File size: 342 Bytes
5d61448 | 1 2 3 4 5 6 7 8 9 10 11 12 13 | # test_fork_edit.td — Test load -> fork -> edit -> eval -> commit
load "Qwen/Qwen3-VL-8B-Instruct" as base
# Fork the base model
fork base as experimental_branch
# Surgical edit with DoRA on specific layers
edit experimental_branch layers 20-28 using dora lr 1e-4
eval experimental_branch -> edit_report.json
commit experimental_branch
|