Laajteb position Rotary

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

1. naka lay def ba RoPE dugal ay leeral ci position bi ci biir transformateur bi?
   • Ni ñuy wëlbati ñaari dimension ci laaj bi ak vecteur bu am solo ci angle bu aju ci barab bi
   • Yokk benn vecteur bu takku ci dugal yi
   • Ni ñuy komàndee jeton yi ci anam wu mucc
   • Soo yokke nimero position bi ci bind
2. Ginaaw ñu jëfandikoo RoPE, poñ yi ñuy am ci diggante ñaari token mingi aju ci:
   • seen position absolu rek
   • seen diggante (m dindi n)
   • Dayo vokabileer bi
   • Dayo lote bi
3. What training-efficiency comparison did the YaRN paper report for context extension?
   • Exactly the same data and steps as all prior methods
   • No fine-tuning or training data of any kind
   • About 10x fewer tokens and 2.5x fewer training steps than prior methods
   • A fixed 100x increase in output tokens
4. Lan moo waral ñaari dimension yu wuute di wëréelu ci frequence yu wuute ci RoPE?
   • Ngir sakkanal mémoire ci salte yenn dimension
   • ngir aleatoire génnug model bi
   • Ndax peer yépp dañu wara jëfandikoo benn angle
   • Ngir jàpp komànd bu baax ak position bu sori
5. What is the goal of techniques such as Position Interpolation and YaRN for RoPE-based models?
   • Extend the usable context length beyond the original training window using additional scaling/fine-tuning methods
   • Guarantee accurate recall at any sequence length with no evaluation
   • Remove position information from attention
   • Replace all token embeddings with absolute learned vectors
6. Does standard RoPE require learned absolute-position vectors to inject position into query and key representations?
   • Yes; it adds one learned vector for every possible sequence position
   • No; it applies position-dependent rotations to paired query/key dimensions
   • It removes query and key vectors entirely
   • It only adds position to value vectors
7. What does standard RoPE alone guarantee about a model’s context length?
   • Unlimited accurate context at every position
   • A fixed context of exactly 128 tokens
   • It does not by itself guarantee reliable use beyond the trained context length
   • Removal of the attention mechanism
8. What extended context length did the Position Interpolation paper report for its LLaMA evaluations?
   • Exactly 1,000 tokens with no position changes
   • Unlimited context with no fine-tuning
   • Up to 2 million tokens for all models
   • Up to 32,768 tokens with minimal fine-tuning