Update README.md
#1
by Takosaga - opened
README.md
CHANGED
|
@@ -8,54 +8,21 @@ app_port: 7860
|
|
| 8 |
pinned: false
|
| 9 |
---
|
| 10 |
|
| 11 |
-
# Build Small · Hackathon Field Guide
|
| 12 |
|
| 13 |
-
|
| 14 |
-
site listing each sponsor's models, capabilities, prizes, starter Spaces and
|
| 15 |
-
support channels.
|
| 16 |
|
| 17 |
-
|
| 18 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
-
## Deployment (Hugging Face Spaces · Docker)
|
| 21 |
|
| 22 |
-
|
| 23 |
-
[`Dockerfile`](./Dockerfile) and runs the resulting container, which serves the
|
| 24 |
-
app on the port declared by `app_port` (`7860`).
|
| 25 |
|
| 26 |
-
|
| 27 |
|
| 28 |
-
|
| 29 |
-
The app uses [`@sveltejs/adapter-node`](https://svelte.dev/docs/kit/adapter-node),
|
| 30 |
-
which emits a standalone Node server at `build/index.js`.
|
| 31 |
-
2. **run stage** — installs production dependencies only, copies the built
|
| 32 |
-
server, and launches it as a non-root user (UID 1000, as Spaces requires).
|
| 33 |
|
| 34 |
-
The server reads `PORT` and `HOST` from the environment; the Dockerfile sets
|
| 35 |
-
`PORT=7860` and `HOST=0.0.0.0` so it binds correctly inside the Space.
|
| 36 |
|
| 37 |
-
Note: the site is fully prerendered (`prerender = true`), so the Node server is
|
| 38 |
-
mostly serving static HTML today. Docker + adapter-node leaves room to add
|
| 39 |
-
server-side routes or SSR later without changing the deploy path.
|
| 40 |
-
|
| 41 |
-
## Local development
|
| 42 |
-
|
| 43 |
-
```sh
|
| 44 |
-
pnpm install
|
| 45 |
-
pnpm run dev
|
| 46 |
-
```
|
| 47 |
-
|
| 48 |
-
## Production build
|
| 49 |
-
|
| 50 |
-
```sh
|
| 51 |
-
pnpm run build # outputs build/ via adapter-node
|
| 52 |
-
node build/index.js # runs the server (defaults to PORT=3000)
|
| 53 |
-
```
|
| 54 |
-
|
| 55 |
-
## Build the container locally
|
| 56 |
-
|
| 57 |
-
```sh
|
| 58 |
-
docker build -t build-small .
|
| 59 |
-
docker run --rm -p 7860:7860 build-small
|
| 60 |
-
# open http://localhost:7860
|
| 61 |
-
```
|
|
|
|
| 8 |
pinned: false
|
| 9 |
---
|
| 10 |
|
|
|
|
| 11 |
|
| 12 |
+
# Model weights
|
|
|
|
|
|
|
| 13 |
|
| 14 |
+
| Model | HF Hub Repo | GGUF File | Runtime | Params | Size | Role |
|
| 15 |
+
|---|---|---|---|---|---|---|
|
| 16 |
+
| MiniCPM5-1B Q8_0 | [Abiray/MiniCPM5-1B-GGUF](https://huggingface.co/Abiray/MiniCPM5-1B-GGUF) | `minicpm5-1b-Q8_0.gguf` | llama-cpp-python | 1.08 B | ~1.1 GB | English text generation (Phase 1) |
|
| 17 |
+
| tiny-aya-water Q4_K_M | [CohereLabs/tiny-aya-water-GGUF](https://huggingface.co/CohereLabs/tiny-aya-water-GGUF) | `tiny-aya-water-q4_k_m.gguf` | llama-cpp-python | 3.35 B | ~2.1 GB | Translation (active) |
|
| 18 |
+
| OmniVoice Q8_0 (base + tokenizer) | [Serveurperso/OmniVoice-GGUF](https://huggingface.co/Serveurperso/OmniVoice-GGUF) | `omnivoice-base-Q8_0.gguf` + `omnivoice-tokenizer-Q8_0.gguf` | omnivoice.cpp | 0.6 B | ~950 MB | Text-to-speech |
|
| 19 |
+
| FLUX.2-klein 4B Q4_K_M | [unsloth/FLUX.2-klein-4B-GGUF](https://huggingface.co/unsloth/FLUX.2-klein-4B-GGUF) | `flux-2-klein-4b-Q4_K_M.gguf` | diffusers | 4 B | ~2.6 GB | Image generation |
|
| 20 |
|
|
|
|
| 21 |
|
| 22 |
+
[Social Media Post](https://www.linkedin.com/posts/gonzalo-gamez_buildsmallhackathon-huggingface-ai-activity-7472322421472051200-iUBa/?rcm=ACoAADjnxE4BIBmKXlLcq6ecaJUWIc8fuJGMb9g)
|
|
|
|
|
|
|
| 23 |
|
| 24 |
+
[Demo Video](https://youtu.be/OVBDAwCTuxk)
|
| 25 |
|
| 26 |
+
The demo works on my machine, two days to figure out how to deploy and still was stuck.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
|
|
|
|
|
|
|
| 28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|