Update README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,12 @@ inference: false
|
|
| 15 |
Install 0cc4m's ->latest<- update from his GPTQ+KoboldAI fork, it has proper support for 8bit models in this repo's format out of the box on both windows & Linux:
|
| 16 |
|
| 17 |
- https://github.com/0cc4m/KoboldAI/tree/latestgptq
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
-----
|
| 19 |
## Model Details:
|
| 20 |
|
|
|
|
| 15 |
Install 0cc4m's ->latest<- update from his GPTQ+KoboldAI fork, it has proper support for 8bit models in this repo's format out of the box on both windows & Linux:
|
| 16 |
|
| 17 |
- https://github.com/0cc4m/KoboldAI/tree/latestgptq
|
| 18 |
+
|
| 19 |
+
With this fix applied:
|
| 20 |
+
- https://github.com/0cc4m/GPTQ-for-LLaMa/pull/14
|
| 21 |
+
|
| 22 |
+
GPTQ via Ooba UI may not need this patch.
|
| 23 |
+
|
| 24 |
-----
|
| 25 |
## Model Details:
|
| 26 |
|