initial org README
Browse files
README.md
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Northstar Aurora
|
| 2 |
+
|
| 3 |
+
NorthStar Aurora is a touch-first Christmas light show engine — it composes, sequences, and streams pixel-mapped lighting effects to Falcon F16 controllers over E1.31/DDP. The AI side of the project (Aurora AI) fine-tunes large language models to compose original light shows from audio input.
|
| 4 |
+
|
| 5 |
+
**What lives here on Hugging Face:**
|
| 6 |
+
|
| 7 |
+
- Benchmark and reproducibility data from training/inference workloads on consumer-grade AMD hardware (Strix Halo / gfx1151)
|
| 8 |
+
- Eventually: open-sourced fine-tunes once their training pipelines are fully reproducible from public data
|
| 9 |
+
|
| 10 |
+
**Related work:**
|
| 11 |
+
|
| 12 |
+
- **[strix-halo-llm-finetune-guide](https://github.com/h34v3nzc0dex/strix-halo-llm-finetune-guide)** — the production guide for the hardware platform we train on. Everything from kernel patches through training scripts, with the troubleshooting record from six months of daily-driving the box
|
| 13 |
+
- **[Paul Durkin (@H34v3nzC0d3x)](https://huggingface.co/H34v3nzC0d3x)** — the human behind the work
|
| 14 |
+
|
| 15 |
+
Most of our model and dataset repos are kept private; the public ones are the pieces directly useful to the broader Strix Halo and open-LLM communities.
|