Views
No views yet
ckd_* (agentic) were
trained partly on APIGen-MT-5k (CC-BY-NC-4.0) → those subdirs are non-commercial / research-only.
Training data: OpenR1-Math-220k (Apache-2.0), openwebmath (ODC-By), xlam-function-calling-60k (CC-BY-4.0),
ToolACE (Apache-2.0), APIGen-MT-5k (CC-BY-NC-4.0), PopQA. Third-party datasets are NOT redistributed here.pk_p2_frozen — a FROZEN Qwen3-4B-Base backbone + a large content-addressed product-key memory
(dq512 / 65536 keys / 1.6B params) reaches 52.5% direct fact recall (full 14k set; 77.5 on the
first-3000 subset) vs small-PK 24.3 and bare-frozen 0 — the project's strongest near-zero-inference
capacity positive (direct-probe only; generalization untested).*.safetensors + config/tokenizer (+ ctx_gate.pt for grafts, pk_memory.pt for PK).sparse_memory/layer_*.pt (learned memory grafts only): nonzero rows only. Reconstruct dense:
1import torch
2d = torch.load("sparse_memory/layer_00.pt")
3dense = torch.zeros(d["V"], d["I"], dtype=d["mean_rows"].dtype)
4dense[d["rows"].long()] = d["mean_rows"]fcuo/calibrate_selfgen_math.py (see code repo). Frozen-graft trained_memory (= calib copy) is omitted.