Guide-yakabatana mibvunzo · Pakati Nhanho

Nous Research Quiz

Ongorora vabatsiri veNous Tsvagurudzo yakavhurika, sarudzo yakanaka-tuning, DeMo nzira dzekutaurirana, uye Psyche yakagoverwa-yekudzidzisa chirongwa.

Nzira dzekutungamira dzinoenderanaNous Research
Mubvunzo 1 ye 8

Chii chinonzi Nous Research inonyanya kuzivikanwa mukutanga kwayo kuve mukurumbira?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Chii chinonzi Nous Research inonyanya kuzivikanwa mukutanga kwayo kuve mukurumbira?
    • Yakanaka-tuning yakavhurika base modhi mune yeHermes mubatsiri akateedzera
    • Kugadzira AI chips
    • Kumhanyisa sevhisi yemitambo yemakore
    • Kuvaka yakavharwa-source yemuganhu mamodheru kubva kutanga
  2. Ndeapi mabhesi modhi ane Nous anowanzo gadziridzwa zvakanaka?
    • Google's PaLM uye Gemini
    • Meta's Llama neMistral modhi
    • OpenAI's GPT-4
    • IBM Watson
  3. Nderipi dambudziko rinosangana neNous Research's DisTrO chirongwa chechirongwa?
    • Kugadzira mifananidzo yechokwadi
    • Kudzvanya mavhidhiyo mafaera
    • Kuderedza bandwidth yekukurukurirana inodiwa pakugoverwa kudzidziswa
    • Kutsvaga spam emails
  4. Chii chinonzi Psyche network?
    • A social media platform
    • Chiyero chekuyera kufunga
    • Rudzi rwekutarisisa michina
    • Kuedza kudzidzisa mamodheru munzvimbo dzese dzakaparadzirwa internet-yakabatana hardware
  5. Ndeipi nzira iyo Nous anowanzo shandisa kurongedza mamodheru ayo akakwenenzverwa?
    • Inotariswa kunyatsoita-tuning pamwe neanofarira optimization seDPO pane curated data
    • Kudzidzira zvachose kubva kuhuremu huremu pasina base modhi
    • Mitemo yekunyora chete nemaoko pasina kudzidza
    • Kusimbisa kudzidza kubva mbishi pixels
  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