Hard

Implement sequence packing with a block-diagonal attention mask so packed samples can't at

SFT, Instruction Tuning, Data & PEFT · Problem 3 of 6

Chapter 08SFT, Instruction Tuning, Data & PEFT

Implement sequence packing with a block-diagonal attention mask so packed samples can't at

HardProblem 3 / 6

Implement sequence packing with a block-diagonal attention mask so packed samples can't attend across boundaries.

Implement the function/class skeleton in the editor. Any correct approach is accepted.

Hints