodhi-yakareba kodhi kana yemutemo-gwaro kuongororwa pamhando dzakadzidziswa pakutanga nemahwindo mapfupi
Positional Interpolation yakave hwaro hwemafungu ekuteedzera, kusanganisira NTK-inoziva kuyera uye YaRN, iyo inodudzira zvakanyanya kusarudza kuchengetedza ruzivo rwenzvimbo. Iyo nzira ndeye nzira dzinoda kushoma kana kusanyatso gadzirisa uye kuenda kubheka-refu-mamiriro ekubata mupretraining. PI inoramba iri yakakosha yekutanga uye inowanzobatanidzwa neazvino frequency-aware zvirongwa zvekusvika 128K-pamwe nemamiriro ekunze windows zvinobudirira.
Tsamba yemahara
Nhatu dzakasimbiswa dzeAI nyaya mangwanani ega ega pakati pevhiki, dzakanyorwa neChirungu chakajeka. Yemahara zvachose, hapana ads.
Imwe email zuva rega rega revhiki. Bvisa kunyoresa kamwe chete. Hatimbotengese kana kugovera kero yako.
Zviedze iwe pachako
Mhinduro yepakarepo pamhinduro yega yega, uye chitupa chinogovaniswa chine ID inobatika kana wapedza kosi.
Tsigira dzidzo yemahara yeAI. AI Understanding ndeye 501(c)(3) isingabatsiri - hapana ads, hapana paywall, zvachose. Ita chipo
Positional Interpolation (PI) inzira yakapfava, ine pesvedzero inotambanudza hwindo reTransformer remukati nekudzvanya ma indices ezvinzvimbo muhuwandu iyo modhi inotoziva. Panzvimbo pokuwedzera kune zvisingaoneki, inopindirana mukati mevakadzidziswa, ichingoda kurongeka kwenguva pfupi.
PI inokamura maindisi enzvimbo nechikero zvekuti mepu yakarebesa inoteedzana kudzokera muchikamu chakadzidziswa, ichichengeta kutenderera mukugovera.
Iyo PI bepa yakaratidza zvisingaonekwe zvinzvimbo zvakakura zvinogona kuburitsa kutarisisa zvibodzwa zvehukuru kupfuura kudzidziswa, kudzikamisa softmax.
Pepanhau rakashuma kuti nhanho dzinokwana chiuru dzekugadzirisa zvakanaka dzaive dzakakwana kuwedzera mamiriro kusvika kumatokeni makumi matatu nemaviri.
PI inodzoreredza chinzvimbo m kusvika m/s, ichidzvanya hutsva hukuru muyero yepakutanga yakadzidziswa.
PI yakamisa kududzira senzira yakachengeteka; NTK-inoziva kuyera uye YaRN yakakwenenzvera nekududzira ma frequency zvakanyanya kusarudza.
Ramba uchidzidza
Mamwe madhairekitori akasarudzirwa nyaya iyi
InoteveraGaidhi rinotevera
Position Interpolation yeContext Extension
Mutauro AI