Commit Graph
827 Commits
Author SHA1 Message Date
Mac Lee bb1e8935ee [refactor] use existing workflow namespace for InterleaveThinker 2026-06-21 20:37:13 +00:00
Mac Lee 58256b1282 [docs] record InterleaveThinker workflow migration 2026-06-21 19:07:47 +00:00
Mac Lee 91d8fb85e6 [misc] format InterleaveThinker workflow helpers 2026-06-21 19:03:31 +00:00
Mac Lee 11d55fb5a2 [refactor] move InterleaveThinker helpers to workflows 2026-06-21 19:00:11 +00:00
Mac Lee d2c5395132 [docs] update InterleaveThinker handoff instructions 2026-06-21 18:53:43 +00:00
Mac Lee 704e56674f [docs] record InterleaveThinker CLI cleanup validation 2026-06-21 06:38:17 +00:00
Mac Lee 555a600f3f [bugfix] remove InterleaveThinker CLI surface 2026-06-21 06:37:44 +00:00
Mac Lee c6128ab765 [docs] record InterleaveThinker review package push 2026-06-20 04:05:05 +00:00
Mac Lee 6a6ebf1ee3 [docs] add InterleaveThinker review package 2026-06-20 04:04:30 +00:00
Mac Lee f1f7ac0738 [docs] record interleave trace eval validation 2026-06-20 04:01:49 +00:00
Mac Lee 47335f09ee [feat] add InterleaveThinker trace evaluation 2026-06-20 03:56:36 +00:00
Mac Lee 9e7a30acbc [docs] record interleave eval validation 2026-06-20 03:43:22 +00:00
Mac Lee 022aedb0e1 [bugfix] clean up interleave eval mypy 2026-06-20 03:39:44 +00:00
Mac Lee 874e4e2f9c [bugfix] defer interleave eval config loading 2026-06-20 03:36:05 +00:00
Mac Lee eca1444101 [feat] add InterleaveThinker prompt-set eval 2026-06-20 03:32:16 +00:00
Mac Lee 000d48b74d [docs] record InterleaveThinker planner GRPO push 2026-06-19 20:28:54 +00:00
Mac Lee 2cf9aa0d09 [feat] add InterleaveThinker planner GRPO path 2026-06-19 20:28:15 +00:00
Mac Lee be0bacbe35 [docs] record InterleaveThinker reference policy push 2026-06-19 20:07:55 +00:00
Mac Lee 42c2fe6a62 [feat] add InterleaveThinker reference policy KL 2026-06-19 20:06:57 +00:00
Mac Lee 8bfcb66447 [docs] record InterleaveThinker PEFT smoke 2026-06-19 19:55:28 +00:00
Mac Lee 0cc0478463 [feat] add PEFT LoRA for InterleaveThinker actors 2026-06-19 19:54:52 +00:00
Mac Lee a312d7c6e1 [docs] record InterleaveThinker GRPO push 2026-06-19 19:33:58 +00:00
Mac Lee b7a923c0bb [feat] add InterleaveThinker GRPO policy loss 2026-06-19 19:33:20 +00:00
Mac Lee 0b4e9764b6 [docs] record InterleaveThinker SFT push 2026-06-19 19:08:55 +00:00
Mac Lee df88af316b [feat] add InterleaveThinker SFT method 2026-06-19 19:08:10 +00:00
Mac Lee 033b75a662 [docs] record InterleaveThinker data normalizer push 2026-06-19 18:48:15 +00:00
Mac Lee dcd82f93e8 [feat] add InterleaveThinker data normalizers 2026-06-19 18:47:41 +00:00
Mac Lee a22da778a6 [docs] record interleave run generator smoke 2026-06-19 18:38:16 +00:00
Mac Lee 38513d896c [docs] record interleave CLI config fix 2026-06-19 18:32:50 +00:00
Mac Lee 375b944b58 [bugfix] preserve interleave CLI config paths 2026-06-19 18:32:16 +00:00
Mac Lee f4d1b59b9e [docs] record InterleaveThinker run CLI push 2026-06-19 18:23:47 +00:00
Mac Lee ee4021e5cb [feat] add InterleaveThinker run CLI 2026-06-19 18:23:03 +00:00
Mac Lee 269544c09b [docs] record InterleaveThinker provider push 2026-06-19 18:11:50 +00:00
Mac Lee 2d3bb7c795 [feat] wire InterleaveThinker model providers 2026-06-19 18:11:03 +00:00
Mac Lee a2dd0b6398 [docs] update InterleaveThinker planner handoff 2026-06-19 17:55:40 +00:00
Mac Lee 3b9ecb3485 [feat] add InterleaveThinker planner actor 2026-06-19 17:54:56 +00:00
Mac Lee 87dbb78002 [docs] add full InterleaveThinker integration plan 2026-06-19 17:28:07 +00:00
Mac Lee 06b6c43d3f [docs] record InterleaveThinker critic smoke 2026-06-19 16:57:19 +00:00
Mac Lee 9973307b11 [docs] update InterleaveThinker integration handoff 2026-06-19 16:46:15 +00:00
Mac Lee ace421bc2b [feat] harden InterleaveThinker critic backend 2026-06-19 16:45:33 +00:00
Mac Lee fc04d01930 [feat] integrate InterleaveThinker model backends 2026-06-19 05:26:24 +00:00
Mac Lee c2a86bef4c [misc] record InterleaveThinker RL handoff 2026-06-18 19:37:47 +00:00
Mac Lee 9521077f21 [feat] add InterleaveThinker RL training loop 2026-06-18 19:37:13 +00:00
Mac Lee e73521d04e [misc] record InterleaveThinker validation handoff 2026-06-18 02:47:52 +00:00
Mac Lee 0c56a4aa53 [feat] add interleave trace runner 2026-06-18 02:44:01 +00:00
Mac Lee eb33639cbd [feat] add InterleaveThinker compatibility service 2026-06-18 02:40:54 +00:00
Mac Lee 7e70f8598a [misc] track InterleaveThinker integration plan 2026-06-18 02:28:24 +00:00
alexzmsandmergify[bot] 633d393568 [ci] layer-0 grad-norm regression for per-method training tests (5a-ii) (#1396)
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-06-12 04:45:07 +00:00
Junda SuandPeiyuan Zhang 5854aec2ce [feat] Add Wan RL DiffusionNFT training (#1450)
Co-authored-by: Peiyuan Zhang <a1286225768@gmail.com>
2026-06-11 21:18:59 -07:00
Mook 30e45c2411 [bugfix] Classify new config/sampling fields in schema parity inventory (#1446) 2026-06-10 13:38:36 -07:00