tiararodney/sekft
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

todo(15): in-progress

Browse source 
build_masked_example normalises apply_chat_template's BatchEncoding (transformers 5.x) and list[int] (4.x) returns via a _render_ids helper; a BatchEncoding-returning fake tokenizer produces the same mask as the list-returning one (regression test added); existing tests pass; mypy strict clean; verified end-to-end on the box that sekft-train --inspect produces a correct assistant-only mask against Mistral.
This commit is contained in:
Tiara Rodney 2026-06-18 12:34:55 +02:00
parent 01e4d75237
commit 7853224796
Signed by: tiara
GPG key ID: 5CD8EC1D46106723
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
TODO
View file

@ -255,7 +255,7 @@ Content-Type: application/issue
ID: 15 ID: 15
Type: bugfix Type: bugfix
Title: apply_chat_template returns BatchEncoding on transformers 5.x Title: apply_chat_template returns BatchEncoding on transformers 5.x
Status: open Status: in-progress
Priority: high Priority: high
Created: 2026-06-18 Created: 2026-06-18
Module: sekft Module: sekft