todo(2): done

Trainer renders with the model's chat template, canonicalises turns, masks to assistant-only by token-prefix differencing, and trains a QLoRA adapter.
This commit is contained in:
Tiara Rodney 2026-06-16 20:14:15 +02:00
parent 0bb9c1983b
commit 4e45bacf0b
Signed by: tiara
GPG key ID: 5CD8EC1D46106723

2
TODO
View file

@ -37,7 +37,7 @@ Content-Type: application/issue
ID: 2
Type: feature
Title: SFT trainer with chat-template render and assistant-only mask
Status: in-progress
Status: done
Priority: medium
Created: 2026-06-16
Module: sekft