Skip to content

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

Latest

Choose a tag to compare

@devang007 devang007 released this 25 Jul 19:40
Immutable release. Only release title and notes can be modified.
aefc243

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