Skip to content

About

BH-Decision — Bosnian Decision Models (Kolektiv x Gamatrade). FAZA 4.

Resources

Code of conduct

Contributing

Security policy

Stars

0 stars

Watchers

0 watching

Forks

🤖 BH-Decision

Porodica modela za odlučivanje na bosanskoj ijekavici + engleskom
3 veličine (2B/4B/9B) · jedan format podataka · zajedničke izlazne sheme · zajednički benchmark

License Tests Held-out Model Datasets Benchmark

Nosioci: Kolektiv d.o.o. + Gamatrade d.o.o. · Kontakt: xnetba@gmail.com
Primarni README na ijekavici: README.bs.md

🏆 Najbolji rezultati

Šta Skor Gdje
Stock Tacit-4B, readout 16/19 (84%) held-out v1
v1.0 (mix v4) + readout, q2/q3 16/19 (84%) — paritet held-out v1
v1.0 generacija (tolerantno) 6/19 (32%) held-out v1
Format (strogi JSON) 18–20/20 (mix v9: 18/20) held-out v1
Jev 1.13 Free, DI staza 14/14 (100%), p50 256 ms 18 scenarija A/B
Sudzuki-4b-cloud, DI staza 15/18 (83%) held-out v1

Proizvodna konfiguracija: v0.4-rc + AnyJev readout = 17/19, prvi put iznad stocka. Pravilo repoa: bez fabriciranja — svaka brojka ispod je iz stvarnog runa.

Status (20.11.2026)

  • FAZE 1–4 — gotove (research, arhitektura, dataseti/benchmark, infrastruktura).
  • FAZA 5 — Linija 2 do v1.0: BH-Language-AI/bh-decision-2-4b (LoRA na Tacit-4B; readout paritet 15–16/19; generacija tolerantno 7/19). SFT serija v1–v9: format popravljen podacima (0.05→0.90), prior mican (o2→o3→nijedan), rasuđivanje ostalo na stock nivou. Nalazi: docs/training/.
  • DI staza — Core/MCP/Skill/Plugin gotovi (71 test zeleno); sudzuki-4b-cloud profilisan (15/18, ECE 0.16); provider-selection čeka cijenu/licencu. Vlastiti pipeline ovdje ne radi bez ključa (Jev mrtav, Clef nema).

📊 Benchmark modela — held-out (20 neviđenih, 19 bodovanih)

held-out rezultati

Verzija Readout Generacija (tolerantno) Generacija (strogo) val_loss
stock Tacit-4B 16/19 (84%) 7/19 (37%) — —
✅ v1.0 (mix v4, q2/q3) 16/19 (84%) 6/19 (32%) 1/20 0.100
v1.0 (mix v4, q2/q3) 16/19 (84%) 6/19 (32%) 1/20 0.100
v0.2-rc (mix v4) 15/19 (79%) 6/19 (32%) 1/20 0.100
v0.1 (mix v2) — 2/10 (20%) 10/20 0.124

Eval set: bs-decision-heldout-v01 (zaključan, leakage 0). Slike/grafike: bedževi su shields.io, graf je mjereni held-out (matplotlib).

📈 Decision Intelligence benchmark (18 scenarija, 9 bs + 9 en) — klikni za detalje
Ruta Točnost (12.11.) Rerun (13.11.) p50 rerun Reproducibilnost
A Jev-1.13-Free (hosted, $0) 14/14 (100%) 14/14 256 ms bit-za-bit ✓
B AnyJev Decider L0 (Tacit-4B, CPU) 11/14 (79%) 11/14 strogo 17,1 s 18/18 identično ✓
C AnyJev Tacit L0 (CPU) 11/14 norm. 9/14 strogo (= 11 norm.) 6,4 s 18/18 identično ✓
D Tacit Adaptive 11/14 nije ponavljan (D==C dokazano, cot 0/18) — —
E Clef lokalno — blokirano (treba GPU/download) — —

Sirovo: benchmarks/reports/live-{A-jev,B-decider-l0,C-tacit-l0,D-tacit-adaptive}.json

  • *-rerun-20261113.json. Metodologija: docs/benchmarking/anyjev-comparison.md.

Agent s skillom je brži i bolji: L0 je jedan forward (CPU) ili jedan hosted poziv (p50 256 ms); svaka odluka nosi kalibrirano povjerenje; ispod praga 0.80 slijedi eskalacija. Mermaid dijagram toka: docs/architecture/system-architecture.md.

✅ Testovi

Sloj Broj Komanda
Python (pytest) 24 zeleno python3 -m pytest tests/ -q
TypeScript (core/mcp/plugin/integracija) 47 zeleno node --experimental-strip-types --test tests/core/normalize.test.ts tests/core/providers.test.ts tests/core/anyjev.test.ts tests/mcp/server.test.ts tests/plugin/loading.test.ts tests/integration/project.test.ts
pip install pytest pyyaml
python3 -m pytest tests/ -q
python3 scripts/train.py --config configs/2b.yaml   # dry-run: samo validira i ispisuje plan
python3 scripts/evaluate.py --ref ref.json --pred pred.json [--out out.json]  # +Brier scoring

📁 Struktura

configs/         trening konfiguracije 2b/4b/9b
scripts/         train.py, evaluate.py (+Brier), build_bh2_mix*.py, readout_eval.py, pilot.py
slurm/ kaggle/  LUMI sbatch + Kaggle kerneli (mix v2–v9, svi runovi)
tests/           24 pytest + 47 TS (core/mcp/plugin/integracija)
docs/            model-selection, architecture, decisions, training (v1–v9 + readout izvještaji), providers (jev/clef/sudzuki)
benchmarks/      harness (accuracy + Brier) + reports
datasets/        train-mix-v1/v2, bh-decision-2 (mix v2–v9), expanded-v05..v09 human, heldout-v1 (zaključan), external (CSQA+QASC+ETHICS)
packages/        decision-core, decision-mcp, opencode-plugin
skills/          decision-intelligence (SKILL.md)

Decision Intelligence staza (odvojeno od treninga)

Skill + MCP server + OpenCode plugin + zajednički Core. Ne mijenja trening kod: packages/, skills/, config/.

  • Arhitektura: docs/architecture/system-architecture.md, docs/architecture/decision-protocol.md
  • Provideri: docs/providers/jev.md, docs/providers/clef-flash.md, docs/providers/sudzuki.md, docs/decisions/provider-selection.md
  • Instalacija: docs/installation/opencode.md, docs/installation/local-clef.md
  • Verzije: basic (Jev Free) vs advanced (lokalni Tacit-4B) — docs/installation/tiers.md
  • Privatnost: docs/security/privacy.md — Benchmark: benchmarks/reports/phase-6.md

Licenca

Apache License 2.0 — vidi LICENSE. Doprinosi: CONTRIBUTING.md. Upravljanje: GOVERNANCE.md. Sigurnost: SECURITY.md.

Citiranje

Vidi CITATION.cff.

About

BH-Decision — Bosnian Decision Models (Kolektiv x Gamatrade). FAZA 4.

Resources

Code of conduct

Contributing

Security policy

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages