todo(4): open
This commit is contained in:
parent
a374e3a69c
commit
6f5245cda6
1 changed files with 14 additions and 0 deletions
14
TODO
14
TODO
|
|
@ -61,3 +61,17 @@ Description: Add the behavioural eval: load base plus LoRA adapter, drop it into
|
||||||
held-out scenarios with no scaffold, drive them through a local
|
held-out scenarios with no scaffold, drive them through a local
|
||||||
operator that renders with the model's chat template, and report
|
operator that renders with the model's chat template, and report
|
||||||
reach/terminate/checker rates.
|
reach/terminate/checker rates.
|
||||||
|
|
||||||
|
--ISSUE
|
||||||
|
Content-Type: application/issue
|
||||||
|
ID: 4
|
||||||
|
Type: feature
|
||||||
|
Title: Resident-base train/eval harness
|
||||||
|
Status: open
|
||||||
|
Priority: medium
|
||||||
|
Created: 2026-06-16
|
||||||
|
Module: sekft
|
||||||
|
Relationships:
|
||||||
|
Description: Add the resident harness that loads the 14GB base once and keeps it
|
||||||
|
hot, training fresh LoRA adapters and evaluating them without
|
||||||
|
reloading the base, for the slow-OcuLink iterate loop.
|
||||||
|
|
|
||||||
Loading…
Add table
Add a link
Reference in a new issue