Idanwo ti o sopọ mọ itọsọna · Alabọde Ipele

Nous Iwadi adanwo

Explore Nous Research's open assistants, preference fine-tuning, DeMo communication methods, and Psyche distributed-training project.

Jẹmọ itọsọna awọn ọnaNous Iwadi
Ibeere 1 ti 8

Kini Iwadi Nous ti a mọ julọ fun ni ibẹrẹ ibẹrẹ rẹ si olokiki?

Awotẹlẹ gbogbo ibeere8 ibeere

Awọn idahun ati awọn alaye han bi o ṣe n mu ibeere naa.

  1. Kini Iwadi Nous ti a mọ julọ fun ni ibẹrẹ ibẹrẹ rẹ si olokiki?
    • Titun-tuntun awọn awoṣe ipilẹ ṣiṣi sinu jara oluranlọwọ Hermes
    • Ṣiṣe awọn eerun AI
    • Nṣiṣẹ a awọsanma ere iṣẹ
    • Ilé pipade-orisun Furontia si dede lati ibere
  2. Awọn awoṣe ipilẹ wo ni o ni Nous ti o wọpọ julọ ni aifwy-aifwy?
    • _AIU_PROTECTED_11__'s PaLM ati Gemini
    • Meta's Llama ati awọn awoṣe Mistral
    • GPT-4 ti AIU_PROTECTED_10__
    • IBM Watson
  3. What problem does Nous Research’s DisTrO project address?
    • Ti o npese bojumu images
    • Fisinuirindigbindigbin awọn faili fidio
    • Idinku bandiwidi ibaraẹnisọrọ ti o nilo fun ikẹkọ pinpin
    • Ṣiṣawari awọn imeeli spam
  4. Kini nẹtiwọki Psyche?
    • A awujo media Syeed
    • Aṣepari fun idiwon ero
    • A iru ti akiyesi siseto
    • Igbiyanju lati ṣe ikẹkọ awọn awoṣe kọja ohun elo ti o sopọ mọ intanẹẹti ti pin kaakiri
  5. Ilana wo ni Nous nigbagbogbo lo lati ṣe deede awọn awoṣe ti o ni aifwy daradara?
    • Abojuto atunṣe-itanran pẹlu iṣapeye ayanfẹ bii DPO lori data ti a ti sọtọ
    • Ikẹkọ ni kikun lati awọn iwuwo laileto laisi awoṣe ipilẹ
    • Awọn ofin kikọ ọwọ nikan laisi ẹkọ
    • Ẹkọ imudara lati awọn piksẹli aise
  6. What does the name DeMo stand for in Nous Research's distributed-training work?
    • Distributed Model Orchestration
    • Decoupled Momentum Optimization
    • Decoder-Mixture Operation
    • Deterministic Memory Offload
  7. According to the DeMo paper, which training state need not be fully synchronized between accelerators?
    • The text prompts used for evaluation
    • The vocabulary definitions in the tokenizer
    • The complete optimizer states and model parameters
    • The labels used to evaluate image classifiers
  8. Which three roles does Psyche's training system assign?
    • A tokenizer, a rendering engine, and a search index
    • An underwriter, an auditor, and a policyholder
    • A browser, an operating system, and a GPU driver
    • A coordinator, training clients, and a data provider