nla-qwen2.5-7b-L20-av-matryoshka-sonnet46-v3 — v3 warm-start (bullets prompt)
Actor (AV) of the NLA Qwen2.5-7B
(layer-20) pair, v3 warm-start: SFT from the base
kitft/nla-qwen2.5-7b-L20-av
on Claude Sonnet-4.6 explanations in the v3 format.
v3 changes vs v2 (see the repo's experiment README):
- The prompt actually says bullet points ("a list of bullet points, one per line");
output text is plain one-item-per-line (no literal "- " markers). The
nla_meta.yamlsidecar carries the real trained template (v1/v2 shipped a stale tagged one). - AV: trained with NLA_NO_TRAIN_EOS=1 (never taught to stop; RL caps generation).
- Intended as the starting point for the v3 RL phase (KL 0.03, uniform token truncation ~U[1,120]).
Warm-start data: v3 splits (v3/ folder).
Hyperparameters: global batch 256, lr 2e-5→2e-6 cosine, warmup 50, 1 epoch, injection_scale 150.