Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ tags:
|
|
| 14 |
|
| 15 |
Quantized using the [cleaned PIPPA](https://huggingface.co/datasets/royallab/PIPPA-cleaned) roleplay dataset. Uploading as I didn't see anyone else do this one yet.
|
| 16 |
|
| 17 |
-
[4.0bpw8h quants](https://huggingface.co/luigi86/magnum-72b-v1-exl2-rpcal/tree/4.0bpw8h)
|
| 18 |
|
| 19 |
|
| 20 |
See [original model](https://huggingface.co/alpindale/magnum-72b-v1) for further details.
|
|
|
|
| 14 |
|
| 15 |
Quantized using the [cleaned PIPPA](https://huggingface.co/datasets/royallab/PIPPA-cleaned) roleplay dataset. Uploading as I didn't see anyone else do this one yet.
|
| 16 |
|
| 17 |
+
[4.0bpw8h quants](https://huggingface.co/luigi86/magnum-72b-v1-exl2-rpcal/tree/4.0bpw8h) (tested and working on two 3090s with Q4 cache at 32k context)
|
| 18 |
|
| 19 |
|
| 20 |
See [original model](https://huggingface.co/alpindale/magnum-72b-v1) for further details.
|