Spaces:
Running
Running
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,10 +1,29 @@
|
|
| 1 |
---
|
| 2 |
title: README
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
title: README
|
| 3 |
+
emoji: 🦀
|
| 4 |
+
colorFrom: red
|
| 5 |
+
colorTo: yellow
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
+
# RustingStudio
|
| 11 |
+
|
| 12 |
+
We build machine-learning software in Rust and train our own models on
|
| 13 |
+
consumer hardware. Everything here was trained from scratch on a single
|
| 14 |
+
RTX 3060 12 GB, with no Python in training or in use. The code is open:
|
| 15 |
+
|
| 16 |
+
- [RustingBrain](https://github.com/RustingStudio/RustingBrain): the deep-learning library the models are trained with.
|
| 17 |
+
- [RustingRunner](https://github.com/RustingStudio/RustingRunner): the small program that runs the released weights.
|
| 18 |
+
- [RustingStrata](https://github.com/RustingStudio/RustingStrata): an inference engine for Qwen GGUF models.
|
| 19 |
+
|
| 20 |
+
## Models
|
| 21 |
+
|
| 22 |
+
**[Kaze-3D-v0.1](https://huggingface.co/rusting-studio/Kaze-3D-v0.1)**: one
|
| 23 |
+
image in, one 3D mesh out, in 4 seconds on an RTX 3060. An early release:
|
| 24 |
+
it gets the rough shape of an object, geometry only. Apache-2.0, trained
|
| 25 |
+
only on CC-BY and CC0 data. The model page has the measured numbers and
|
| 26 |
+
the limits.
|
| 27 |
+
|
| 28 |
+
More at [rustingstudio.github.io](https://rustingstudio.github.io) and
|
| 29 |
+
[github.com/RustingStudio](https://github.com/RustingStudio).
|