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

Hard

Instruction Tuning & Efficient Fine-Tuning3 / 6

Chapter 113 / 6

Instruction Tuning & Efficient Fine-Tuning

Hard

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

Target interface

pack(samples, max_len, pad_id=0)

Complete the starter code in the editor. Any correct approach is accepted.

Hints0 / 2

Reference solution

Your own code stays in the editor.

solution.pyPython

Local draft

import torch

def pack(samples, max_len, pad_id=0):
    raise NotImplementedError

def block_diagonal_mask(seg_ids):
    raise NotImplementedError

Local draft

⌘/Ctrl↵to submit

AI review

Ready when you are

Submit your solution for a score and feedback on correctness, edge cases, and clarity. Any correct approach is accepted.

Chapter 113 / 6

Instruction Tuning & Efficient Fine-Tuning

Hard

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

Target interface

pack(samples, max_len, pad_id=0)

Complete the starter code in the editor. Any correct approach is accepted.

Hints0 / 2

Reference solution

Your own code stays in the editor.