feat(pi052): add subtask-only (no-memory) recipe

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
pepijn
2026-07-08 10:21:05 +00:00
parent cae4a2de43
commit 18ddf98ab5
+30
View File
@@ -0,0 +1,30 @@
# subtask — subtask + action blend, no memory.
#
# Same as subtask_mem but with the memory_update sub-recipe dropped, so
# the model only learns:
#
# high_level_subtask — predict the subtask from the task.
# low_level_execution — flow loss with [images, subtask, state].
#
# No persistent high-level state (no memory note, no plan): the prompt is
# just the task / subtask. Requires the dataset to carry `subtask`
# annotations; samples whose `if_present` bindings are missing don't
# render.
blend:
high_level_subtask:
weight: 0.30
messages:
- {role: user, content: "${task}", stream: high_level}
- {role: assistant, content: "${subtask}", stream: high_level, target: true, if_present: subtask}
low_level_execution:
weight: 0.70
messages:
# The action expert is conditioned on the SUBTASK — at inference
# `HighLevelSubtaskFwd` generates it via the LM head and feeds it
# here. `stream: low_level` flips `predict_actions=True` so the
# flow loss fires; no text-CE target (subtask prediction is owned
# by `high_level_subtask`).
- {role: user, content: "${subtask}", stream: low_level, if_present: subtask}