Update README.md
Browse files
README.md
CHANGED
|
@@ -49,9 +49,9 @@ It turns **music constraints + stem descriptors** into strict **Spatial9Scene JS
|
|
| 49 |
> This includes code, schema, sample data, evaluation, and upload helpers.
|
| 50 |
> It does **not** include fine-tuned weights yet. After training, upload the contents of your `outputs/...` folder as the actual model repo.
|
| 51 |
|
| 52 |
-
Demo at
|
| 53 |
|
| 54 |
-
## What
|
| 55 |
|
| 56 |
- Proper instruction fine-tuning with **prompt masking**, so the loss is applied to the target JSON instead of the instruction prefix.
|
| 57 |
- **LoRA** and **QLoRA** training paths for efficient fine-tuning on small-to-medium GPUs.
|
|
|
|
| 49 |
> This includes code, schema, sample data, evaluation, and upload helpers.
|
| 50 |
> It does **not** include fine-tuned weights yet. After training, upload the contents of your `outputs/...` folder as the actual model repo.
|
| 51 |
|
| 52 |
+
Demo at **s9.audio/demo**
|
| 53 |
|
| 54 |
+
## What you will find in this repo
|
| 55 |
|
| 56 |
- Proper instruction fine-tuning with **prompt masking**, so the loss is applied to the target JSON instead of the instruction prefix.
|
| 57 |
- **LoRA** and **QLoRA** training paths for efficient fine-tuning on small-to-medium GPUs.
|