Yi Models by 01.AI Quiz

Answers and explanations appear as you take the quiz.

1. Who founded 01.AI, the company behind the Yi models?
   • Kai-Fu Lee
   • Robin Li
   • Jack Ma
   • Andrew Ng
2. What were two of the first Yi base models released?
   • Yi-1 and Yi-2
   • Yi-6B and Yi-34B
   • Yi-100 and Yi-200
   • Yi-Mini and Yi-Max
3. What capability are the Yi models particularly known for?
   • Generating only images
   • Running without any GPU
   • Strong bilingual Chinese-English performance
   • Translating only spoken audio
4. What base architecture lineage do the Yi models follow?
   • A recurrent LSTM design
   • A diffusion model
   • A pure encoder model like BERT
   • The Llama-style decoder-only transformer
5. Roughly how long is the context window of the long-context Yi variants?
   • 200K tokens
   • 4K tokens
   • 32K tokens
   • 1 million tokens
6. What did 01.AI’s Yi technical report identify as an important driver of model performance?
   • Abandoning AI entirely
   • Data quality resulting from data-engineering efforts
   • Only building hardware chips
   • Merging with OpenAI
7. What does supervised fine-tuning plus reinforcement learning from human feedback aim to improve in Yi chat models?
   • Compressing retinal images
   • Changing the model into an encoder-only network
   • Following instructions in conversational use
   • Removing all text-generation ability
8. What data strategy did 01.AI emphasize for the Yi models?
   • Training exclusively on synthetic audio
   • Avoiding all data filtering
   • Using only programming-language source code
   • Careful data quality and curation rather than relying only on sheer scale