|
Download MODAL_GUIDE.md from build-small-hackathon/cloud-parade-cabinet: direct link, hf CLI and curl.
- Browser
- Download file 1.09 kB
-
https://huggingface.co/spaces/build-small-hackathon/cloud-parade-cabinet/resolve/main/MODAL_GUIDE.md
- Command line
-
hf download hf://spaces/build-small-hackathon/cloud-parade-cabinet/MODAL_GUIDE.md
-
curl -L -o MODAL_GUIDE.md https://huggingface.co/spaces/build-small-hackathon/cloud-parade-cabinet/resolve/main/MODAL_GUIDE.md
1.09 kB
A newer version of the Gradio SDK is available: 6.32.0
Modal Guide
Cloud Parade Cabinet can use Modal in two ways.
1. Cheap Smoke Test
This confirms your Modal account/profile works without starting a GPU:
$env:PYTHONUTF8="1"
$env:PYTHONIOENCODING="utf-8"
modal run cloud_parade_cabinet/modal_smoke.py
Expected output includes:
status: ok
project: Cloud Parade Cabinet
2. OpenBMB GPU Endpoint
The GPU scaffold serves openbmb/MiniCPM4-8B with a vLLM OpenAI-compatible server on Modal.
Create a Modal secret once:
modal secret create huggingface-secret HF_TOKEN=$env:HF_TOKEN
Deploy:
modal deploy cloud_parade_cabinet/modal_openbmb.py
Then point the app at the Modal web endpoint once Modal prints it:
$env:PARADE_MODEL="openbmb/MiniCPM4-8B"
Cost Notes
- The smoke test should be negligible.
- The OpenBMB endpoint uses
A10Gby default to keep spend controlled. - Upgrade to
A100orH100only if latency matters for a demo recording. - Stop deployed GPU apps when not testing:
modal app stop cloud-parade-openbmb