OpenJarvis

mirror of https://github.com/open-jarvis/OpenJarvis.git synced 2026-07-28 05:12:26 +00:00

Files

T

Andrew Park 28ef7e5cb5 feat(orchestrator): ADP-derived SFT cold-start data pipeline

Train a single ~9B orchestrator (Qwen3-8B) for local<->cloud routing via SFT
on synthetic traces derived from NeuLab ADP (agent-data-collection).

- sft_data/: full ADP trajectory loader, tier model + pricing, 4 paradigm
  renderers, reward-ranked selection, conversations-JSONL serializer, CLI
- wire sft_trainer._generate_traces() to the pipeline (no GPU / no API keys)
- Qwen3-8B SFT config + scripts/orchestrator CLI wrapper
- offline fixture tests (12)

Heuristic competence labels for the cold-start; real paradigm execution +
GRPO are the documented v2.

2026-06-05 10:27:02 -07:00

install

fix(install): use requires-python range; bootstrap shims are Python-free (#476 , #484 ) (#492 )

2026-06-03 16:59:29 -07:00

mining

feat(mining): validate Gemma E4B and Qwen 3.6 Pearl artifacts (#328 )

2026-05-14 20:11:24 -07:00

orchestrator

feat(orchestrator): ADP-derived SFT cold-start data pipeline

2026-06-05 10:27:02 -07:00

pearl

feat(mining): validate Gemma E4B and Qwen 3.6 Pearl artifacts (#328 )