EleutherAI Quiz

Answers and explanations appear as you take the quiz.

1. How did EleutherAI first bring together its research community?
   • As a Discord server for discussing GPT-3 and open language modeling
   • As a venture-funded startup in Silicon Valley
   • As a government research laboratory
   • As a university’s official AI department
2. What is 'The Pile'?
   • A proprietary chatbot product
   • An 825GB open curated text dataset for training language models
   • A type of neural network layer
   • EleutherAI's cloud computing platform
3. Which of these is an EleutherAI language model?
   • BERT-Large
   • LLaMA-2
   • GPT-NeoX-20B
   • PaLM
4. What is the LM Evaluation Harness used for?
   • Generating images from text
   • Compressing model weights
   • Hosting models as web APIs
   • Benchmarking language models across many tasks
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. What organizational change did EleutherAI make in 2023?
   • It was acquired by OpenAI
   • It formalized as a nonprofit research institute
   • It became a for-profit hedge fund
   • It shut down entirely
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