Update README.md
Browse files
README.md
CHANGED
|
@@ -50,7 +50,7 @@ GGUF:
|
|
| 50 |
- [Official static GGUF quants](https://huggingface.co/allura-quants/allura-org_Q3-8B-Kintsugi-GGUF)
|
| 51 |
|
| 52 |
MLX:
|
| 53 |
-
-
|
| 54 |
|
| 55 |
# Usage
|
| 56 |
|
|
@@ -84,6 +84,6 @@ Both stages here are very similar to [Q3-30B-A3B-Designant](https://huggingface.
|
|
| 84 |
|
| 85 |
- Axolotl, Unsloth, Huggingface - Making the frameworks used to train this model (Axolotl was used for the SFT process, and Unsloth+TRL was used for the KTO process)
|
| 86 |
|
| 87 |
-
- All quanters, inside and outside the org, specifically Artus and
|
| 88 |
|
| 89 |
We would like to thank the Allura community on Discord, especially Curse, Heni, Artus and Mawnipulator, for their companionship and moral support. You all mean the world to us <3
|
|
|
|
| 50 |
- [Official static GGUF quants](https://huggingface.co/allura-quants/allura-org_Q3-8B-Kintsugi-GGUF)
|
| 51 |
|
| 52 |
MLX:
|
| 53 |
+
- [8, 6, and 4bpw MLX-formrt quants by soundTeam](https://huggingface.co/collections/allura-quants/q3-8b-kintsugi-mlx-684fc48444f1214749f538c4)
|
| 54 |
|
| 55 |
# Usage
|
| 56 |
|
|
|
|
| 84 |
|
| 85 |
- Axolotl, Unsloth, Huggingface - Making the frameworks used to train this model (Axolotl was used for the SFT process, and Unsloth+TRL was used for the KTO process)
|
| 86 |
|
| 87 |
+
- All quanters, inside and outside the org, specifically Artus, Lyra, and soundTeam/Heni
|
| 88 |
|
| 89 |
We would like to thank the Allura community on Discord, especially Curse, Heni, Artus and Mawnipulator, for their companionship and moral support. You all mean the world to us <3
|