Laajteb EleutherAI

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

1. How did EleutherAI first bring together its research community?
   • As a Discord server for discussing GPT-3 and open language modeling
   • Bi nga xamee ni ab sosete buy tàmbali ci Silicon Valley
   • Laboratoire gëstu bu nguur gi
   • As a university’s official AI department
2. Luy 'Pile' bi?
   • Produit chatbot buñu moomeel
   • ab done bu ubbeeku bu 825GB ngir tàggat ay xeetu làkk
   • Benn xeetu lalu reso neuronal
   • Platform ordinatëru niir bu EleutherAI
3. Ci yii, yan ci ñoom mooy xeetu làkku EleutherAI?
   • BERT-Yaatu
   • Llama-2
   • GPT-NeoX-20B
   • PALM
4. Lan lañuy jëfandikoo ngir jàngat LM?
   • Defar ay nataal ci mbind
   • kompresse diisaayu model
   • Royuwaayi dalal ni API web
   • Benchmarking xeetu làkk ci liggéey yu bari
5. Which organizations are named in EleutherAI’s retrospective as research supporters?
   • CoreWeave and Google TPU Research Cloud
   • Nvidia and the National Science Foundation only
   • The U.S. Department of Energy and NASA
   • Amazon and the European Space Agency
6. Ban coppite ci mbootaay la EleutherAI amal ci 2023?
   • OpenAI moo ko jëndoon
   • Ñu ngi ko formalise ni daara buy def gëstu buy def te Yàlla tax
   • Nekk na fond de couverture buy wut xaalis
   • Dafa tëju lëmm
7. Which positional method does the GPT-NeoX-20B paper describe using instead of learned absolute position embeddings?
   • A separate learned embedding for every document
   • A convolutional image-position map
   • Rotary Positional Embeddings (RoPE)
   • A random position permutation at each layer
8. What architectural arrangement is highlighted as a GPT-NeoX-20B difference from GPT-3?
   • The model replaces its Transformer with a decision tree
   • Every layer removes the attention mechanism
   • It uses only an encoder and no autoregressive decoder
   • Attention and feed-forward layers can be computed in parallel