Commit Graph

3 Commits

Author SHA1 Message Date
Alexander Whitestone
f598f0c9d8 feat(training): add indirect crisis signal pairs (#597)
Some checks failed
Architecture Lint / Linter Tests (pull_request) Successful in 27s
PR Checklist / pr-checklist (pull_request) Failing after 2m9s
Smoke Test / smoke (pull_request) Failing after 13s
Validate Config / YAML Lint (pull_request) Failing after 11s
Validate Config / JSON Validate (pull_request) Successful in 13s
Validate Config / Python Syntax & Import Check (pull_request) Failing after 1m11s
Validate Config / Shell Script Lint (pull_request) Failing after 51s
Validate Config / Cron Syntax Check (pull_request) Successful in 11s
Validate Config / Deploy Script Dry Run (pull_request) Successful in 12s
Validate Config / Playbook Schema Validation (pull_request) Successful in 20s
Architecture Lint / Lint Repository (pull_request) Has been cancelled
Validate Config / Python Test Suite (pull_request) Has been cancelled
2026-04-14 18:38:21 -04:00
Alexander Whitestone
82ba8896b3 docs: clarify sidecar boundary and training status 2026-03-27 17:15:57 -04:00
perplexity
6507cffc15 feat: migrate autolora pipeline into training/
Per direction shift (the-nexus#542).

Replaces the autolora repo (1,500 lines of custom pipeline code)
with config files for existing tools:

- axolotl.yaml: replaces train_modal.py (239 lines)
- mlx-lora.yaml: replaces MLX training scripts
- eval-tasks.yaml: replaces run_eval.py (300 lines)
- Makefile: replaces run_vibes.py, compare.py, convert_to_mlx.py

Data migrated as-is:
- curated_dataset.jsonl (26 gold-standard conversations)
- preference_pairs.jsonl (DPO pairs)
- prompts_vibes.yaml, prompts_nexus_vibes.yaml
- v0-baseline eval results (historical record)

Thin glue kept:
- build_curated.py (data authoring, not infrastructure)
- ingest_trajectories.py (domain-specific quality filter)

Dependencies: pip install axolotl mlx-lm lm-evaluation-harness
2026-03-25 23:05:50 +00:00