From fab16d175d10fac5f2494ab991d7606b5fbef067 Mon Sep 17 00:00:00 2001 From: Tiara Rodney Date: Tue, 16 Jun 2026 20:14:09 +0200 Subject: [PATCH] todo(2): open --- TODO | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/TODO b/TODO index b9e1ed8..6840657 100644 --- a/TODO +++ b/TODO @@ -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.