Merge pull request #2 from devang007/release/v0.2.0

[devang007]

New model weights. Exact match on the validation set goes from 90.95% → 95.3%, and held-out test / test_ood are measured and published for the first time.

Split	n	Exact match	JSON-valid	Schema-valid
val	4,641	95.3%	99.1%	99.1%
test (held out)	4,641	95.2%	99.0%	99.0%
test_ood	4,775	94.2%	98.8%	98.8%

Retrained on a 2× larger corpus (83,544 train rows, up from 42,558) on a Colab GPU. Latency on 1-thread CPU: p50 532 ms, p95 983 ms per query. Still 15.57M params — the model stays tiny and fully offline.

Upgrading

git pull && ./install.sh

install.sh now pins MODEL_VERSION=v0.2.0, so a fresh install pulls these weights automatically and verifies the sha256.

Assets

• logx-model-v0.2.0.zip (58 MB) — safetensors + JSON only, no pickle files
• logx-model-v0.2.0.zip.sha256 — verified automatically by the installer

Notes

• The tokenizer now adds 50 tokens (the 6 ASCII ones for JSON braces, plus accented-Latin and CJK characters present in the corpus). As always, load the tokenizer shipped in the zip, never the base model's.
• Largest remaining error buckets across all splits: top-K value errors, action confusion, and invalid JSON. Training data is synthetic — test_ood at 94.2% is the honest generalization signal.

Full model card: MODEL_CARD.md

---

This discussion was created from the release Merge pull request #2 from devang007/release/v0.2.0.