zeekay 7f466d8fc9 zen-router: scaled + privacy-safe run on local+agentic corpus ...

- catalog.yaml: 28 routable models (add claude-opus-4-5/4-1, sonnet-4-5,
  minimax-m2 from the agentic corpus; all gateway-priced). Route head 24->28.
- session_common.py: shared session-extraction (DRY) -- task heuristic, catalog
  mapping with dated-id normalization, user/assistant pairing.
- extract_agentic_dataset.py: stream zen-agentic-dataset-private, pull embedded
  Claude transcripts out of assistant turns, stratified cap. 9.9B-token corpus
  yields ~4.4k real routing rows (rest is synthetic identity SFT + git history).
- extract_local_sessions.py: refactored onto session_common.
- sft.py: --freeze-backbone -> precompute pooled embeddings once, train the 3
  linear heads only; publish heads-only (1.2MB) so private data cannot be
  memorized. Backbone stays public zen-nano-0.6b.
- eval_routing.py: strict=False load (heads-only), device-aware, latency + dist.
- README Measured: Run A (local, full) vs Run B (combined, frozen, published)
  side by side. Run B route_acc 0.791 = +25.8pts over majority, 5/28 models
  emitted -- genuine multi-model discrimination; task_acc 0.723. All caveats.

HF: https://huggingface.co/zenlm/zen-router (heads-only weights + README).

2026-07-07 17:44:37 -07:00

..

eval_routing.py

zen-router: scaled + privacy-safe run on local+agentic corpus

2026-07-07 17:44:37 -07:00