Update README.md
Browse files
README.md
CHANGED
|
@@ -19,9 +19,6 @@ datasets:
|
|
| 19 |
|
| 20 |
This repository contains a **QLoRA fine-tuned adapter** for [CohereLabs/tiny-aya-earth](https://huggingface.co/CohereLabs/tiny-aya-earth) (3.35B parameters), specialized on the **Yorùbá (`yo`)** instruction-following split of `masakhane/african-ultrachat`.
|
| 21 |
|
| 22 |
-
Developed as part of the KubeCon + CloudNativeCon Europe 2027 case study:
|
| 23 |
-
> **"Serving Sovereign AI: Deploying Quantized, Localized LLMs on Resource-Constrained Kubernetes"**
|
| 24 |
-
|
| 25 |
## Model Details
|
| 26 |
- **Developer:** Hussein Alamutu
|
| 27 |
- **Base Architecture:** Dense decoder-only transformer with Grouped Query Attention (GQA), 36 layers, 8k context window.
|
|
|
|
| 19 |
|
| 20 |
This repository contains a **QLoRA fine-tuned adapter** for [CohereLabs/tiny-aya-earth](https://huggingface.co/CohereLabs/tiny-aya-earth) (3.35B parameters), specialized on the **Yorùbá (`yo`)** instruction-following split of `masakhane/african-ultrachat`.
|
| 21 |
|
|
|
|
|
|
|
|
|
|
| 22 |
## Model Details
|
| 23 |
- **Developer:** Hussein Alamutu
|
| 24 |
- **Base Architecture:** Dense decoder-only transformer with Grouped Query Attention (GQA), 36 layers, 8k context window.
|