Andrew Park 1a843d1ece orchestrator: SFT training + eval harness ...

Tokenize the cleaned routing data (all-turns masking for ChatML),
full-parameter FSDP SFT (fsdp4/8 configs for Lambda 8xH100), and an eval
backend that drives the fine-tuned orchestrator as the scored model over
GAIA/MMLU-Pro/SuperGPQA. Includes split-making, Braintrust upload, eval
sample rendering, scorer fixes, and a boxed-tool-call salvage for SFT'd
checkpoints that emit their action inside \boxed{}.

2026-07-15 13:47:06 -07:00

..

install

feat(core): consolidate all state under a single env-aware home directory (#462) (#549)

2026-06-15 09:32:02 -07:00

mining

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

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

orchestrator

orchestrator: SFT training + eval harness

2026-07-15 13:47:06 -07:00

pearl

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

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

train

orchestrator: SFT training + eval harness

2026-07-15 13:47:06 -07:00

bump-desktop-version.sh

refactor: merge desktop/ into frontend/, eliminate duplicate Tauri scaffolding (#246)

2026-04-14 09:48:12 -07:00

index_docs.py

Feature/twitter bot (#259)

2026-04-17 15:22:17 -07:00

oauth_all.py

fix(windows): cross-platform python discovery + browser open helpers (#436)

2026-05-29 16:28:45 -07:00

quickstart.sh

Fix desktop speech dependency setup (#574)

2026-06-20 17:08:24 -07:00

smoke_framework_comparison.sh

fix(evals): clean up AI stack runtime harness (#320)

2026-05-05 19:28:50 -07:00