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

todo(2): open

Browse source
This commit is contained in:
Tiara Rodney 2026-06-16 20:14:09 +02:00
parent 703cb863ec
commit fab16d175d
Signed by: tiara
GPG key ID: 5CD8EC1D46106723
1 changed files with 15 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

15
TODO
View file

@ -31,3 +31,18 @@ Description: Turn the flat trainer scripts into an installable tiararodney.sekft
posix-sdc dependency and an optional gpu extra, console scripts, a
Pipfile pinning posix-sdc as a local editable override, and tox
environments.
--ISSUE
Content-Type: application/issue
ID: 2
Type: feature
Title: SFT trainer with chat-template render and assistant-only mask
Status: open
Priority: medium
Created: 2026-06-16
Module: sekft
Relationships:
Description: Add the supervised fine-tuner: render trajectories through the
tokenizer's own chat template (matching serving), canonicalise
turns (fold system, merge consecutive), derive an assistant-only
loss mask by token-prefix differencing, and train a QLoRA adapter.