quiz bu lëkkale ak tegtal · Diggante Niveau

Laaj ak tontu ci modelu tasaare GLIDE

Saytu GLIDE ci defar ak defar ci biir mbind, tàggat ci anam wu jaar yoon, jël misaal bu amul benn klassifikatër, ak architecture model taarix.

Yooni njiit yu jëm ciModèlu diffusion glide
Laaj 1 de 8

Ban xeetu tegtal la GLIDE gis ni moo defar nataal yu gëna baax te gaaw?

Xoolaatal laaj bu nekk8 laaj

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

  1. Ban xeetu tegtal la GLIDE gis ni moo defar nataal yu gëna baax te gaaw?
    • Njàngale bu amul xaaj
    • Njàngaley CLIP
    • Amul tegtal
    • Soppi ak loxo
  2. What size did the published full GLIDE base diffusion model have, before counting its upsampler?
    • About 3.5 thousand parameters
    • About 350 billion parameters
    • About 3.5 billion parameters
    • No trainable parameters
  3. naka la ko njiitu bu amul klassifikatër di doxee ci diiru tàggat yaram?
    • Modèle bi du gis lenn ludul laaj bu jaar yoon
    • Benn xeetu nataal bu wuute lañu tàggat ci wetu
    • Laajte yi dañu leen di tekki ci nimero ci anam wu mucc
    • Yenn saa model bi dafay gis prompt bi dëgg, yenn saa muy gis benn bu amul dara
  4. Which later system describes its diffusion decoder as modifying the GLIDE architecture in the DALL-E 2 research paper?
    • The original text-only GPT-2 model
    • The unCLIP system associated with DALL-E 2
    • The Whisper speech recognizer
    • The CLIP contrastive encoder alone
  5. Lu tax OpenAI génnewul ludul benn xeetu GLIDE bu gëna ndaw, buñ segg ci ñépp?
    • Modèle bi yépp réer na
    • Ci ordinatër yu mag rek lay dox
    • Njàqare ci jëfandikoo bu baax ab defarkatu nataal bu am doole
    • Lisaas bu bawoo ci ñeneen
  6. Ban man-manu soppali la GLIDE jàppale?
    • Inpainting bu lalu ci bind
    • Transkripsioŋ audio
    • Formul këyitu xayma
    • Rendu wideo
  7. How did GLIDE's upsampler complement its base text-conditioned diffusion model?
    • It replaced the text prompt with an audio transcript
    • It increased the resolution of the image produced by the base model
    • It converted the image into the training tokenizer's vocabulary
    • It supplied manual labels for every generated object
  8. At GLIDE sampling time, how does classifier-free guidance strengthen prompt conditioning?
    • It retrains the model weights after every generated pixel
    • It requires a separate class-label classifier to score every step
    • It replaces the conditional prediction with the unconditional one
    • It combines conditional and unconditional predictions, extrapolating toward the conditional one