training: move amygdala training scripts out of vllm plugin

The fynnsu-based vllm/plugins/amygdala/ scaffold was superseded by the
readout infrastructure landed as vllm commit d3e74edf8500
(vllm/model_executor/layers/readout.py +
vllm/v1/worker/readout_manager.py). Training code remained useful so
it moved here rather than being deleted.

train_steering_vectors.py: CAA diff-of-means trainer that produces the
[n_concepts, hidden_size] per-layer projection matrices the runner
loads via VLLM_READOUT_VECTORS.

extract_training_pairs.py: memory graph -> JSONL converter using
per-emotion score thresholds from the subconscious agents' tag lines.

Co-Authored-By: Proof of Concept <poc@bcachefs.org>
This commit is contained in:
Kent Overstreet 2026-04-18 00:07:58 -04:00
parent ec7568c726
commit 34bd122590
4 changed files with 545 additions and 0 deletions

View file

@ -0,0 +1,6 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""Training utilities for amygdala steering vectors.
See README.md in this directory for overall design.
"""