Spaces:

build-small-hackathon
/

godseed

Paused

App Files Files Community

godseed

1.88 MB

Ctrl+K

1 contributor

History: 34 commits

AndresCarreon

GPU final: model resident on cuda (no per-call transfer) + 240s budget + one-shot — fixes empty-output timeout

54342fa verified about 2 months ago

engine
FORGIVING TOWNS: map any building kind (never reject), district reroute, restore god's voice (content-only moderation), town few-shot pushes build_district+roads, honest fail on empty about 2 months ago
mind
GPU final: model resident on cuda (no per-call transfer) + 240s budget + one-shot — fixes empty-output timeout about 2 months ago
server
security: re-moderate model text, identity-bound rite token, XFF/queue-freeze hardening, OOM guard; README truth fixes about 2 months ago
tests
FORGIVING TOWNS: map any building kind (never reject), district reroute, restore god's voice (content-only moderation), town few-shot pushes build_district+roads, honest fail on empty about 2 months ago
tools
Town Mode: close town view by default, build_district + place_road, bank/market/house, grow-one-town steering, behold-the-world reveal, tamed needle about 2 months ago
traces
GODSEED v0 about 2 months ago
web
Town Mode: close town view by default, build_district + place_road, bank/market/house, grow-one-town steering, behold-the-world reveal, tamed needle about 2 months ago
.gitattributes

1.52 kB
initial commit about 2 months ago
ARCHITECTURE.md

24.1 kB
Town Mode: close town view by default, build_district + place_road, bank/market/house, grow-one-town steering, behold-the-world reveal, tamed needle about 2 months ago
Dockerfile.fallback

1.19 kB
GODSEED v0 about 2 months ago
FIELD_NOTES.md

4.87 kB
prebuilt llama-cpp wheel index + field notes about 2 months ago
README.md

7.78 kB
Town Mode: close town view by default, build_district + place_road, bank/market/house, grow-one-town steering, behold-the-world reveal, tamed needle about 2 months ago
app.py

23.4 kB
disable flaky LLM judge layer (default-denied every clean wish on llama.cpp); wordlist layers 1-2 remain the gate about 2 months ago
requirements.txt

434 Bytes
GPU final: model resident on cuda (no per-call transfer) + 240s budget + one-shot — fixes empty-output timeout about 2 months ago